汽车辅助驾驶系统动态目标检测方法

计算机工程

汽车辅助驾驶系统动态目标检测方法

罗栩豪 ¹,王培 ¹,李绍华 ¹,梁巍 ²,马心坦¹

(1.河南科技大学车辆与交通工程学院,河南洛阳 471003; 2.海军航空工程学院电子信息工程系,山东烟台 264001)

收稿日期:2017-01-03 出版日期:2018-01-15 发布日期:2018-01-15
作者简介:罗栩豪(1995—),男,本科生,主研方向为汽车电子控制技术;王培、李绍华,本科生;梁巍,工程师、硕士;马心坦,副教授、博士。
基金资助:
国家自然科学基金(61271444)。

Dynamic Target Detection Method in Motor Vehicle Assisted Driving System

LUO Xuhao ¹,WANG Pei ¹,LI Shaohua ¹,LIANG Wei ²,MA Xintan ¹

(1.College of Vehicle and Traffic Engineering,Henan Science and Technology University,Luoyang,Henan 471003,China;2.Department of Electronic and Information Engineering,Naval Aeronautical University,Yantai,Shandong 264001,China)

Received:2017-01-03 Online:2018-01-15 Published:2018-01-15

摘要/Abstract

摘要： 针对汽车辅助驾驶系统中动态目标检测的复杂背景和实时性要求,提出一种基于改进尺度不变特征变换(SIFT)算子和改进假设检验方法的动态目标检测方法。通过小波多分辨率分析和相邻帧间特征点位置估计改进SIFT方法,实现快速全局背景运动补偿参数估计,并在三帧差分图像上优化背景方差估计过程,解决因目标分布在图像边缘导致传统假设检验方法漏检的问题。实验结果表明,该方法不仅能够保持SIFT算子的优越性能,提高参数估计精确性,而且能加快特征配准和检测速度,满足系统的实时性要求。

关键词: 全局运动补偿, 尺度不变特征变换算子, 假设检验, 帧间位置估计, 三帧差分法

Abstract: In view of the complex background and real-time requirement of the dynamic target detection in motor vehicle Assisted Driving System(ADS),a dynamic target detection method is proposed based on improved Scale-Invariant Feature Transform(SIFT) operator and improved hypothesis testing method.Firstly,the wavelet multi-resolution analysis and the position estimation of feature points between adjacent frames are used to improve the SIFT method,so as to achieve fast parameter estimation for global background motion compensation.And then,by improving the background variance estimation in the three frame difference image,the targets closing to the edge of the image which are missed in the traditional hypothesis testing method can be detected exactly.Experimental results demonstrate that,not only the superior performance of the SIFT operator is maintained and the accuracy of parameter estimation is improved,but also the speeds of the feature points matching and targets detection are improved.The proposed method can meet the real-time requirements of the system.

Key words: Global Motion Compensation(GMC), Scale-Invariant Feature Transform(SIFT) operator, hypothesis testing, inter-frame position estimation, three frame difference method

中图分类号:

U463.6

罗栩豪,王培,李绍华,梁巍,马心坦. 汽车辅助驾驶系统动态目标检测方法[J]. 计算机工程.

LUO Xuhao,WANG Pei,LI Shaohua,LIANG Wei,MA Xintan. Dynamic Target Detection Method in Motor Vehicle Assisted Driving System[J]. Computer Engineering.

