基于建筑特征及二维地图的复杂城市场景中移动机器人视觉定位算法

doi:10.11772/j.issn.1001-9081.2014.09.2557

计算机应用 ›› 2014, Vol. 34 ›› Issue (9): 2557-2561.DOI: 10.11772/j.issn.1001-9081.2014.09.2557

基于建筑特征及二维地图的复杂城市场景中移动机器人视觉定位算法

李海丰,王怀超

中国民航大学计算机科学与技术学院，天津 300300

收稿日期:2014-03-10 修回日期:2014-04-18 出版日期:2014-09-01 发布日期:2014-09-30
通讯作者: 李海丰
作者简介:
李海丰(1984-),男,内蒙古通辽人,讲师,博士,主要研究方向:计算机视觉、智能机器人、民航信息系统;
王怀超(1984-),男,天津人,讲师,博士,主要研究方向:移动机器人导航。
基金资助:
国家自然科学基金资助项目;中央高校基本科研业务费资助项目;中国民航大学预研重大项目;中国民航大学科研启动基金资助项目

Visual localization for mobile robots in complex urban scene using building features and 2D map

LI Haifeng,WANG Huaiqiang

College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China

Received:2014-03-10 Revised:2014-04-18 Online:2014-09-01 Published:2014-09-30
Contact: LI Haifeng
Supported by:
;the Fundamental Research Funds for the Central Universities;Pre-research Major Project of Civil Aviation University of China;the Scientific Research Funds for Civil Aviation University of China

摘要/Abstract

摘要：

针对城市环境中全球定位系统(GPS)信号易受到高层建筑遮挡而无法提供准确位置信息的问题，提出了一种基于建筑物竖直侧平面特征及建筑物二维轮廓地图的移动机器人定位方法。该方法利用车载视觉，首先对两视图间的竖直直线特征进行匹配;然后基于匹配的竖直线特征对建筑物的竖直侧平面进行重建;最后，利用建筑物竖直侧平面特征及建筑物二维俯视轮廓地图，设计了一种基于随机采样一致性(RANSAC)的移动机器人视觉定位算法，从而解决了在建筑物方向任意的复杂城市环境中的机器人定位问题。实验结果表明，算法的平均定位误差约为3.6m，可以有效地提高移动机器人在复杂城市环境中自主定位的精度及鲁棒性。

Abstract:

For the localization problem in urban areas, where Global Positioning System (GPS) cannot provide the accurate location as its signal can be easily blocked by the high-rise buildings, a visual localization method based on vertical building facades and 2D bulding boundary map was proposed. Firstly, the vertical line features across two views, which are captured with an onboard camera, were matched into pairs. Then, the vertical building facades were reconstructed using the matched vertical line pairs. Finally, a visual localization method, which utilized the reconstructed vertical building facades and 2D building boundary map, was designed under the RANSAC (RANdom Sample Consensus) framework. The proposed localization method can work in real complex urban scenes. The experimental results show that the average localization error is around 3.6m, which can effectively improve the accuracy and robustness of self-localization of mobile robots in urban environments.

中图分类号:

TP18
TP242

李海丰王怀超. 基于建筑特征及二维地图的复杂城市场景中移动机器人视觉定位算法[J]. 计算机应用, 2014, 34(9): 2557-2561.

LI Haifeng WANG Huaiqiang. Visual localization for mobile robots in complex urban scene using building features and 2D map[J]. Journal of Computer Applications, 2014, 34(9): 2557-2561.

参考文献

［1］WONGPHATI M, NIPARNAN N, SUDANG A. Bearing only FastSLAM using vertical line information from an omnidirectional camera ［C］// ROBIO 2008: Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics． Piscataway: IEEE, 2009: 1188-1193.

［2］DAVISON A J, REID I D, MOLTON N D, et al.MonoSLAM: real-time single camera SLAM ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1052-1067.

［3］CARELLI R, OLIVEIRA F E. Corridor navigation and wall-following stable control for sonar-based mobile robots ［J］. Robotics and Autonomous Systems, 2003, 45 (3): 235-247.

［4］BORENSTEIN J, FENG L. A new method for combining data from gyros and odometry in mobile robots ［C］// Proceedings of the 1996 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 1996: 423-428.

［5］RAMALINGAM S, BOUAZIZ S, STURM P, et al.SKYLINE2GPS: localization in urban canyons using omni-skylines ［C］// Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2010: 3816-3823.

