营区扫描式监控中的运动目标检测

Moving object detection by scanning monitor in camp's area

为解决部队营区监控中运动目标检测问题,提出了基于扫描式的运动目标检测法。对通过云台采集的背景帧提取边缘特性生成特征图,搜索与实时视频帧特征图相似度最大的背景帧。采用一种基于非规则形状的K值模板匹配进行运动补偿,并提出一种基于分块的前景连通法。实验结果表明,该背景搜索法降低了计算维度,算法快速;匹配算法对图像噪声、局部光照变化具有很好的鲁棒性;前景连通算法具有很好的检测效果,且可行有效。

In order to solve the problem of moving object auto-detection of large field in camp＇s area,this paper proposed a new method about moving object detection which based on scanning monitor.By using Pan-Tilt-Zoom（PTZ） camera to scan a certain cycle time when no moving object to get the vertical projection using the result of vertical edge detection.When entering real-time video,by comparing the similarity between feature map of real-time frame and background frame to find out the most similar one to real-time video.Based on the irregular shape K-degree template matching to compensate the real-time image and got the foreground due to background subtraction.By setting up a method of using block template to connect foreground to find out the solution to incoherence of foreground area.Experiment resuls show the method of searching background reduces the dimension of calculation.The matching algorithm is robust and fast under the condition of local lighting,noise.The algorithm of foreground connection is effective and efficient.