Localization and ego-velocity estimation for vehiclebased on binocular image sequences
-
摘要: 为了确定车辆在行驶过程中的相对位置与速度，提出一种基于双目序列图像的实时测距定位及自车速度估计方法。该方法利用车载双目视觉传感器采集周围环境的序列图像，并对同一时刻的左右图像进行基于SURF(speeded up robust features)特征的立体匹配，以获取环境特征点的景深，实现车辆测距定位；同时又对相邻两帧图像进行基于SURF特征的跟踪匹配，并通过对应匹配点在相邻两帧摄像机坐标系下的三维坐标，计算出摄像机坐标系在车辆运动前后的变换参数，根据变换参数估算出车辆的行驶速度。模拟实验表明，该方法具有良好的可行性，速度计算结果比较稳定，平均误差均在6%以内。Abstract: A real-time ranging location and ego-velocity estimation method based on binocular image sequences was presented to obtain the relative location and velocity of the vehicle in the running process. This method used the vehicle-borne binocular vision sensor to collect the image sequence of the surrounding environment. Then the depth of field of environmental feature points was obtained through matching feature points of left and right images at the same time based on speeded up robust features(SURF) in order to achieve vehicle location. Meanwhile, the feature points of two adjacent frames were tracked and matched based on SURF.The transformation parameter of the camera coordinate system before and after vehicle movement was computed through the 3D coordinates of the corresponding matching points in the two adjacent frames. And the velocity of the vehicle was estimated according to the transformation parameter. The simulation experiment results show that the method is feasible, and the speed calculation results are relatively stable, the average error is less than 6%.
-
-
![]()
图 2 基于双目视觉的车辆定位与自车速度估计方法流程图
Figure 2. Flow chart of vehicle location and ego-velocity estimation based on binocular vision
![]()
图 4 某一帧左右图像立体匹配结果
Figure 4. Stereo matching results of left and rightimages for one frame
表 1 某相邻两帧间部分对应环境特征点的三维坐标
单位：mm Table 1 3D coordinates of some corresponding environmental feature points between two adjacent frames
特征点编号 tk时刻特征点坐标(X, Y, Z) tk+1时刻特征点坐标(X, Y, Z) 1 (8.670，19.344，566.393) (127.463，20.283，571.327) 2 (2.908，-29.373，583.549) (122.217，-28.423，588.623) 3 (10.918，2.246，571.093) (129.843，3.175，575.927) 4 (10.790，9.766，569.612) (129.677，10.689，574.461) 5 (18.595，-24.373，581.284) (137.824，-23.405，585.815) 6 (17.429，14.277，566.984) (136.228，15.205，571.607) 
下载: 导出CSV
-
[1] 金守峰.基于机器视觉的工程机械行走速度测量系统研究[D].西安: 长安大学, 2015: 8-13. http://cdmd.cnki.com.cn/Article/CDMD-10710-1015803584.htm Jin Shoufeng.A research on engineering machine speed detect system based on machine vision[D]. Xi'an: Chang'an University, 2015: 8-13. http://cdmd.cnki.com.cn/Article/CDMD-10710-1015803584.htm
[2] Yamaguchi K, Kato T, Ninomiya Y.Vehicle ego-motion estimation and moving object detection using a monocular camera[C]//Proceedings of the International Conference on Pattern Recognition.NJ, USA: IEEE, 2006: 610-613. https://www.researchgate.net/publication/224649636_Vehicle_Ego-Motion_Estimation_and_Moving_Object_Detection_using_a_Monocular_Camera
[3] 刘威, 魏存伟, 赵逢, 等.基于单目视觉的自车运动参数鲁棒估计[J].机器人, 2009, 31(1):20-21. doi: 10.3321/j.issn:1002-0446.2009.01.004 Liu Wei, Wei Cunwei, Zhao Feng, et al.A robust method for vehicle ego-motion estimation based on monocular vision[J]. ROBOT, 2009, 31(1):20-21. doi: 10.3321/j.issn:1002-0446.2009.01.004
