【摘要】 复杂背景下运动人体目标的自动检测与跟踪效果常易受环境光线变化的干扰.面向变光线环境下运动人体检测与跟踪,提出一种基于混合高斯模型优化的Camshift检测跟踪算法,首先采用混合高斯模型进行前景建模,将外界扰动作为背景信息进行处理;然后进行色彩空间转换并计算反向投影值,进一步利用Meanshift迭代定位运动目标;最后,通过更新混合高斯模型及后续帧的处理保持人体目标的有效检测及跟踪.实验结果表明,该方法相较于传统的光流方法及Camshift算法,可更好地适应环境光线变化及枝叶晃动影响,较好地获取运动目标前景信息,提高运动人体目标的检测及跟踪精度.更多还原

【Abstract】 The automatic detection and tracking effects of moving human target are always susceptible to the change of ambient light under the complex backgrounds. Aiming at the moving human target detection and tracking in variable lighting environments,the paper proposes a detection and tracking algorithm based on Camshift optimized by Gaussian mixture model. Firstly,the Gaussian mixture model is used to build the foreground model,and the external interference is settled as background information. Secondly,the color space is converted and backprojection values are calculated,and Meanshift iterative method is further used to locate the moving targets. Finally,the update of Gaussian mixture model and processing of subsequent frames can keep an effective detection and tracking of the moving human body. The experiment results show that the proposed algorithm has a better adaptive ability to the changing light of the ambient environment and the shaking of the foliage compared with traditional optical flow and Camshift methods. Besides,this algorithm can improve the detection and tracking accuracy of moving human body,and can better extract the foreground information of moving target.更多还原