Human Upper Body Post Estimation Based On Modified Multiple Importance Sampling Algorithm
Main Article Content
Abstract
Tracking of human motion and their body parts under dynamic environment has been the difficult task during video detection situations. The work is to propose the human object video tracking methods to estimate the movement of human upper body under dynamic environment. Considering the mixture of frequent moving object parts with occlusion problem, deciding of target object identification and upper body pose variations will end in improving the accuracy. It also helps with reduction in occlusion of the moving body parts detection. The Modified Multiple Importance Sampling filter (MMIS) has been proposed to trace the human poses with fast paced actions. Dynamic sampling filer tracks the upper a part of physical body with 2D image and 3D postures. The high accuracy of the system has been obtained for cluttered environment with occlusion problem by properly obtaining the sampling states of the filter as shown within the experimental result analysis part.