원문정보
초록
영어
Most researches on human behavior recognition are mainly based on the features of whole body motion. This paper proposed a hierarchical discriminative approach for recognizing human behavior based on limbs motion. The approach consists of feature extraction with mutual motion pattern analysis and discriminative behavior modeling in the hierarchical manifold space. A cascade CRF is introduced to estimate the motion patterns in the corresponding manifold subspace, and the trained SVM classifier is used to predict the behavior label for the current observation. The results on motion capure data prove the significance motion analysis of body parts, and the results on synthetic image sequences are also presented to demonstrate the robustness of the proposed algorithm.
목차
1. Introduction
2. Motion Pattern
2.1. Hierarchical Latent Variable Space of Human Behaviors
2.2. Visualization of Partial Body Movement Trails
2.3. Trajectory Clustering
3. Single Behavior Modeling based on Discriminative Models
4. Experiment Design and Discussion
4.1 Single behavior database
4.2. Results of Experiments with Motion Capture Data
5. Conclusion
References