智能车辆视觉里程计算法研究进展

doi:10.3969/j.issn.1000-1093.2012.02.014

摘要/Abstract

摘要： 对智能车辆视觉里程计算法进行了综述，首先说明了视觉里程计的基本原理，然后从所使用的信息特征、相机配置、两帧或多帧计算框架等方面对视觉里程计系统进行了分类与比较，其次详细介绍了视觉里程计算法中的关键技术问题，包括特征选择与匹配、鲁棒运动估计等，最后讨论了视觉里程计未来发展方向。

关键词: 信息处理技术, 智能车辆, 视觉里程计, 运动估计

Abstract: Algorithms of the visual odometry for intelligent vehicles are reviewed. Firstly, the basic principle of the visual odometry is introduced. Secondly, the classification and comparison are made according to types of visual information, the configuration of cameras and the calculation framework. Thirdly, the key techniques including feature selection and matching, robust motion estimation in two-frame visual odometry system are analyzed. Finally the development trends of the visual odometry algorithms are discussed.

Key words: information processing, intelligent vehicles, visual odometry, motion estimation

中图分类号:

TP242.6

江燕华，熊光明，姜岩，龚建伟，陈慧岩. 智能车辆视觉里程计算法研究进展[J]. 兵工学报, 2012, 33(2): 214-220.

JIANG Yan-hua, XIONG Guang-ming, JIANG Yan, GONG Jian-wei, CHEN Hui-yan. A Review of Visual Odometry for Intelligent Vehicles[J]. Acta Armamentarii, 2012, 33(2): 214-220.

