Detecting and tracking body parts of multiple people
Abstract
This paper describes a framework for tracking body parts (e.g., hands and face) of multiple people in image sequences. We use a probabilistic model to fuse color and motion information to local- or the body parts and employ multiple hypothesis tracking (MHT) algorithm to track these features simultaneously. We incorporated a path coherence function along with MHT to reduce the negative effects of spurious measurements that produce unconvincing tracks and needless computations. The performance of the framework has been validated using experiments on synthetic and real sequence of images.
Publication Title
IEEE International Conference on Image Processing
Recommended Citation
Polat, E., Yeasin, M., & Sharma, R. (2001). Detecting and tracking body parts of multiple people. IEEE International Conference on Image Processing, 405-408. Retrieved from https://digitalcommons.memphis.edu/facpubs/13656