全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于图像线特征和点云面特征的水下人造目标定位

DOI: 10.11834/jig.20150808

Keywords: 机器视觉,人造目标定位,椭圆检测,随机抽样一致性,超二次曲面

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的针对水下人造目标的位姿参数估计问题,提出一种基于图像线特征与点云面特征的目标定位算法。方法基于对人造物体成像后的边缘特征及其本身曲面特征的认知,将目标描述成为一种线特征与面特征的组合。首先依据指定线型对目标图像边缘进行线特征检测,初步定位目标在图像中的位置;然后采用RANSAC(randomsampleconsensus)算法对投影到目标区域内的点云进行曲面特征检测,得到目标参数的近似值并从视场点云中提取目标点云;最后以超二次曲面作为目标的部件化模型,以检测到的目标参数为初值,建立3维目标尺寸和位姿估计的非线性目标函数,将该目标函数的优化结果作为3维目标的定位结果。结果通过水下实验对算法的有效性进行验证,定位后的目标旋转轴角度偏差不超过2°,相对位置偏差不超过1%,单目标定位耗时不超过5s。结论实验结果表明,该算法的定位精度和耗时均能满足应用需要,可有效定位未知尺寸的人造目标,且对水下复杂环境有较强的适应性。

References

[1]  Prats M, Ribas D, Palomeras N, et al. Reconfigurable AUV for intervention missions: a case study on underwater object recovery [J]. Intelligent Service Robotics, 2012, 5(1):19-31. [DOI: 10.1007/s11370-011-0101-z]
[2]  Sanz P J, Ridao P, Oliver G, et al. TRIDENT: a framework for autonomous underwater intervention mission with dexterous manipulation capabilities [C]//The 7th Symposium on Intelligent Autonomous Vehicles. Lecce, Italy: University of Salento, 2010: 187-192. [DOI: 10.3182/20100906-3-IT-2019.00034]
[3]  Prats M, Fernandez J J, Sanz P J. An approach for semi-autonomous recovery of unknown objects in underwater environments[C] //Proceedings of the 13th International Conference on Optimization of Electrical and Electronic Equipment. Brasov: IEEE, 2012:1452-1457.[DOI: 10.1109/OPTIM.2012.6231874]
[4]  Rusu R B, Bradski G, Thibaux R, et al. Fast 3D recognition and pose using the Viewpoint Feature Histogram[C]//Proceedings of 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. Taipei: IEEE, 2010:2155-2162. [DOI: 10.1109/IROS. 2010. 5651280]
[5]  Wang L, Cao J F, Han C Z. Superquadrics Model-based 3D object localization algorithm [J]. Robot, 2013, 35(4): 439-448.[汪霖,曹建福,韩崇昭. 基于超二次曲面模型的3维目标定位算法[J]. 机器人, 2013, 35(4): 439-448][DOI: 10. 3724/SP.J.1218. 2013.00439]
[6]  Biegelbauer G, Vincze M, Wohlkinger W. Model-based 3D object detection: Efficient approach using superquadric [J]. Machine Vision and Applications, 2010,21: 497-516. [DOI: 10. 1007/s00138-008-0178-3]
[7]  Schnabel R, Wahl R, Klein R. Efficient RANSAC for point-cloud shape detection [J]. Computer Graphics Forum, 2007, 26(2): 214-226. [10.1111/j.1467-8659. 2007. 01016.x]
[8]  Alan H B. Superqadrics and angle preserving transformations [J]. Computer Graphics Applications, 1981, 18: 21-30.[DOI: 10.1109/MCG.1981.1673799]
[9]  Moré J J. The Levenberg-Marquardt algorithm: implementation and theory [M]//Numerical Analysis. Berlin Heidelberg: Springer, 1978: 105-116.[DOI: 10.1007/BFb0067700]
[10]  Xie Z X, Gao X, Cui J. Extraction algorithm of circular targets used for mobile three-dimensional measurement [J]. Chinese Journal of Lasers, 2013, 40(12): 166-171.[解则晓,高翔, 崔健. 移动式三维测量用圆形标记点提取算法[J]. 中国激光, 2013, 40(12):166-171.][DOI: 10.3788/CJL201340. 1208002]
[11]  Liu Y, Zhu Z Y, Shi S J. Novel strategy for spatial k-NN query [J]. Journal of Shanghai JiaoTong University, 2001, 35 [9] : 1298-1302.[刘宇,朱仲英,施颂椒. 空间k近邻查询的新策略[J]. 上海交通大学学报, 2001,35 (9): 1298-1302.][DOI: 10.3321/j.issn: 1006-2467.2001.09.007]
[12]  Solina F, Bajcsy R. Recovery of parametric models from range images: the case for superquadrics with global deformations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(2):131-147.[DOI: 10.1109/34.44401]
[13]  Prats M, Juan C, Garcia J, et al. Towards specification, planning and sensor-based control of autonomous underwater intervention [C]//proceedings of Preprints of the 18th IFAC Word Congress. Milano, Italy: Catholic University of the Sacred Heart, 2011: 10361-10366. [DOI: 10.3182/20110828-6-IT-1002.02456]
[14]  Xie Z X, Liu P. Underwater 3D structured light system based on refraction compensation [J]. Journal of Optoelectronics Laser, 2012, 23(4):745-750. [解则晓,刘鹏.基于折射补偿的水下结构光三维测量系统[J].光电子激光,2012,23(4):745-750.]
[15]  Xie Z X, Li X Y, Xin S H. Underwater line structured-light self-scan three-dimension measuring technology [J]. Chinese Journal of Lasers, 2010, 37(8): 2010-2014. [解则晓,李绪勇,辛少辉.水下线结构光自扫描三维测量技术[J].中国激光,2010,37(8):2010-2014.][DOI: 10. 3788/CJL20103708. 2010]
[16]  Huebner K, Ruthotto S, Kragic D. Minimum volume bounding box decomposition for shape approximation in robot grasping[C]//Proceedings of IEEE International Conference on Robotics and Automation. Pasadena, CA: IEEE, 2008:1628-1633.[DOI:10.1109/ROBOT.2008.4543434]
[17]  Huebner K, Kragic D. Selection of robot pre-grasps using box-based shape approximation[C]//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice, France: IEEE, 2008:1765-1770. [DOI: 10.1109/IROS. 2008. 4650722]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133