Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Preprint
Abstract
Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions. The existing methods either have difficulties in balancing the tasks of image enhancement and object detection, or often ignore the latent information beneficial for detection. To alleviate this problem, we propose a novel Image-Adaptive YOLO (IA-YOLO) framework, where each image can be adaptively enhanced for better detection performance. Specifically, a differentiable image processing (DIP) module is presented to take into account the adverse weather conditions for YOLO detector, whose parameters are predicted by a small convolutional neural net-work (CNN-PP). We learn CNN-PP and YOLOv3 jointly in an end-to-end fashion, which ensures that CNN-PP can learn an appropriate DIP to enhance the image for detection in a weakly supervised manner. Our proposed IA-YOLO approach can adaptively process images in both normal and adverse weather conditions. The experimental results are very encouraging, demonstrating the effectiveness of our proposed IA-YOLO method in both foggy and low-light scenarios.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Multiscale Domain Adaptive Yolo For Cross-Domain Object Detection2021
- A PSO and BFO-Based Learning Strategy Applied to Faster R-CNN for Object Detection in Autonomous DrivingIEEE Access, 2019
- Getting to know low-light images with the Exclusively Dark datasetComputer Vision and Image Understanding, 2019
- Benchmarking Single-Image Dehazing and BeyondIEEE Transactions on Image Processing, 2018
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Vision and the AtmosphereInternational Journal of Computer Vision, 2002
- Image enhancement via adaptive unsharp maskingIEEE Transactions on Image Processing, 2000
- Optics of the Atmosphere: Scattering by Molecules and ParticlesPhysics Today, 1977