Learned Spatio-Temporal Texture Descriptors for RGB-D Human Action Recognition

Abstract

Due to the recent arrival of Kinect, action recognition with depth images has attracted researchers' wide attentions and various descriptors have been proposed, where Local Binary Patterns (LBP) texture descriptors possess the properties of appearance invariance. However, the LBP and its variants are most artificially-designed, demanding engineers' strong prior knowledge and not discriminative enough for recognition tasks. To this end, this paper develops compact spatio-temporal texture descriptors, i.e. 3D-compact LBP (3D-CLBP) and local depth patterns (3D-CLDP), for color and depth videos in the light of compact binary face descriptor learning in face recognition. Extensive experiments performed on three standard datasets, 3D Online Action, MSR Action Pairs and MSR Daily Activity 3D, demonstrate that our method is superior to most comparative methods in respects of performance and can capture spatial-temporal texture cues in videos.