基于自适应前景分割及粒子滤波的人体运动跟踪

提出了在图像序列中用自适应前景分割及粒子滤波对人体的3-D运动轨迹进行跟踪的方法．首先建立了像素点的高斯模型，并结合图像帧间的差分信息以及灰度分布的先验概率等因素完成了图像中人体的自适应分割．根据所得到的分割结果建立了透视投影下的运动平面跟踪模型．根据投影过程的非线性以及图像中噪声分布的未知性，提出了粒子滤波的跟踪方法，并最终得到了人体运动平面的3-D轨迹．实际人体运动图像序列的实验证明，本文方法能有效地跟踪人体运动的3-D轨迹，并反映出在此跟踪问题上粒子滤波比传统的扩展卡尔曼滤波更具优势．

Tracking of Human Motion Based on Adaptive Foreground Segmentation and Particle Filter

An approach to the tracking of trajectories of 3-D human motion from image sequence based on adaptive foreground segmentation and particle filter is proposed in this paper. First, the Gaussian model for image pixel is presented, Based on this, the adaptive segmentation of human body is finished using the information of difference image and the prior distribution of pixel density. Then, the tracking model under perspective imaging for body plane is established. Due to the fact that image function is nonlinear and the distribution of the noise in images is unknown, the particle filter based tacking is used. Finally, the 3-D trajectory of body plane is obtained. Experimental results show that 3-D trajectory of body plane can be effectively tracked, and the tracking results of particle filter is better than that of extended Kalman filter for this human motion tracking problem.