［6］LEE S C, JUNG S K, NEVATIA R. Automatic pose estimation of complex 3D building models ［C］// Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision. Piscataway: IEEE, 2002: 148-152.

［7］McHENRY M, CHENG Y, MATTHIES L. Vision based localization in urban environments ［C］// Proceedings of the 2005 International Society for Optics and Photonics. Bellingham: SPIE, 2005: 359-370.

［8］LEUNG K Y, CLARK C M, HUISSOON J P. Localization in urban environments by matching ground level video images with an aerial image ［C］// Proceedings of the 2008 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2008: 551-556.

［9］CHAM T J, TAN W C, PHAM M T, et al.Estimating camera pose from a single urban ground-view omnidirectional image and a 2D building outline map ［C］// Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 366-373.

〖HJ1.72mm〗［10］LI H, LIU J, LU X. Visual localization in urban area using orthogonal building boundaries and a GIS database ［J］. Robot, 2012, 34(5): 604-613. 〖BP(〗(李海丰，刘景泰，卢翔. Visual Localization in Urban Area Using Orthogonal Building Boundaries and a GIS Database［J］. 机器人, 2012, 34(5): 604-613.)【是英文文章】〖BP)〗

［11］LI H, XIANG J, LIU J. An automatic building extraction method from high resolution satellite image ［C］// Proceedings of the 31st Chinese Control Conference. Piscataway: IEEE, 2012: 4884-4889. (李海丰，相吉磊，刘景泰. 一种基于高分辨率卫星图像的建筑物轮廓自动提取方法［C］// 第31届中国控制会议论文集. Piscataway: IEEE, 2012: 4884-4889.)

［12］HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision ［M］. 2nd ed. Cambridge: Cambridge University Press, 2003: 151-233.

〖WW)〗〖HT〗〖HJ〗〖HQK〗〖FL)〗

[1]	杜航原郝思聪王文剑. 结合图自编码器与聚类的半监督表示学习方法[J]. 计算机应用, 0, (): 0-0.
[2]	陈露张晓霞于洪. 基于先验知识的非负矩阵半可解释三因子分解算法[J]. 计算机应用, 0, (): 0-0.
[3]	韩舒宁徐敏董学士林青沈凡凡. 混合伊藤算法求解多尺度着色旅行商问题[J]. 计算机应用, 0, (): 0-0.
[4]	李晓杰崔超然宋广乐苏雅茜吴天泽张春云. 基于时序超图卷积神经网络的股票趋势预测方法[J]. 计算机应用, 0, (): 0-0.
[5]	张建严珂马祥. 基于神经网络的复杂垃圾信息过滤算法分析[J]. 计算机应用, 0, (): 0-0.
[6]	邱云志汪廷华戴小路. 双重特征加权模糊支持向量机[J]. 计算机应用, 0, (): 0-0.
[7]	李宗正周恺卿丁雷欧云. 基于基因交换的自适应人工鱼群算法[J]. 计算机应用, 0, (): 0-0.
[8]	刘清华廖士中. 基于随机素描方法的在线核回归[J]. 计算机应用, 0, (): 0-0.
[9]	张小清王晨曦吕彦林耀进. 基于ReliefF的层次分类在线流特征选择算法[J]. 计算机应用, 0, (): 0-0.
[10]	于婉莹梁美玉王笑笑陈徵曹晓雯. 基于深度注意力网络的课堂教学视频中学生表情识别与智能教学评估[J]. 计算机应用, 0, (): 0-0.
[11]	黄勇康梁美玉王笑笑陈徵曹晓雯. 基于深度时空残差卷积神经网络的课堂教学视频中多人课堂行为识别[J]. 计算机应用, 0, (): 0-0.
[12]	康猛蒙祖强. 基于局部条件区分能力的高效属性约简算法[J]. 计算机应用, 0, (): 0-0.
[13]	谢鑫张贤勇王旋晔唐鹏飞. 变精度邻域等价粒邻域决策树构造算法[J]. 计算机应用, 0, (): 0-0.
[14]	刘忠慧王梓宥闵帆. 近似概念的遗传生成算法及其推荐应用[J]. 计算机应用, 0, (): 0-0.
[15]	潘仁志钱付兰赵姝张燕平. 基于卷积神经网络交互的用户属性偏好建模的推荐模型[J]. 计算机应用, 0, (): 0-0.

基于建筑特征及二维地图的复杂城市场景中移动机器人视觉定位算法

Visual localization for mobile robots in complex urban scene using building features and 2D map

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics