In this paper, we propose a novel multi-class graph boosting algorithm to recognize different visual objects. The proposed method treats subgraph as feature to construct base classifier, and utilizes popular error correcting output code scheme to solve multi-class problem. Both factors, base classifier and error-correcting coding matrix are considered simultaneously. And subgragphs, which are shareable by different classes, are wisely used to improve the classification performance. The experimental results on multi-class object recognition show the effectiveness of the proposed algorithm.

Human action recognition is a significant task in automatic understanding systems for video surveillance. Probabilistic Latent Semantic Analysis (PLSA) model has been used to learn and recognize human actions in videos. Specifically, PLSA employs the expectation maximization (EM) algorithm for parameter estimation during the training. The EM algorithm is an iterative estimation scheme that is guaranteed to find a local maximum of the likelihood function. However its convergence usually takes a large number of iterations. For action recognition with large amount of training data, this would result in long training time. This paper presents an incremental version of EM to speed up the training of PLSA without sacrificing performance accuracy. The proposed algorithm is tested on two challenging human action datasets. Experimental results demonstrate that the proposed algorithm converges with fewer number of full passes compared with the batch EM algorithm. And the trained PLSA models achieve comparable or better recognition accuracies than those using batch EM training.

A multiclass classification problem can be reduced to a collection of binary problems using an error-correcting coding matrix that specifies the binary partitions of the classes. The final classifier is an ensemble of base classifiers learned on binary problems and its performance is affected by two major factors: the qualities of the base classifiers and the coding matrix. Previous studies either focus on one of these factors or consider two factors separately. In this paper, we propose a new multiclass boosting algorithm called AdaBoost.SIP that considers both two factors simultaneously. In this algorithm, informative patterns, which are shareable by different classes rather than only discriminative on specific single class, are generated at first. Then the binary partition preferred by each pattern is found by performing stage-wise functional gradient descent on a margin-based cost function. Finally, base classifiers and coding matrix are optimized simultaneously by maximizing the negative gradient of such cost function. The proposed algorithm is applied to scene and event recognition and experimental results show its effectiveness in multiclass classification.

In this paper, we formulate the feature clustering problem for vehicle detection and tracking as a general MAP problem and solve it using MCMC. The proposed approach exhibits two advantages over existing methods: general Bayesian model can handle arbitrary objective functions and MCMC guarantees global optimal solution. Our algorithm is validated on real-world traffic video sequences, and is shown to outperform the state-of-the-art approach.

In this paper, we propose a novel approach to automatically generating, instead of manually designing, discriminative visual features for face detection. The features are composed by multiple local features (e.g., Haar features), and such features can capture not only the local texture information but also their spatial configurations. Therefore, the proposed feature contains rich semantic information so that the classifier built on a set of such features can achieve high accuracy and high efficiency. Experimental results show that the proposed approach outperforms the techniques based on local features and the state-of-the-art discriminative features for face detection.

Multi-instance learning (MIL) has many applications, including image and text categorization. One of the most effective approaches to MIL is by using support vector machines with multi-instance kernels. In this paper we propose a multi-instance kernel, called MIR-kernel, that takes into account the relational information of instances when computing similarities between bags. The relational information of instances are derived from the statistics of the distances between instances in feature space. The aim of MIR-kernel is to efficiently capture the context in which instances occur within bags, so that it is able to better compute the similarities between bags. Experimental results on image and text categorization demonstrate the effectiveness of the proposed method compared to other methods.

This paper proposes a joint random field (JRF) model for moving vehicle detection in video sequences. The JRF model extends the conditional random field (CRF) by introducing auxiliary latent variables to characterize the structure and evolution of visual scene. Hence detection labels (e.g. vehicle/roadway) and hidden variables (e.g. pixel intensity under shadow) are jointly estimated to enhance vehicle segmentation in video sequences. Datadependent contextual constraints among both detection labels and latent variables are integrated during the detection process. The proposed method handles both moving cast shadows/lights and background illumination variations. Computationally efficient algorithm has been developed for realtime vehicle detection in video streams. Experimental results show that the approach effectively deals with various illumination conditions and robustly detects moving vehicles even in grayscale video. 1

In this paper, we propose an efficient approach to moving pedestrian detection in video. This approach incorporates both motion and shape information and learns a codebook of shape context descriptors from a very small number of training samples. During the testing process, moving edgelets are firstly identified between adjacent frames using a local search method. Shape context descriptors for numerous sample points on identified edgelets are then produced and are matched against the instances of the learned codebook to generate initial hypotheses. The final hypotheses for pedestrians are obtained by pruning initial hypotheses. The proposed approach has the following advantages by comparison with the existing techniques: (1) lower computational cost, (2) lower false positive rate, and (3) fewer training samples. Experiments with a publicly available dataset confirm the performance of the proposed approach.

