Scene recognition is a basic task towards image understanding. Spatial Pyramid Matching (SPM) has been shown to be an efficient solution for spatial context modeling. In this paper, we introduce an alternative approach, Orientational Pyramid Matching (OPM), for orientational context modeling. Our approach is motivated by the observation that the 3D orientations of objects are a crucial factor t...

In this work, we propose a new algorithm for spectral color image segmentation based on the use of a kernel matrix. A cost function for spectral kernel clustering is introduced to measure the correlation between clusters. An efficient multiscale method is presented for accelerating spectral color image segmentation. The multiscale strategy uses the lattice geometry of images to construct an ima...

Traditional sparse representation algorithms usually operate in a single Euclidean space. This paper leverages a self-explanatory reformulation of sparse representation, i.e., linking the learned dictionary atoms with the original feature spaces explicitly, to extend simultaneous dictionary learning and sparse coding into reproducing kernel Hilbert spaces (RKHS). The resulting single-view self-...

In this paper, a real-time multi-layer background subtraction based on Gaussian pyramid is proposed for moving object detection. The proposed method models background on two levels: region analysis in the high-resolution level with averaging background model and pixel analysis in the low-resolution level with hierarchical non-parametric kernel density estimation method. The new method has lower...

Foveated imaging exploits the fact that the spatial resolution of the human visual system decreases dramatically away from the point of gaze. Because of this fact, large bandwidth savings are obtained by matching the resolution of the transmitted image to the fall-off in resolution of the human visual system. We have developed a foveated multiresolution pyramid (FMP) video coder/decoder which r...

In this paper, we propose a new approach of visual vocabulary optimization with spatial context, which contains important spatial information that has not been fully exploited. The novelty of our method mainly lies in two aspects: when spatial information is considered, and how spatial information is used. For the first aspect, the existing methods generally consider spatial information after t...

Action recognition in videos is a relevant and challenging task of automatic semantic video analysis. Most successful approaches exploit local space-time descriptors. These descriptors are usually carefully engineered in order to obtain feature invariance to photometric and geometric variations. The main drawback of space-time descriptors is high dimensionality and efficiency. In this paper we ...

Spatial pyramids have been successfully applied to incorporating spatial information into bag-of-words based image representation. However, a major drawback is that it leads to high dimensional image representations. In this paper, we present a novel framework for obtaining compact pyramid representation. Firstly, we investigate the usage of the divisive information theoretic feature clustering...