摘要
行车间距检测是汽车主动安全辅助驾驶系统的关键技术之一,为了提高车辆行驶过程中行车间距检测的精度与实时性,提出了一种实时单目深度估计方法。首先,构建畸变模型并用相机标定算法进行单目相机标定。然后,以车牌作为前车目标定位基准,采用颜色、轮廓的车牌筛选算法快速提取前车车牌信息。最后,基于方向梯度直方图特征和支持向量机实现车牌的精准定位。实验结果表明,相比其他方法,融合已知车牌的透视N点深度估计模型精度高、实时性好。本方法对前车车牌定位的识别率为99.326%,行车间距的检测误差小于10%,处理一张图像所需的时间约为170 ms,满足车辆行驶过程中对车间距检测的应用需求。
Driving distance detection is one of the key technologies of the car's active safety driving assistance system.This paper proposes a method of real-time monocular depth estimation,to improve the accuracy and real-time performance of the distance detection during the vehicle driving process.First,the distortion model is constructed,and the camera calibration algorithm is used to calibrate the monocular camera.Then,the license plate is used as the target location benchmark of the front vehicle,and the license plate information of the front vehicle is extracted quickly by using the license plate filtering algorithm of color and contour.Finally,based on directional gradient histogram feature and support vector machine,the license plate is located accurately.Experimental results show that,compared with other methods,the perspective N-point depth estimation model fused with known license plates has high accuracy and good real-time performance.This method has a recognition rate of 99.326%for the location of the license plate of the front vehicle,and the detection error of the driving distance is less than 10%,and the time required to process an image is about 170 ms,which meets the application requirements for the detection of the distance between vehicles during the vehicle driving process.
作者
郭克友
杨民
张沫
郭晓丽
李雪
Guo Keyou;Yang Min;Zhang Mo;Guo Xiaoli;Li Xue(School of Artificial Intelligence,Beijing Technology and Business University,Beijing 100048,China;Research Institute of Highway Ministry of Transport,Beijing 100088,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第6期321-330,共10页
Laser & Optoelectronics Progress
基金
交通运输行业重点科技项目清单(2018-ZD1-010)
北京工商大学2020年研究生科研能力提升计划。
关键词
机器视觉
深度模型
机器学习
支持向量机
machine vision
deep model
machine learning
support vector machine
