A novel pixel neighborhood differential statistic feature for pedestrian and face detection

详细信息    查看全文

• 作者：Jifeng Shen^a ; Author Vitae ; Xin Zuo^bAuthor Vitae ; Jun Li^cAuthor Vitae ; Wankou Yang^cAuthor Vitae ; Haibin Ling^dAuthor Vitae
• 关键词：Pedestrian detection ; Face detection ; PDF ; Neighborhood differential statistic patterns
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：127-138
• 全文大小：1966 K
• 卷排序：63

文摘

Our proposed methods can be viewed as a simplified one-stage CNN, which can also achieve state-of-art results. We proposed four different types of pixel neighborhood differential features, which aim to mine the discriminative information of the intrinsic structure for the pedestrian. We proposed an unsupervised feature pattern learning method, which can reduce the redundancy of the feature and discover discriminative differential statistic patterns. We proposed a supervised feature pattern learning method, which is utilized to get more compacted and informative feature for pedestrian detection.