DOI QR코드

DOI QR Code

정밀지도 구축을 위한 다중카메라기반 모바일매핑시스템 개발

Development of Multi-Camera based Mobile Mapping System for HD Map Production

  • 투고 : 2021.12.18
  • 심사 : 2021.12.23
  • 발행 : 2021.12.31

초록

본 연구는 자율주행을 위한 정밀지도 구축 및 신속갱신을 위한 다중카메라 기반의 MMS (Mobile Mapping System)기술개발을 목표로 한다. 고가의 라이다 센서를 대체하고 긴 처리시간을 단축하기 위해 다수의 카메라를 적용하고 실시간 데이터 전처리를 통해 저가이면서 효율적인 MMS를 개발하고자 한다. 이를 위해 다중카메라 저장 기술개발, 다중카메라 시각동기화 기술개발, MMS 시제품 개발을 수행하였다. 다중의 카메라로부터 취득되는 고속영상의 실시간 JPG압축저장을 위해 엔진을 선정하고 저장모듈을 개발하였으며, 다중영상이 촬영된 정확한 시간을 실시간으로 기록하기 위해 이벤트 및 GNSS (Global Navigation Satellite System) 타임서버 기반 시각동기화 방안을 개발했다. 그리고 각 부문별 요구사항을 바탕으로 MMS를 설계하고 시제품을 제작하였다. 마지막으로 제작된 다중카메라기반 MMS의 성능검증을 위해 실제 1,000km 도로에서 데이터를 취득하고 정량적 평가를 수행했고, 평가결과 시각동기화 성능은 1/1000초 이하를 나타내었으며, SFM영상처리를 통해 얻은 포인트 클라우드의 위치정확도는 5cm 내외를 나타냈다. 정량적 평가 결과를 통해 본 연구에서 개발된 다중카메라 기반 MMS기술이 정밀지도 구축 기준을 만족하는 성능을 나타내는 것을 알 수 있었고, 향후 정밀지도 구축 분야에서 특히 외산기술에 의존하고 있던 고가의 MMS를 대체하는데 기여할 것으로 판단된다.

This study aims to develop a multi-camera based MMS (Mobile Mapping System) technology for building a HD (High Definition) map for autonomous driving and for quick update. To replace expensive lidar sensors and reduce long processing times, we intend to develop a low-cost and efficient MMS by applying multiple cameras and real-time data pre-processing. To this end, multi-camera storage technology development, multi-camera time synchronization technology development, and MMS prototype development were performed. We developed a storage module for real-time JPG compression of high-speed images acquired from multiple cameras, and developed an event signal and GNSS (Global Navigation Satellite System) time server-based synchronization method to record the exposure time multiple images taken in real time. And based on the requirements of each sector, MMS was designed and prototypes were produced. Finally, to verify the performance of the manufactured multi-camera-based MMS, data were acquired from an actual 1,000 km road and quantitative evaluation was performed. As a result of the evaluation, the time synchronization performance was less than 1/1000 second, and the position accuracy of the point cloud obtained through SFM (Structure from Motion) image processing was around 5 cm. Through the evaluation results, it was found that the multi-camera based MMS technology developed in this study showed the performance that satisfies the criteria for building a HD map.

키워드

과제정보

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었음(과제번호 20NSIP-B145070-03).

참고문헌

  1. Ahn, H.R., Kim, J.I., and Kim, T.J. (2014), 3D Accuracy Analysis of Mobile Phone-based Stereo Images, Journal of Broadcast Engineering, Vol. 19, No. 5, pp. 677-686. (in Korean with English abstract) https://doi.org/10.5909/JBE.2014.19.5.677
  2. Khoramshahi, E., Campos, M.B., Tommaselli, A.M.G., Vilijanen, N., Mielonen, T., Kaartinen, H., Kukko, A., and Honkavaara, E. (2019), Accurate Calibration Scheme for a Multi-Camera Mobile Mapping System, Remote Sens., Vol. 11, No. 23
  3. Kim, C.Y. and Lee, W.S. (2016), Developing Stereo-vision based Drone for 3D Model Reconstruction of Collapsed Structures in Disaster Sites, Journal of the Korea Academia-Industrial cooperation Society, Vol. 17, No. 6, pp. 33-38. (in Korean with English abstract) https://doi.org/10.5762/KAIS.2016.17.6.33
  4. Kim, J.C., Kwon, K.S., and Kim, B.G. (2017), A study on the Application of stereo camera for coastal surveying, Proceedings of Korean Society for Geospatial Information Science, korean Society for Geospatial Information Science, 2017.10, Korea, pp. 19-20.
  5. Moon, B.S. (2015), A study on how to build a map with precision to support autonomous vehicles, etc., KICT, Korea.
  6. Oliveira, H.C., Mendonca, M.A., Ribeiro, M.B., and Alves R. (2019), CAMERA SYNCHRONIZATION USING AN AUDIO-BASED APPROACH FOR MOBILE MAPPING SYSTEMS, The 11th International Conference in Mobile Mapping Technology, 2019, 6-8 May, Shenzhen, China
  7. Park, H.G. (2017), Domestic Trend Analysis of Mobile Mapping System through Geospatial Information Market and Patent Survey, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 35, No. 6, / pp.495-508. (in Korean with English abstract) https://doi.org/10.7848/KSGPC.2017.35.6.495
  8. Park, S.G., Kim, E.M., and Lee, J.H. (2018), 3D positioning without control information using a high-resolution stereo camera, Proceedings of Korean Society for Geospatial Information Science, Korea Society for Geospatial Information Science, 2018.5, Korea, pp. 203-204.
  9. Riid, A., Louk, R., Pihlak, R., Tepljakov, A., and Vassiljeva , K. (2019), Pavement Distress Detection with Deep Learning Using the Orthoframes Acquired by a Mobile Mapping System, 2019 42nd International Conference on Telecommunications and Signal Processing, Vol. 9, No. 22
  10. Wang, Y., Chao, W.L., Garg, D., Hariahran, B., Campbell, M., and Weinberger, K.Q. (2019), Pseudo-LiDAR from Visual Depth Estimation : Bridging the Gap in 3D Object Detection for Autonomous Driving, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, 16-20 June, California, USA, pp. 8445-8453.