参考文献

参考文献［1］游安清,程义民.基于背景运动补偿的红外运动分析［J］.强激光与粒子束,2003,15(5):431-434. ［2］李强,张钹.一种基于图像灰度的快速匹配算法［J］.软件学报,2006,17(2):216-222. ［3］施家栋,王建中.动态场景中运动目标检测与跟踪［J］.北京理工大学学报,2009,29(10):858-891. ［4］RAATH G B,MAKUR A.Iterative Least Squares and Compression Based Estimations for a Four-parameter Linear Global Motion Model and Global Motion Com-pensation［J］.IEEE Transactions on Circuits and Systems for Video Technology,2005,9(7):1075-1099. ［5］ALBU F,FLOREA C,ZAMFIR A,et al.Low Complexity Global Motion Estimation Techniques for Image Stabilization［C］//Proceedings of International Conference on Consumer Electronics.Washington D.C.,USA:IEEE Press,2008:1-2. ［6］吴强,侯树艳,李旭雯.融合图像灰度信息与边缘特征的快速匹配算法［J］.信号处理,2013,29(2):268-273. ［7］YE K,SUKTANKAR R.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors［C］//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2004:506-513. ［8］MIKOLAJCZYK K,SCHMID C.A Performance Evaluation of Local Descriptors［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630. ［9］MORTENSEN E N,DENG H,SHAPIRO L.A SIFT Descriptor with Global Context［C］//Proceedings of CVPR’05.Washington D.C.,USA:IEEE Press,2005:184-190. ［10］MORENO P,BERNARDINO A,VICTOR S J.Improving the SIFT Descriptor with Smooth Derivative Filters［J］.Pattern Recognition Letters,2009,30(1):18-26. ［11］LOWE D G.Object Recognition from Local Scale-invariant Features［C］//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,1999:1150-1157. ［12］LOWE D G.Distinctive Image Features from Scale-invariant Key Points［J］.International Journal of Computer Vision,2004,60(2):91-110. ［13］何孝莹,岳建伟,张栩然.基于SIFT算法的无人机影像快速匹配［J］.计算机工程,2011,37(7):216-218,230. ［14］BAY H,TUYTELAARS T,VAN G L.SURF:Speeded up Robust Features［C］//Proceedings of the 9th European Conference on Computer Vision.New York,USA:ACM Press,2006:404-417. ［15］ALAA E,FARAG A A.CSIFT:A SIFT Descriptor with Color Invariant Characteristics［C］//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2006:1978-1983. ［16］MOREL J M,YU Guoshen.ASIFT:A New Framework for Full Affine Invariant Image Comparison［J］.SIAM Journal on Imaging Sciences,2009,2(2):438-469. ［17］LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK:Binary Robust Invariant Scalable Key Points［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:2548-2555. ［18］ALAHI A,ORTIZ R.FREAK:Fast Retina Keypoint［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:510-517. ［19］李星,郭晓松,郭君斌.基于多特征融合的前向车辆检测方法［J］.计算机工程,2014,40(2):203-207. ［20］赖作镁,王敬儒,张启衡.背景运动补偿和假设检验的目标检测算法［J］.光学精密工程,2007,15(1):112-116. ［21］吴骏,李文杰,耿磊,等.基于单目视觉的前方车辆检测与测距［J］.计算机工程,2017,43(2):26-32. 编辑金胡考

[1]	韩佳良, 徐明. 高斯矢量多路输入信道下的消息认证方案[J]. 计算机工程, 2020, 46(12): 120-126.
[2]	于金亮, 涂山山, 孟远. 移动雾计算中基于强化学习的伪装攻击检测算法[J]. 计算机工程, 2020, 46(1): 38-44.
[3]	李立,李晓东,任刚. 基于Greenshield模型的VANET异常节点检测机制[J]. 计算机工程, 2018, 44(2): 114-118,123.
[4]	刘仁峰, 周华兵, 田金文. 一种基于尺度最优的极线校正优化方法[J]. 计算机工程, 2013, 39(6): 287-289,294.
[5]	张辉帅, 王劲林, 朱小勇, 孙鹏. 一种实时自适应HTTP流化码流切换算法[J]. 计算机工程, 2013, 39(2): 1-5.
[6]	徐保树, 史泽林. 光电成像探测系统的性能预测方法[J]. 计算机工程, 2012, 38(3): 7-8,11.
[7]	张海洋, 李谢华, 江英. 基于假设检验的自适应粒子滤波红外目标跟踪[J]. 计算机工程, 2012, 38(11): 153-155,159.
[8]	李秋林, 何家峰. 基于三帧差法和交叉熵阈值法的车辆检测[J]. 计算机工程, 2011, 37(4): 172-174.
[9]	牛武泽, 石林锁, 金广智, 李喜来, 白向峰. 融合时空信息的运动目标检测算法[J]. 计算机工程, 2011, 37(18): 171-173.
[10]	李丽婧, 黄永东. 分层FDR阈值滤波算法[J]. 计算机工程, 2011, 37(01): 187-189,193.
[11]	陈明, 陈一民, 黄诗华, 姚争为. 增强现实中的视频对象跟踪算法[J]. 计算机工程, 2010, 36(12): 229-231.
[12]	冯霞, 刘志辉, 田继存. 基于独立性理论的文本分类特征选择方法[J]. 计算机工程, 2010, 36(12): 22-24.
[13]	汤光明;蒋小标;王亚弟. 信息隐藏理论安全性研究[J]. 计算机工程, 2009, 35(8): 192-194.
[14]	石祥滨;刘芳;赵鑫. 基于双边假设检验的NEO改变帧长度机制[J]. 计算机工程, 2007, 33(17): 280-282.

选择文件类型/文献管理软件名称

选择包含的内容