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。
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.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第30期60-62,76,共4页
Computer Engineering and Applications
关键词
颜色空间
直方图
区域生长
预测
识别
color space, color histogram, region grow, prediction, recognition
