CAJ | 학술논문

为了改进目前常用的运动目标检测方法易受到亮度和噪声的影响及出现虚假目标的情况，提出了一种在视频序列中结合帧间差分法和背景差分法的运动目标识别算法。该算法利用帧间差分法得到当前帧中运动目标的信息，通过3帧差分运算和阈值分割，更好地实现视频序列中运动目标的识别；同时针对实时图像监控系统中视频信号传输的安全性，对信号传输进行了方式和技术上的对比分析；实验结果表明能够得到较好的识别结果。
위료개진목전상용적운동목표검측방법역수도량도화조성적영향급출현허가목표적정황，제출료일충재시빈서렬중결합정간차분법화배경차분법적운동목표식별산법。해산법이용정간차분법득도당전정중운동목표적신식，통과3정차분운산화역치분할，경호지실현시빈서렬중운동목표적식별；동시침대실시도상감공계통중시빈신호전수적안전성，대신호전수진행료방식화기술상적대비분석；실험결과표명능구득도교호적식별결과。
The current methods commonly used in moving targets detection are vulnerable to the impact of noise and brightness. It even leads to the emergence of false target. To solve the problem, a moving target identification method is proposed in this paper. This method combines the frame difference and background difference in video sequence. It uses the frame difference method to get the information of the moving target in the current frame, and improves the recognition rate of the moving target in video frame by using three frame difference operations and threshold segmentation. Furthermore, the paper analyzes and compares the signal transmission mode and technology for the security of video signal transmission in the real-time monitoring system. The experiment shows that this method could get better recognition results than traditional motion detection methods.