Weakly Supervised Semantic Roadside Object Segmentation Using Digital Maps

Johannes A.P. Guelen, Albert Ali Salah, Bastiaan J. Boom, Julien A. Vijverberg

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

Abstract

Publicly available digital maps may offer semantic information regarding objects in street view images. In this paper, we propose an approach to exploit such information to automatically create object detection datasets on which state-of-the-art object detection methods can be trained. To accomplish this, we use two detailed maps of the Netherlands containing the location of a large number of street objects. We link the object information to street view images to use them as image-wide labels. Our results show that even though there are many sources for noise in the labels, we can create useful data with this approach.
Original languageEnglish
Title of host publication2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR)
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Electronic)978-1-7281-9331-1
ISBN (Print)978-1-7281-9332-8
DOIs
Publication statusPublished - 2020
EventJoint 9th International Conference on Informatics, Electronics and Vision and 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020 - Kitakyushu, Japan
Duration: 26 Aug 202029 Aug 2020

Conference

ConferenceJoint 9th International Conference on Informatics, Electronics and Vision and 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020
Country/TerritoryJapan
CityKitakyushu
Period26/08/2029/08/20

Keywords

  • CAM loss
  • Class activation maps
  • Deep learning
  • Learning
  • Maps
  • Roadside object detection
  • semantic segmentation

Fingerprint

Dive into the research topics of 'Weakly Supervised Semantic Roadside Object Segmentation Using Digital Maps'. Together they form a unique fingerprint.

Cite this