基于幂次变换和区域收缩算法的运动目标检测与定位

运动目标分割与跟踪是计算机视觉中的重要研究课题,而目标检测与定位是其中的必要步骤,对分割与跟踪效果影响很大.在此提出一种新的运动目标检测与定位方法,该方法在差分二值图像上,通过区域收缩定位到运动像素密度较大的区域,从而实现运动目标定位.在多目标情况下,先通过幂次变换突出不同位置的目标,然后再通过区域收缩实现目标定位,给出目标的特征矩形,便于进一步的跟踪与识别.该方法不需要任何关于目标数的先验知识,对噪声鲁棒性较强.文中给出的实验结果证明该算法的有效性.

Moving object detection and location based on region shrinking algorithm

Object detection and location are the essential steps in moving object segmentation and tracking which are the important tasks in computer vision.A new approach of moving object detection and location is proposed in this paper.In a binary difference image the region with high density of motion pixels is approached by region shrinking to implement moving object detection and location.Under the situation of more than one object in an image power translation is adopted to enhance objects at different position,...