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

Author:

Chen, Jiahao (Chen, Jiahao.) | Shen, Yehu (Shen, Yehu.) | Zhu, Qixin (Zhu, Qixin.) | Jiang, Quansheng (Jiang, Quansheng.) | Xie, Ou (Xie, Ou.) | Miao, Jing (Miao, Jing.)

Indexed by:

EI Scopus SCIE

Abstract:

In visual simultaneous localization and mapping (vSLAM) systems, motion blur often leads to insufficient number of matched features, resulting in tracking failure. Existing solutions often tackle this problem by restoring sharp images from blurry ones. However, the computational costs are high, and the restored sharp images are usually distorted. The effect of blurry image sequences to vSLAM system is analyzed, and the relationships between feature matching and motion blur are acquired to deal with the above mentioned problems. A local residual motion blur discrimination network is proposed to detect images with motion blur efficiently. Motion blur recognition results are coupled with a vSLAM system so that the feature extraction process is guided by the results from the local residual motion blur discrimination network. The performance of the vSLAM system can be effectively enhanced when it is applied to sequences with motion blur. Experimental results on the Technische Universitat Munchen dataset show that the proposed algorithm increases the average tracking length by about 200 frames compared with the original method on some image sequences with violent motions. This algorithm effectively improves the stability and accuracy of the vSLAM system.

Keyword:

Motion blur detection vSLAM system Feature tracking Local residual motion blur discrimination network

Author Community:

  • [ 1 ] [Chen, Jiahao]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 2 ] [Shen, Yehu]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 3 ] [Zhu, Qixin]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 4 ] [Jiang, Quansheng]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 5 ] [Xie, Ou]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 6 ] [Miao, Jing]Suzhou Univ Sci & Technol, Coll Mech Engn, Suzhou, Peoples R China
  • [ 7 ] [Chen, Jiahao]Beijing Univ Technol, Dept Informat, Coll Artificial Intelligence & Automat, Beijing, Peoples R China

Reprint Author's Address:

Show more details

Related Keywords:

Source :

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY

ISSN: 1738-494X

Year: 2022

Issue: 7

Volume: 36

Page: 3653-3666

1 . 6

JCR@2022

1 . 6 0 0

JCR@2022

ESI Discipline: ENGINEERING;

ESI HC Threshold:49

JCR Journal Grade:4

CAS Journal Grade:4

Cited Count:

WoS CC Cited Count: 2

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:631/5310415
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.