首页 | 本学科首页   官方微博 | 高级检索  
     

基于自适应颜色识别技术的快速多目标跟踪方法
引用本文:李会猛,陈家乾,诸静.基于自适应颜色识别技术的快速多目标跟踪方法[J].计算机工程与应用,2005,41(30):60-62,76.
作者姓名:李会猛  陈家乾  诸静
作者单位:[1]工业控制技术国家重点实验室,杭州310027 [2]浙江大学电气自动化研究所,杭州310027
摘    要:该文提出一种以YUV颜色空间作为目标特征向量的跟踪算法。文章提出的自适应颜色模板克服了传统颜色识别方法性能受光照变化影响大的缺点,目标位置预测结合颜色识别的思想解决了多个目标点颜色相近的问题,螺旋形搜索和区域生长的策略则进一步加快了目标跟踪速度。

关 键 词:颜色空间  直方图  区域生长  预测  识别
文章编号:1002-8331-(2005)30-0060-03
收稿时间:2005-01
修稿时间:2005-01

Quick Multi-objects Tracking Based on Adaptive Color Recognition
Li Huimeng, Chen Jiaqian, Zhu Jing.Quick Multi-objects Tracking Based on Adaptive Color Recognition[J].Computer Engineering and Applications,2005,41(30):60-62,76.
Authors:Li Huimeng  Chen Jiaqian  Zhu Jing
Affiliation:1.National Laboratory of Industrial Control Technology, Hangzhou 310027; 2.Insititute of Electrical Automation,Zhejiang University,Hangzhou 310027
Abstract:This article provides a novel multi-objects tracking algorithm with YUV color space as character vector space.The self-adaptive color template overcomes the defects of traditional color identification algorithm whose performance is affected greatly by diverse light conditions.The idea that combines position prediction and color identification solves the problem that multi-objects have identical color. Spiral search and regional growth methods accelerate the tracking process.
Keywords:color space  color histogram  region grow  prediction  recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号