Defog YOLO for road object detection in foggy weather
Authors:
- 9 August 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (11) , 3115-3127
Abstract
Object detection research predominantly focuses on clear weather conditions, often overlooking the challenges posed by foggy weather. Fog impairs the vision of onboard cameras, creating significant obstacles for autonomous vehicles. To tackle these issues, we present the Defog YOLO algorithm, specifically designed for road object detection in foggy conditions. Our approach integrates an enhanced U-Net framework for visual defogging, where the encoder leverages super-resolution back projection to combine multi-layer features. The decoder employs a back projection feedback mechanism to improve image restoration. Additionally, we augment the Feature Pyramid Network with a noise-aware attention mechanism, allowing the network to emphasize critical channel and spatial information while mitigating noise. Given the scarcity of labeled foggy images, we introduce a fog addition module to generate a more diverse training dataset. We validate our method using a synthesized FOG-TRAINVAL dataset, derived from the VOC dataset, demonstrating its robustness in foggy scenarios. Experimental results show that our proposed method achieves an mAP score of 60% on the Real-world Task-driven Testing Set foggy weather test set, with a precision of 86.7% and a recall of 54.2%. These findings underscore the effectiveness and improved generalizability of our approach for object detection in adverse weather conditions.Keywords
This publication has 25 references indexed in Scilit:
- A Light Weight Depthwise Separable Layer Optimized CNN Architecture for Object-Based Forgery Detection in Surveillance VideosThe Computer Journal, 2024
- Multiscale Domain Adaptive Yolo For Cross-Domain Object Detection2021
- A Systematic Review on Foggy Datasets: Applications and ChallengesArchives of Computational Methods in Engineering, 2021
- Robust Object Detection and Localization Using Semantic Segmentation NetworkThe Computer Journal, 2021
- LEDet: A Single-Shot Real-Time Object Detector Based on Low-Light Image EnhancementThe Computer Journal, 2021
- Object Detection and Localization Using Sparse-FCM and Optimization-driven Deep Convolutional Neural NetworkThe Computer Journal, 2021
- Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging TechniquesIEEE Signal Processing Magazine, 2020
- Domain Adaptive Object Detection via Asymmetric Tri-Way Faster-RCNN2020
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- Bilateral Back-Projection for Single Image Super Resolution2007