In this paper we propose a new algorithm for region-based image categorization that is formulated as a multiple instance learning (MIL) problem. The proposed algorithm transforms the MIL problem into a traditional supervised learning problem, and solves it using a standard supervised learning method. The features used in the proposed algorithm are the hyperclique patterns which are ldquocondensedrdquo into a small set of discriminative features. Each hyperclique pattern consists of multiple strongly-correlated instances (i.e., features). As a result, hyperclique patterns are able to capture the information that are not shared by individual features. The advantages of the proposed algorithm over existing algorithms are threefold: (i) unlike some existing algorithms which use learning methods that are specifically designed for MIL or for certain datasets, the proposed algorithm uses a general-purpose standard supervised learning method, (ii) it uses a significantly small set of features which are empirically more discriminative than the PCA features (i.e. principal components), and (iii) it is simple and efficient and achieves a comparable performance to most state-of-the-art algorithms. The efficiency and good performance of the proposed algorithm make it a practical solution to general MIL problems. In this paper, we apply the proposed algorithm to both drug activity prediction and image categorization, and promising results are obtained.

Smart camera system design and implementation is a challenging task due to the constant need to perform computationally demanding image processing tasks with the limited resource constraints of embedded systems. This paper presents the hardware and software co-design and implementation of the first stage of TraffiCam, an FPGA based smart camera prototype for traffic surveillance at intersections, consisting of a CMOS image sensor capture device and FPGA main video processor. In particular, creative solutions for balancing gate array utilization, memory and computation time are presented for the initial stage of Harris keypoint detection with discussions on the algorithm implementation conversions between PC-based to FPGA based platforms. Preliminary results show satisfactory real-time tracking and estimation performance.

Detecting and recognizing pedestrians in video footages are two essential and significant tasks in many automatic video understanding systems. In this paper, we propose an efficient approach to moving pedestrian detection and recognition in video. The testing process of this approach involves two main steps: moving edge detection and hypotheses generation. Moving edges are firstly extracted by comparing the edges identified in adjacent frames. Shape context descriptors are then produced for the edge points sampled from the moving edges and matched against the instances of a codebook that is learned from a set of training samples to generate initial hypotheses. Final hypotheses are formed by pruning initial hypotheses with large overlaps. Experiments with a publicly available dataset show that the proposed approach can reliably detect and recognize moving pedestrians in real scenes that contain either different viewing angles or different degrees of occlusions.

The MPEG-4 video coding standard introduces a novel concept of sprite or mosaic that is a large image composed of pixels belonging to a video object visible throughout a video segment. The sprite captures spatio-temporal information in a very compact way and makes it possible for efficient object-based video compression. In this paper, we propose a practical approach to generating multiple super-resolution sprites for sprite coding. In order to construct super-resolution sprites and reduce coding cost, we firstly partition a video sequence into multiple independent sprites and group the images covering a similar scene into the same sprite. We then propose efficient and practical algorithms for cumulative global motion estimation and super-resolution sprite construction. Experiments with real video sequences show that the proposed approach outperforms the previous single sprite and multiple sprite techniques.

In recent years, trajectory analysis of moving vehicles in video-based traffic monitoring systems has drawn the attention of many researchers. Trajectory extraction is a fundamental step that is required prior to trajectory analysis. Lots of previous work have focused on trajectory extraction via tracking. However, they often fail to achieve long-term consistent trajectories. In this paper, we propose a robust approach for extracting long-term trajectories of moving vehicles in traffic monitoring using SIFT-descriptor. Experimental results show that the proposed method outperforms tracking-based techniques.

In this paper, we propose a robust approach to super-resolution static sprite generation from multiple low-resolution images. Considering both short-term and long-term motion influences, a hybrid global motion estimation technique is first presented for sprite generation. An iterative super-resolution reconstruction algorithm is then proposed for the super-resolution sprite construction. This algorithm is robust to outliers and results in a sprite image with high visual quality. In addition, the generated super-resolution sprite can provide better reconstructed images than a conventional low-resolution sprite. Experimental results demonstrate the effectiveness of the proposed methods.

In this paper, we propose some extensions of an efficient gradient-based image registration method called the inverse compositional algorithm. Specifically, these extensions include cumulative multi-image registration and incorporations of illumination change and lens distortion correction. By combining these extensions, we propose efficient cumulative multi-image registration methods with illumination and lens distortion correction. It is shown that high efficiency can still be achieved for multiple images using the proposed methods. Some experimental results show the efficacy of the proposed methods.

In this paper, we present a multisensor surveillance system that consists of an optical sensor and an infrared sensor. In this system, a background subtraction method based on zero-order statistics is utilized for the moving object segmentation. Additionally, we propose a generic approach to simultaneous object tracking and multisensor image registration. An efficient face detection system is shown as an application that will have enhanced performance from the registration and fusion of the information from the two sensors. Experimental results show the efficacy of the proposed system.

An efficient blind adaptive multiuser detector based on the modified RLS algorithm is proposed for synchronous DS-CDMA systems over a flat fading channel with large spreading sequences. We first properly decompose the optimal weight vector associated with the original code of the desired user into several adaptive weight subvectors. A modified adaptive algorithm based on the conventional RLS algorithm is derived to update the weight subvectors. Simulation results show that the proposed detector achieves better performance than the adaptive detector using conventional RLS algorithm especially for DS-CDMA systems with large processing gains. In addition, it is computationally efficient and robust against the near-far problem.

In this paper, we consider maximum likelihood estimation of multipath channel parameters in asynchronous direct-sequence code-division multiple access communication systems. The proposed algorithm is based on the training sequence which is transmitted by the desired user. By modeling the interfering signals as unknown colored Gaussian noise, the multiuser estimation problem is decomposed into a series of single user problems. Simulation results show that the proposed estimator is efficient and robust against the near-far problem and channel fading.