Design of visual odometer based on RANSAC optical flow method and feature point matching method

ZHANG Junqi; HU Likun

doi:10.5768/JAO202041.0602005

Journal of Applied Optics > 2020 > 41(6): 1214-1221. > DOI: 10.5768/JAO202041.0602005

ZHANG Junqi, HU Likun. Design of visual odometer based on RANSAC optical flow method and feature point matching method[J]. Journal of Applied Optics, 2020, 41(6): 1214-1221. DOI: 10.5768/JAO202041.0602005

Citation:

PDF (1002 KB)

Design of visual odometer based on RANSAC optical flow method and feature point matching method

College of Electrical Engineering, Guangxi University, Nanning 530000, China

More Information

Received Date: April 10, 2020
Revised Date: May 31, 2020
Available Online: October 16, 2020

Graphical Abstract

Abstract

Abstract

In order to solve the problem of insufficient positioning accuracy, error accumulation and long time consuming of feature point matching method, a visual odometer that combines RANSAC optical flow method and improved feature point matching method was designed. The RANSAC optical flow method was used to estimate the small-scale motion between key frames. The RANSAC algorithm eliminated the mismatch points of optical flow, which greatly reduced the mismatch existing in the optical flow method. The motion estimation between key frames used the improved feature point matching method to correct the estimation error of the optical flow method. Finally, the RANSAC optical flow method and the improved feature point matching method were fused by using the Kalman filtering. The experimental results show that the algorithm can overcome the problems of insufficient accuracy and error accumulation of the optical flow method, which increases the MRE from 15.5% to 2.6%. And it can also improve the speed of the feature point matching method, which increases the average consuming time from 37.28 ms to 21.07 ms.
- visual odometer,
- feature point matching method,
- optical flow method,
- RANSAC,
- Kalman filtering

FullText(HTML)

References (20)

