Deep Learning Off-the-shelf Holistic Feature Descriptors for Visual Place Recognition in Challenging Conditions

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

In this paper, we present a comprehensive study on the utility of deep learning feature extraction methods for visual place recognition task in three challenging conditions, appearance variation, viewpoint variation and combination of both appearance and viewpoint variation. We extensively compared the performance of convolutional neural network architectures with batch normalization layers in terms of fraction of the correct matches. These architectures are primarily trained for image classification and object detection problems and used as holistic feature descriptors for visual place recognition task. To verify effectiveness of our results, we utilized four real world datasets in place recognition. Our investigation demonstrates that convolutional neural network architectures coupled with batch normalization and trained for other tasks in computer vision outperform architectures which are specifically designed for place recognition tasks.
Original languageEnglish
Title of host publication2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-7281-9320-5
ISBN (Print)978-1-7281-9323-6
DOIs
Publication statusPublished - 2020
Publication typeA4 Article in conference proceedings
EventIEEE International Workshop on Multimedia Signal Processing - Tampere, Finland
Duration: 21 Sep 202024 Sep 2020
https://attend.ieee.org/mmsp-2020/

Publication series

NameIEEE International Workshop on Multimedia Signal Processing
ISSN (Print)2163-3517
ISSN (Electronic)2473-3628

Conference

ConferenceIEEE International Workshop on Multimedia Signal Processing
Country/TerritoryFinland
CityTampere
Period21/09/2024/09/20
Internet address

Publication forum classification

  • Publication forum level 1

Fingerprint

Dive into the research topics of 'Deep Learning Off-the-shelf Holistic Feature Descriptors for Visual Place Recognition in Challenging Conditions'. Together they form a unique fingerprint.

Cite this