https://orcid.org/0000-0002-3069-8337
https://orcid.org/0000-0001-5735-2507
https://orcid.org/0000-0003-4228-2774
https://orcid.org/0000-0002-3069-8337
https://orcid.org/0000-0001-5735-2507
https://orcid.org/0000-0003-4228-2774
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, we 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, we 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.
Perceptual Enhancement for Autonomous Vehicles: Restoring Visually Degraded Images for Context Prediction via Adversarial Training
IEEE Transactions on Intelligent Transportation Systems ; 23 , 7 ; 9430-9441
01.07.2022
7085682 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Robust autonomous flight in constrained and visually degraded shipboard environments
| British Library Online Contents | 2017
Visually simulating driving plans in autonomous vehicles
| Europäisches Patentamt | 2020
VISUALLY SIMULATING DRIVING PLANS IN AUTONOMOUS VEHICLES
| Europäisches Patentamt | 2018