一种基于压缩感知的运动目标检测技术

A Moving Target Detection Technology Based on Compressed Sensing

运动目标检测是计算机视觉、图像处理等相关领域的研究热点,其核心就是对视频图像中的每一帧图像进行相应的研究和处理。本文主要研究思路是从压缩感知技术采样信号的角度出发,将每一帧的二维图像压缩采样成具有少量信息的一维信号,再通过信号重构用少量数据量将图像重构出来,最后通过目标检测技术对每一帧的图像进行运动目标提取。仿真实验表明该方法是可行和有效的,同时可以大大减少目标检测中所记录的数据量,解决海量数据的存储与传输问题。

Moving target detection is a research hotspot in computer vision, image processing and other related fields. The core is to study and process each frame of image in video image. The main research idea of this paper is to compress and sample the two-dimensional image of each frame into a one-dimensional signal with a small amount of information, and reconstruct the image. Finally, the moving target extraction is performed on the image of each frame by the target detection technique. Simulation experiments show that the method is feasible and effective, and can greatly reduce the amount of data recorded in the target detection, and solve the problem of storage and transmission of massive data.