基于改进BRISK算法的单目视觉里程计

doi:10.3969/j.issn.1006-2475.2018.09.013

计算机与现代化

基于改进BRISK算法的单目视觉里程计

(河海大学计算机与信息学院，江苏南京211100)

收稿日期:2018-03-07 出版日期:2018-09-29 发布日期:2018-09-30
作者简介:冯钧（1969-），女，江苏常州人，河海大学计算机与信息学院教授，博士，研究方向：时空数据管理，水利信息化，人工智能; 黄多辉（1993-），男，安徽六安人，硕士研究生，研究方向：计算机视觉，机器人导航，人工智能。
基金资助:
国家重点研发计划项目(2017YFC0405806); 江苏省重点研发计划（社会发展）项目(BE2015707)

Monocular Visual Odometry Based on Improved BRISK Algorithm

(College of Computer and Information, Hohai University, Nanjing 211100, China)

Received:2018-03-07 Online:2018-09-29 Published:2018-09-30

摘要/Abstract

摘要： 在传统的BRISK算法中使用自定义的抽样模式来描述检测到的特征点，使用基于汉明距离的方法进行特征点匹配。BRISK的这种特征点描述与匹配的方法使得其匹配准确率不高。因此本文提出将匹配准确率较高的SURF算法与BRISK算法相结合，在BRISK特征点描述与匹配阶段使用SURF描述符和基于欧氏距离的匹配方法。实验结果表明，该算法在时间消耗下降不大的情况下，特征点匹配准确率有很大提高，且该算法具有较好的鲁棒性。

关键词: BRISK, SURF, 视觉里程计, 特征检测, 特征匹配

Abstract: In the traditional BRISK algorithm, a custom sampling pattern is used to describe the detected feature points, and a method based on the Hamming distance is used for feature matching. This feature point description and matching method of BRISK makes the low matching accuracy. Therefore, this paper proposes to combine SURF algorithm with high accuracy of matching and BRISK algorithm, and to use SURF descriptor and Euclidean distance-based matching method in BRISK feature point description and matching stage. The experimental results show that the accuracy of feature point matching is greatly improved when the time consumption of the algorithm is not greatly reduced. At the same time, the experiment also shows that the algorithm has good robustness.

Key words: BRISK, SURF, visual odometry, feature detection, feature matching

中图分类号:

TP242.6

冯钧，黄多辉. 基于改进BRISK算法的单目视觉里程计[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.09.013.

FENG Jun, HUANG Duo-hui. Monocular Visual Odometry Based on Improved BRISK Algorithm[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.09.013.

参考文献

［1］蔡自兴,贺汉根,陈虹. 未知环境中移动机器人导航控制研究的若干问题［J］. 控制与决策, 2002,17(4):385-390.
［2］ Konolige K, Agrawal M, Solà J. Large-scale visual odometry for rough terrain［C］// Proceedings of the 13th International Symposium on Robotics Research. 2007:201-212.
［3］ Maimone M, Cheng Yang, Matthies L. Two years of visual odometry on the Mars exploration rovers: Field reports［J］. Journal of Field Robotics, 2007,24(3):169-186.
［4］ Zhang Ji, Kaess M, Singh S. Real-time depth enhanced monocular odometry［C］// Proceedings of the 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2014:4973-4980.
［5］ Mur-Artal R, Tardós J D. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras［J］. IEEE Transactions on Robotics, 2017,33(5):1255-1262.
［6］ 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.
［7］ Endres F, Hess J, Engelhard N, et al. An evaluation of the RGB-D SLAM system［C］// Proceedings of the 2012 IEEE International Conference on Robotics and Automation. 2012:1691-1696.
［8］ Badino H, Yamamoto A, Kanade T. Visual odometry by multi-frame feature integration［C］// Proceedings of the 2013 IEEE International Conference on Computer Vision Workshops. 2013:222-229.
［9］ Song Shiyu, Chandraker M, Guest C C. Parallel, real-time monocular visual odometry［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. 2013:4698-4705.〖ZK）〗
［10］Mur-Artal R, Montiel J M M, Tardós J D. ORB-SLAM: A versatile and accurate monocular SLAM system［J］. IEEE Transactions on Robotics, 2015,31(5):1147-1163.
［11］Scaramuzza D, Siegwart R. Appearance-guided monocular omnidirectional visual odometry for outdoor ground vehicles［J］. IEEE Transactions on Robotics, 2008,24(5):1015-1026.
［12］Scaramuzza D, Fraundorfer F, Siegwart R. Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC［C］// Proceedings of the 2009 IEEE International Conference on Robotics and Automation. 2009:4293-4299.
［13］高云峰,李伟超,李建辉. 室内移动机器人视觉里程计研究［J］. 传感器与微系统, 2012,31(2):26-29.
［14］王亚龙,张奇志,周亚丽. 基于Kinect的三维视觉里程计的设计［J］. 计算机应用, 2014,34(8):2371-2374.
［15］Guclu O, Can A B. A comparison of feature detectors and descriptors in RGB-D SLAM methods［C］// Proceedings of the 2015 IEEE International Conference on Image Analysis and Recognition. 2015:297-305.
［16］索春宝,杨东清,刘云鹏. 多种角度比较SIFT、SURF、BRISK、ORB、FREAK算法［J］. 北京测绘, 2014(4):23-26.
［17］Mair E, Hager G D, Burschka D, et al. Adaptive and generic corner detection based on the accelerated segment test［C］// Proceedings of the 11th European Conference on Computer Vision. 2010,2:183-196.
［18］Rosten E, Drummond T. Machine learning for high-speed corner detection［C］// Proceedings of the 9th European Conference on Computer Vision. 2006,1:430-443.
［19］Karpushin M, Valenzise G, Dufaux F. Improving distinctiveness of BRISK features using depth maps［C］// Proceedings of the 2015 IEEE International Conference on Image Processing. 2015:2399-2403.