参考文献

［1］吴功伟. 立体视觉里程计的关键技术研究[D]. 杭州：浙江大学，2007.
WU Gong-wei. Research on key technologies in stereo visual odometry[D]. Hangzhou: Zhejiang University, 2007. (in Chinese)
[2] Moravec H. Obstacle avoidance and navigation in the real world by a. seeing robot rover[D]. Stanford: Univ. of Stanford, 1980.
[3] Matthies L, Shafer S A. Error modeling in stereo navigation[J]. IEEE J. Robot. Automat., 1987, RA23(3)：239-250.
[4] 彭勃, 周文晖, 刘济林. 基于Harris角点检测的立体视觉里程计[J]. 兵工学报，2007，28(12)：1498-1502.
PENG Bo, ZHOU Wen-hui, LIU Ji-lin. Harris corner detection-based stereo visual odometry[J]. Acta Armanmentarii, 2007, 28(12)：1498-1502. (in Chinese)
[5] Eade E, Drummond T. Scalable monocular SLAM[C]∥Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York: IEEE, 2006: 469-476.
[6] Davison A J, Reid I D, Molton N D, et al. Mono SLAM: real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1052-1067.
[7] Davison A J. Real-time simultaneous localization and mapping with a single camera[C]∥Proc. International Conference on Computer Vision, Nice: IEEE, 2003: 1403-1410.
[8] 马玉娇. 基于立体视觉里程计的移动机器人定位研究[D]. 武汉：武汉科技大学，2009.
MA Yu-jiao. Research on mobile robot localization based on stereo visual odometry[D]. Wuhan: Wuhan University of Science and Technology, 2009. (in Chinese)
[9] Badino H. A robust approach for ego-motion estimation using a mobile stereo platform[J]. Lecture Notes in Computer Science, 2007, 3417: 198-208.
[10] Nistér D, Naroditsky O, Bergen J. Visual odometry[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington: IEEE, 2004: 652-659.
[11] Mouragnon E, Lhuillier M, Dhome M, et al. Real time localization and 3D reconstruction[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York: IEEE, 2006: 363-370.
[12] Tardif J, Pavlidis Y, Daniilidis K. Monocular visual cdometry in urban environments using an omnidirectional camera[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice: IEEE, 2008: 2531-2538.
[13] Corke P, Strelow D, Singh S. Omnidirectional visual odometry for a planetary rover[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, 2004: 4007-4012.
[14] Agrawal M, Konolige K. Rough terrain visual odometry[C]. International Conference on Advanced Robotics, Menlo Park: 2007.
[15] Hirschmüller H, Innocent P R, Garibaldi J M. Fast, unconstrained camera motion estimation from stereo without tracking and robust statistics[C]∥In International Conference on Control, Automation, Robotics and Vision, Singapore: Nayang Technological Univ, 2002: 1099-1104.
[16] Milella A, Reina G. Vision-based methods for mobile robot localization and wheel sinkage estimation[C]∥ASME Dynamic Systems and Control Conference, Michigan: 2008: 625-621.
[17] Milella A, Siegwart R. Stereo-based ego-motion estimation using pixel-tracking and iterative closest point[C]∥Proc. IEEE International Conference on Computer Vision Systems, New York: IEEE, 2006: 21-27.
[18] Kitt B, Geiger A, Lategahn H. Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme[C]∥IEEE Intelligent Vehicle Symposium, San Diego: IEEE, 2010: 486-492.
[19] Howard A. Real-time stereo visual odometry for autonomous ground vehicles[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice: IEEE, 2008: 3946-3952.
[20] García-García R, Sotelo M A, Parra I, et al. 3D visual odometry for road vehicles[J]. Journal of Intelligent and Robotic Systems Archive, 2008, 51(1): 113-134.
[21] Sappa A D, Dornaika F, Ponsa D, et al. An efficient approach to onboard stereo vision system POSE estimation[J]. IEEE Trans. Intell. Transp. Syst, 2008, 9(3): 476-490.
[22] Jong Weon Lee, Suya You, Ulrich Neumann. Large motion estimation for omnidirectional vision[C]∥IEEE Workshop on Omnidirectional Vision, Hilton Head Island: IEEE, 2000: 161-168.
[23] Wen Lik Dennis Lui, Ray A. Jarvis. An omnidirectional vision system for outdoor mobile robots[C]∥IEEE Workshop on Omnidirectional Robot Vision, Anchorage: IEEE, 2008: 273-284.
[24] Parra I, Sotelo M A, Llorca D F. Robust visual odometry for vehicle localization in urban environments[J]. Robotica, 2010, 28(3): 441-452.
[25] Parra I, Sotelo M A, Vlacic L. Robust visual odometry for complex urban environments[C]∥IEEE Intelligent Vehicles Symposium, Eindhoven: IEEE, 2008: 440-445.
[26] Triggs B, McLauchlan P F, Hartley R I, et al. Bundle adjustment-a modern synthesis[J]. In Vision Algorithms: Theory and Practice, ser. LNCS. Springer Verlag, 2000, 1883: 298-375.
[27] Shum H, K E Q, Zhang Z. Efficient bundle adjustment with virtual key frames: a hierarchical approach to multi-frame structure from motion[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Collins: IEEE, 1999: 538-543.
[28] Jungho Kim,In So Kweon. Vision-based autonomous navigation based on motion estimation[C]∥International Conference on Control, Seoul: Automation and Systems, 2008: 1738-1743.
[29] Royer E, Lhuillier M, Dhome M, et al. Monocular vision for mobile robot localization and autonomous navigation[J]. International Journal of Computer Vision, 2007, 74(3): 237-260.
[30] Levin A, Szeliski R. Visual odometry and map correlation[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington: IEEE, 2004:1611-1618.
[31] Konolige K, Agrawal M, Sola J. Large scale visual odometry for rough terrain[C]∥In International Symposium on Research in Robotics, Hiroshima: 2007.
