RE-Flare has 7,680 images, including 1,820 triplets of flare-corrupted, flare-free, and low-light images captured by conventional cameras. Specifically, to tackle the challenge of accur
Aiming at the imbalance between accuracy and real-time of existing fatigue driving detection models, and the accuracy is lower in low illumination, an LDIE-FDNet (Lightweight Dynamic Image Enhancement
Aiming at the imbalance between accuracy and real-time of existing fatigue driving detection models, and the accuracy is lower in low illumination, an LDIE-FDNet (Lightweight Dynamic Image Enhancement
