Rgbd-hudaact: A color-depth video database for human daily activity recognition

In this paper, we present a home-monitoring oriented human activity recognition benchmark database, based on the combination of a color video camera and a depth sen-sor. Our contributions are two-fold: 1) We have cre-ated a publicly releasable human activity video database (i.e., named as RGBD-HuDaAct), which contains synchro-nized color-depth video streams, for the task of human daily activity recognition. This database aims at encour-aging more research efforts on human activity recognition based on multi-modality sensor combination (e.g., color plus depth). 2) Two multi-modality fusion schemes, which naturally combine color and depth information, have been developed from two state-of-the-art feature representation methods for action recognition, i.e., spatio-temporal in-terest points (STIPs) and motion history images (MHIs). These depth-extended feature representation methods are evaluated comprehensively and superior recognition per-formances over their uni-modality (e.g., color only) coun-terparts are demonstrated. 1