비전 및 HD Map 기반 차로 내 차량 정밀측위 기법
Vehicle Localization Method for Lateral Position within Lane Based on Vision and HD Map
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
자율 주행 기술이 발전함에 따라 주행 주변 환경을 인식하는 데 차량 위치의 정확성은 매우중요하다. 측위의 정확도를 높이기 위해 정밀지도를 사용한 지도 정합 측위기술(map-matching localization)이 연구되고 있다. 기존의 지도 정합 기법은 지도에서 차선의 중심으로 표현된 데이터를 기반으로 차량 위치를 추정하기에 차선 내 측면 거리의 편차를 반영하지 않는다. 따라서본 논문에서는 정밀한 측위를 제공하기 위해 영상처리를 통한 차선 검출 기법과 정밀지도의차선 위치 정보를 이용한 기법을 제안한다. 영상 처리 기법으로 IPM(inverse perspective mapping)과 다중 차선 검출 기법, 중앙선 검출 기법을 통하여 차선 번호를 검출하고 차선 이탈감지 방법으로 차선 중심으로부터 차량의 측면 거리를 추정한다. 최종적으로 영상처리로 검출한 차선 번호와 GNSS / INS의 위치를 기반으로 정밀지도에서 위치 링크정보를 추출하고 추출된 링크에 측면 거리를 반영하여 차선 내 차량의 위치를 추정한다. 제안된 방법의 성능을 평가하기 위하여 실제 도로에서 실험하였다. 제안하는 방법은 GNSS / INS와 비교 시 약 1.0m 정도정확도가 개선되며, 기존의 차선레벨 맵매칭 방법과 비교 시 구간별로 약 0.04m ~ 0.21m (7~30%) 정확도가 개선됨을 확인하였다.
Abstract
As autonomous driving technology advances, the accuracy of the vehicle position is important for recognizing the environments around driving. Map-matching localization techniques based on high definition (HD) maps have been studied to improve localization accuracy. Because conventional map-matching techniques estimate the vehicle position based on an HD map reference dataset representing the center of the lane, the estimated position does not reflect the deviation of the lateral distance within the lane. Therefore, this paper proposes a localization system based on the reference lateral position dataset extracted using image processing and HD maps. Image processing extracts the driving lane number using inverse perspective mapping, multi-lane detection, and yellow central lane detection. The lane departure method estimates the lateral distance within the lane. To collect the lateral position reference dataset, this approach involves two processes: (i) the link and lane node is extracted based on the lane number obtained from image processing and position from GNSS/INS, and (ii) the lateral position is matched with the extracted link and lane node. Finally, the vehicle position is estimated by matching the GNSS/INS local trajectory and the reference lateral position dataset. The performance of the proposed method was evaluated by experiments carried out on a highway environment. It was confirmed that the proposed method improves accuracy by about 1.0m compared to GNSS / INS, and improves accuracy by about 0.04m～0.21m (7～30%) for each section when compared with the existing lane-level map matching method.
참고문헌 (28)
- Aly M., "Real time detection of lane markers in urban streets", 2008 IEEE Intelligent Vehicles Symposium (2008)
- Badino H., "Visual topometric localization", 2011 IEEE Intelligent Vehicles Symposium (IV), pp.794~799 (2011)
- Bernstein D., "An introduction to map matching forpersonal navigation assistants", pp.1~14 (1998), TIDE Center
- Cai H., "Integration of gps, monocular vision and high definition(hd) map for accurate vehicle localization", Sensors, 18(10) (2018)
- Cui D., "Real-time global localization of robotic cars in lane level via lane marking detection and shape registration", IEEE Transactions on Intelligent Transportation Systems, 17(4), pp.1039~1050 (2016)
- Deng L., "Semantic segmentation-based lane-level localization using around view monitoring system", IEEE Sensors Journal, 19(21), pp.10077~10086 (2019)
- Du X., "Comprehensive and practical vision system for self-driving vehicle lane-level localization", IEEE Transactions on Image Processing, 25(5), pp.2075~2088 (2016)
- Durrant-Whyte H., "Simultaneous localization and mapping: Part i", IEEE Robotics Automation Magazine, 13(2), pp.99~110 (2006)
- Forsyth D., "Computer vision: A modern approach" (2003), Prentice Hall
- Grompone von Gioi R., "Lsd: A fast line segment detector with a false detection control", IEEE Trans-actions on Pattern Analysis and Machine Intelligence, 32(4), pp.722~732 (2010)
- Hashemiand M., "A critical review of real-time map-matching algorithms:Current issues and future directions", Computers, Environment and Urban Systems, 48, pp.153~165 (2014)
- Hsueh Y. L., "Map matching for low-sampling-rategps trajectories by exploring real-time moving directions", Information Sciences, 433-434, pp.55~69 (2018)
- Jeong M., "Lane-level map-matching method for vehicle localization using gps and camera on a high-definition map", Sensors, 20(8) (2020)
- Jo K., "Precise localization of an autonomous car based on probabilistic noise models of road surface marker features using multiple cameras", IEEE Transactions on Intelligent Transportation Systems, 16(6), pp.3377~3392 (2015)
- Kang J. M., "An enhanced map-matching algorithm for real-time position accuracy improvement with a low-cost GPS receiver", Sensors, 18(11), pp.3836~ (2018)
- Kim D., "Lane-level localization using an avm camera for an automated driving vehicle in urban environments", IEEE, 2017, pp.22(1), 280~290
- Kim S., "Real time multi-lane detection using relevant lines based on line labeling method", 2019 4th International Conference on Intelligent Transportation Engineering (ICITE), pp.301~305 (2019)
- Mattern N., "High-accurate vehicle localization using digital maps and coherency images", 2010 IEEE Intelligent Vehicles Symposium, pp.462~469 (2010)
- Ochieng W., "Map-matching in complex urban road networks", Revista Brasileira de Cartografia, 55(2) (2003)
- Parra I., "Robust visual odometry for vehicle localization in urban environments", Robotica, 28(3), pp.441~452 (2010)
- Quddus M. A., "A high accuracy fuzzy logic based map matching algorithm for road transport", Journal of Intelligent Transportation Systems, 10(3), pp.103~115 (2006)
- Tanaka S., "Vehicle detection based on perspective transformation using rear-view camera", International Journal of Vehicular Technology, 2011, pp.1~9 (2011)
- Valiente D., "Robust visual localization with dynamic uncertainty management in omnidirectional slam", Appl. Sci, 7, pp.1294~ (2017)
- Woo R., "A fuzzy-innovation-based adaptive kalman filter for enhanced vehicle positioning in dense urban environments", Sensors, 19(5), pp.1142~ (2019)
- Xing Y., "Advanced driver intention inference: Theory and design" (2020), Elsevier Science
- Yang G., "Rapid relocation method for mobile robot based on improved orb-slam2 algorithm", Remote Sens, 11, pp.149~ (2019)
- Zhang F., "Lap-slam: A line-assisted point-based monocular vslam", Electronics, 8, pp.243~ (2019)
- Zhou Q., "An adaptive low-cost GNSS", MEMS-IMU tightly-coupled integration system with aiding measurement in agnss signal-challenged environment, 2015, pp.15, 23953~23982