基于高速公路交通图像的安全带自动识别算法

Seatbelt Automatic Recognition Algorithm Based on Highway Traffic Image

提出一种高速公路上机动车司机和前排乘客系安全带情况的自动识别算法。算法输入源于高速公路交通信息共享与诱导系统中的机动车行驶照片。本文算法利用车牌定位技术、人脸检测技术、安全带识别技术从图像中发现特定的机动车,并对其中司机和前排乘客系安全带事件进行识别,从而判断该图像中的车辆是否有交通违规情况。实验结果表明,本识别算法可行、有效。

This study presents an algorithm to automatically recognize the seatbeh wearing of the driver and the front passenger on highway. The input of the proposed algorithm is the vehicle image from the highway traffic information. The algorithm uses license plate location, face detection and seatbelt detection to detect the object vehicle and recognize whether the driver and the front passenger wear the seatbelt. The output of the algorithm is used to check the seatbeh incident based on the image. The experimental results indicate the proposed algorithm achieves a feasible and valid result for application.