摘要
视频监控常常采用多个静止的摄像机监控视场范围比较大的区域,本文研究了多个摄像机的视频图像合成算法。对于多个静止的摄像机,利用相位相关算法估计输入视频的相应第一帧重叠区域,并在重叠区域内进行Harris角点检测和匹配,以加快角点匹配的速度并且提高匹配的稳健性;对于非首帧的视频,也只需在第一帧估计的重叠区域内进行角点检测。使用RANSAC算法去除外点,计算各个摄像机间的变换矩阵,并将多个视频序列合成一个大视频序列。与传统算法相比,该算法提高了运行速度,增加了实用性。
Multiple static cameras is often used to monitor activities over a wide area in video surveillance system. This paper studies the video compositing algorithm of multiple static cameras. For multiple static cameras, phase correlation was used to roughly compute the translation offset between the first corresponding frames of two video streams, so corner match procedure was speeded up and matching stability was inproved. Then, in the overlapped region, Harris method was used to detect and register corners. For the other frames, estimated in the first frame only within the region of overlap corner detection. RANSAC algorithm was used to eliminate outliers to ensure effectiveness of the matched corner pairs. Then it computes the homography of each camera, and a large video sequence is composited from the multiple video sources. Invalid parameters were verified by the translation offset to make Levenberg-Marquardt optimization more successful.
出处
《电子测试》
2011年第12期8-11,15,共5页
Electronic Test
