제한된 트랙 환경에서 모바일 로봇의 비젼 기반 실시간 차선 검출과 추적
Vision-based Real-time Lane Detection and Tracking for Mobile Robots in a Constrained Track Environment
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
실생활에서의 모바일 로봇 응용이 증가하면서 저비용의 자율 주행 기능이 요구되고 있다. 본논문은 모바일 로봇의 실내 주행 여건을 고려한 제한된 트랙을 가정하고, 제한된 트랙에서 모바일 로봇의 자율 주행을 지원하는 비젼 기반 실시간 차선 검출 및 추적 시스템을 제안한다. 다양한 형태의 차선 처리와 동작 파리미터의 사전 조정 등을 고려하여 다중 동작 모드를 가진 시스템구조와 상태 기계를 설계하였으며, 파라미터 조정 모드에서 차선 두께의 기하학적 특성을 바탕으로 컬러 필터의 임계값을 동적으로 조정하고, 곡선 트랙의 불안정 입력 모드와 직선 트랙의 안정입력 모드에서 차선의 기하학적 그리고 시간적 특성을 바탕으로 차선 특징 픽셀을 적응적으로 추출하고 최소제곱법으로 차선 모형을 추정한다. 추정된 차선 모형으로 트랙 중앙선을 산출하고 움직임 모형을 단순화시켜 선형 칼만 필터를 통해 추적한다. 주행 실험에서 저성능의 로봇 구성에서도 실시간 처리를 통해 제한된 트랙에서 정상적으로 자율 주행이 이루어짐을 확인하였다.
Abstract
As mobile robot applications increase in real life, the need of low cost autonomous driving are gradually increasing. We propose a novel vision-based real-time lane detection and tracking system that supports autonomous driving of mobile robots in constrained tracks which are designed considering indoor driving conditions of mobile robots. Considering the processing of lanes with various shapes and the pre-adjustment of operation parameters, the system structure with multi-operation modes are designed. In parameter tuning mode, thresholds of the color filter is dynamically adjusted based on the geometric property of the lane thickness. And in the unstable input mode of curved tracks and the stable input mode of straight tracks, lane feature pixels are adaptively extracted based on the geometric and temporal characteristics of the lanes and the lane model is fitted using the least-squared method. The track centerline is calculated using lane models and the motion model is simplified and tracked by a linear Kalman filter. In the driving experiments, it was confirmed that even in low-performance robot configurations, real-time processing produces the accurate autonomous driving in the constrained track.
참고문헌 (25)
- Yang Xing, "Advances in Vision-Based Lane Detection: Algorithms, Integration, Assessment, and Perspectives on ACP-Based Parallel Vision", IEEE, 2018, pp.5(3), 645~661[DOI]
- Haojie Zhang, "A Low Cost Vision-Based Road-Following System for Mobile Robots", Applied Sciences, 8(9), pp.1635~ (2018), MDPI AG[DOI]
- C.Y. Kuo, "On the Image Sensor Processing for Lane Detection and Control in Vehicle Lane Keeping Systems", Sensors, 19(7), pp.1665~ (2019), MDPI AG[DOI]
- Sun, T. Y., "HSI color model based lane-marking detection", Proceedings of the IEEE Conference on Intelligent Transportation Systems, pp.1168~1172 (2006)
- H. Cheng, "Lane Detection With Moving Vehicles in the Traffic Scenes", IEEE Transactions on Intelligent Transportation Systems, 7(4), pp.571~582 (2006)
- J. Canny, "A Computational Approach to Edge Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(6), pp.679~698 (1986)
- Q. Lin, "Real-Time Lane Departure Detection Based on Extended Edge-Linking Algorithm", 2010 Second International Conference on Computer Research and Development, pp.725~730 (2010)
- Y. Otsuka, "Multitype lane markers recognition using local edge direction", Intelligent Vehicle Symposium 2002, 2, pp.604~609 (2002), IEEE
- J. W. Lee, "A lane-departure identification based on LBPE, Hough transform, and linear regression", Computer Vision and Image Understanding, 99(3), pp.359~383 (2005)
- Aly, M., "Real time detection of lane markers in urban streets", Proceedings of the IEEE Intelligent Vehicles Symposium, pp.7~12 (2008)
- Deng, J., "A real-time system of lane detection and tracking based on optimized RANSAC B-spline fitting", Proceedings of the ACM International Conference on Research in Adaptive and Convergent Systems, pp.157~164 (2013)
- Tan, H., "A novel curve lane detection based on improved river flow and RANSAC", Proceedings of the IEEE Conference on Intelligent Transportation Systems, pp.133~138 (2014)
- Mammeri, A., "Lane detection and tracking system based on the MSER algorithm, hough transform and kalman filter", Proceedings of the ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, pp.259~266 (2014)
- Li, Y., "Multiple lane boundary detection using a combination of low-level image features", Proceedings of the IEEE Conference on Intelligent Transportation Systems, pp.1682~1687 (2014)
- M. B. de Paula, "Automatic Detection and Classification of Road Lane Markings Using Onboard Vehicular Cameras", IEEE Transactions on Intelligent Transportation Systems, 16(6), pp.3160~3169 (2015)
- Seo, Y. W, "Utilizing instantaneous driving direction for enhancing lane-marking detection", Proceedings of the IEEE Intelligent Vehicles Symposium, pp.170~175 (2014)
- Nan, Z., "Efficient Lane Boundary Detection with Spatial-Temporal Knowledge Filtering", Sensors, 16, pp.1276~ (2016)
- J. C. McCall, "Video-based lane estimation and tracking for driver assistance : survey, system, and evaluation", IEEE Transactions on Intelligent Transportation Systems, 7(1), pp.20~37 (2006)
- R. Danescu, "Probabilistic Lane Tracking in Difficult Road Scenarios Using Stereovision", IEEE Transactions on Intelligent Transportation Systems, 10(2), pp.272~282 (2009)
- Berriel, R.F, "A particle filter-based lane marker tracking approach using a cubic spline model", Proceedings of the SIBGRAPI Conference on Graphics, Patterns and Images, pp.149~156 (2015)
- Borkar, A., "Robust lane detection and tracking with ransac and Kalman filter", Proceedings of the IEEE International Conference on Image Processing, pp.3261~3264 (2009)
- Kenji Suzuki, "Linear-time connected-component labeling based on sequential local operations", Computer Vision and Image Understanding, 89, pp.1~23 (2003)
- "ROS"[URL]
- "Robotis Turtlebot-3"[URL]
- "Hardkernel Odroid XU-4"[URL]