Research on Low Illumination Image Enhancement Algorithm and Its Application in Driver Monitoring System

The driver monitoring system (DMS) plays an essential role in reducing traffic accidents caused by human errors due to driver distraction and fatigue. The vision-based DMS has been the most widely used because of its advantages of non-contact and high recognition accuracy. However, the traditional RGB camera-based DMS has poor recognition accuracy under complex lighting conditions, while the IR-based DMS has a high cost. In order to improve the recognition accuracy of conventional RGB camera-based DMS under complicated illumination conditions, this paper proposes a lightweight low-illumination image enhancement network inspired by the Retinex theory. The lightweight aspect of the network structure is realized by introducing a pixel-wise adjustment function. In addition, the optimization bottleneck problem is solved by introducing the shortcut mechanism. Model performance comparison test results demonstrate that the Structure Similarity Index Measure index of the proposed model is 7.04% and 31.03% higher than that of Multi-Scale Retinex with Color Restoration and Contrast Limiting Adaptive Histogram Equalization, respectively. In the use case, the proposed model is capable to process videos with a resolution of 400×600 at a speed of 20fps on average, which meets the requirements of DMS video stream processing speed. Furthermore, a MobileNet based distraction state recognition network pre-trained on the SFD3 dataset is adopted as the back-end to verify its application in the DMS system. The results show that the accuracy in the driver's distracted behavior recognition with a low-light environment is improved by 75.39% compared to before use.