[32] Kwolek B. Visual odometry based on gabor filters and sparse bundle adjustment[C]∥IEEE International Conference on Robotics and Automation, Roma: IEEE, 2007: 3573-3578.
[33] Chiuso A, Favaro P, Jin H, et al. Structure from motion causally integrated over time[J]. IEEE Trans. on Pattern Anal. Mach. Intell., 2002, 24(4): 523-535.
[34] Rudolph van der Merwe, Eric A. Wan. Sigma-point kalman filters for integrated navigation[C]∥Proc. Annual Meeting of The Institute of Navigation, Dayton: NSF, 2004: 641-654.
[35] Mclauchlan P, Reid I, Murray D. Recursive affine structure and motion from image sequences[C]∥Proc. European Conf. Comp. Vision, Stockholm: Springer Verlag, 1994: 217-224.
[36] García-García R G, Sotelo M A, Parra I, et al. 3D visual odometry for GPS navigation assistance[C]∥Proc. IEEE Intelligent Vehicles Symposium, Istanbul: IEEE, 2007: 444-449.
[37] Zhu Z, Oskiper T, Samarasekera S, et al. Sawhney. Ten-fold improvement in visual odometry using landmark matching[C]∥IEEE International Conference on Computer Vision, Rio de Janeiro: IEEE, 2007: 1747-1754.
[38] Oskiper T, Zhu Z, Samarasekera S. Visual odometry system using multiple stereo cameras and inertial measurement unit[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis: IEEE, 2007: 976-983.
[39] P. H. S . Torr and A. Zisserman. Feature based methods for structure and motion estimation[J]. in Vision Algorithms: Theory and Practice, 2000, 1883: 278-295.
[40] Taylor C J, Kriegman D J. Structure and motion from line segments in multiple images[J]. IEEE Trans. on Pattern Anal. Mach. Intell., 1995, 17(11): 1021-1032.
[41] Wong K Y K, Mendonca P R S, Cipolla R. Structure and motion estimation from apparent contours under circular motion[J]. Image and Vision Computing, 2002, 20: 441-448.
[42] Schmid C, Mohr R, Baukhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37(2): 151-172.
[43] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[44] 李智, 周文晖, 刘济林. 动态场景下基于视差空间的立体视觉里程计[J]. 浙江大学学报（工学版），2008，42(10)：1661-1665.
LI Zhi, ZHOU Wen-hui, LIU Ji-lin. Stereo visual odometry from disparity space in dynamic environments[J]. Journal of Zhejiang University: Engineering Science, 2008, 42(10): 1661-1665. (in Chinese)
[45] Gong P L, Zhang Q F, Zhang A Q. Stereo vision based motion estimation for underwater vehicles[C]∥International Conference on Intelligent Computation Technology and Automation, Changsha: IEEE, 2009: 745-749.
[46] Rodriguez S A, Fremont F V, Bonnifait P. An experiment of a 3D real-time robust visual odometry for intelligent vehicles[C]∥Proc. International Conference on Intelligent Transportation Systems, Shizuoka: IEEE, 2009: 226-231.
[47] Zhang T, Liu X, Kuhnlenz K, et al. Visual odometry for the autonomous city explorer[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems, St. Louis: IEEE, 2009: 3513-3518.
[48] Gordon I, Lowe D G. What and where: 3D object recognition with accurate pose[C]∥International Symposium on Mixed and Augmented Reality, Santa Barbara: IEEE, 2006: 67-82.
[49] Horn B K P. Relative orientation[J]. International Journal of Computer Vision, 1990, 4: 59-78.
[50] Nistér D. An efficient solution to the five-point relative pose problem[J]. IEEE Trans. on Pattern Anal. Mach. Intell., 2004, 26(6): 756-770.
[51] Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with apphcatlons to image analysis and automated cartography[J]. Graphics and Image Processing, 1981, 24(6): 381-395.
[52] Nister D. Preemptive RANSAC for live structure and motion estimation[C]∥Proc. International Conference on Computer Vision, Nice: 2003: 199-206.
[53] Scaramuzza D, Fraundorfer F, Siegwart R. Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC[C]∥International Conference on Robotics and Automation, Kobe: 2009: 4293-4299.
[54] Nourani-Vatani N, Roberts J, Srinivasan M V. Practical visual odometry for car-like vehicles[C]∥International Conference on Robotics and Automation, Kobe: 2009: 3551-3557.
[55] Haralick R, Lee C, Ottenberg K, et al. Review and analysis of solutions of the three point perspective pose estimation problem[J]. International Journal of Computer Vision, 1994, 13(3): 331-356.
[56] Nistér D. A minimal solution to the generalised 3-Point pose problem[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington: IEEE, 2004: 560-567.
[57] Horn B K P, Hilden H M, Negahdaripour S. Closed-form solution of absolute orientation using orthonormal matrices[J]. Journal Opt. Soc. Am. A, 1988, 5: 1127-1135.
[58] Horn B K P. Closed-form solution of absolute orientation using unit quaternions[J]. Journal Opt. Soc. Am. A, 1987, 4(4): 629-642.
[59] Stéwenius H, Engels C, Nistér D. Recent developments on direct relative orientation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 60: 284-294.
[60] Matthies L, Maimone M, Johnson A, et al. Computer vision on mars[J]. International Journal of Computer Vision, 2007, 75(1): 67-92.
[61] Kitt B, Moosmann F, Stiller C. Moving on to dynamic environments: visual odometry using feature classification[C]∥International Conference on Intelligent Robots and Systems, Taipei: IEEE, 2010: 5551-5556.
[62] Sakai A, Mitsuhashi M, Kuroda Y. Noise model creation for visual odometry with neural-fuzzy model[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei: IEEE, 2010: 5190-5195.
[63] Sáez J M, Escolano F. 6DOF entropy minimization SLAM for stereo-based wearable devices[J]. Computer Vision and Image Understanding, 2011, 115(2): 270-285.

