Passive and convenient depth estimation from single-shot image is still an open problem. Existing depth from defocus methods require multiple input images or special hardware customization. Recent deep monocular depth estimation is also limited to an image with sufficient contextual information. In this work, we propose a novel method which realizes a single-shot deep depth measurement based on physical depth cue using only an off-the-shelf camera and lens. When a defocused image is taken by a camera, it contains various types of aberrations corresponding to distances from the image sensor and positions in the image plane. We call these minute and complexly compound aberrations as Aberration Map (A-Map) and we found that A-Map can be utilized as reliable physical depth cue. Additionally, our deep network named A-Map Analysis Network (AMA-Net) is also proposed, which can effectively learn and estimate depth via A-Map. To evaluate validity and robustness of our approach, we have conducted extensive experiments using both real outdoor scenes and simulated images. The qualitative result shows the accuracy and availability of the method in comparison with a state-of-the-art deep context-based method.

This paper presents a patch-based approach for crowd density estimation in public scenes. We formulate the problem of estimating density in a structured learning framework applied to random decision forests. Our approach learns the mapping between patch features and relative locations of all objects inside each patch, which contribute to generate the patch density map through Gaussian kernel density estimation. We build the forest in a coarse-to-fine manner with two split node layers, and further propose a crowdedness prior and an effective forest reduction method to improve the estimation accuracy and speed. Moreover, we introduce a semi-automatic training method to learn the estimator for a specific scene. We achieved state-of-the-art results on the public Mall dataset and UCSD dataset, and also proposed two potential applications in traffic counts and scene understanding with promising results.

While online approaches for multi-person tracking are still hard to deal with occlusions, many tracking methods use a global data association approach to find person trajectories on a long segment of consecutive frames. Such offline approaches often cause long output latencies, which are unsuitable for camera-based surveillance systems. Based on an observation that the current position of an object should be estimated from both its past and future positions that are observed in a short period of time, we propose a novel object tracking method based on a dynamic programming framework. This method iteratively associates and integrates track lets obtained by visual tracking which are observed just before and after occlusions. We always produce outputs at a constant short delay time, and requires only the standard HOG detector for high performance. Our tracking method can run at 10-60 fps on a single CPU core, and attains the state-of-the-art performance for the Town Center dataset.

This paper presents a novel and generic approach for metric learning, random ensemble metrics (REMetric). To improve generalization performance, we introduce the concept of ensemble learning to the metric learning scheme. Unlike previous methods, our method does not optimize the global objective function for the whole training data. It learns multiple discriminative projection vectors obtained from linear support vector machines (SVM) using randomly subsampled training data. The final metric matrix is then obtained by integrating these vectors. As a result of using SVM, the learned metric has an excellent scalability for the dimensionality of features. Therefore, it does not require any prior dimensionality reduction techniques such as PCA. Moreover, our method allows us to unify dimensionality reduction and metric learning by controlling the number of the projection vectors. We demonstrate through experiments, that our method can avoid overfitting even though a relatively small number of training data is provided. The experiments are performed with three different datasets; the Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset, the Labeled Face in the Wild (LFW) dataset and the Oxford 102 category flower dataset. The results show that our method achieves equivalent or superior performance compared to existing state-of-the-art metric learning methods.

This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) representing the process of blur on faces. Inferring a PSF from a single facial image is an ill-posed problem. Our method uses learned prior information derived from a training set of blurred faces to make the problem more tractable. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another. We learn statistical models that represent prior knowledge of predefined PSF sets in this feature space. A query image of unknown blur is compared with each model and the closest one is selected for PSF inference. The query image is deblurred using the PSF corresponding to that model and is thus ready for recognition. Experiments on a large face database (FERET) artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared to existing methods. We also demonstrate improved performance on real blurred images on the FRGC 1.0 face database. Furthermore, we show and explain how combining the proposed facial deblur inference with the local phase quantization (LPQ) method can further enhance the performance.

This paper proposes a novel method for deblurring facial images to recognize faces degraded by blur. The main problem is how to infer a point spread function (PSF) representing the process of blur. Inferring a PSF from a single facial image is an ill-posed problem. To make this problem more tractable, our method uses learned prior information derived from a training set of blurred facial images of several individuals. We construct a feature space such that blurred faces degraded by the same PSF are similar to one another and form a cluster. During training, we compute a statistical model of each PSF cluster in this feature space. For PSF inference we compare a query image of unknown blur with each model and select the closest one. Using the PSF corresponding to that model, the query image is deblurred, ready for recognition. Experiments on a standard face database artificially degraded by focus or motion blur show that our method substantially improves the recognition performance compared with state-of-the-art methods. We also demonstrate improved performance on real blurred images.

In this paper, we propose a generic and efficient object detection framework based on two heterogeneous features and demonstrate effectiveness of our method for a cat face detection problem. Simple Haar-like features with AdaBoost are fast to compute but they are not discriminative enough to deal with complicated shape and texture. Therefore, we cascade joint Haar-like features with AdaBoost and CoHOG descriptors with a linear classifier. Since the CoHOG descriptors are extremely high dimensional pattern descriptors based on gradient orientations, they have a strong classification capability to represent various cat face patterns. The combination of these two distinct classifiers enables fast and accurate cat face detection. The experimental result with about 10,000 cat images shows that our method gives better performance in comparison with the state-of-the-art cat head detection method, although our method does not exploit any cat specific characteristics.

In this paper, we propose a novel feature localization method based on a global vector concentration approach. Our approach does not rely on the detection of local salient features around feature points. Instead, we exploit global structural information of the object extracted by calculating the concentration of directional vectors from sampling points. Those vectors are combined with local pattern descriptors of a query image and selected from preliminarily trained extended templates by nearest neighbor search. Due to the insensitivity of local changes, our method can handle partially occluded and noisy objects. We apply the proposed method to fully automatic feature localization of the left ventricular in echocardiograms. The results show the effectiveness of our method in comparison with a conventional edge-based method in terms of accuracy and robustness.

In this paper, we propose an efficient and generic facial feature localization method based on a weighted vector concentration approach. Our method does not require any specific priors on facial shape but implicitly learns its structural information from a training data. Unlike previous work, facial feature points are globally estimated by the concentration of directional vectors from sampling points on a face region, and those vectors are weighted by using local likelihood patterns which discriminate the appropriate position of the feature points. The directional vectors and local likelihood patterns are provided through nearest neighbor search between local patterns around the sampling points and a trained codebook of extended templates. The combination of the global vector concentration and the verification with the local likelihood patterns achieves robust facial feature point detection. We demonstrate that our method outperforms state-of-the-art method based on the Active Shape Models in our evaluation.