The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network
The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network
复制标题
DOI：
10.3390/electronics10141737
复制
发表时间：
2021-07-01
期刊：
影响因子：
2.9
通讯作者：
Hwang, Keeyeon
中科院分区：
文献类型：
--
作者：
Lee, Wooseop;Kang, Min-Hee;Hwang, Keeyeon
由于自动车辆已被认为是智能交通系统的重要趋势之一，因此正在进行各种研究以提高其安全性。特别是预防性自动驾驶系统设计技术的重要性，例如检测周围物体和估计车辆之间的距离。目标检测主要是通过摄像头和LiDAR进行的，但由于成本和LiDAR识别距离的限制，对相对便于商业化的摄像头识别技术的改进需求越来越大。本研究通过CNN（Faster R-CNN）和You Only Look Once（YOLO）V2学习基于卷积神经网络（CNN）的更快区域，以改进车载单目摄像头的识别技术，用于预防性自动驾驶系统的设计，识别黑匣子高速公路驾驶视频中的周围车辆，并通过更适合自动驾驶系统的模型估计与周围车辆的距离。此外，我们还学习了PASCAL视觉对象类（VOC）数据集以进行模型比较。更快的R-CNN显示出类似的准确性，平均精度（mAP）为76.4，而YOLO的mAP为78.6，但每秒帧数（FPS）为5，显示出比FPS为40的YOLO V2和更快的R-CNN更慢的处理速度，我们很难检测到。因此，YOLO V2在准确性和处理速度方面表现出更好的性能，被确定为更适合自动驾驶系统的模型，在估计车辆之间的距离方面取得了进一步进展。对于距离估计，我们通过摄像机校准和透视变换进行坐标值转换，将阈值设置为0.7，并进行目标检测和距离估计，对于近距离车辆，准确率超过80%。通过这项研究，相信它将有助于预防自动驾驶汽车的事故，预计进一步的研究将提供各种预防事故的替代方案，例如根据车辆类型计算和确保适当的安全距离。
As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR's recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through more suitable models for automated driving systems. Moreover, we learned the PASCAL visual object classes (VOC) dataset for model comparison. Faster R-CNN showed similar accuracy, with a mean average precision (mAP) of 76.4 to YOLO with a mAP of 78.6, but with a Frame Per Second (FPS) of 5, showing slower processing speed than YOLO V2 with an FPS of 40, and a Faster R-CNN, which we had difficulty detecting. As a result, YOLO V2, which shows better performance in accuracy and processing speed, was determined to be a more suitable model for automated driving systems, further progressing in estimating the distance between vehicles. For distance estimation, we conducted coordinate value conversion through camera calibration and perspective transform, set the threshold to 0.7, and performed object detection and distance estimation, showing more than 80% accuracy for near-distance vehicles. Through this study, it is believed that it will be able to help prevent accidents in automated vehicles, and it is expected that additional research will provide various accident prevention alternatives such as calculating and securing appropriate safety distances, depending on the vehicle types.