基于扩展卡尔曼滤波的实时视觉SLAM算法

doi:10.3969/j.issn.1000-3428.2013.08.050

计算机工程 ›› 2013, Vol. 39 ›› Issue (8): 231-234,238. doi: 10.3969/j.issn.1000-3428.2013.08.050

基于扩展卡尔曼滤波的实时视觉SLAM算法

梁超，王亮，刘红云

(北京工业大学电子信息与控制工程学院，北京 100124)

收稿日期:2012-04-09 出版日期:2013-08-15 发布日期:2013-08-13
作者简介:梁超(1987－)，男，硕士研究生，主研方向：机器视觉，图像处理；王亮，讲师、博士；刘红云，副教授、硕士
基金资助:
国家自然科学基金资助项目(60975065)

Real-time Vision SLAM Algorithm Based on Extend Kalman Filtering

LIANG Chao, WANG Liang, LIU Hong-yun

(College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China)

Received:2012-04-09 Online:2013-08-15 Published:2013-08-13

摘要/Abstract

摘要： 单目视觉同步定位与地图创建(SLAM)算法的计算复杂度较高，难以满足实时处理的要求。为解决该问题，提出一种SLAM的优化算法。使用FAST特征点提取环境特征，对于每一个特征点构造BRIEF描述子，以提高算法执行效率，通过引入1-point随机抽样一致算法对算法的框架进行改进，降低算法的计算复杂度，实现视觉SLAM算法的实时处理。实验结果表明，在相机速度为30 f/s的情况下，该算法能满足实时性要求。

关键词: 同步定位与地图创建, 扩展卡尔曼滤波, FAST角点, BRIEF描述子, 随机抽样一致, 单目视觉

Abstract: Monocular Simultaneous Localization and Mapping(SLAM) is computational complexity, and it is hard to reach real-time process. In order to solve this problem, this paper proposes an SLAM optimization algorithm. It uses the Feature from Accelerated Segment Test(FAST) corner to extract the environment featrures, and makes the Binary Robust Independent Elementary Feature(BRIEF) descriptor for every feature points, and improves the execution efficiency of the algorithm. 1-point Random Sample Consensus(RANSAC) algorithm is introduced to improve the algorithm framework, to reduce the computational complexity of algorithm and to achieve real-time processing of visual SLAM. Experimental results show that when the camera speed is 30 frames per second, the proposed algorithm can meet the real-time requirements.

Key words: Simultaneous Localization and Mapping(SLAM), Extended Kalman Filtering(EKF), FAST corner, BRIEF descriptor, Random Sample Consensus(RANSAC), monocular vision

中图分类号:

TP24

梁超, 王亮, 刘红云. 基于扩展卡尔曼滤波的实时视觉SLAM算法[J]. 计算机工程, 2013, 39(8): 231-234,238.

LIANG Chao, WANG Liang, LIU Gong-Yun. Real-time Vision SLAM Algorithm Based on Extend Kalman Filtering[J]. Computer Engineering, 2013, 39(8): 231-234,238.

http://www.ecice06.com/CN/Y2013/V39/I8/231

参考文献

[1] Durrant W H F, Bailey T. Simultaneous Localization and Mapping: Part Ⅰ[J]. IEEE Robotics and Automation Magazine, 2006, 13(2): 99-110.
[2] Bailey T, Durrant W H F. Simultaneous Localization and Mapping(SLAM): Part Ⅱ[J]. IEEE Robotics and Automation Magazine, 2006, 13(3): 108-117.
[3] 孙荣川, 马书根, 李斌, 等. 基于分治法的同步定位与环境采样地图创建[J]. 自动化学报, 2010, 36(12): 1697-1703.
[4] Christopher M, Sibley G M, Cummins P, et al. A Constant Time Efficient Stereo SLAM System[C]//Proc. of the 20th British Machine Vision Conference. London, UK: [s. n.], 2009.
[5] Konolige K, Agrawal M. FrameSLAM: From Bundle Adjust- ment to Real-time Visual Mapping[J]. IEEE Transactions on Robotics, 2008, 24(5): 1066-1077.
[6] Civera J, Davison A J, Montiel J M M. Inverse Depth Para- meterization for Monocular SLAM[J]. IEEE Transactions on Robotics, 2008, 24(5): 932-945. (下转第238页)
(上接第234页)

