高技术通讯2016，Vol.26Issue(3)：246-254,9.DOI:10.3772/j.issn.1002-0470.2016.03.004
一种新的基于颜色统计特征的判别跟踪方法
A new discriminative tracking algorithm based on color statistical characteristics
摘要
Abstract
In view of the problem that most discriminative algorithms for target tracking focus on the tracking speed while neglect the scale variation , a simple , robust discriminative algorithm based on color statistical characteristics was presented .The new color statistical characteristics not only possess the certain illumination invariance , but also maintain the higher discriminative power .An affine kinematics model for tracking was established to keep optimi-zing the parameters during tracking to solve the scale variation and the view angle change .To improve the tracking speed, the low-dimensional color statistical characteristics were used to describe the target appearance , and the color statistical characteristics were used to train naive Bayes classifiers and update classifiers online .The sample with the maximum confidence was regarded as the tracking result .Numerous comprehensive experiments were con-ducted for evaluation of the proposed algorithm and other algorithms , and the remarkable effectiveness under differ-ent challenge factors of the proposed tracking algorithm was showed .关键词
视觉跟踪/颜色统计特征/仿射变换/降维/判别分类器Key words
visual tracking/color statistical characteristics/affine transformation/dimensionality reduction/discriminative classifier引用本文复制引用
胡昭华,鞠蓉,欧阳雯,金蓉..一种新的基于颜色统计特征的判别跟踪方法[J].高技术通讯,2016,26(3):246-254,9.基金项目
国家自然科学青年基金（61203273），江苏省自然科学基金青年基金（ BK20141004），江苏省普通高校自然科学研究资助项目（11KJB510009，14KJB510019），江苏省“信息与通信工程”优势学科资助和江苏省大学生实践创新训练计划（201410300021）资助项目。女，1981年生，博士，副教授；研究方向视频目标跟踪，模式识别，粒子滤波等；E－mail zhaohua hu＠163．com （）
