Qiong Liu’s research while affiliated with Beijing Institute of Technology and other places

For sophisticated background, a human body tracking algorithm using particle filter based on a 3D articulated body model is introduced. First, a high-fidelity biomechanical upper body model, which is accurate for representing varies complicated human poses and simple to be developed, has been built. Then sequences of images are obtained by using a stereo camera. After calibration, verification and background subtraction, depth map, foreground silhouette, arms skeleton are chosen to construct the likelihood function. The state vectors describing the human pose are computed by fitting the articulated body model to observed person using particle filter. In order to reduce the computational complexity and the number of particles, constraints are employed to restrict the state parameters. Experimental results show that the proposed algorithm can track human upper body with different poses, different person under different illumination conditions fast and accurately.

For sophisticated background, a fast and self-adaptive face detection algorithm based on skin color is introduced. In this algorithm, histogram skin color model was built with great amount of skin color pixels in HS color space first, and then skin color segmentation was made to images by using histogram backprojection, in which a binary image of skin color area was obtained after thresholding. Morphological and Blob analysis were used to make further optimization to the segmentation result. Experimental results show that the proposed algorithm can detect faces with different sizes, rotations and expressions under different illumination conditions fast and accurately.