摘要
针对传统前方车辆检测方法难以同时满足准确性与实时性问题,提出一种结合AdaBoost集成学习与位置信息约束的车辆检测方法。首先,利用Edge Boxes算法根据车辆边缘序列信息计算推荐窗口。然后,通过帧存坐标系中车辆位置信息对非目标推荐窗口进行排除。最后,将过滤后窗口聚类处理并择优选取作为AdaBoost分类器输入,进行检测评判,并对最终检测结果进行边框回归处理,以提升检测精准度。实验结果表明,该方法对于不同检测场景有较强鲁棒性,能够同时满足车辆检测的准确性与实时性要求。
Since the traditional preceding vehicle detection strategies cannot meet the accuracy and real-time requirements simultaneously,we propose an approach which combines AdaBoost,an integrated learning method,with the constraint of positions information.Firstly,regions proposal(RP)are obtained by edge boxes method according to the sequence information of vehicle edges.Secondly,the position information of vehicles in the frame coordinate system is used to filter out non-target RPs.Finally,the obtained windows are clustered and fed into the AdaBoost classifiers for vehicles detection,and at the same time borders regression is utilized to improve the accuracy of detection results.Experimental results demonstrate that the proposed method has robustness to different detection scenarios and that it can meet the accuracy and real-time requirements of vehicle detection.
作者
耿磊
彭晓帅
肖志涛
李秀艳
甘鹏
GENG Lei;PENG Xiao-shuai;XIAO Zhi-tao;LI Xiu-yan;GAN Peng(Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems,Tianjin 300387;School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China)
出处
《计算机工程与科学》
CSCD
北大核心
2018年第10期1844-1850,共7页
Computer Engineering & Science
基金
国家自然科学基金(61601325
61771340)
天津市自然科学基金(17JCQNJC01400)
关键词
前方车辆检测
集成学习
位置信息
边框回归
preceding vehicles detection
integrated learning
position information
borders regression
