Title :
Dynamic body posture tracking using evolutionary optimisation
Author :
Robertson, C. ; Trucco, E. ; Ivekovic, S.
Author_Institution :
Sch. of Eng. & Phys. Sci., Heriot Watt Univ., Edinburgh, UK
Abstract :
A novel evolutionary approach for fitting and tracking articulated skeletons to 3D data of upper-body sequences typical of videoconferencing or newscasting is presented. A 24-dimensional skeleton fitting problem is solved with a novel particle swarm optimisation technique designed for simultaneous fitting and tracking. Experiments show good quality fits even in the presence of self-occlusions and partial 3D data.
Keywords :
evolutionary computation; image sequences; particle swarm optimisation; stereo image processing; tracking; 24-dimensional skeleton fitting problem; articulated skeleton models; dynamic body posture tracking; evolutionary optimisation; newscasting; partial 3D data; particle swarm optimisation; self-occlusions; upper-body sequences; videoconferencing;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20053672
