• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Zhang, Wenli (Zhang, Wenli.) | Guo, Xiang (Guo, Xiang.) | Wang, Jiaqi (Wang, Jiaqi.) | Wang, Ning (Wang, Ning.) | Chen, Kaizhen (Chen, Kaizhen.)

Indexed by:

EI Scopus SCIE PubMed

Abstract:

In recent years, human detection in indoor scenes has been widely applied in smart buildings and smart security, but many related challenges can still be difficult to address, such as frequent occlusion, low illumination and multiple poses. This paper proposes an asymmetric adaptive fusion two-stream network (AAFTS-net) for RGB-D human detection. This network can fully extract person-specific depth features and RGB features while reducing the typical complexity of a two-stream network. A depth feature pyramid is constructed by combining contextual information, with the motivation of combining multiscale depth features to improve the adaptability for targets of different sizes. An adaptive channel weighting (ACW) module weights the RGB-D feature channels to achieve efficient feature selection and information complementation. This paper also introduces a novel RGB-D dataset for human detection called RGBD-human, on which we verify the performance of the proposed algorithm. The experimental results show that AAFTS-net outperforms existing state-of-the-art methods and can maintain stable performance under conditions of frequent occlusion, low illumination and multiple poses.

Keyword:

asymmetric adaptive fusion multimodal RGB-D human detection two-stream network

Author Community:

  • [ 1 ] [Zhang, Wenli]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Guo, Xiang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Wang, Jiaqi]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Wang, Ning]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Chen, Kaizhen]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Reprint Author's Address:

  • [Zhang, Wenli]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

Show more details

Related Keywords:

Source :

SENSORS

Year: 2021

Issue: 3

Volume: 21

3 . 9 0 0

JCR@2022

ESI Discipline: CHEMISTRY;

ESI HC Threshold:96

JCR Journal Grade:2

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 7

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:483/5316437
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.