A deep learning-based car accident detection approach in video-based traffic surveillance

Car accident detection plays a crucial role in video-based traffic surveillance systems, contributing to prompt response and improved road safety. In the literature, various methods have been investigated for accident detection, among which deep learning approaches have shown superior accuracy compared to other methods. The popularity of deep learning stems from its ability to automatically learn complex features from data. However, the current research challenge in deep learning-based accident detection lies in achieving high accuracy rates while meeting real-time requirements. To address this challenge, this study introduces a deep learning approach using convolutional neural networks (CNNs) to enhance car accident detection, prioritizing accuracy and real-time performance. It includes a tailored dataset for evaluation, and the F1-scores reveal reasonably accurate detection for "damaged-rear-window" (62%) and "damaged-window" (63%), while "damaged-windscreen" exhibits exceptional performance at 83%. These results demonstrate the potential of CNNs in improving car accident detection, particularly for certain classes. Following extensive experiments and performance analysis, the proposed method demonstrates accurate results, significantly enhancing car accident detection in video-based traffic surveillance scenarios.