It has become increasingly popular to study animal behaviors with the assistance of video recordings. The traditional way to do this is to first videotape the animal for a period of time, and then a human observer watches the video and annotates the behaviors of the animal manually. This is a time and labor consuming process. Moreover, the observation results vary among different observers. Thus it would be a great help if the behaviors could be accurately derived from an automated video processing and behavior analysis system. We are interested in developing techniques that will facilitate such a system for studying animal behaviors.;The video based behavior analysis systems can be decomposed into four major problems: behavior modeling, feature extraction from video sequences, basic behavior unit (BBU) discovery and complex behavior recognition. The recognition of basic and complex behaviors involves behavior definition, characterization and modeling. In the literature, there exist various techniques that partially address these problems for applications involving human motions and vehicle surveillance.;We propose a system approach to tackle these problems for animals. We first propose a behavior modeling framework, and a behavior model consisting of four levels: physical, physiological, contextual, and conceptual. Then we propose that the feature extraction and selection shall be guided by intrinsic variables that can distinguish different BBUs. BBUs are then determined from these features using the modified affinity graph method and a classification tree approach. We further investigated the application of a vector fusion method to reduce the feature dimensionality. Finally, we present results on analyzing behavior patterns for a simple problem, and apply the behavior models (transition probabilities, etc.) and rules (gained from prior knowledge) to correct and update the behaviors. These steps have been successfully applied to synthetic or real mouse video data, and in the future we expect to extend the methodology to study other video scenarios, like human behaviors or sports analysis.
展开▼
