Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded...

詳細記述

書誌詳細

出版年:	Sensors
主要な著者:	Xiaotao Shao, Qing Wang, Wei Yang, Yun Chen, Yi Xie, Yan Shen, Zhongli Wang
フォーマット:	論文
言語:	英語
出版事項:	MDPI AG 2021-03-01
主題:	pedestrian detection heavy occlusion handling feature enhancement MFPN
オンライン･アクセス:	https://www.mdpi.com/1424-8220/21/5/1820