基于双目视觉的运动目标检测系统

为了满足室内环境监控的需求,提出一套基于双目视觉的运动目标检测系统。该系统由数据采集与存储模块、运动目标检测模块、对应点匹配模块和测距模块共四部分组成。运动目标检测模块对采集到的双通道视频分别采用背景差分法进行目标提取,然后对双通道的每帧图像进行粗匹配,并采用尺度不变特征变换算法进行精匹配,找到双通道图像的匹配点对,完成运动目标的距离测量。经实验证明,新系统可以有效提取运动目标,并进行距离测量,尤其可以解决目标物被部分遮挡的距离测量问题。

A binocular vision-based moving object detection system

In order to satisfy the needs of the indoor environment monitoring,a set of binocular vision-based motion detection system is presented.The system consists of data acquisition and storage module,moving target detection module,the corresponding point matching module and ranging module.In motion detection module,for dual-channel video capture respectively,the background difference method was used for target extraction.Each of the dual-channel frames was coarse matched firstly,then fine matching using SIFT algorithm to find the match points.Finally,using the matching point calculates the distance.The experiments show that this system can be very effective in extracting moving target and measuring distance,especially in distance measuring of obstructed targets.