An evaluation of deep learning in loop closure detection for visual SLAM

Yifan Xia, Jie Li, Lin Qi, Hui Yu, Junyu Dong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Loop closure detection is a crucial module in simultaneous localization and mapping (SLAM), which reduces the accumulative error in building the environment map. Traditional appearance-based methods mostly utilize hand-crafted features, which are designed based on human expertise. Recent advances in deep learning inspire us to investigate its application in loop closure detection. Different from traditional approaches, deep learning methods automatically learn features from raw data and has better adaptability to complex environment changes. In this paper, we perform a comparison and analysis of several popular deep neural networks and traditional methods for loop closure detection. We evaluate their performance on two open datasets in terms of accuracy and processing time. According to the experimental results, we conclude that deep neural network is suitable for loop closure detection.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
EditorsGeyong Min, Xiaolong Jin, Laurence T. Yang, Yulei Wu, Nektarios Georgalas, Ahmed Al-Dubi
PublisherInstitute of Electrical and Electronics Engineers
Pages85-91
Number of pages7
ISBN (Electronic)978-1-5386-3066-2
ISBN (Print)978-1-5386-3067-9
DOIs
Publication statusPublished - 1 Feb 2018
EventJoint 10th IEEE International Conference on Internet of Things, iThings 2017, 13th IEEE International Conference on Green Computing and Communications, GreenCom 2017, 10th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2017 and the 3rd IEEE International Conference on Smart Data, Smart Data 2017 - Exeter, United Kingdom
Duration: 21 Jun 201723 Jun 2017

Conference

ConferenceJoint 10th IEEE International Conference on Internet of Things, iThings 2017, 13th IEEE International Conference on Green Computing and Communications, GreenCom 2017, 10th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2017 and the 3rd IEEE International Conference on Smart Data, Smart Data 2017
CountryUnited Kingdom
CityExeter
Period21/06/1723/06/17

Keywords

  • Deep Learning
  • Loop Closure Detection
  • Simultaneous Localization and Mapping
  • noissn

Fingerprint

Dive into the research topics of 'An evaluation of deep learning in loop closure detection for visual SLAM'. Together they form a unique fingerprint.

Cite this