In the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query. To enhance the expression ability of a proposal, we propose a Gaussian mixture proposal (GMP) that can depict arbitrary shapes by learning importance, centroid, and range of every Gaussian in the mixture. In learning GMP, each Gaussian is not trained in a feature space but is implemented over a temporal location. Thus the conventional feature-based learning for Gaussian mixture model is not valid for our case. In our special setting, to learn moderately coupled Gaussian mixture capturing diverse events, we newly propose a pull-push learning scheme using pulling and pushing losses, each of which plays an opposite role to the other. The effects of components in our scheme are verified in-depth with extensive ablation studies and the overall scheme achieves state-of-the-art performance. Our code is available at https://github.com/sunoh-kim/pps.

While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents. This challenge lies in the lack of clear separation between content and style of a motion. To tackle this challenge, we propose a novel motion style transformer that effectively disentangles style from content and generates a plausible motion with transferred style from a source motion. Our distinctive approach to achieving the goal of disentanglement is twofold: (1) a new architecture for motion style transformer with 'part-attentive style modulator across body parts' and ‘Siamese encoders that encode style and content features separately’; (2) style disentanglement loss. Our method outperforms existing methods and demonstrates exceptionally high quality, particularly in motion pairs with different contents, without the need for heuristic post-processing. Codes are available at https://github.com/Boeun-Kim/MoST.

In the field of out-of-distribution (OOD) detection, a previous method that use auxiliary data as OOD data has shown promising performance. However, the method provides an equal loss to all auxiliary data to differentiate them from inliers. However, based on our observation, in various tasks, there is a general imbalance in the distribution of the auxiliary OOD data across classes. We propose a balanced energy regularization loss that is simple but generally effective for a variety of tasks. Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data. The main concept is to regularize auxiliary samples from majority classes, more heavily than those from minority classes. Our approach performs better for OOD detection in semantic segmentation, long-tailed image classification, and image classification than the prior energy regularization loss. Furthermore, our approach achieves state-of-the-art performance in two tasks: OOD detection in semantic segmentation and long-tailed image classification.

While 3D-based GAN techniques have been successfully applied to render photo-realistic 3D images with a variety of attributes while preserving view consistency, there has been little research on how to fine-control 3D images without limiting to a specific category of objects of their properties. To fill such research gap, we propose a novel image manipulation model of 3D-based GAN representations for a fine-grained control of specific custom attributes. By extending the latest 3D-based GAN models (e.g., EG3D), our user-friendly quantitative manipulation model enables a fine yet normalized control of 3D manipulation of multi-attribute quantities while achieving view consistency. We validate the effectiveness of our proposed technique both qualitatively and quantitatively through various experiments.

In this paper, we provide an analysis on channel-wise cross-correlation features on Siamese trackers. Channel statistics of the correlation feature is studied, where the correlation feature is computed from the features of the template and tracked target patches. From the study, a statistical pattern of the feature is observed regarding the tracking overlapping performance. The analysis is conducted on three frequently used tracking benchmark datasets.

Failure prediction has rarely been studied for Siamese trackers due to a lack of meaningful analysis of tracking failing cases. In this paper, we provide a meaningful analysis of tracking failure in Siamese trackers. Our analysis includes the statistics of the channel-wise feature correlation between the exemplar and tracked target patches. We observe that the correlation statistics (max, mean, and std) are highly related to the overlapping ratio between tracked and ground-truth bounding boxes. Based on this observation, we devise a tracking failure prediction model that extracts more plentiful factors than simple statistics. The proposed tracking failure prediction model is validated on most-popular tracking benchmark datasets through extensive experiments.

In this paper, to effectively capture non-sequential dependencies among semantic words for temporal video grounding, we propose a novel framework called Semantic Word-Aware Graph Network (SWAG-Net), which adopts graph-guided semantic word embedding in an end-to-end manner. Specifically, we define semantic word features as node features of semantic word-aware graphs and word-to-word correlations as three edge types (i.e., intrinsic, extrinsic, and relative edges) for diverse graph structures. We then apply Semantic Word-aware Graph Convolutional Networks (SW-GCNs) to the graphs for semantic word embedding. For modality fusion and context modeling, the embedded features and video segment features are merged into bi-modal features, and the bi-modal features are aggregated by incorporating local and global contextual information. Leveraging the aggregated features, the proposed method effectively finds a temporal boundary semantically corresponding to a sentence query in an untrimmed video. We verify that our SWAG-Net outperforms state-of-the-art methods on Charades-STA and ActivityNet Captions datasets.

In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling. We formulate deep metric learning as a hypergraph node classification problem in which each sample in a mini-batch is regarded as a node and each hyperedge models class-specific semantic relations represented by a semantic tuplet. Unlike previous graph-based losses that only use a bundle of pairwise relations, our HIST loss takes advantage of the multilateral semantic relations provided by the semantic tuplets through hypergraph modeling. Notably, by leveraging the rich multilateral semantic relations, HIST loss guides the embedding model to learn class-discriminative visual semantics, contributing to better generalization performance and model robustness against input corruptions. Extensive experiments and ablations provide a strong motivation for the proposed method and show that our HIST loss leads to improved feature learning, achieving state-of-the-art results on three widely used benchmarks. Code is available at https://github.com/ljin0429/HIST.

The problem of class imbalanced data is that the gener-alization performance of the classifier deteriorates due to the lack of data from minority classes. In this paper, we pro-pose a novel minority over-sampling method to augment di-versified minority samples by leveraging the rich context of the majority classes as background images. To diversify the minority samples, our key idea is to paste an image from a minority class onto rich-context images from a majority class, using them as background images. Our method is simple and can be easily combined with the existing long-tailed recognition methods. We empirically prove the effectiveness of the proposed oversampling method through extensive experiments and ablation studies. Without any architectural changes or complex algorithms, our method achieves state-of-the-art performance on various long-tailed classification benchmarks. Our code is made available at https://github.com/naver-ai/cmo.

