Improving night driving behavior recognition with ResNet50

Abstract

The issue of driving behavior at night poses significant challenges due to reduced visibility and increased risk of accidents. Recent works have leveraged deep learning techniques to enhance night-time driving safety. However, the limited availability of high-quality training data and the lack of robustness in existing models present significant problems. In this work, we propose a novel approach to improve driving behavior recognition at night using ResNet50 with contrast limited adapted histogram equalization (CLAHE). We collected a new dataset and developed a more effective and robust model that can accurately recognize driving behaviors under low-illumination conditions, thereby reducing the likelihood of collisions and improving overall road safety. The experimental results demonstrate significant improvements in the deep learning model’s performance compared to conventional methods. Notably, the ResNet50 model delivers the best performance with accuracy rates of 90.73% using NIGHT-VIS-CLAHE data, demonstrating a 16% improvement in accuracy. For benchmark purposes, the InceptionV3, GoogleNet, and MobileNetV2 models also show enhanced accuracy through CLAHE implementation. Furthermore, NIGHT-VIS-CLAHE implementation in ResNet50 achieved 90.29% accuracy, surpassing the best NIGHT-IR InceptionV3 at 89.27%, highlighting the advantage of ResNet50 with CLAHE in low-light conditions even against infra-red sensor.