Perceptual Enhancement for Autonomous Vehicles: Restoring Visually Degraded Images for Context Prediction via Adversarial Training
Realizing autonomous vehicles is one of the ultimate dreams for humans. However, perceptual information collected by sensors in dynamic and complicated environments, in particular, vision information, may exhibit various types of degradation. This may lead to mispredictions of context followed by more severe consequences. Thus, it is necessary to improve degraded images before employing them for context prediction. To this end, the authors propose a generative adversarial network to restore images from common types of degradation. The proposed model features a novel architecture with an inverse and a reverse module to address additional attributes between image styles. With the supplementary information, the decoding for restoration can be more precise. In addition, the authors develop a loss function to stabilize the adversarial training with better training efficiency for the proposed model. Compared with several state-of-the-art methods, the proposed method can achieve better restoration performance with high efficiency. It is highly reliable for assisting in context prediction in autonomous vehicles.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
-
Supplemental Notes:
- Copyright © 2022, IEEE.
-
Authors:
- Ding, Feng
- Yu, Keping
- Gu, Zonghua
- Li, Xiangjun
- Shi, Yunqing
- Publication Date: 2022-7
Language
- English
Media Info
- Media Type: Web
- Pagination: pp 9430-9441
-
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: Accuracy; Autonomous vehicles; Data quality; Image analysis
- Subject Areas: Highways; Operations and Traffic Management; Vehicles and Equipment;
Filing Info
- Accession Number: 01886071
- Record Type: Publication
- Files: TRIS
- Created Date: Jun 27 2023 5:13PM