Image retrieval is a challenging problem that requires learning generalized features enough to identify untrained classes, even with very few classwise training samples. In this article, to obtain generalized features further in learning retrieval data sets, we propose a novel fine-tuning method of pretrained deep networks. In the retrieval task, we discovered a phenomenon in which the loss reduction in fine-tuning deep networks is stagnated, even while weights are largely updated. To escape from the stagnated state, we propose a new fine-tuning strategy to roll back some of the weights to the pretrained values. The rollback scheme is observed to drive the learning path to a gentle basin that provides more generalized features than a sharp basin. In addition, we propose a multihead ensemble structure to create synergy among multiple local minima obtained by our rollback scheme. Experimental results show that the proposed learning method significantly improves generalization performance, achieving state-of-the-art performance on the Inshop and SOP data sets.

Recently, graph neural networks for semi-supervised classification have been widely studied. However, existing methods only use the information of limited neighbors and do not deal with the inter-class connections in graphs. In this paper, we propose Adaptive aggregation with Class-Attentive Diffusion (AdaCAD), a new aggregation scheme that adaptively aggregates nodes probably of the same class among K-hop neighbors. To this end, we first propose a novel stochastic process, called Class-Attentive Diffusion (CAD), that strengthens attention to intra-class nodes and attenuates attention to inter-class nodes. In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier. Then, we further propose an adaptive update scheme that leverages different reflection ratios of the diffusion result for each node depending on the local class-context. As the main advantage, AdaCAD alleviates the problem of undesired mixing of inter-class features caused by discrepancies between node labels and the graph topology. Built on AdaCAD, we construct a simple model called Class-Attentive Diffusion Network (CAD-Net). Extensive experiments on seven benchmark datasets consistently demonstrate the efficacy of the proposed method and our CAD-Net significantly outperforms the state-of-the-art methods. Code is available at https://github.com/ljin0429/CAD-Net.

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that lower-level layers extract general features and higher-level layers extract specific features. Based on our discussion, we propose an algorithm that improves fine-tuning performance and reduces network complexity through layer-wise pruning and auto-tuning of layer-wise learning rates. The proposed algorithm has verified the effectiveness by achieving state-of-the-art performance on the image retrieval benchmark datasets (CUB-200, Cars-196, Stanford online product, and Inshop). Code is available at https://github.com/youngminPIL/AutoLR.

The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects. Conventional methods ignore comprehensive contexts for the phrase or require heavy computation for multiple phrases. To understand comprehensive contexts with only one semantic phrase, we propose Position-aware Location Regression Network (PLRN) which exploits position-aware features of a query and a video. Specifically, PLRN first encodes both the video and query using positional information of words and video segments. Then, a semantic phrase feature is extracted from an encoded query with attention. The semantic phrase feature and encoded video are merged and made into a context-aware feature by reflecting local and global contexts. Finally, PLRN predicts start, end, center, and width values of a grounding boundary. Our experiments show that PLRN achieves competitive performance over existing methods with less computation time and memory.

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit from learned representations in hyperbolic space. To explore how well the hierarchical structure of un-labeled data can be represented in hyperbolic spaces, we design a novel hyperbolic message passing auto-encoder whose overall auto-encoding is performed in hyperbolic space. The proposed model conducts auto-encoding the networks via fully utilizing hyperbolic geometry in message passing. Through extensive quantitative and qualitative analyses, we validate the properties and benefits of the unsupervised hyperbolic representations. Codes are available at https://github.com/junhocho/HGCAE.

In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent resampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems. Our code is made available at https://github.com/pseulki/IB-Loss.

In this paper, we propose a novel structure for a multi-modal data association referred to as Associative Variational Auto-Encoder (AVAE). In contrast to the existing models using a shared latent space among modalities, our structure adopts distributed latent spaces for multi-modalities which are connected through cross-modal associators. The proposed structure successfully associates even heterogeneous modality data and easily incorporates the additional modality to the entire network via the associator. Furthermore, in our structure, only a small amount of supervised (paired) data is enough to train associators after training auto-encoders in an unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.

Particulate matter (PM) is the blend of various solid and liquid particles suspended in atmosphere. These submicron particles are imperceptible for usual hand-held camera photography, but become a great obstacle in microscopic imaging. PM removal from a single microscopic image is a highly ill-posed and one of the challenging image denoising problems. In this work, we thoroughly analyze the physical properties of PM, microscope and their inevitable interaction; and propose an optimization scheme, which removes the PM from a high-resolution microscopic image within a few seconds. Experiments on real world microscopic images show that the proposed method significantly outperforms other competitive image denoising methods. It preserves the comprehensive microscopic foreground details while clearly separating the PM from a single monochromatic or color image.

Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier. The generalization performance of a classifier is closely related to the adequacy of its decision boundary, so a good classifier bears a good decision boundary. Therefore, transferring information closely related to the decision boundary can be a good attempt for knowledge distillation. To realize this goal, we utilize an adversarial attack to discover samples supporting a decision boundary. Based on this idea, to transfer more accurate information about the decision boundary, the proposed algorithm trains a student classifier based on the adversarial samples supporting the decision boundary. Experiments show that the proposed method indeed improves knowledge distillation and achieves the state-of-the-arts performance.

An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks that the activations of neurons, rather than their exact output values, play the most important role in forming classificationfriendly partitions of the hidden feature space. However, as far as we know, this aspect of neural networks has not been considered in the literature of knowledge transfer. In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neurons. For the distillation, we propose an activation transfer loss that has the minimum value when the boundaries generated by the student coincide with those by the teacher. Since the activation transfer loss is not differentiable, we design a piecewise differentiable loss approximating the activation transfer loss. By the proposed method, the student learns a separating boundary between activation region and deactivation region formed by each neuron in the teacher. Through the experiments in various aspects of knowledge transfer, it is verified that the proposed method outperforms the current state-of-the-art.

In person re-identification (ReID) task, because of its shortage of trainable dataset, it is common to utilize fine-tuning method using a classification network pre-trained on a large dataset. However, it is relatively difficult to sufficiently finetune the low-level layers of the network due to the gradient vanishing problem. In this work, we propose a novel fine-tuning strategy that allows low-level layers to be sufficiently trained by rolling back the weights of high-level layers to their initial pre-trained weights. Our strategy alleviates the problem of gradient vanishing in low-level layers and robustly trains the low-level layers to fit the ReID dataset, thereby increasing the performance of ReID tasks. The improved performance of the proposed strategy is validated via several experiments. Furthermore, without any addons such as pose estimation or segmentation, our strategy exhibits state-of-the-art performance using only vanilla deep convolutional neural network architecture.

