Long-term Visual Localization using Semantically Segmented Images
Paper in proceeding, 2018

Robust cross-seasonal localization is one of the major challenges in long-term visual navigation of autonomous vehicles. In this paper, we exploit recent advances in semantic segmentation of images, i.e., where each pixel is assigned a label related to the type of object it represents, to attack the problem of long-term visual localization. We show that semantically labeled 3D point maps of the environment, together with semantically segmented images, can be efficiently used for vehicle localization without the need for detailed feature descriptors (SIFT, SURF, etc.). Thus, instead of depending on hand-crafted feature descriptors, we rely on the training of an image segmenter. The resulting map takes up much less storage space compared to a traditional descriptor based map. A particle filter based semantic localization solution is compared to one based on SIFT-features, and even with large seasonal variations over the year we perform on par with the larger and more descriptive SIFT-features, and are able to localize with an error below 1 m most of the time.

Author

Erik Stenborg

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Zenuity AB

Carl Toft

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Lars Hammarstrand

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Proceedings - IEEE International Conference on Robotics and Automation

10504729 (ISSN)

6484-6490
978-1-5386-3081-5 (ISBN)

IEEE International Conference on Robotics and Automation (ICRA)
Brisbane, Australia,

COPPLAR CampusShuttle cooperative perception & planning platform

VINNOVA (2015-04849), 2016-01-01 -- 2018-12-31.

Subject Categories

Robotics

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing

DOI

10.1109/ICRA.2018.8463150

ISBN

9781538630815

More information

Latest update

1/3/2024 9