The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Line Segments Matching Framework for Image Based Real-Time Vehicle Localization

이미지 기반 실시간 차량 측위를 위한 선분 매칭 프레임워크

  • Choi, Kanghyeok (Dept. of Future & Smart Construction Research, Korea Institute of Civil Engineering and Building Tech.)
  • 최강혁 (한국건설기술연구원 미래스마트건설연구본부)
  • Received : 2022.02.26
  • Accepted : 2022.03.24
  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Vehicle localization is one of the core technologies for autonomous driving. Image-based localization provides location information efficiently, and various related studies have been conducted. However, the image-based localization methods using feature points or lane information has a limitation that positioning accuracy may be greatly affected by road and driving environments. In this study, we propose a line segment matching framework for accurate vehicle localization. The proposed framework consists of four steps: line segment extraction, merging, overlap area detection, and MSLD-based segment matching. The proposed framework stably performed line segment matching at a sufficient level for vehicle positioning regardless of vehicle speed, driving method, and surrounding environment.

차량 측위 기술은 차량의 정확한 위치 정보를 제공한다는 점에서 자율주행을 위한 핵심 기술 중 하나로 평가되고 있다. 이미지 기반의 측위 기술은 위치 정보를 효율적으로 제공할 수 있을 것으로 판단되어 다양한 관련 연구가 진행되고 있다. 하지만, 기존 특징점 또는 차선 정보를 이용한 이미지 기반 측위 방법론은 도로 및 운행 환경에 측위 정확도가 큰 영향을 받을 수 있다는 한계가 있다. 선분 매칭은 특징점에 비하여 텍스쳐 반복에 강건하고 주변 환경 전체에서 추출된 선분을 활용하기 때문에 기존 방법론의 단점을 해결할 수 있다. 하지만, 차량 운행환경을 대상으로 한 선분 매칭 방법론을 다루는 연구는 거의 진행된 바 없다. 따라서 본 연구에서는 정확한 차량 측위 지원을 위한 선분 매칭 프레임워크를 제안한다. 또한 도로 주행 환경에서의 알고리즘 성능 비교 분석을 통하여 최적 선분 매칭 알고리즘을 결정하였다. 최종적으로 제안된 프레임워크는 선분 추출, 병합, 중첩 영역 탐지 및 MSLD 기반 선분 매칭의 4단계로 구성되었다. 제안된 프레임워크는 차량의 속도, 운행 방식, 주변 환경에 상관없이 차량 측위에 충분한 수준의 선분 매칭을 안정적으로 수행하였다.