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function. Our proposed distillation loss includes a feature transform with a newly designed margin ReLU, a new distillation feature position, and a partial L2distance function to skip redundant information giving adverse effects to the compression of student. In ImageNet, our proposed method achieves 21.65% of top-1 error with ResNet50, which outperforms the performance of the teacher network, ResNet152. Our proposed method is evaluated on various tasks such as image classification, object detection and semantic segmentation and achieves a significant performance improvement in all tasks. The code is available at bhheo.github.io/overhaul.

We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture. In order to prevent the numerical instability of the network caused by the Laplacian sharpening introduction, we further propose a new numerically stable form of the Laplacian sharpening by incorporating the signed graphs. In addition, a new cost function which finds a latent representation and a latent affinity matrix simultaneously is devised to boost the performance of image clustering tasks. The experimental results on clustering, link prediction and visualization tasks strongly support that the proposed model is stable and outperforms various state-of-the-art algorithms.

In visual surveillance systems, it is necessary to recognize the behavior of people handling objects such as a phone, a cup, or a plastic bag. In this paper, to address this problem, we propose a new framework for recognizing object-related human actions by graph convolutional networks using human and object poses. In this framework, we construct skeletal graphs of reliable human poses by selectively sampling the informative frames in a video, which include human joints with high confidence scores obtained in pose estimation. The skeletal graphs generated from the sampled frames represent human poses related to the object position in both the spatial and temporal domains, and these graphs are used as inputs to the graph convolutional networks. Through experiments over an open benchmark and our own data sets, we verify the validity of our framework in that our method outperforms the state-of-the-art method for skeleton-based action recognition.

This paper proposes a novel unified framework to solve the 3-D localization and tracking problem that occurs multiple camera settings with overlapping views. The main challenge is to overcome the uncertainty of the back projection arising from the challenges of ground point detection in an environment that includes severe occlusions and the unknown heights of people. To tackle this challenge, we establish a Bayesian learning framework that maximizes a posterior over the trajectory assignments and 3-D positions for given detections from multiple cameras. To solve the Bayesian learning problem in a tractable form, we develop an expectation-maximization scheme based on the variation inference approximation, where the probability distributions are designed to follow Boltzmann distributions of seven terms that are induced from multicamera tracking settings. The experimental results show that the proposed method outperforms the state-of-the-art methods on the challenging multicamera data sets.

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert autoencoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.

This paper proposes a selective ensemble deep network architecture for crowd density estimation and people counting. In contrast to existing deep network-based methods, the proposed method incorporates two sub-networks for local density estimation: one to learn sparse density regions and one to learn dense density regions. Locally estimated density maps from the two sub-networks are selectively combined in ensemble fashion using a gating network to estimate an initial crowd density map. The initial density map is refined as a high resolution map, using another sub-network that draws on contextual information in the image. In training, a novel adaptive loss scheme is applied to resolve an ambiguity in the crowded region. the proposed scheme improves both density map accuracy and counting accuracy by adjusting the weighting value between density loss and counting loss according to the degree of crowdness and training epochs. Experiments using public datasets confirm that the proposed method outperforms state-of-the-art methods. Through self-evaluation, the effectiveness of each part in the network is also verified.

In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential actions learned using deep neural networks. The proposed deep neural network to control tracking actions is pretrained using various training video sequences and fine-tuned during actual tracking for online adaptation to a change of target and background. The pretraining is done by utilizing deep reinforcement learning (RL) as well as supervised learning. The use of RL enables even partially labeled data to be successfully utilized for semisupervised learning. Through the evaluation of the object tracking benchmark data set, the proposed tracker is validated to achieve a competitive performance at three times the speed of existing deep network-based trackers. The fast version of the proposed method, which operates in real time on graphics processing unit, outperforms the state-of-the-art real-time trackers with an accuracy improvement of more than 8%.

We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional Correlation Filter Network which allows adaptive tracking of dynamic targets. (ii) Utilising an attentional network which shifts the attention to the best candidate modules, as well as predicting the estimated accuracy of currently inactive modules. (iii) Enlarging the variety of correlation filters which cover target drift, blurriness, occlusion, scale changes, and flexible aspect ratio. (iv) Validating the robustness and efficiency of the attentional mechanism for visual tracking through a number of experiments. Our method achieves similar performance to non real-time trackers, and state-of-the-art performance amongst real-time trackers.

Absence of a clear eye visibility not only degrades the aesthetic value of an entire face image but also creates difficulties in many computer vision tasks. Even mild reflections produce the undesired superpositions of visual information, whose decomposition into the background and reflection layers using a single image is a highly ill-posed problem. In this work, we enforce the tight constraints derived by thoroughly analysing the properties of an eyeglass reflection. In addition, our strategy regularizes gradients of the reflection layer to be highly sparse and proposes the facial symmetry prior via formulating a non-convex optimization scheme, which removes the reflections within a few iterations. Experiments on frontal face image inputs demonstrate the high quality reflection removal results and improvement of the iris detection rate.

This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework. In contrast to other regression methods, the proposed method focuses on the case where output responses are on a complex high dimensional manifold, such as images. Our contributions are summarized as follows: (i) A new regression method estimating high dimensional image responses, which is not handled by existing regression algorithms, is proposed. (ii) The proposed regression method introduces a strategy to learn the latent space as well as the encoder and decoder so that the result of the regressed response in the latent space coincide with the corresponding response in the data space. (iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework. We demonstrate the robustness and effectiveness of our method through a number of experiments on various visual data regression problems.

This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences and fine-tuned during tracking for online adaptation to target and background changes. The pre-training is done by utilizing deep reinforcement learning as well as supervised learning. The use of reinforcement learning enables even partially labeled data to be successfully utilized for semi-supervised learning. Through evaluation of the OTB dataset, the proposed tracker is validated to achieve a competitive performance that is three times faster than state-of-the-art, deep network-based trackers. The fast version of the proposed method, which operates in real-time on GPU, outperforms the state-of-the-art real-time trackers.

Interestingly, shape of the high-altitude clouds serves as a beacon for weather forecasting, so its detection is of vital importance. Besides these clouds often cause hindrance in an endeavor of satellites to inspect our world. Even thin clouds produce the undesired superposition of visual information, whose decomposition into the clear background and cloudy layer using a single satellite image is a highly ill-posed problem. In this work, we derive sophisticated image priors by thoroughly analyzing the properties of high-altitude clouds and geological images; and formulate a non-convex optimization scheme, which simultaneously detects and removes the clouds within a few seconds. Experimental results on real world RGB images demonstrate that the proposed method outperforms the other competitive methods by retaining the comprehensive background details and producing the precise shape of the cloudy layer.

Background subtraction from the given image is a widely used method for moving object detection. However, this method is vulnerable to dynamic background in a moving camera video. In this paper, we propose a novel moving object detection approach using deep learning to achieve a robust performance even in a dynamic background. The proposed approach considers appearance features as well as motion features. To this end, we design a deep learning architecture composed of two networks: an appearance network and a motion network. The two networks are combined to detect moving object robustly to the background motion by utilizing the appearance of the target object in addition to the motion difference. In the experiment, it is shown that the proposed method achieves 50 fps speed in GPU and outperforms state-of-the-art methods for various moving camera videos.

In this paper, we propose a novel deep-learning architecture for accurate 3-D localization and tracking of a pedestrian using multiple cameras. The deep-learning network is composed of two networks: detection network and localization network. The detection network yields the pedestrian detections and the localization network estimates the ground position of a pedestrian within its detection box. In addition, an attentional pass filter is introduced to effectively connect the two networks. Using the detection proposals and their 2-D grounding positions obtained from the two networks, multi-camera multi-target 3-D localization and tracking algorithm is developed through min-cost network flow approach. In the experiments, it is shown that the proposed method improves the performance of 3-D localization and tracking.

We propose an online tracking algorithm for multiple target tracking with multiple cameras. In this paper, we suggest a multiple hypothesis tracking (MHT) framework to find an unknown number of multiple tracks through the spatio-temporal association between tracklets generated from multiple cameras. In this framework, the MHT is realized online by solving the maximum weighted clique problem (MWCP) at every frame to estimate the 3D trajectories of the targets. To handle the NP-hard issue of the MWCP, we propose a novel online scheme that formulates the MWCP using feedback information from the previous frame's result to find optimal tracks at every frame. This scheme enables the MWCP to be formulated by multiple subproblems and will significantly reduce the computation. The experiments show that the proposed algorithm performs comparably with the state-of-the-art batch algorithms, even though it adopts an online scheme.

In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types. In the integration stage it recombines the units to memorize and recognize the target object effectively. With respect to the elementary trackers, we present a novel attentional feature-based correlation filter (AtCF) that focuses on distinctive attentional features. The effectiveness of the proposed algorithm is validated through experimental comparison with state-of-theart methods on widely-used tracking benchmark datasets.

This paper proposes a novel path prediction algorithm for progressing one step further than the existing works focusing on single target path prediction. In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects. To solve this problem, we first suggest a two-layered probabilistic model to find major movement patterns and their cooccurrence tendency. By utilizing the unsupervised learning results from the model, we present an algorithm to find the future location of any target object. Through extensive qualitative/quantitative experiments, we show that our algorithm can find a plausible future path in complex scenes with a large number of moving objects.

This paper proposes a moving object detection algorithm for a monocular dashcam mounted on a vehicle. To deal with dynamic changes of the scene from the dashcam, we propose a new scheme inspired by human-attention inclination for change detection. Humans do not build a detailed visual representation and perceive a change of the scene based on the structure of an interesting region. In this perspective, our method focuses on a sky and road region of the scene and builds an abstracted background model, which is updated with a spatially adaptive learning rate according to the center-focused tendency of the human gaze. To improve the robustness of detection, the final detection map is refined by combining the results from twin processes applied to the original image and the median-filtered image, respectively. In experiments, we have found that our method outperforms state-of-the-art methods qualitatively and quantitatively on a realistic dashcam video.

In this paper, we propose a novel algorithm for 3D object cuboid detection. Contrary to the conventional algorithms based on image segmentation, we propose a part-based voting process to robustly generate cuboids when the object is partially occluded. Our method finds the distinctive parts of RGB-D images and generates the 3D cuboids covering the target objects from the distinctive parts by the proposed probabilistic voting model. To validate the performance of the proposed method, experiments are conducted on the challenging NYU v2 and SUN RGB-D datasets. Experimental results show that our method is computationally efficient and has a competitive performance compared with the state-of-the-art methods. In addition, our method can be combined with the conventional segmentation-based method parallelly, and the combined algorithm is evaluated by experiments to show that it achieves a significant improvement of performance.

Fire detection is one of the most interesting issues for surveillance. The existing approaches for the fire detection suffer from a high false positive ratio. To solve the problems, we present a patch-based fire detection algorithm with online outlier learning. In the proposed algorithm, the candidates of fire are obtained in the form of patch, while the classical candidates have been based on pixels or blobs. Because the patches of fire have more distinctive shape than the entire fire, the shape classifier can recognize the candidates correctly from fire-like outliers. In addition, we propose an online outlier learning scheme which handles the irregularity of fire based on the repeatability of shape in time. The proposed algorithm is experimented with new challenging dataset, consisting of 50 positive videos with fire and 44 negative ones with fire-like outliers. By evaluating on the dataset, we validate the performance of our algorithm qualitatively and quantitatively.

This paper proposes a new pan-tilt-zoom (PTZ) tracking method to improve the robustness against occlusions and appearance changes by using motion likelihood map and scale change estimation as well as appearance correlation filter. For this purpose, we introduce a motion likelihood map constructed from motion detection result in addition to the correlation filter. The motion likelihood map is generated by blurring the motion detection result, which shows high probability in the center of target. To combine the correlation filter and the motion likelihood map, we formulate an optimization problem. In addition, to handle the scale change of target, we repeat the combining process for various scale of bounding box. The experiments show that the proposed method outperforms the state-of-the-art methods.

