Human and Animal Behavior Understanding

Abstract

Human and Animal Behavior Understanding Wenbin Chen Human and animal behavior understanding is an important yet challenging task in computer vision. It has a variety of real-world applications including human computer interaction (HCI), video surveillance, pharmacology, genetics, etc. We first present an evaluation of spatiotemporal interest point features (STIPs) for depth-based human action recognition, and then propose a framework call TriViews for 3D human action recognition with RGB-D data. Finally, we investigate a new approach for animal behavior recognition based on tracking, video content extraction and data fusion. STIPs features are widely used with good performances for action recognition using the visible light videos. Recently, with the advance of depth imaging technology, a new modality has appeared for human action recognition. It is important to assess the performance and usefulness of the STIPs features for action analysis on the new modality of 3D depth map. Three detectors and six descriptors are combined to form various STIPs features in this thesis. Experiments are conducted on four challenging depth datasets. After evaluating STIPs features for depth-based human action recognition, we propose an effective framework called TriViews to utilize 3D information for human action recognition. It projects the 3D depth maps into three views, i.e., front, side, and top views. Under this framework, five features, i.e., spatiotemporal interest points (STIP), dense trajectory First of all, I would like to express my sincere thanks to my advisor, Dr Guodong Guo for his guidance, encouragement and help during my graduate study as a research assistant. I appreciate his support and trust in me.