CAJ | 학술논문

采用中值滤波去除视频图像中所含的椒盐噪声，通过形态学处理对目标的二值化图像进行去噪处理。利用多点定位算法实现目标跟踪。根据运动目标的轮廓高宽比、面积、质心等特征量识别人体，当行人进入视频中特定区域后，进行人流量的统计。实验结果表明，该方法稳定性强、准确率高，所设计的系统能够满足实时要求。
채용중치려파거제시빈도상중소함적초염조성，통과형태학처리대목표적이치화도상진행거조처리。이용다점정위산법실현목표근종。근거운동목표적륜곽고관비、면적、질심등특정량식별인체，당행인진입시빈중특정구역후，진행인류량적통계。실험결과표명，해방법은정성강、준학솔고，소설계적계통능구만족실시요구。
In order to realize single target tracking and target statistics in video monitoring , a method of combining background difference and inter-frame difference is proposed .The method can both detect moving objects effectively and improve the precision of target detection .Median filter is adopted to remove salt and pepper noise in the image and morphology processing is introduced to reduce noise of extracted target binary image .Target tracking is well re-alized by using multi-point location algorithm .Human is detected according to moving target characteristic parame-ters, such as body ratio between height and width , target area, center of mass.When pedestrians go into a specific area in video monitoring , the system can count the number of pedestrians .Experimental results show that the pro-posed method is robust and of high accuracy .The proposed system could satisfy the real-time requirement .