This paper proposes a novel multi-target tracking method which jointly solves a data association problem using images from multiple cameras. In this work, the spatiotemporal data association problem is formulated as a multidimensional assignment problem (MDA). To achieve a fast, efficient, and easily implementable approximation algorithm, we solve the MDA problem approximately by solving a sequence of bipartite matching problems using random splitting and merging operations. In this formulation, we design a new cost function, considering the accuracy in 3D reconstruction, motion smoothness, visibility from cameras, starting/ending at entrance and exit zone, and false positive. Our approach reconstructs 3D trajectories that represent people’s movement as 3D cylinders whose locations are estimated considering all adjacent frames. The experiments illustrate the proposed method shows the state-of-the-art performance in challenging multi-camera datasets and the computational efficiency with 8 times faster computation than the existing BIP approach.

This paper proposes a novel approach for user interactive segmentation based on graph-cut, which improves the robustness against the initial parameter setting. The existing graph-cut based segmentation uses a parametric model to estimate the color distributions of foreground/background. However, the parametric model is sensitive to the predefined number of distribution models and can be easily biased by a wrong initialization. In this paper, we develop a non-parametric approach based on random forest to handle the biased initialization problem. In addition, we design a new structure of random forest referred to as partially growing random forest to reduce the training time. We compare the proposed approach quantitatively and qualitatively to the existing graph-cut based segmentation baseline, where our method shows a remarkable performance on the new colorful dataset as well as comparable results on the classical dataset.

This paper proposes a new algorithm for color-to-gray conversion preserving the gradient information in input color image. To preserve the gradient in a color image, we construct a random forest representing the relation between color intensity and gradient in an input image. The leaf nodes of random trees indicate the gray colors (single channel colors) corresponding to the input RGB colored pixels. From these initial gray colors obtained by the random forest, we determine the final gray scale by keeping the balance between intensity and luminance channels. In our experiments, we show that the proposed method outperforms the state-of-the-arts in view of color constrast preserving ratio and mean squared error versus luminance.

This paper proposes a robust and fast scheme to detect moving objects in a non-stationary camera. The state-of-the art methods still do not give a satisfactory performance due to drastic frame changes in a non-stationary camera. To improve the robustness in performance, we additionally use the spatio-temporal properties of moving objects. We build the foreground probability map which reflects the spatio-temporal properties, then we selectively apply the detection procedure and update the background model only to the selected pixels using the foreground probability. The foreground probability is also used to refine the initial detection results to obtain a clear foreground region. We compare our scheme quantitatively and qualitatively to the state-of-the-art methods in the detection quality and speed. The experimental results show that our scheme outperforms all other compared methods.

In this paper, we propose a novel selective search method to speed up the object detection via category-based attention scheme. The proposed attentional searching strategy is designed to focus on a small set of selected regions where the object category is expected to exist. The selected regions are estimated by mimicking three properties of the attentional scheme of human visual perception: spotlighting interest regions with low-level saliency (saliency attention), focusing on distinctive features for an object category (feature attention), and estimating potential object position by following human gaze path (gaze attention). Also, the time complexity of each attentional scheme is implemented to be low so that it can hardly affect the computational time. To validate the performance of our method, experiments were conducted on the challenging PASCAL VOC dataset. Experimental results show that our method efficiently generates a small number of candidate boxes for object detection (less than 10ms=image), and the combined object detection system achieves more than 2 times faster performance than the baseline with comparable average precision.

Features play a vital role in human action recognition (HAR), as they encapsulate the underlying dynamics of the action. We propose the features (frequencygrams) based on frequency domain analysis of histograms of the motion and its spatiotemporal gradient (rate of change in motion flow). Feature extraction is quite simple and can be performed in real time using sparse or interest point motion flow. They are resilient to delayed initiated actions, scale variation, moving background, sudden illumination changes (high frequency noise) and avoid the overload of person detection and tracking. Being robust to camera motions, they also provide a natural, compact and discriminative representation for reciprocating motions by preserving comprehensive temporal information of the action sequences. As other global features also bear some action semantics, we fuse all these features together in a systematic way to improve the overall HAR performance, by employing the joint sparse representation with group sparsity regularization. The extensive experimental results, on three benchmark action datasets and one gesture recognition dataset, show the effectiveness and generality of the proposed method.

This paper presents an online data association approach to handle new detection and missing detection problems of multiple people tracking in crowded scenes. The key contribution of our paper includes two aspects: one is automatic initiation of tracking models for newly appeared detections and the other is selective update of tracking models for missing detections by occlusions. For the automatic initiation, instead of the conventional matching algorithm, our data association is solved by a maximum a posteriori probability (MAP) formulation considering object's size, center distance, motion and appearance. The selective update scheme for tracking models is developed by considering the spatial information which prevents the tracking model from being corrupted with unreliable information. Even if the head detector is less discriminative due to low number of features than full body and only the recent tracking models are used for online association purpose, the proposed method shows improved performance compared to the state-of-art offline association approach with significantly low computational load.

Occurrence of high imbalance in real-world domains is a direct result of rarity of interesting events, which results in skewed datasets. Without dataset rebalancing, the learning algorithm will encounter extremely low minority class samples therefore it gets biased towards the majority class in the classification tasks. Hence properly handling the imbalanced dataset is a crucial issue in the pattern recognition domain. We have employed bootstrapping by simultaneous oversampling of the minority class and under sampling of the majority class to build the ensemble of classifiers. Oversampling is partially guided by the extracted hidden patterns from minority class, which prevents its over-generalization and amplify subtle vital patterns. The proposed framework is evaluated on four highly imbalanced datasets with employing a series of classifiers like, support vector machine, logistic regression, nearest neighbor and Gaussian process classifier. Experimental results showed that the pattern classification performance for various tasks improves after rebalancing datasets using the proposed framework.

This paper proposes a transfer learning scheme for traffic pattern analysis where the transferred classifier could be trained with a small number of samples. First we make feature descriptors to represent the traffic trajectories so that they should be adequate to transfer and classify the traffic patterns. Then, we use support vector machine (SVM) to learn the feature descriptors of traffic trajectories. The transfer learning scheme is formulated by a convex optimization problem using the geometric relation between target and source patterns. Not only parameters of SVM but also the geometric relation are found at the same time through two step minimization process of the optimization problem. Through experiments on various surveillance videos, the proposed formulation is shown to be valid by investigating the improvement of performance compared to a transfer scheme without the proposed geometric relation as well as SVM without transfer scheme.

