무인 자동차의 주변 환경 인식을 위한 도시 환경에서의 그래프 기반 물체 분할 방법
Graph-based Segmentation for Scene Understanding of an Autonomous Vehicle in Urban Environments
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
In recent years, the research of 3D mapping technique in urban environments obtained bymobile robots equipped with multiple sensors for recognizing the robot’s surroundings is beingstudied actively. However, the map generated by simple integration of multiple sensors data onlygives spatial information to robots. To get a semantic knowledge to help an autonomous mobile robotfrom the map, the robot has to convert low-level map representations to higher-level ones containingsemantic knowledge of a scene. Given a 3D point cloud of an urban scene, this research proposes amethod to recognize the objects effectively using 3D graph model for autonomous mobile robots. Theproposed method is decomposed into three steps: sequential range data acquisition, normal vectorestimation and incremental graph-based segmentation. This method guarantees the both real-timeperformance and accuracy of recognizing the objects in real urban environments. Also, it can provideplentiful data for classifying the objects. To evaluate a performance of proposed method, computationtime and recognition rate of objects are analyzed. Experimental results show that the proposedmethod has efficiently in understanding the semantic knowledge of an urban environment.
Abstract
In recent years, the research of 3D mapping technique in urban environments obtained bymobile robots equipped with multiple sensors for recognizing the robot’s surroundings is beingstudied actively. However, the map generated by simple integration of multiple sensors data onlygives spatial information to robots. To get a semantic knowledge to help an autonomous mobile robotfrom the map, the robot has to convert low-level map representations to higher-level ones containingsemantic knowledge of a scene. Given a 3D point cloud of an urban scene, this research proposes amethod to recognize the objects effectively using 3D graph model for autonomous mobile robots. Theproposed method is decomposed into three steps: sequential range data acquisition, normal vectorestimation and incremental graph-based segmentation. This method guarantees the both real-timeperformance and accuracy of recognizing the objects in real urban environments. Also, it can provideplentiful data for classifying the objects. To evaluate a performance of proposed method, computationtime and recognition rate of objects are analyzed. Experimental results show that the proposedmethod has efficiently in understanding the semantic knowledge of an urban environment.
참고문헌 (15)
- I. Miller, "Cornell University's 2005DARPA grand challenge entry", Journal of filed Robotics, 23(8), pp.625~652 (2006)
- S. Thrun, "Stanley: The robot that won the DARPA Grand Challenge", Journal of filed Robotics, 23(9), pp.661~692 (2006)
- D. Dolgov, "Path planning for autonomous vehicles in unknown semi-structured environments", The International Journal of Robotics Research (IJRR), 29(5), pp.485~501 (2010)
- I. Baldwin, "Road vehicle localization with 2D push-broom LIDAR and 3D priors", IEEE International Conference on Robotics and Automation (ICRA), pp.2611~2617 (2012)
- J. Strom, "Graph-based segmentation for colored 3d laser point clouds", IEEE, 2010, 2131~2136
- X. Zhu, "Segmentation and classification of range image from an intelligent vehicle in urban environment", IEEE, 2010, 1457~1462
- X. Zhao, "Computing object-based saliency in urban scenes using laser sensing", IEEE International Conference on Robotics and Automation (ICRA), pp.4436~4443 (2012)
- A. Golovinskiy, "Shape-based recognition of 3d point clouds in urban environments", IEEE International Conference on Computer Vision (ICCV), pp.2154~2161 (2009)
- C. C. Wang, "Simultaneous localization, mapping and moving object tracking", The International Journal of Robotics Research (IJRR), 26(9), pp.889~916 (2007)
- P. Newman, "Navigating, recognizing and describing urban spaces with vision and lasers", The International Journal of Robotics Research (IJRR), 28(11), pp.1406~1413 (2009)
- K. Klasing, "Realtime segmentation of range data using continuous nearest neighbors", IEEE International Conference on Robotics and Automation (ICRA), pp.2431~2436 (2009)
- K. Klasing, "Comparison of surface normal estimation methods for range sensing applications", IEEE International Conference on Robotics and Automation (ICRA), pp.3206~3211 (2009)
- P. F. Felzenszwalb, "Efficient graph-based image segmentation", International Journal of Computer Vision (IJCV), 59(2), pp.167~181 (2004)
- J. L. Blanco, "A collection of outdoor robotic datasets with centimeter-accuracy ground truth", Autonomous Robots, 27(4), pp.327~351 (2009)
- B. Douillard, "On the segmentation of 3D LIDAR point clouds", IEEE International Conference on Robotics and Automation (ICRA), pp.2798~2805 (2011)