Search

In this paper, a method based on depth spatial-temporal maps(DSTMs) is presented for human action recognition from depth video sequences, which provides compact global spatial and temporal information of human motion for action recognition. In our approach, the initial frame of depth sequences is dilated to generate 3D body mask. The new depth sequences of major part of the human body are then computed after using 3D body mask on each depth frame. We project each frame of the new depth sequences onto three orthogonal axes to get three binary lists. Under each projection axis, binary lists are stitching in order through an entire depth sequence forming a DSTM. We evaluate our method on two standard databases. Experimental results show that this method could effectively capture the spatial and temporal information of human motion and improve the accuracy of human action recognition.

This paper presents a new method for human action recognition fusing depth images and skeletal maps. Each depth image is represented by 2D and 3D auto-correlation of gradients features. A feature using spatial and orientational auto-correlation is extracted from depth images. Mutual information is used to define the similarity of each frame in the skeleton sequence, and then extract the key frames from the skeleton sequence. The skeleton feature extracted from the key frames as complementary features to cope with the temporal information loss in depth images. Each set of feature is used as input to two extreme learning machine classifiers and assign different weight to each set of feature. Using different classifier weights provides more flexible to different features. The final class label is determined according to the fused result. Experiments conducted on MSR_Action3D depth action data set show the accuracy of this proposed method is 1.5% higher than the state-of-the-art action recognition methods.

In this paper, we introduce multi-symplectic Lagrangian variational integrators for solving Chan-Vese active contour models in image segmentation. Energy functionals are discretized firstly, and numerical schemes are derived from discrete Euler-Lagrange equations based on discrete variational principle. Lagrangian variational integrators preserve native differential structure-multi-symplecticity, that makes the numerical methods have a satisfied behavior. Experiments are performed on the benchmark images from literature. We further evaluated the methods in a segmentation database containing 1023 images. It shows that the proposed numerical schemes attain relatively faster convergence rates and better segmentation accuracy. Comparisons with the standard explicit Euler method of the original Chan-Vese model and other fast numerical optimization methods show that the proposed methods have better stability, higher accuracy, and are more robust when dealing with a large number of pictures. This study provides an example for further research to improve the performance of other existing image segmentation methods based on active contour models.

Face recognition has attracted extensive interests due to its wide applications. However, there are many challenges in the real world scenario. For example, relatively few samples are available for training. Face images collected from surveillance cameras may consist of complex variations (e.g. illumination, expression, occlusion and pose). To address these challenges, in this paper we propose learning class-specific and intra-class variation dictionaries separately. Specifically, we first develop a discriminative class-specific dictionary amplifying the differences between training classes. We impose a constraint on sparse coefficients, which guarantees the sparse representation coefficients having small within-class scatter and large between-class scatter. Moreover, we introduce a new intra-class variation dictionary based on the assumption that similar variations from different classes may share some common features. The intra-class variation dictionary not only captures the inner-relationship of variations, but also addresses the limitation of the manually designed dictionaries that are person-specific. Finally, we apply the combined dictionary to adaptively represent face images. Experiments conducted on the AR, CMU-PIE, FERET and Extended Yale B databases show the effectiveness of the proposed method.