侦查目标追踪过程中视频浓缩方法仿真  

Video Concentration Method Simulation in Investigation Target Tracking Process

作　　者：李娟 LI Juan(Shanxi Police College,Taiyuan Shanxi 030000,China;Shanxi University of Finance and Economics,Taiyuan Shanxi 030006,China)

机构地区：[1]山西警察学院,山西太原030000 [2]山西财经大学,山西太原030006

出　　处：《计算机仿真》2020年第4期441-445,共5页Computer Simulation

摘　　要：在侦查目标追踪过程中,采用当前方法对视频进行浓缩处理时,所用时间较长,浓缩处理后视频中有效信息丢失率较高。为此,提出新的侦查目标追踪过程中视频浓缩方法。通过混合高斯模型模拟视频信号,实现视频前景建模和背景建模;在Camshift算法下降H分量的颜色概率分布图和颜色直方图相结合,对视频中存在的图像帧进行运算,通过调整搜索窗的大小实现对运动目标的追踪;采用松弛线性规划算法获得目标运动轨迹对应的最优时间标签,结合目标轨迹、背景序列和最优时间标签实现视频的浓缩处理。仿真结果表明,所提方法的浓缩耗时较短,视频中有效信息得到了有效保存。In the process of investigation target tracking, the current method leads to high loss rate of effective information in video after the concentrated treatment. Therefore, a new concentration method was proposed in the process of investigation target tracking. Firstly, the video signals were simulated by Gaussian mixture model, and then foreground modeling and background modeling were realized. Based on the Camshift algorithm, the color probability distribution diagram and color histogram of H component were combined to compute the image frames in video. Secondly, the moving target was tracked by adjusting the size of search window. Thirdly, relaxation linear programming algorithm was used to obtain the optimal time tag corresponding to the target trajectory. Finally, the video concentration was achieved by combining the target trajectory, background sequence and optimal time tag. Simulation results show that the concentration time of the proposed method is short and the effective information in video is preserved.

关 键 词：侦查目标 目标追踪 视频浓缩 浓缩耗时 有效信息丢失率 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]