arrow
返回

A Part-Aware Multi-Scale Fully Convolutional Network for Pedestrian Detection

delete2021-02-01
delete48
PRE
AI
P
Peiyu Yang
张国峰 封面图
张国峰 (Guofeng Zhang)
L
Lu Wang *
徐
徐礼胜 (Lisheng Xu)
Q
Qingxu Deng
M
Ming–Hsuan Yang
DOI:10.1109/TITS.2019.2963700delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Pedestrian detection is a crucial task in intelligent transportation systems, which can be applied in autonomous vehicles and traffic scene video surveillance systems. The past few years have witnessed much progress on the research of pedestrian detection methods, especially through the successful use of the deep learning based techniques. However, occlusion and large scale variation remain the challenging issues for pedestrian detection. In this work, we propose a Part-Aware Multi-Scale Fully Convolutional Network (PAMS-FCN) to tackle these difficulties. Specifically, we present a part-aware Region-of-Interest (RoI) pooling module to mine body parts with different responses, and select the part with the strongest response via voting. As such, a partially visible pedestrian instance can receive a high detection confidence score, making it less likely to become a missing detection. This module operates in parallel with an instance RoI pooling module to combine local parts and global context information. To handle vast scale variation, we construct a fully convolutional network in which multi-scale feature maps are generated efficiently, and small-scale and large-scale pedestrians are detected separately. By integrating these structures, the proposed detector achieves the state-of-the-art performance on the Caltech, KITTI, INRIA and ETH pedestrian detection datasets.
Keyword:
Detectors
Feature extraction
Proposals
Semantics
Intelligent transportation systems
Object detection
Buildings
Pedestrian detection
part-aware RoI pooling
multi-scale detection
fully convolutional network
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Intelligent Transportation Systems 封面图
IEEE Transactions on Intelligent Transportation Systems
IF:
8.4
论文数:
9.7K
被引数:
6.3W

机构

N
northeastern university - china
学者数:
3.2W
论文数: 2.7W
被引数: 37
University of California System 封面图
University of California System
学者数:
37.7W
论文数: 33.8W
被引数: 6.6K
引用论文

引用论文

Design, synthesis, and evaluation of phenylglycinols and phenyl amines as agonists of GPR88
err2015-04-01
err0
PREAI
errCarolyn D. Dzierba; Yingzhi Bi; Bireshwar Dasgupta; Richard A. Hartz; Vijay Ahuja; Giovanni Cianchetta; Godwin Kumi; Li Dong; Saadat Aleem; Cynthia Fink; Yudith Garcia; Michael Green; Jianxin Han; Soojin Kwon; Ying Qiao; Jiancheng Wang; Yulian Zhang; Ying Liu; Greg Zipp; Zhi Liang; Neil Burford; Meredith Ferrante; Robert Bertekap; Martin Lewis; Angela Cacace; James Grace; Alan Wilson; Amr Nouraldeen; Ryan Westphal; David Kimball; Kenneth Carson; Joanne J. Bronson; John E. Macor
err分享
err收藏
err分享
err收藏
Scale-Aware Fast R-CNN for Pedestrian Detection基于尺度感知的快速r-cnn行人检测
err2017-01-01
err587
errOAAI
errLi, Jianan; Liang, Xiaodan; Shen, Shengmei; Xu, Tingfa; Feng, Jiashi; Yan, Shuicheng
err分享
err收藏
Identification of Significant Features by the Global Mean Rank Test
err2014-08-13
err0
errOAAI
errMartin Klammer; J. Nikolaj Dybowski; Daniel Hoffmann; Christoph Schaab
err分享
err收藏
0.9% saline is neither normal nor physiological
err2016-03-11
err0
errOAAI
errHeng Li; Shi-ren Sun; John Q. Yap; Jiang-hua Chen; Qi Qian
err分享
err收藏
ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
学者 查看更多内容