Comparison of Machine Vision Algorithms used by Autonomous Driving Robots to Recognize Road Signs in Underground Mines

Heonmoo Kim; Yosoon Choi

doi:10.32390/ksmer.2021.58.6.559

All Issue

2021 Vol.58, Issue 6 Preview Page Next Page

Research Paper

Comparison of Machine Vision Algorithms used by Autonomous Driving Robots to Recognize Road Signs in Underground Mines 지하광산용 자율주행 로봇의 도로 표지판 인지를 위한 머신비전 알고리즘 비교

31 December 2021. pp. 559-567

PDF XML

Abstract

This study compared four types of machine vision algorithms (color pattern matching, geometric matching, pattern matching, shape matching) used by autonomous driving robots to recognize road signs in underground mines. Through an indoor experiment, the accuracy of sign recognition using each algorithm was evaluated while varying the distance and angle between the autonomous driving robot and the road sign. Consequently, the geometric matching algorithm showed the highest accuracy of sign recognition. Additionally, the accuracy of sign recognition obtained using this algorithm was evaluated according to the presence or absence of lighting and symbol changes. This algorithm could reliably recognize road signs even under different lighting conditions and symbols.

Keywords

Autonomous driving robot

Machine vision

Road sign recognition

Underground mine

본 연구에서는 자율주행 로봇이 지하광산에서 도로 표지판을 인지하기 위해 사용될 수 있는 4종의 머신비전 알고리즘(컬러 패턴 매칭, 기하 매칭, 패턴 매칭, 형상 매칭)을 비교하였다. 실내실험을 통해 자율주행 로봇과 도로 표지판 사이의 거리와 각도 조건을 달리하면서 각각의 알고리즘의 표지판 인지 정확도를 평가하였다. 기하 매칭 알고리즘이 가장 높은 표지판 인지 정확도를 나타냈다. 추가적으로 조명의 여부와 상징(symbol) 변화에 따라 기하 매칭 알고리즘 도로 표지판 인지 정확도를 평가하였다. 기하 매칭 알고리즘은 조명 조건과 도로 표지판의 상징이 달라질 때도 안정적으로 작동하였다.

키워드

자율주행 로봇

머신비전

도로 표지판 인지

지하광산

References

Bakambu, J.N. and Polotski, V., 2007. Autonomous system for navigation and surveying in underground mines, Journal of Field Robotics, 24(10), p.829-847. 10.1002/rob.20213

Baker, C., Morris, A., Ferguson, D., Thayer, S., Whittaker, C., Omohundro, Z., Reverte, C., Whittaker, W., Hahnel, D., and Thrun, S., 2004. A campaign in autonomous mine mapping, Proc. of the IEEE International Conference on Robotics and Automation, New Orleans, LA, USA, p.1-6. 10.1109/ROBOT.2004.1308118

CDC, 2013. https://www.cdc.gov/niosh/mining/statistics/content/allminingdisasters.html. (Accessed at 17 November 2021)

CDC, 2016. https://www.cdc.gov/niosh/mining/works/statistics/factsheets/miningfacts2014.html. (Accessed at 17 November 2021)

Günther, F., Mischo, H., Lösch, R., Grehl, S., and Güth, F., 2019. Increased safety in deep mining with IoT and autonomous robots, Proc. of the 39th International Symposium 'Application of Computers and Operations Research in the Mineral Industry, Wroclaw, Poland, p.603-611. 10.1201/9780429320774-70

IMAQ Vision Concept Manual, 2021. https://www.ni.com/pdf/manuals/322916a.pdf. (Accessed at 17 November 2021)

Kim, H. and Choi, Y., 2021a. Location estimation of autonomous driving robot and 3D tunnel mapping in underground mines using pattern matched LiDAR sequential images, International Journal of mining science and technology, 31(5), p.779-788. 10.1016/j.ijmst.2021.07.007

Kim, H. and Choi, Y., 2021b. Self-Driving algorithm and location estimation method for small environmental monitoring robot in underground mines, Computer modeling in Engineering & Sciences, 127(3), p.943-964. 10.32604/cmes.2021.015300

Kim, H. and Choi, Y., 2021c. Autonomous driving robot that drives and returns along a planned route in underground mines by recognizing road signs, Applied Sciences, 11(21), p.1-13. 10.3390/app112110235

Larsson, J., Broxvall, M., and Saffiotti, A., 2005. A navigation system for automated loaders in underground mines, Proc. of the 5th International Conference on Field and Service Robotics, Port douglas, Australia, p.129-140. 10.1007/978-3-540-33453-8_12

Marshall, J., Barfoot, T., and Larsson, J., 2008. Autonomous underground tramming for center‐articulated vehicles. Journal of Field Robotics, 25(6‐7), p.400-421. 10.1002/rob.20242

MobileTronics, 2019. https://tunnelingonline.com/mobiletronics-demonstrates-autonomous-tbm-supply-vehicle/. (Accessed at 17 November 2021)

National Instruments, 2019. https://www.ni.com/ko-kr/shop/labview.html. (Accessed at 17 November 2021)

Sharma, G., Sood, S., Gaba, GS., and Gupta, N., 2012. Image Recognition System using Geometric Matching and Contour Detection, International Journal of Computer Applications, 51(7), p.48-53. 10.5120/8138-1905

Zhao, J., Gao, J., Zhao, F., and Liu, Y., 2017. A Search-and-Rescue Robot System for Remotely Sensing the Underground Coal Mine Environment, Sensors, 17(10), p.1-23. 10.3390/s1710242629065560PMC5677175

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 58
No :6
Pages :559-567
Received Date : 2021-11-22
Revised Date : 2021-12-22
Accepted Date : 2021-12-27
DOI :https://doi.org/10.32390/ksmer.2021.58.6.559

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue