基于OpenCV的前方车辆检测和前撞预警算法研究
|
摘要
针对汽车的追尾碰撞事故,提出了基于OpenCV的前方车辆检测和多信息融合预警的方法。该方法首先利用Haar-like+Gentle Adaboost实现前方车辆的快速识别,结合Kalman滤波原理跟踪车辆,实现前方车辆检测,然后基于几何模型实时计算前车与本车的横纵向距离,最后根据本车及前车车速、碰撞时间TTC、横向距离等信息与阈值进行比较,分级识别碰撞风险。试验结果表明,该检测方法平均耗时22 ms/帧,检测率达到96%,并能较准确地测量车距,实现可靠的前方避撞预警输出。
A preceding vehicle detection and multi-information fusion warning method based on Open CV was proposed for the rear-end collision accident,that utilized Haar-like+Gentle Adaboost to detect preceding vehicles rapidly,and used the Kalman filter principle to track these vehicles.Geometric model was used to calculate the lateral and longitudinal distances in real-time with the preceding vehicle,then vehicle speed and the preceding vehicle speed,collision time TTC and lateral distance,etc.,were compared with threshold value to identify the risk of collision.The experimental results show that the proposed detection method can detect preceding vehicles in about 22 ms per frame with an accuracy of 96%,and can measure the vehicle distance accurately to realize reliable front collision warning output.
A preceding vehicle detection and multi-information fusion warning method based on Open CV was proposed for the rear-end collision accident,that utilized Haar-like+Gentle Adaboost to detect preceding vehicles rapidly,and used the Kalman filter principle to track these vehicles.Geometric model was used to calculate the lateral and longitudinal distances in real-time with the preceding vehicle,then vehicle speed and the preceding vehicle speed,collision time TTC and lateral distance,etc.,were compared with threshold value to identify the risk of collision.The experimental results show that the proposed detection method can detect preceding vehicles in about 22 ms per frame with an accuracy of 96%,and can measure the vehicle distance accurately to realize reliable front collision warning output.
引文
1马钧,曹静.基于中国市场特定需求的汽车先进驾驶辅助系统发展趋势研究.上海汽车,2012,4(9):36~40.
2 Izumi T,Kikawa M,Hase S,et al.Forward vehicle trackin based on shadow detection.Proceedings of the SICE Annua Conference,2007:1449~1453.
3 Jazayeri A,Cai H,Zheng J Y,et al.Vehicle detection and tracking in car video based on motion model,IEEE Trans Intell.Transp.Syst,2011,12(2):583~595.
4 Wang Hai,Zhang Weigong,Cai Yingfeng.Design of a road detection system based on monocular vision.Journal o Southeast University(English Edition),2011,27(2):169~173.
5徐豪.汽车主动防撞预警系统规避控制研究:[学位论文]长春:吉林大学,2012.
6孙晓艳.基于单目视觉的夜晚汽车前撞预警系统研究:[学位论文].西安:西安工业大学,2013.
7周松盛,何天明,张明涛,等.简易安全车距和高速公路安全视距计算模型.北京汽车,2009(2):35~38.
8陈益如.基于视觉的行人检测算法研究及系统设计:[学位论文].杭州:浙江大学,2014.
9 Friedman J,Hastie T,Tibshirani R.Additive logistic regression:a statistical view of boosting.The Annals of Statistics,2000,28(2):337~407.
10 Lienhart R,Kuranov A,Pisarevsky V.Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection.Lecture Notes in Computer Science,2003,2781:297~304.
11张玲增.基于多特征的前方车辆检测与跟踪方法研究:[学位论文].镇江:江苏大学,2010.
12 Yoshikawa N.spatial position detection of three-dimensional object using complex amplitude derived from Fourier transform profilometry.Meeting on Information Photonics,2005:1~3.
13王牛,李祖枢,武德臣,等.机器人单目视觉定位模型及其参数辨识.华中科技大学学报,2008,36(10):57~60.
14 Wu C,Cao X,Lin R,et al.Registration-based Moving Vehicle Detection for Low-altitude Urban Traffic Surveillance.lntclligcnt Control and Automation(WCICA),2010,20(1):373~378.
15 Wang CCR,Lien JJJ.Automatic Vehicle Detection Using Local Features-A Statistical Approach,IEEE Transactions on Intelligent Transportation Systems,2008,9(1):83~96.
16 Ali S,Shah M.A supervised learning framework for generic object detection in images,Proc.IEEE CVPR,San Diego,CA,USA,2005,2:1347~1354.
17 Gall J,Lempitsky V.Class-Specific Hough Forests for Object Detection,Proc.IEEE CVPR,Miami,Florida,USA,2009,1022~1029.
2 Izumi T,Kikawa M,Hase S,et al.Forward vehicle trackin based on shadow detection.Proceedings of the SICE Annua Conference,2007:1449~1453.
3 Jazayeri A,Cai H,Zheng J Y,et al.Vehicle detection and tracking in car video based on motion model,IEEE Trans Intell.Transp.Syst,2011,12(2):583~595.
4 Wang Hai,Zhang Weigong,Cai Yingfeng.Design of a road detection system based on monocular vision.Journal o Southeast University(English Edition),2011,27(2):169~173.
5徐豪.汽车主动防撞预警系统规避控制研究:[学位论文]长春:吉林大学,2012.
6孙晓艳.基于单目视觉的夜晚汽车前撞预警系统研究:[学位论文].西安:西安工业大学,2013.
7周松盛,何天明,张明涛,等.简易安全车距和高速公路安全视距计算模型.北京汽车,2009(2):35~38.
8陈益如.基于视觉的行人检测算法研究及系统设计:[学位论文].杭州:浙江大学,2014.
9 Friedman J,Hastie T,Tibshirani R.Additive logistic regression:a statistical view of boosting.The Annals of Statistics,2000,28(2):337~407.
10 Lienhart R,Kuranov A,Pisarevsky V.Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection.Lecture Notes in Computer Science,2003,2781:297~304.
11张玲增.基于多特征的前方车辆检测与跟踪方法研究:[学位论文].镇江:江苏大学,2010.
12 Yoshikawa N.spatial position detection of three-dimensional object using complex amplitude derived from Fourier transform profilometry.Meeting on Information Photonics,2005:1~3.
13王牛,李祖枢,武德臣,等.机器人单目视觉定位模型及其参数辨识.华中科技大学学报,2008,36(10):57~60.
14 Wu C,Cao X,Lin R,et al.Registration-based Moving Vehicle Detection for Low-altitude Urban Traffic Surveillance.lntclligcnt Control and Automation(WCICA),2010,20(1):373~378.
15 Wang CCR,Lien JJJ.Automatic Vehicle Detection Using Local Features-A Statistical Approach,IEEE Transactions on Intelligent Transportation Systems,2008,9(1):83~96.
16 Ali S,Shah M.A supervised learning framework for generic object detection in images,Proc.IEEE CVPR,San Diego,CA,USA,2005,2:1347~1354.
17 Gall J,Lempitsky V.Class-Specific Hough Forests for Object Detection,Proc.IEEE CVPR,Miami,Florida,USA,2009,1022~1029.