Deep Convolutional Neural Network for Pedestrian Detection with Multi-Levels Features Fusion

摘要：

　　Pedestrian detection aims to localize and recognize every pedestrian instance in an image with a bounding box.The current state-of-the-art method is Faster RCNN,which is such a network that uses a region proposal network(RPN)to generate high quality region proposals,while Fast RCNN is used to classifiers extract features into corresponding categories.The contribution of this paper is integrated low-level features and high-level features into a Faster RCNN-based pedestrian detection framework,which efficiently increase the capacity of the feature.Through our experiments,we comprehensively evaluate our framework,on the Caltech pedestrian detection benchmark and our methods achieve state-of-the-art accuracy and present a competitive result on Caltech dataset.

作者: Danhua Li Xiaofeng Di Xuan Qu Yunfei Zhao Honggang Kong

作者单位: China Academy of Transportation Sciences,100088 Beijing,China

会议类型: 国际会议

会议名称: 2018 2nd International Conference on Electronic Information Technology and Computer Engineering (EITCE 2018)(2018第二届电子信息技术与计算机工程国际会议)(EITCE2018)

会议地点: 上海

会议语种:英文

页码: 1-3

在线出版日期: 2018-10-12（万方平台首次上网日期，不代表论文的发表时间）