HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 716 - 723
• Main Authors: Oreifej, Omar, Zicheng Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: 4D Normals; Action Recognition; Activity Recognition; Depth; Histogram of Gradients; Histogram of Normals; Histograms; HOG; HON; Joints; Kinect; MSR Action 3D; MSR Action Pairs; MSR Daily Activity; Polychoron; Quantization (signal); Shape; Support vector machines; Three-dimensional displays; Vectors
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2013.98

We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates. To build the histogram, we create 4D projectors, which quantize the 4D space and represent the possible directions for the 4D normal. We initialize the projectors using the vertices of a regular polychoron. Consequently, we refine the projectors using a discriminative density measure, such that additional projectors are induced in the directions where the 4D normals are more dense and discriminative. Through extensive experiments, we demonstrate that our descriptor better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.