Target detection in adverse conditions such as low illumination has always been a challenging aspect of object detection. The factors of low light and fog can lead to reduced visibility and increased noise in images, significantly disrupting the precision of object detection. To address these issues, a low-light image enhancement network for machine vision perception, MVP-Net, was proposed and integrated with the YOLOv3 object detection network to construct an end-to-end enhancement detection framework, MVP-YOLO. MVP-Net employs inverse mapping network technology to transform conventional RGB images into pseudo-RAW image feature space and introduces a pseudo-ISP enhancement network, DOISP, for image enhancement. The objective of MVP-Net is to harness the potential advantages of RAW images in object detection while overcoming the limitations encountered in their direct application. The model has outperformed previous works on multiple real-world low-light datasets and is adaptable to detectors with various architectures. Its end-to-end detection framework achieved an mAP (50%) metric of 78.3%, an improvement of 1.85% over the YOLO detectors.

[2023-11-15] Accepted Paper /doc/2023.08.0404/v1