[1]	杨旭朝, 雷志勇, 王娇娇. 基于局部重叠区域的无显著特征图像配准算法[J]. 计算机与现代化, 2023, 0(01): 24-29.
[2]	徐惠, 铁治欣, 舒莹. 基于特征匹配的快速降维排序搜索方法[J]. 计算机与现代化, 2022, 0(02): 85-91.
[3]	王文，徐亦白，卢杉，冯宇. 一种结合区域检测和语义分割的SLAM技术[J]. 计算机与现代化, 2019, 0(07): 55-.
[4]	陆兴华,刘铭原,龙庆佳,陈泽江. 基于灰度直方图的运动目标特征检测算法[J]. 计算机与现代化, 2019, 0(06): 71-.
[5]	陶筱娇，卢锦. 基于改进SURF特征与模糊推理的复杂图片中的文字识别[J]. 计算机与现代化, 2019, 0(04): 72-.
[6]	程金芝，郭玲. 相位标志牌图像识别与缺陷检测[J]. 计算机与现代化, 2017, 0(10): 20-23,28.
[7]	胡晨1，江泽涛2. 一种SIFT像素点筛选预处理降维双向匹配方法[J]. 计算机与现代化, 2016, 0(9): 54-59+72.
[8]	郭倩,孙涵. 一种基于最小哈希的二值特征匹配方法[J]. 计算机与现代化, 2016, 0(6): 73-78.
[9]	段珊珊1，李昕2. 基于RGBD传感器的场景自适应性视觉里程计算法[J]. 计算机与现代化, 2016, 0(12): 73-77.
[10]	周敏1，刘宁钟2，王立春2. 基于无人机航拍的公路图像拼接方法研究[J]. 计算机与现代化, 2016, 0(10): 49-53.
[11]	吕俊1，王福田1,2，汤进1,2，罗斌1,2. 基于全景温度场的电力设备在线自动识别与诊断[J]. 计算机与现代化, 2015, 0(8): 19-23.
[12]	熊琰铖，孙涵. 结合全局信息的对称SURF算法在车辆检测中的应用[J]. 计算机与现代化, 2015, 0(1): 80-83.
[13]	张志强 . 基于云计算的大规模人脸特征检索[J]. 计算机与现代化, 2014, 0(7): 71-74+79.
[14]	隋建凯1，刘惠义1，严烁2. 一种基于随机森林的特征匹配方法[J]. 计算机与现代化, 2014, 0(4): 81-85.
[15]	赵莹，刘森，李庆猛，张浩，魏宏来. 基于图像特征匹配的商品识别算法[J]. 计算机与现代化, 2014, 0(1): 18-21.

基于改进BRISK算法的单目视觉里程计

Monocular Visual Odometry Based on Improved BRISK Algorithm

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

本文评价