[4] 刘红亮, 陈维义, 许中胜.基于序列图像匹配的车载自主测速方法[J].系统工程与电子技术, 2015, 37(4):964-965. http://d.old.wanfangdata.com.cn/Periodical/xtgcydzjs201504037 Liu Hongliang, Chen Weiyi, Xu Zhongsheng.Research on vehicle-borne autonomous velocity measurement method based on sequence image matching[J]. Systems Engineer and Electronics, 2015, 37(4):964-965. http://d.old.wanfangdata.com.cn/Periodical/xtgcydzjs201504037
[5] 纪利娥, 杨风暴, 王志社, 等.基于边缘与SURF算子的SAR与可见光图像配准方法[J].应用光学, 2013, 34(5):811-812. http://d.old.wanfangdata.com.cn/Periodical/yygx201305017 Ji Li'e, Yang Fengbao, Wang Zhishe, et al.SAR and visible image registration method based on edge and SURF algorithm[J]. Journal of Applied Optics, 2013, 34(5):811-812. http://d.old.wanfangdata.com.cn/Periodical/yygx201305017
[6] Bay H, Tuytelaars T, Gool L V.SURF:speeded up robust features[J]. Lecture Notes in Computer Science, 2006, 3951:404-407. http://d.old.wanfangdata.com.cn/Periodical/hwyjggc200901035
[7] 徐树奎.基于计算摄影的运动模糊图像清晰化技术研究[D].长沙: 国防科学技术大学, 2011: 85-86. http://cdmd.cnki.com.cn/Article/CDMD-90002-1012020578.htm Xu Shukui.Research on motion blur image deburring technology based on computational photography[D]. Changsha: National University of Defense Technology, 2011: 85-86. http://cdmd.cnki.com.cn/Article/CDMD-90002-1012020578.htm
[8] 钟灵, 章云, 许哲民.近邻点一致性的随机抽样一致性算法[J].应用光学, 2011, 32(6):1146-1148. http://www.yygx.net/CN/abstract/abstract9870.shtml Zhong Ling, Zhang Yun, Xu Zhemin.Improved random sample consensus algorithm with near point consistency[J]. Journal of Applied Optics, 2011, 32(6):1146-1148. http://www.yygx.net/CN/abstract/abstract9870.shtml
[9] 代俣西, 沈秋, 王惠南, 等.双目视觉中基于对偶四元数的三维运动估计[J].光学技术, 2015, 41(2):132-135. http://d.old.wanfangdata.com.cn/Periodical/gxjs201502009 Dai Yuxi, Shen Qiu, Wang Huinan, et al.3D motion estimation of binocular vision based on dual quaternion[J]. Optical Technique, 2015, 41(2):132-135. http://d.old.wanfangdata.com.cn/Periodical/gxjs201502009
[10] 曹凤萍, 王荣本.基于立体视觉的月球车运动估计算法[J].吉林大学学报:工学版, 2011, 41(6):1593-1595. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jlgydxzrkxxb201106015 Cao Fengping, Wang Rongben.Stereovision based ego-motion estimation algorithm for lunar rover[J]. Journal of Jilin University:Engineering and Technology Edition, 2011, 41(6):1593-1595. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jlgydxzrkxxb201106015
[11] 孙大伟.基于双目视觉的月球车导航方法研究[D].哈尔滨: 哈尔滨工业大学, 2010: 46-48. http://cdmd.cnki.com.cn/article/cdmd-10213-1011261434.htm Sun Dawei.Research on navigation algorithm based on binocular vision for a lunar rover[D]. Harbin: Harbin Institute of Technology, 2010 46-48. http://cdmd.cnki.com.cn/article/cdmd-10213-1011261434.htm
-
期刊类型引用(5)
1. 韦晓孝，戴振秋，何晓冰，周辰，胡蝶. 用于病理切片检测的大视场变焦显微镜光学系统设计. 光学技术. 2025(01): 7-12 . 
百度学术
2. 赵志明，王乃余，李治国. 基于霍夫变换的透镜中心偏差检测方法. 光学技术. 2024(04): 441-447 . 百度学术
3. 韩颖，项建胜. 基于OptiCentric中心偏测量仪的红外光学镜组装调方法. 应用光学. 2022(04): 726-731 . 本站查看
4. 徐彦，朱元，单良. 应用OPD-Scan像差仪对白内障超声乳化患者像差分析的意义. 中国医疗器械信息. 2021(21): 120-122 . 百度学术
5. 赵希婷，张超，冀翼，刘辉，焦文春，黄阳，李重阳，张志飞. 超宽视场离轴光学系统畸变一致性校正技术. 应用光学. 2020(05): 1032-1036 . 本站查看
其他类型引用(1)
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
- 被引次数: 6
陕公网安备 61011302001501号 