基于空间边缘方向直方图的Mean Shift跟踪算法

王新红; 王晶; 田敏; 杨煜; 李志鹏

doi:10.11834/jig.20080335

主题栏目 | 浏览量 : 0 下载量: 242 CSCD: 0

PDF
导出
分享
收藏
专辑

基于空间边缘方向直方图的Mean Shift跟踪算法
Mean Shift Tracking Algorithm based on Spatial Edge Orientation Histograms
2008年13卷第3期页码：586
纸质出版：2008
DOI： 10.11834/jig.20080335
稿件说明：

移动端阅览

王新红, 王晶, 田敏, 杨煜, 李志鹏. 基于空间边缘方向直方图的Mean Shift跟踪算法[J]. 中国图象图形学报, 2008,13(3):586. DOI： 10.11834/jig.20080335.

Mean Shift Tracking Algorithm based on Spatial Edge Orientation Histograms[J]. Journal of Image and Graphics, 2008, 13(3): 586. DOI： 10.11834/jig.20080335.

摘要

传统的基于色彩直方图或空间色彩直方图的Mean Shift跟踪算法，在诸如跟踪目标出现尺度变化的复杂条件下，无法得到准确的跟踪结果。这是因为色彩直方图或空间色彩直方图无法显著区分颜色相近的目标和背景。鉴于此，提出了一种基于空间边缘方向直方图的Mean Shift跟踪算法，使用空间分布和纹理信息作为匹配信息。实验结果表明，该算法能够有效的处理遮挡、光照变化和尺度缩放等复杂情况，对目标进行准确有效的跟踪，改善了传统方法在尺度缩放等方面的局限性。

Abstract

Traditional mean shift tracking algorithm based on color histogram or spatial color histogram sometimes fails to get accurate results under intricate conditions

such as scale modifications occur to the objects. That is because the histograms based on color cannot distinguish objects and background have the same color. This paper presents a new mean shift algorithm based on spatial edge orientation histograms

using space distribution and texture information as matching information. Experiments proved the new algorithm can deal with intricate conditions

such as occlusion

different luminance and scale modifications

and track objects accurately

effectively and real time. The new algorithm also overcomes the limitations of the traditional one.