复杂背景下运动目标分割算法研究

综合运动目标的边缘信息和运动信息,提出一种复杂背景下运动目标的分割算法。在计算光流场时采用各向异性的平滑约束,从而实现了对图像光流场的自适应计算。利用Canny算子检测出的不封闭边缘作为初始信息,根据光流场的连续特性进行边缘生长后可获得对目标的初始分割。对初始分割结果进行边界跟踪,通过保留具有最长边界长度的团块,去掉背景中的杂散噪声,就可获得清楚的分割图。实验证明,该方法能对复杂背景下的运动目标进行准确的分割。

Segmentation of moving object in complex environment

A new segmentation algorithm, which combines the edge information and motion information for segmenting moving object in complex environment, is proposed. The new method puts different smoothness constraints on different directions and optical flow constraint is used according to the gradient magnitude. Then the optical flow field can be obtained with adaptive optical flow method. Canny edge detector can get the most edge information but miss some pixels. In order to restore these missing pixels the edge has a growing based on the continuity of optical flow field. Next, by remaining the block that has the longest edge could delete the noise in the background, and then the last segmentation result is obtained. The experimental result demonstrates that this method can segment the moving object in complex environment precisely.