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 language | English |
---|---|
Title of host publication | 2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR) |
Publisher | IEEE |
Pages | 1-8 |
Number of pages | 8 |
ISBN (Electronic) | 978-1-7281-9331-1 |
ISBN (Print) | 978-1-7281-9332-8 |
DOIs | |
Publication status | Published - 2020 |
Event | Joint 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 2020 → 29 Aug 2020 |
Conference
Conference | Joint 9th International Conference on Informatics, Electronics and Vision and 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020 |
---|---|
Country/Territory | Japan |
City | Kitakyushu |
Period | 26/08/20 → 29/08/20 |
Keywords
- CAM loss
- Class activation maps
- Deep learning
- Learning
- Maps
- Roadside object detection
- semantic segmentation