基于角点特征的粘连车辆分割方法

Occluded Vehicle Segmentation Method Based on Corner Feature

在智能交通系统粘连车辆的分割中,已有方法不能很好地保留车辆目标的轮廓细节。为此,提出一种基于角点特征的粘连车辆分割方法。采用帧差法提取运动车辆,借助数学形态学方法进行修复,引入长宽比、面积比等形态参数,判定粘连类别,结合Harris角点和K-means算法,检测并还原粘连区的角点,以实现粘连车辆的分割。实验结果表明,该方法能较好地保留车辆的轮廓细节信息,达到预期的实验效果。

How to segment the occluded vehicle is a key problem in Intelligent Transportation System（ITS）. But the available algorithms can not preserve the edge characteristics of vehicle. This paper presents a new occluded vehicle segmentation method based on comer feature. It chooses the frame difference method to extract object and uses the mathematical morphology to repair, introduces two geometric parameters to judge the overlapping type, combines Harris comer detection with the K-means algorithm to identify the comer points which is in the overlapping area, realizes the segmentation for overlapping vehicle according to the axial symmetry. Experimental results show that this method can keep the vehicle＇s profile details information, and realizes the desired results.