Keywords

References

  1. Chiwata, M. and Matsushima, K.(2019), "Map Matching using Line Segment Features for Self-Vehicle Localization in Road Environments", In 2019 International Symposium on Electrical and Electronics Engineering, pp.124-129.
  2. Damen, D., Bunnun, P., Calway, A. and Mayol-Cuevas, W. W.(2012), "Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach", In The British Machine Vision Conference 2012, no. 2, pp.1-12.
  3. Fan, B., Wu, F. and Hu, Z.(2012), "Robust line matching through line-point invariants", Pattern Recognition, vol. 45, no. 2, pp.794-805. https://doi.org/10.1016/j.patcog.2011.08.004
  4. Gee, A. P. and Mayol-Cuevas, W.(2006), Real-time model-based SLAM using line segments, Springer, pp.354-363.
  5. Georgiev, A. and Allen, P. K.(2004), "Localization methods for a mobile robot in urban environments", IEEE Transactions on Robotics, vol. 20, no. 5, pp.851-864. https://doi.org/10.1109/TRO.2004.829506
  6. Gong, M., Yang, L., Potts, C., Asari, V. K., Oyen, D. and Wohlberg, B.(2020), TGGLines: A robust topological graph guided line segment detector for low quality binary images, arXiv preprint arXiv, vol. 2002, p.12428.
  7. Hamid, N. and Khan, N.(2016), "LSM: Perceptually accurate line segment merging", Journal of Electronic Imaging, vol. 25, no. 6, p.061620. https://doi.org/10.1117/1.jei.25.6.061620
  8. Han, S. J., Kang, J., Jo, Y., Lee, D. and Choi, J.(2018), "Robust ego-motion estimation and map matching technique for autonomous vehicle localization with high definition digital map", In 2018 International Conference on Information and Communication Technology Convergence, pp.630-635.
  9. Hara, K. and Saito, H.(2015), "Vehicle localization based on the detection of line segments from multi-camera images", Journal of Robotics and Mechatronics, vol. 27, no. 6, pp.617-626. https://doi.org/10.20965/jrm.2015.p0617
  10. Hwang, J., Ahn, K. J. and Kang, Y.(2019), "Validation of Localization Method for Autonomous Vehicles using Road Feature Map and 3D LiDAR Sensor", Journal of Institute of Control, Robotics and Systems, vol. 25, no. 6, pp.557-564. https://doi.org/10.5302/j.icros.2019.19.0015
  11. Im, J. H., Im, S. H. and Jee, G. I.(2018), "Extended line map-based precise vehicle localization using 3D LIDAR", Sensors, vol. 18, no. 10, p.3179. https://doi.org/10.3390/s18103179
  12. Kang, J. M., Yoon, T. S., Kim, E. and Park, J. B.(2020), "Lane-level map-matching method for vehicle localization using GPS and camera on a high-definition map", Sensors, vol. 20, no. 8, p.2166. https://doi.org/10.3390/s20082166
  13. Li, K. and Yao, J.(2017), "Line segment matching and reconstruction via exploiting coplanar cues", International Society for Photogrammetry and Remote Sensing Journal of Photogrammetry and Remote Sensing, vol. 125, pp.33-49. https://doi.org/10.1016/j.isprsjprs.2017.01.006
  14. Li, K., Yao, J., Lu, X., Li, L. and Zhang, Z.(2016), "Hierarchical line matching based on line-junction-line structure descriptor and local homography estimation", Neurocomputing, vol. 184, pp.207-220. https://doi.org/10.1016/j.neucom.2015.07.137
  15. Ma, W. C., Tartavull, I., Barsan, I. A., Wang, S., Bai, M., Mattyus, G., Homayounfar, N., Lakshmikanth, S. K., Pokrovsky, A. and Urtasun, R.(2019), "Exploiting sparse semantic HD maps for self-driving vehicle localization", In 2019 IEEE/Robotics Society of Japan International Conference on Intelligent Robots and Systems, pp.5304-5311.
  16. Micusik, B. and Wildenauer, H.(2015), "Descriptor free visual indoor localization with line segments", In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3165-3173.
  17. Shipitko, O. and Grigoryev, A. S.(2018), "Ground Vehicle Localization With Particle Filter Based On Simulated Road Marking Image", In Proceedings of 32nd European Conference on Modelling and Simulation, pp.341-347.
  18. Vakhitov, A. and Lempitsky, V.(2019), "Learnable line segment descriptor for visual slam", IEEE Access, vol. 7, pp.39923-39934. https://doi.org/10.1109/access.2019.2901584
  19. Vedaldi, A. and Fulkerson, B.(2010), "VLFeat: An open and portable library of computer vision algorithms", In Proceedings of the 18th Association for Computing Machinery International Conference on Multimedia, pp.1469-1472.
  20. Von Gioi, R. G.(2014), A contrario line segment detection, Springer, New York.
  21. Wang, Q., Zhao, H., Zhang, Z., Cui, X., Ullah, S., Sun, S. and Liu, F.(2018), "Line matching based on viewpoint-invariance for stereo wide-baseline aerial images", Applied Sciences, vol. 8, no. 6, p.938. https://doi.org/10.3390/app8060938
  22. Wang, Z., Wu, F. and Hu, Z.(2009), "MSLD: A robust descriptor for line matching", Pattern Recognition, vol. 42, no. 5, pp.941-953. https://doi.org/10.1016/j.patcog.2008.08.035
  23. Yoneda, K., Yang, C., Mita, S., Okuya, T. and Muto, K.(2015), "Urban road localization by using multiple layer map matching and line segment matching", In 2015 IEEE Intelligent Vehicles Symposium (IV), pp.525-530.
  24. Zhang, L. and Koch, R.(2013), "An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency", Journal of Visual Communication and Image Representation, vol. 24, no. 7, pp.794-805. https://doi.org/10.1016/j.jvcir.2013.05.006