摘要
目标跟踪系统中如何有效地在复杂环境内快速准确识别可疑目标是一个关键问题。文章基于多特征值提取的方式提出一种目标识别方法,该方法提取色矩特征、身高特征、基于Hough变换步态特征、SIFT特征和纹理特征的特征值,然后按照权重关系将多特征值形成向量和可疑目标特征向量进行比较实现目标识别的目的。实验结果表明该方法可以提高目标识别的精确度。
It is a key problem that how to identify a suspicious target effectively in the target tracking system in complex environment.This paper presents a target recognition method based on a variety of eigenvalue extraction.This features of the color moment,height,transform gait characteristics based on Hough,SIFT and texture can be extracted.The features makes a result according to the relationship between weight.The result is compared with the results of the suspicious target characteristics for identify a target.The experimental results show that this method can improve the accuracy of target recognition.
出处
《河南机电高等专科学校学报》
CAS
2016年第3期26-28,共3页
Journal of Henan Mechanical and Electrical Engineering College
基金
河南省教育厅科学技术研究重点项目(15A510022)
关键词
目标识别
多特征提取
权重关系
target recognition
feature extraction
the relationship between the weight
