Dangerous driving, e.g., using mobile phone while driving, can result in serious traffic problem and threaten to safety. To efficiently alleviate such problem, in this paper, we design an intelligent monitoring system to detect the dangerous behavior while driving. The monitoring system is combined by a designed target detection algorithm, camera, terminal server and voice reminder. An efficiently deep learning model, namely Mobilenet combined with single shot multi-box detector (Mobilenet-SSD), was applied to identify the behavior of driver. To evaluate the performance of proposed system, a dangerous driving dataset,consisting of 6796 images, was constructed. The experimental results show that the proposed system can achieve the accuracy of 99%, and could be used for real-time monitoring of the drivers’ status.

危险驾驶，例如在驾驶时使用手机，会导致严重的交通问题并威胁到安全。为了有效缓解这一问题，在本文中，我们设计了一个智能监控系统来检测驾驶时的危险行为。监控系统由设计的目标检测算法、摄像头、终端服务器和语音提醒相结合。一种高效的深度学习模型，即 Mobilenet 与单次多框检测器 (Mobilenet-SSD) 相结合，被应用于识别驾驶员的行为。为了评估所提出系统的性能，构建了一个由 6796 张图像组成的危险驾驶数据集。实验结果表明，该系统可以达到99%的准确率，可用于实时监控驾驶员状态。