Better, Faster Small Hazard Detection: Instance-Aware Techniques, Metrics and Benchmarking
Vision-based detection of hazards in the path of ego-vehicle is a challenging task because of the variability in the type of hazards. In this paper, the authors present a detailed review of vision-based hazard detection methods followed by a set of new architectures and methods include semantic segmentation, instance segmentation, object detection, monocular vision with depth fusion based methods and ensembles. Additionally, they propose a set of new (and some old) benchmarking metrics that accurately capture the effectiveness of hazard detection algorithms, in terms of both algorithmic accuracy and deployability in vehicles. Detailed performance evaluations show that the proposed methods using Mask-RCNN, ensembles and monocular-stereo fusion surpass current state-of-the-art techniques in terms of accuracy and computational speed. Additionally, the fusion based object detection architectures provide a good tradeoff between accuracy (e.g. Average Precision) and computation requirements, with operating speeds that are 15 times faster than existing techniques.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
-
Supplemental Notes:
- Copyright © 2022, IEEE.
-
Authors:
- Geisler, Simon
- Cunha, Carlos
- Satzoda, Ravi Kumar
- Publication Date: 2022-7
Language
- English
Media Info
- Media Type: Web
- Pagination: pp 9062-9077
-
Serial:
- IEEE Transactions on Intelligent Transportation Systems
- Volume: 23
- Issue Number: 7
- Publisher: Institute of Electrical and Electronics Engineers (IEEE)
- ISSN: 1524-9050
- Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979
Subject/Index Terms
- TRT Terms: Detection and identification; Highway safety; Intelligent vehicles; Proximity detectors
- Subject Areas: Highways; Operations and Traffic Management; Safety and Human Factors;
Filing Info
- Accession Number: 01885469
- Record Type: Publication
- Files: TRIS
- Created Date: Jun 21 2023 5:10PM