[7] Klein G, Murray D W. Parallel Tracking and Mapping for Small AR Workspaces[C]//Proc. of International Symposium on Mixed and Augmented Reality. Nara, Japan: [s. n.], 2007.
[8] Calonder M, Lepetit V, Strecha C, et al. BRIEF: Binary Robust Independent Elementary Features[EB/OL]. (2010-11-21). http://soc.fudan.edu.cn/vip/projects/gradproj/wiki/BRIEF_Binary_Robust_Independent_Elementary_Features.
[9] Civera J, Grasa O G, Davison A J, et al. 1-point RANSAC for EKF-based Structure from Motion[C]//Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems. St. Louis, USA: [s. n.], 2009.
[10] Davison A J. Real-time Simultaneous Localization and Map- ping with a Single Camera[C]//Proc. of the 9th International Conference on Computer Vision. Nice, France: [s. n.], 2003.
[11] Lowe D G. Object Recognition from Local Scale-invariant Features[C]//Proc. of the 7th International Conference on Computer Vision. Washington D. C., USA: IEEE Computer Society, 1999.
[12] Shi J, Tomasi C. Good Features to Track[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE Press, 1994.
[13] Rosten E, Drummond T. Machine Learning for High-speed Corner Detection[C]//Proc. of European Conference on Computer Vision. Graz, Austria: [s. n.], 2006.
[14] Davison A J, Molton N D, Reid I D, et al. MonoSLAM: Real- time Single Camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1052-1067.
编辑刘冰

[1]	王宽, 杨环, 潘振宽, 司建伟. 基于单目和双目视觉信息的全参考立体图像质量评价模型[J]. 计算机工程, 2022, 48(2): 207-214,223.
[2]	杨刚, 朱士玲, 李强, 赵克松. 融合UWB与INS的消防员室内定位与NLOS检测算法[J]. 计算机工程, 2021, 47(9): 153-161.
[3]	吴海滨, 徐若彤, 王爱丽, 于晓洋, 岩堀祐之, 赵蓝飞, 刘赫. 基于计算机视觉的人体内腔三维重建技术综述[J]. 计算机工程, 2021, 47(10): 1-15.
[4]	庞智华, 齐臣坤. 一种鲁棒的单目视觉里程计算法[J]. 计算机工程, 2020, 46(12): 80-87.
[5]	曾维林, 刘桂华, 陈豪. 基于概率运动统计特征匹配的单目视觉SLAM[J]. 计算机工程, 2019, 45(12): 222-231,236.
[6]	吕立,姚拓中,宋加涛,肖江剑,王建军. 基于单目视觉三维重建系统的设计与实现[J]. 计算机工程, 2018, 44(12): 233-239.
[7]	吴骏,李文杰,耿磊,肖志涛,张芳,李月龙. 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.
[8]	赵越,李晶皎,王爱侠,杨丹. 基于IEKF-SLAM的未知场景增强现实跟踪注册算法[J]. 计算机工程, 2016, 42(1): 272-277.
[9]	陶明,凌有铸,陈孟元,戴雪梅. 迭代的平方根容积卡尔曼滤波SLAM算法[J]. 计算机工程, 2015, 41(9): 317-321.
[10]	王喜梅,,吕泽均,张涛,颜可壹. 基于高频地波雷达的无角度双站雷达目标跟踪算法[J]. 计算机工程, 2015, 41(3): 312-316.
[11]	安维胜,余让明,伍玉铃. 基于FAST和SURF的图像配准算法[J]. 计算机工程, 2015, 41(10): 232-235,239.
[12]	杨磊，李桂菊. 一种动态稀疏式观测系统的场景重建方案[J]. 计算机工程, 2014, 40(7): 202-206.
[13]	罗元, 孔维熙, 张毅. 基于Android手机的智能轮椅室外导航方法[J]. 计算机工程, 2013, 39(6): 312-315,318.
[14]	谢锦, 蔡自兴, 李昭, 尤作. 基于方向边缘匹配的人行横道与停止线检测[J]. 计算机工程, 2013, 39(6): 261-265,282.
[15]	杨小辉, 王敏. 基于ASIFT的无缝图像拼接方法[J]. 计算机工程, 2013, 39(2): 241-244.

选择文件类型/文献管理软件名称

选择包含的内容

基于扩展卡尔曼滤波的实时视觉SLAM算法

Real-time Vision SLAM Algorithm Based on Extend Kalman Filtering

PDF

可视化

被引次数

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

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于扩展卡尔曼滤波的实时视觉SLAM算法

Real-time Vision SLAM Algorithm Based on Extend Kalman Filtering

PDF

可视化

被引次数

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

本文评价