In this paper, we propose a framework which self-organizes the cascaded object detection filters for fast object detection with maintaining high accuracy. The proposed scheme consists of root and part filter modules, which are cascaded in a self-organizing structure. The pruning of non-object regions in low resolution at the root cascade stage is critical for the object detection speed. At root stage, to prune as many non-object regions as possible, we build a root cascade structure using multiple root models. These models are obtained via bagging procedure for non-linear classification of object and non-object parts in an image. Additional speed-up is achieved by determining proper deployment order of part models. We define a discriminability measure for the part models and suggest a self-organizing scheme to generate an efficient order of part models. The proposed method is evaluated through computational experiments with the PASCAL VOC and INRIA datasets, as a result, our method achieves on average more than 2 times faster performance than the original cascade-DPM, with comparable precision scores.

This paper presents a novel method for modeling of interaction among multiple moving objects to detect traffic accidents. The proposed method to model object interactions is motivated by the motion of water waves responding to moving objects on water surface. The shape of the water surface is modeled in a field form using Gaussian kernels, which is referred to as the Motion Interaction Field (MIF). By utilizing the symmetric properties of the MIF, we detect and localize traffic accidents without solving complex vehicle tracking problems. Experimental results show that our method outperforms the existing works in detecting and localizing traffic accidents.

In this paper, we propose a novel clustering and motif modeling framework for analyzing large number of protein family using k-mer. Our approach of using k-mers utilizes both occurring frequency and position information of k-mers that essential for classification yet not fully used in previous methods. We found that the structure has close relationship between motif of protein family and hence well describe important biological features or motifs of each protein family. The classification/clustering procedure are executed in incremental manner which was difficult for previous algorithms and is modeled by using bipartite model. Furthermore, the method can be efficiently implemented using parallel computing and hash. Experimental results using the entire COG family database shows that our model can model a large number of protein families without sacrificing accuracy. In addition, the classification structure, path of the graph for protein sequences, explains characteristic subsequences or motif of each family quite well. Thus the proposed method has the potential to model both protein families and motifs, even for a large number of families.

In this paper we propose an efficient method for the recognition of long and complex action streams. First, we design a new motion feature flow descriptor by composing low-level local features. Then a new data embedding method is developed in order to represent the motion flow as an one-dimensional sequence, whilst preserving useful motion information for recognition. Finally attentional motion spots (AMSs) are defined to automatically detect meaningful motion changes from the embedded one-dimensional sequence. An unsupervised learning strategy based on expectation maximization and a weighted Gaussian mixture model is then applied to the AMSs for each action class, resulting in an action representation which we refer to as Action Chart. The Action Chart is then used efficiently for recognizing each action class. Through comparison with the state-of-the-art methods, experimental results show that the Action Chart gives promising recognition performance with low computational load and can be used for abstracting long video sequences.

In this paper we propose an object tracking method in case of inaccurate initializations. To track objects accurately in such situation, the proposed method uses "motion saliency" and "descriptor saliency" of local features and performs tracking based on generalized Hough transform (GHT). The proposed motion saliency of a local feature emphasizes features having distinctive motions, compared to the motions which are not from the target object. The descriptor saliency emphasizes features which are likely to be of the object in terms of its feature descriptors. Through these saliencies, the proposed method tries to "learn and find" the target object rather than looking for what was given at initialization, giving robust results even with inaccurate initializations. Also, our tracking result is obtained by combining the results of each local feature of the target and the surroundings with GHT voting, thus is robust against severe occlusions as well. The proposed method is compared against nine other methods, with nine image sequences, and hundred random initializations. The experimental results show that our method outperforms all other compared methods.

Conventional minutiae-based fingerprint recognition approaches consider only local characteristics and their accuracy dramatically decreases as the number of available minutiae decreases. We propose new features based on Abstracted Radon Profile (ARP). Proposed method uses global properties of an image and it does not necessitate any heavy preprocessing as in classical methods. By using independent gradual patching via proposed multilayer architecture, local characteristics of an image are also preserved. ARP features have an advantage of being robust to zero mean additive noise. For sparse signal representation, dictionary is constructed from the ARP features of the training samples. Recognition is done by ℓ1-minimization with quadratic constraints, so this framework can handle dense noise by exploiting the fact that these errors are often sparse. Experimental results in assessing recognition performance demonstrate the proposed approach outperforms the conventional approaches in correlation and distance based comparisons. Computational time comparison result shows the proposed feature is more efficient than brute-force method of image alignment and promising for handling other pattern recognition problems as well.

In this paper, we aim to find the matches of head detections from different cameras. Matching of heads detected in different cameras and assigning the same label to the detection results which are actually from the same person can help to track the person robustly in severe occlusion because matching process can give more clues when the tracked person is even totally occluded in one camera. We present two similarity measurement methods for head matching based on geometry information: homography similarity and epipolar similarity. Each similarity is based on homography and fundamental matrix respectively. Experimental results show that our similarity measures have validity to use for matching head detections. We also compare two similarities and analyze what strong point of each method is.

In this paper, we present an active sampling method to speed up conventional pixel-wise background subtraction algorithms. The proposed active sampling strategy is designed to focus on attentional region such as foreground regions. The attentional region is estimated by detection results of previous frame in a recursive probabilistic way. For the estimation of the attentional region, we propose a foreground probability map based on temporal, spatial, and frequency properties of foregrounds. By using this foreground probability map, active attentional sampling scheme is developed to make a minimal sampling mask covering almost foregrounds. The effectiveness of the proposed active sampling method is shown through various experiments. The proposed masking method successfully speeds up pixel-wise background subtraction methods approximately 6.6 times without deteriorating detection performance. Also realtime detection with Full HD video is successfully achieved through various conventional background subtraction algorithms.

This paper presents a possibility that we can teach what emotions a robot should express. For this, we design an artificial emotion decision system learned by feedbacks of users. The proposed system consists of three parts: a personality space with probability model, an emotion decision process, and an emotion learning process. (1) The personality space is designed based on the Five-Factor Model. In the personality space, we set up probability distributions of emotions. (2) The emotion decision process determines the probability values of emotions using the probability distributions of emotions in the personality space. (3) The emotion learning process updates the probability distributions by the feedbacks that are the teaching information from users; then, different probability values of emotions are determined. By applying to a humanoid robot system, we have verified the validity of the proposed system by being learned from two persons who have different personalities.

This paper proposes a trajectory analysis method by handling the spatio-temporal property of trajectory. Not using similarity measures of two trajectories, our model analyzes overall path of a trajectory. Learning of spatio property is presented as semantic regions (e.g. go straight, turn left, turn right) that are clustered effectively using topic model. The temporal order of observations on a trajectory is taken into account using HMM for detecting global anomaly. Results of experiments show that modeling of semantic region and detecting of unusual trajectories are successful even in complex scenes.

In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invariance and foveal predominance. The rotation and scaling invariance helps to reduce false alarms caused by pose changes and intensify translational changes. Foveal predominant property helps to detect the tracking failing moment by amplifying the resolution around focus (tracking box center) and blurring the peripheries. Each ganglion cell corresponds to a pixel of log-polar image, and its adaptation is modeled as Gaussian mixture model. Its validity is shown through various experiments.

This paper presents a behavior generating method for reflecting emotional probabilities. The proposed method consists of two processes: an emotion-behavior probability generating process and a unit behavior combination generating process. 1) In the emotion-behavior probability generating process, the emotional probabilities of behaviors are determined on the basis of user preferences in terms of the priorities of emotions. 2) In the unit behavior combination generating process, optimal behaviors are found by the simulated annealing algorithm. A final behavior is a set of selected parts of expressions. It is possible to not only reveal an abundance of expressions without one-to-one mapping relations between emotions and behaviors but also apply these expressions in the case of various robots. We have verified the diversity of emotional expression by applying the proposed method to two different robot systems, which are a cyber robot simulator and a real robot system.

In this paper, we propose a novel approach for video stabilization using Markov random field (MRF) modeling and maximum a posteriori (MAP) optimization. We build an MRF model describing a sequence of unstable images and find joint pixel matchings over all image sequences with MAP optimization via Gibbs sampling. The resulting displacements of matched pixels in consecutive frames indicate the camera motion between frames and can be used to remove the camera motion to stabilize image sequences. The proposed method shows robust performance even when a scene has moving foreground objects and brings more accurate stabilization results. The performance of our algorithm is evaluated on outdoor scenes.

We present an efficient and robust measurement model for visual tracking. This approach builds on and extends work on measurement model of subspace representation. Subspace-based tracking algorithms have been introduced to visual tracking literature for a decade and show considerable tracking performance due to its robustness in matching. However, the measures used in their measurement models are not robust enough in cluttered backgrounds. We propose a novel measure of object matching referred to as WDIFS, which aims to improve the discriminability of matching within the subspace. Our measurement model can distinguish target from similar background clutters which often cause erroneous drift by conventional DFFS based measure. Experiments demonstrate the effectiveness of the proposed tracking algorithm under cluttered background.

In this paper, we propose a new discriminant analysis, named as linear boundary discriminant analysis (LBDA), which increases the class separability by differently emphasizing the boundary and non-boundary patterns. This is achieved by defining two novel scatter matrices and solving eigenproblem on the criterion described by these scatter matrices. As a result, the classification performance using the extracted features can be improved. This effectiveness of LBDA is theoretically explained by reformulating scatter matrices in pairwise form. In addition, LBDA can extract larger number of features than original LDA. The experiments are conducted to show the performance of LBDA, and the result shows that LBDA can outperform other algorithms in most cases.

In this paper, we propose a new discrminant analysis based on datawise formulation of scatter matrices to deal with the data of non-normal distribution. Starting from original LDA, datawise formulation of scatter matrices is derived and its meaning is clarified. Based on this formulation, a new feature extraction algorithm is presented. In this formulation, assumption on distribution of data is no more necessary, so appropriate feature space can be found from the data whose distribution is non-normal, as well as multimodally normal. Limitation on the feature dimension also can be removed, and by replacing the inverse matrix of within-class scatter matrix with especially assigned weights, computational problems originating from matrix inversion of within-scatter matrix can be fundamentally avoided. As a result, good feature space for classification task can be found without the problems of LDA. Performance of this algorithm has been evaluated by using feature for real classification tasks.

This paper proposes an emotional behavior generator for emotional robots. The traditional methods for generating emotional behavior are not capable of expressing complex emotions, and lack the diversity of emotional expression and generality of system. To solve these problems, we propose a general emotional behavior generation module. It generates behavior combination expressing complex and phased emotions, using the concept of unit behavior and emotional marks. With behavior training sets of the module user, it generates the emotional matrix which represents expression abilities of unit behaviors. And with the emotional matrix, unit behaviors are combined into emotional expression behaviors using Simulated Annealing. To evaluate the results, we apply it to a robot simulator.

In this paper, we present a neural network structure and a fast incremental learning algorithm using this network. The proposed network structure, named Evolving Logic Networks for Real-valued inputs (ELN-R), is a data structure for storing and using the knowledge. A distinctive feature of ELN-R is that the previously learned knowledge stored in ELN-R can be used as a kind of building block in constructing new knowledge. Using this feature, the proposed learning algorithm can enhance the stability and plasticity at the same time, and as a result, the fast incremental learning can be realized. The performance of the proposed scheme is shown by a theoretical analysis and an experimental study on two benchmark problems.

In this paper, we present a fast incremental one-class classifier algorithm for large scale problems. The proposed method reduces space and time complexities by reducing training set size during the training procedure using a criterion based on sample margin. After introducing the sample margin concept, we present the proposed algorithm and apply it to face detection database to show its efficiency and validity.

In this paper, we propose a scheme to improve the performance of subspace learning by using a pattern (data) selection method as preprocessing. Generally, a training set for subspace learning contains irrelevant or unreliable samples, and removing these samples can improve the learning performance. For this purpose, we use pattern selection preprocessing which discriminates decision boundary/non-boundary patterns by class information and neighborhood property, and removes boundary patterns. Performance improvement by pattern selection is investigated for classification and visual tracking problems, and compared with those of the previous methods.

In this paper, we propose a new method for object tracking based on mean shift algorithm using a kernel which has the shape of the target object, and with probabilistic estimation of the orientation change and scale adaptation. The proposed method uses an object mask to construct a kernel which has the shape of the actual object for tracking. Orientation is adjusted using probabilistic estimation of orientation and scale is adapted using a newly proposed descriptor for scale. Tests results show that the proposed method is robust to background clutter and tracks objects very accurately.

In this paper, we propose a novel approach which integrates adaptive appearance model and hierarchical estimation mechanism composed of global estimation and local estimation. Hierarchical estimation runs in two phases: In first phase, global estimation coarsely predicts a region in where true state may be present, and then local estimation tries to find out the true state inside the region at second phase. The benefits from Hierarchical estimation are two-fold, on one hand, it reduces the number of particles significantly, which enables real-time tracking, while on the other hand, it improves tracking accuracy even with less number of particles. Experimental results show the effectiveness and robustness of the proposed approach.

This paper presents the design and implementation of a reconfigurable heterogeneous modular architecture for service robots. The proposed architecture has five key concepts which are different from conventional reconfigurable modular service robots; 1) easy and multiple assembly according to requirements of users, 2) hardware resource sharing system with other heterogeneous modules, 3) communication ability among all heterogeneous modules which have different operating systems, 4) automatic connection management system when a new module is attached, 5) automatic software upgrading system for new module software. We explain the three parts of the system architecture which meet the five concepts; mechanical architecture, software architecture, and connection architecture. To verify our architecture, we developed and evaluated a reconfigurable heterogeneous modular service robot by applying the proposed design.

This paper introduces an emotional behavior decision model for intelligent service robots. An emotional model should make different behavior decisions according to the purpose of the robots. We propose an emotional behavior decision model which can change the character of emotional model and make different behavior decisions although the situation and environment remain the same. We defined each emotional element such as reactive dynamics, internal dynamics, emotional dynamics, and behavior dynamics by state dynamic equations. The proposed system model is a linear system. If you want to add one external stimulus or behavior, you need to add just one dimensional vector to the matrix of external stimulus or behavior dynamics. The case of removing is same. The change of reactive dynamics, internal dynamics, emotional dynamics, and behavior dynamics also follows the same procedure. We implemented the proposed emotional behavior decision model and verified its performance.

In this paper, we propose a new incremental learning algorithm which uses a new type of experience to reduce the computation time without the aid of addition information. The data structure, Evolutionary Logic Networks for Real-valued Inputs (ELN-R) for storing and using this experience is defined and an incremental learning algorithm for ELN-R is described. The performance of the proposed learning algorithm is tested through experiments on two-spiral problem which is selected as a benchmark problem to compare the performance of the proposed algorithm with those of other algorithms.

Feature extraction is necessary to classify a data with large dimension such as image data. It is important that the obtained features include the maximum information of input data. The representative methods for feature extraction are PCA, ICA, LDA and MLP etc. PCA, LDA are unsupervised type algorithms, and LDA, MLP are supervised type algorithms. Supervised type algorithms are more suitable for feature extraction because of using input data with class information. In this paper, we suggest the feature extraction scheme which uses class information to extract features by PCA. We test our algorithm using Yale face database and analyze the performance to compare with other algorithms.

This paper presents a novel approach to an online trajectory planning of robot arms for the interception of a fast-maneuvering object under torque and velocity constraints. A body axis is newly introduced as a trajectory-planning coordinate in order to meet the position and the velocity matching conditions for a smooth grasp of the fast-maneuvering object. Using the position of the object and the end-effector in the inertia axis, the acceleration commands are generated in the X-, Y-, and Z-directions of the body axis and the acceleration commands are modified considering the torque and the velocity constraints. The trajectory planning in the X-direction becomes the speed planning to achieve the maximum speed, whereas the trajectory planning in the Y- and Z-directions becomes the direction planning where a missile-guidance algorithm is employed to intercept the maneuvering object. Finally, the acceleration commands in the body axis are transformed into the angle commands of the end-effector in the joint axis, which is used as the actual trajectory commands in robot arms.

In this paper, we propose new method, which can provide user the path to the target place efficiently. It stores the state of roads to target place as the form of Q-table and finds the proper path using Q-table is updated by the information about real traffic, which is reported by users. This method can provides the proper path, using less storage and less computation time than the conventional method, which stores entire road traffic information and finds the path by graph search algorithm.

In this paper, we present a new learning algorithm, referred to as the logical evolution (LE) method. To learn a Boolean function, the LE method uses not only new information in the given training examples but also old information learned in the past. By using only one network to learn many functions, old information can be re-used for learning new problems efficiently. In this paper, we present the network structure and the learning algorithm of LE and analyse its properties. Its learning capability is also shown by means of two experiments.

This paper extends the application of neurocontrol approaches to a new class of nonlinear systems diffeomorphic to output feedback nonlinear systems with unmeasured states. A neural-based adaptive observer is introduced for state estimation as well as system identification using only output measurements during online operation. System identification is achieved via the online approximation of a priori unknown functions. The controller is designed using the backstepping control design procedure. Leakage terms in the adaptive laws and nonlinear damping terms in the backstepping controller are introduced to prevent instability from arising due to the inherent approximation error. A primary benefit of the online function approximation is the reduction of approximation errors, which allows reduction of both the observer and controller gains. A semi-global stability analysis for the proposed approach is provided and the feasibility is investigated by an illustrative simulation example.

This paper presents a stable nonparametric adaptive control approach using a piecewise local linear approximator. The continuous piecewise linear approximator is developed and its universal approximation capability is proved. The controller architecture is based on adaptive feedback linearization plus sliding mode control. A time varying activation region is introduced for efficient self-organization of the approximator during operation.We modify the adaptive control approach for piecewise linear approximation and self-organizing structures. In addition, we provide analyses of asymptotic stability of the tracking error and parameter convergence for the proposed adaptive control scheme with the on-line self-organizing structure. The method with a deadzone is also discussed to prevent a high-frequency input which might excite the unmodeled dynamics in practical applications. The application of the piecewise linear adaptive control method is demonstrated by a computational simulation.