编辑推荐 0

Metrics

阅读次数

全文

536

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	1	0	0	535

来源	本网站	其他网站

次数	71	465
比例	13%	87%

摘要

434

最新录用	在线预览	正式出版

0	0	434

来源	本网站	其他网站

次数	123	311
比例	28%	72%

[1]	蒋岩, 丁语嫣, 张兴龙, 徐昕. 基于模型预测与策略学习的智能车辆人机协同控制算法[J]. 兵工学报, 2023, 44(11): 3465-3477.
[2]	曹昊哲, 刘全攀. 基于半直接法的无人集群协同视觉SLAM算法[J]. 兵工学报, 2023, 44(11): 3345-3358.
[3]	密俊霞，于会龙，席军强. 基于MLP-SVM的驾驶员换道行为预测[J]. 兵工学报, 2022, 43(12): 3020-3029.
[4]	吴超, 吴绍斌, 李子睿, 孙冬. 基于人机交互的免锚检测和跟踪系统设计[J]. 兵工学报, 2022, 43(10): 2565-2575.
[5]	陆瑶敏, 龚建伟, 王博洋, 关海杰. 基于多重示范的智能车辆运动基元表征与序列生成[J]. 兵工学报, 2021, 42(4): 851-861.
[6]	王威，陈慧岩，马建昊，刘凯，龚建伟. 基于Frenet坐标系和控制延时补偿的智能车辆路径跟踪[J]. 兵工学报, 2019, 40(11): 2336-2351.
[7]	曾溢良，蓝金辉，邹金霖. 滑动置信度约束的红外弱小目标跟踪算法研究[J]. 兵工学报, 2017, 38(9): 1771-1778.
[8]	李关防，崔杰，袁富宇. 基于线谱瞬时频率估计的被动声纳目标运动分析[J]. 兵工学报, 2017, 38(7): 1395-1401.
[9]	朱甦，薄煜明，何亮. 基于冗余字典的多特征压缩感知目标跟踪算法[J]. 兵工学报, 2017, 38(6): 1140-1146.
[10]	王啸, 韩太林, 张永立, 刘轩, 王义君, 宫玉琳. 多通道瞬态信号自适应变频算法[J]. 兵工学报, 2017, 38(6): 1161-1167.
[11]	陈慧岩，陈舒平，龚建伟. 智能汽车横向控制方法研究综述[J]. 兵工学报, 2017, 38(6): 1203-1214.
[12]	张石，张百海，王飞帆，关子霄. 基于跳数量化的无线传感器网络节点定位算法[J]. 兵工学报, 2017, 38(5): 932-939.
[13]	夏平, 任强, 吴涛, 雷帮军. 融合多尺度统计信息模糊C均值聚类与Markov随机场的小波域声纳图像分割[J]. 兵工学报, 2017, 38(5): 940-948.
[14]	曹俊，郑翠娥，孙大军，张殿伦. 基于凸优化的水下载体定位研究[J]. 兵工学报, 2017, 38(3): 520-526.
[15]	向颉，茅永兴，郭才发. 船载雷达测速数据的船速修正新方法[J]. 兵工学报, 2017, 38(11): 2268-2273.