Specific Shape Feature for Fast Pedestrian Detection in Cascade Way

Yuqing He, Tao Yang, Ya Lu, Mingqi Liu, Xiangyang Zhai

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

A113 various effective pedestrian detection methods have been put forward, it is still a challenging work to detect people with accuracy and speed. This paper proposed a fast pedestrian detector with novel features and effective classifier. Firstly, the shape based luminance comparison (SLC) features were proposed, which can represent the image information well, and compute fast. Secondly, the random trees classifier was trained in a cascade way, which also can reduce compute time. Additionally, several implementation strategies were employed to improve the performance of our detector. This method is evaluated on challenging dataset which demonstrated some improvements to the state of the art of pedestrian detector method.

源语言英语
主期刊名Proceedings of 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018
编辑Bing Xu
出版商Institute of Electrical and Electronics Engineers Inc.
335-339
页数5
ISBN(电子版)9781538618035
DOI
出版状态已出版 - 20 9月 2018
活动2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018 - Xi'an, 中国
期限: 25 5月 201827 5月 2018

出版系列

姓名Proceedings of 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018

会议

会议2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018
国家/地区中国
Xi'an
时期25/05/1827/05/18

指纹

探究 'Specific Shape Feature for Fast Pedestrian Detection in Cascade Way' 的科研主题。它们共同构成独一无二的指纹。

引用此