References

[1]	李扬宇. 基于深度传感器的移动机器人视觉SLAM研究[D]. 重庆: 重庆大学, 2017. LI Yangyu. Research on vision slam of mobile robot based on depth sensor[D]. Chongqing: Chongqing University, 2017.
[2]	NISTER D, NARODITSKY O, BERGEN J. Visual odometry[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. USA: IEEE Computer Society, 2004.
[3]	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. doi: 10.1109/TPAMI.2007.1049
[4]	KITT B, GEIGER A, LATEGAHN H. Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme[C]//2010 IEEE Transactions on Intelligent Vehicles Symposium (IV). USA: IEEE, 2010.
[5]	LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
[6]	BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding,2008,110(3):346-359. doi: 10.1016/j.cviu.2007.09.014
[7]	ETHAN R, VINCENT R, KURT K. ORB: an efficient alternative to SIFT or SURF[C]//2011 International Conference on Computer Vision. USA: IEEE, 2012.
[8]	杨志芳, 袁家凯, 黄瑶瑶. 基于SIFT算法的室内全景图拼接[J]. 自动化与仪表,2020,35(3):58-62, 87. YANG Zhifang, YUAN Jiakai, HUANG Yaoyao. Indoor panorama stitching based on SIFT algorithm[J]. Automation and Instrumentation,2020,35(3):58-62, 87.
[9]	丁小奇, 李健, 胡雅婷, 等. 基于改进SURF算法无人机影像特征匹配的研究[J]. 中国农机化学报,2020,41(2):147-154. DING Xiaoqi, LI Jian, HU Yating, et al. Research on UAV image feature matching based on improved SURF algorithm[J]. Agricultural Machinery News of China,2020,41(2):147-154.
[10]	朱成德, 李志伟, 王凯, 等. 基于改进RANSAC-GMS算法的图像匹配[J]. 计算机应用,2019,39(08):2396-2401. ZHU Chengde, LI Zhiwei, WANG Kai, et al. Image matching based on improved RANSAC-GMS algorithm[J]. Computer Application: 2019,39(8):2396-2401.
[11]	周磊, 马立. 基于稀疏光流法的ORB特征匹配优化[J]. 应用光学,2019,40(4):583-588. doi: 10.5768/JAO201940.0402001 ZHOU Lei, MA Li. ORB feature matching optimization based on sparse optical flow method[J]. Journal of Applied Optics,2019,40(4):583-588. doi: 10.5768/JAO201940.0402001
[12]	ENGEL J, SCHÖPS T, CREMERS D. LSD-SLAM: large-scale direct monocular SLAM[C]//13th European Conference on Computer Vision (ECCV). [S.l.]: Springer Nature, 2014.
[13]	ENGEL J, STURM J, CREMERS D. Semi-dense visual odometry for a monocular camera[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. USA: IEEE, 2013.
[14]	贾哲. 基于光流跟踪和特征匹配的视觉里程计研究[D]. 天津: 天津理工大学, 2019. JIA Zhe. Research on visual odometer based on optical flow tracking and feature matching[D]. Tianjin: Tianjin University of Technology, 2019.
[15]	张国良, 姚二亮, 林志林, 等. 融合直接法与特征法的快速双目SLAM算法[J]. 机器人,2017,39(6):879-888. ZHANG Guoliang, YAO Erliang, LIN Zhilin, et al. Fast binocular SLAM algorithm combining direct m-ethod and feature method[J]. Robot,2017,39(6):879-888.
[16]	齐乃新, 杨小冈, 李小峰, 等. 基于ORB特征和LK光流的视觉里程计算法[J]. 仪器仪表学报,2018,39(12):216-227. QI Naixin, YANG Xiaogang, LI Xiaofeng, et al. Visual odometer based on ORB feature and LK optical flow[J]. Journal of Instrumentation,2018,39(12):216-227.
[17]	郑驰, 项志宇, 刘济林. 融合光流与特征点匹配的单目视觉里程计[J]. 浙江大学学报(工学版),2014,48(2):279-284. ZHENG Chi, XIANG Zhiyu, LIU Jilin. Monocular visual odometer fusing optical flow and feature pointmatching[J]. Journal of Zhejiang University (Engineering Edition),2014,48(2):279-284.
[18]	吴荻, 战凯, 肖小凤. 基于改进光流法和纹理权重的视觉里程计[J]. 计算机工程与设计,2019,40(1):238-243. WU Di, ZHAN Kai, XIAO Xiaofeng. Visual odometer based on improved optical flow method and text-ure weight[J]. Computer Engineering and Design,2019,40(1):238-243.
[19]	赵卫东, 曹蒙, 蒋超. 结合光流法和RANSAC的视觉里程计设计[J]. 兰州工业学院学报,2019(3):62-67. doi: 10.3969/j.issn.1009-2269.2019.03.012 ZHAO Weidong, CAO Meng, JIANG Chao. Design of visual odometer combining optical flow method and RANSAC[J]. Journal of Lanzhou University of Technology,2019(3):62-67. doi: 10.3969/j.issn.1009-2269.2019.03.012
[20]	涂梅林, 郭太良, 林志贤. 基于ORB特征的改进RANSAC匹配点提纯算法[J]. 有线电视技术,2018,344(8):15-19. TU Hailin, GUO Tailiang, LIN Zhixian. Improved RANSAC matching point purification algorithm based on ORB features[J]. Cable TV Technology,2018,344(8):15-19.

Cited By

Cited by

Periodical cited type(6)

1.	李征，韩旭，柯熙政. 无线光通信一对多发射天线研究进展. 激光杂志. 2024(04): 1-15 .
2.	叶井飞，朱润徽，马梦聪，丁天宇，宋真真，曹兆楼. 紫外宽光谱大相对孔径光学系统设计. 应用光学. 2021(05): 761-766 . 本站查看
3.	罗辉，李杰，李金铖，吴晗平. 近地层紫外通信收/发一体光学系统技术研究. 光电技术应用. 2021(06): 10-23 .
4.	李杰，罗箫，吴晗平. 基于折/衍混合的机载红外光学系统设计. 激光与红外. 2020(02): 215-223 .
5.	刘庆杰，王晨，王小英. 调制技术对紫外光通信信号传输衰减特性研究. 激光杂志. 2020(04): 158-161 .
6.	张凯迪，李季，雷震. 同轴收发卡式系统加入平板后的像差校正研究. 应用光学. 2018(06): 796-802 . 本站查看

Other cited types(3)

Get Citation

PDF

XML

Article views (2285) PDF downloads (80) Cited by(9)

Turn off MathJax

Article Contents

Abstract

References

Design of visual odometer based on RANSAC optical flow method and feature point matching method