| 摘 要: 视频监控中的行人跟踪是一个具有实际应用价值的研究领域。针对城市中智能视频监控中行人跟踪问 题，提出了一种改进的基于彩色直方图均衡化的MeanShift行人跟踪算法，实验的图像序列通过监控摄像头获得。这种 行人跟踪算法是基于均值移位算法，它使用颜色直方图均衡化来改进原始算法。通过使用CAVIAR project/IST 2001 37540数据集来进行试验，试验结果表明，改进后的算法在某些情况下比原算法表现得更好。 |
| 关键词: 计算机图像处理；mean shift；行人跟踪；直方图均衡化 |
|
中图分类号: TP391.41
文献标识码: A
|
|
| Improved Mean Shift Algorithm for Pedestrian Tracking Based on Color Histogram Equalization |
|
FU Limei
|
( Department of Software Engineering, Dalian Neusoft University of Information, Dalian 116023, China)
|
| Abstract: The pedestrian tracking in video monitoring is a research field with practical application value.An improved pedestrian tracking algorithm is proposed with image sequences acquired by surveillance cameras to solve the problem of pedestrian tracking in in smart video monitoring in cities.This pedestrian tracking algorithm is based on mean shift algorithm,using color histogram equalization to improve the original algorithm and applying CAVIAR project/IST 2001 37540 dataset to evaluate the algorithm.Experimental results show that the improved algorithm performs much better than the original one in some situations. |
| Keywords: computer image processing;mean shift;pedestrian tracking;histogram equalization |
