基于非局部稀疏特征的行人检测方法  

Pedestrian Detection Based on Nonlocal Sparse Feature

作　　者：彭怡书[1] 颜云辉[1] 赵久梁[1] 张尧[1] 

机构地区：[1]东北大学机械工程与自动化学院,辽宁沈阳110819

出　　处：《东北大学学报（自然科学版）》2015年第4期465-468,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(51374063);中央高校基本科研业务费专项资金资助项目(N120603003)

摘　　要：利用周围邻域信息约束进行加权稀疏表示以达到行人检测的目的.采用Fisher判别字典学习的方法,得到一个能够更好地提取图像的具有更强辨别性稀疏特征的字典,利用图像中周围信息约束,求得该字典表示下的稀疏特征,并根据对当前图像块的稀疏表示残差进行分类.INRIA数据库的实验表明非局部稀疏特征具有明显的区分能力.同时,对行人目标进行邻域约束,能够有效地表示出同目标区域的稀疏特征.By using the constraints around the neighborhoods for weighted sparse representation,the pedestrian detection problem was solved. A dictionary with a strong extracting discriminate and sparse features power was obtained by using the Fisher discriminant dictionary learning method.With the constraint of the neighborhoods,the image patch was represented as a sparse feature via the dictionary. By computing the representation of the residuals and comparing the residuals with a threshold,the patch label was determined to finish the classification task. The experiments on INRIA person datasets showed that non-local sparse feature has an obvious power of discrimination.The constraint of the neighborhoods makes the sparse feature represented effectively.

关 键 词：行人检测 非局部 稀疏表示 判别字典 优化配矿 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]