【摘要】 针对室外复杂交通场景中多运动目标分割问题,提出了一种由变化检测和运动分割组成的算法,利用水平集算法对帧差图像进行变化检测得到运动窗口,在运动窗口范围内进行改进的k-均值聚类分割,利用运动相似性进行分割区域融合.算法避免了整个图像的分割,减少了运算量,完整的分割出运动目标.试验结果表明,算法不仅能从复杂交通场景图像序列中有效的检测和提取出运动目标并有很强的鲁棒性,而且能够解决运动目标的遮挡问题.更多还原

【Abstract】 To solve multiple moving objects segmentation problem in complex traffic scene outdoors,a new segmentation algorithm of multiple moving objects segmentation in complex traffic scene of outdoors was developed.The presented method consists of two phases.In the motion detection phase,motion-changed region was determined using an improved level set algorithm based on Mumford-Shah model of two consecutive frames difference of image sequence,and an simplified clustering algorithm providing initialization evolution curves of level set algorithm.Motion window was generated through detecting motion-changed region.In the motion segmentation phase,regions segmentation using an improved weighted k-means clustering algorithm of moving windows area were merged based on region motion similarity criterion.Computation time was reduced because of avoiding processing of the whole image.Very promising experimental results indicates that the proposed algorithm is effective with strong robustness using real image sequences of complex traffic scene and can resolve occlusions among multiple moving objects.更多还原