基于并行隔帧差分光流场与灰度分析综合算法的运动目标检测

提出了隔帧差分的概念,并将其应用于光流场算法中,用改造后的隔帧差分光流场算法成功克服了传统光流场算法的不足(传统光流场算法不能识别帧间位移小于一个像元的运动目标).进一步对光流场计算结果与原始图像进行灰度综合分析,使目标的探测更加准确,减少了虚警和误判.采用不同间隔的序列差分构成并行识别系统结构,使整个系统能够探测各种不同速度的运动目标.实验结果表明:提出的运动目标检测算法能够准确有效地检测出不同速度的运动目标.

The Moving Target Detecting Based on the Parallelable Discontinuous Frame Difference Optical Flow Field Integrated with Gray Intensity Analysis

A new conception named Discontinuous Frame Difference was proposed, and it was applied in the optical flow field algorithm. The modified optical flow field algorithm successfully overcame the shortcoming of the classical optical flow field method that couldn't detect the object whose displacement was less than one pixel between two continuous frames. The result of the optical flow field algorithm was integrated with its original images to further accurately analyze the moving object, increasing the probability of detection and decreasing the susceptability of the false alarms. The discontinuous frame difference optical flow field algorithm can be composed of the parallel structure system, which can detect different kinds of moving objects with different velocities. The experiment result displayed that the algorithm proposed in this paper can accurately and validly detect different kinds of objects with different velocities.