AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
STUDIES This research is motivated by the need for obtaining semantic knowledge of a large urban outdoor environment after a robot explores and generates a map consisting of a low-level sensing dataset

Scene understanding in a large dynamic environment through a laser-based sensing

ICRA, no. 1 (2010): 127-133

Cited: 47|Views113
EI WOS SCOPUS

Abstract

It became a well known technology that a map of complex environment containing low-level geometric primitives (such as laser points) can be generated using a robot with laser scanners. This research is motivated by the need of obtaining semantic knowledge of a large urban outdoor environment after the robot explores and generates a low-le...More

Code:

Data:

0
Introduction
  • As the rapid development of sensing and mapping technologies, especially the significant advances in SLAM (Simultaneous Localization And Mapping) using laser scanners (i.e. LiDAR sensors), it became a well known technology that a geometric representation of an environment can be generated by a robot with multi-modal sensors.
  • Many of the results represent environments directly using the integration of laser points, or low-level geometric primitives such as feature points, planar surfaces and so on.
  • Such a map has limited capacity in representation, as it tells only spatial existence.
  • In order for a robot to have semantic knowledge of the environment, such as objects, types and their spatial relationships, an automatic technique of converting those low-level map representation into highlevel one is important
Highlights
  • As the rapid development of sensing and mapping technologies, especially the significant advances in SLAM (Simultaneous Localization And Mapping) using laser scanners (i.e. LiDAR sensors), it became a well known technology that a geometric representation of an environment can be generated by a robot with multi-modal sensors
  • Streams of range images can be found in Fig.2, Fig.9 and Fig.10, a 3D view of the integrated laser points measured by the laser scanners L4 and L5 is demonstrated in Fig
  • STUDIES This research is motivated by the need for obtaining semantic knowledge of a large urban outdoor environment after a robot explores and generates a map consisting of a low-level sensing dataset
  • An algorithm is developed in the representation of range image, while data are processed in both 2D and 3D coordinates
  • A framework of simultaneous segmentation and classification is developed in this research, where classification of each segment is conducted based on its geometric properties, while homogeneity in each segment is evaluated conditioned on object class
  • We presented experimental results using the data of a large dynamic urban outdoor environment, and evaluated the performance of the algorithm
Results
  • The authors present results of an experiment that were taken placed in the campus of Peking Univ.
  • Streams of range images can be found in Fig.2, Fig.9 and Fig.10, a 3D view of the integrated laser points measured by the laser scanners L4 and L5 is demonstrated in Fig.8.
  • The authors manually labeled the data on range images as shown in Fig.9 and Fig.10 using the method of extracting training samples.
  • The labeled data of laser scanner L4 are used in training classifiers, while those of L5 are used in examining the automated processing results
Conclusion
  • This research is motivated by the need for obtaining semantic knowledge of a large urban outdoor environment after a robot explores and generates a map consisting of a low-level sensing dataset.
  • An algorithm is developed in the representation of range image, while data are processed in both 2D and 3D coordinates.
  • The authors presented experimental results using the data of a large dynamic urban outdoor environment, and evaluated the performance of the algorithm.
  • Future studies will be addressed in extending object types in classification, and improving robustness in the processing of small scale objects
Tables
  • Table1: DATA CUES OF A SCAN LINE SEGMENT
  • Table2: DATA CUES EXTRACTED FROM A CLOUD OF LASER POINTS
  • Table3: THE NUMBER OF SAMPLE DATA IN TRAINING CLASSIFIERS
Download tables as Excel
Funding
  • This work is partially supported by the NSFC Grants (No.90920304 and No.60975061)
Reference
  • Althaus, P., Christensen, H., “Behavior coordination in structured environments” Advanced Robotics, 17(7):657-674, 2003.
    Google ScholarLocate open access versionFindings
  • Borenstein, E., Ullman, S., “Combined top-down/bottom-up segmentation” IEEE Trans. Pattern Analysis and Machine Intelligence, 30(12):2109-2125, 2008.
    Google ScholarLocate open access versionFindings
  • Chang, C.C., Lin, C.J., “LIBSVM: a library for support vector machines”, 2001. Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm
    Findings
  • Douillard, B., Fox, D., Ramos, F.T., “Laser and vision based outdoor object mapping” Proc. Robotics: Science and Systems, 2008.
    Google ScholarLocate open access versionFindings
  • Douillard, B., “Vision and laser based classification in urban environments” PhD thesis, Univ. of Sydney, 2009.
    Google ScholarFindings
  • Fruh, C., Zakhor, A., “3D model generation for cities using aerial photographs and ground level laser scans” Proc. Computer Vision and Pattern Recognition (CVPR), 2001.
    Google ScholarLocate open access versionFindings
  • Georgiev, A., Allen, P. “Localization methods for a mobile robot in urban environments” IEEE Trans. Robotics, 20(5):851-864, 2004.
    Google ScholarLocate open access versionFindings
  • Golovinskiy, A. Kim, V.G., Funkhouser, T., “Shape-based Recognition of 3D Point Clouds in Urban Environments” IEEE Int. Conf. on Computer Vision, 2009.
    Google ScholarLocate open access versionFindings
  • Hahnel, D., Burgard, W., Thrun, S., “Learning compact 3d models of indoor and outdoor environments with a mobile robot” Robotics and Autonomous Systems, 44:15-27, 2003.
    Google ScholarLocate open access versionFindings
  • Han, F., Tu, Z., Zhu, S.C, “Range image segmentation by an effective jump-diffusion method” IEEE Trans. Pattern Analysis and Machine Intelligence, 26(9):1138-1153, 2004.
    Google ScholarLocate open access versionFindings
  • Hoover, A., Jean-Baptiste, G., Jiang, X., Flynn, P.J., Bunke, H., Goldgof, D., Bowyer, K., “A comparison of range image segmentation algorithms” IEEE Trans. Pattern Analysis and Machine Intelligence, 18(7):673-689, 1996.
    Google ScholarLocate open access versionFindings
  • Jiang, X., Bunke, H., “Fast segmentation of range images into planar regions by scan line grouping” Machine Vision and Application, 7:115122, 1994.
    Google ScholarLocate open access versionFindings
  • Katsoulas, D., Bastidas, C.C., Kosmopoulos, D., “Superquadic segmentation in range image via fusion of region and boundary information” IEEE Trans. Pattern Analysis and Machine Intelligence, 20(5):781-795, 2008.
    Google ScholarLocate open access versionFindings
  • Malisiewicz, T., Efros, A.A., “Recognition by Association via Learning Per-exemplar Distances” Proc. Computer Vision and Pattern Recognition (CVPR), 2008.
    Google ScholarLocate open access versionFindings
  • Martinez-Mozos, O., Stachniss, C., Burgard, W. “Supervised Learning of Places from Range Data using AdaBoost” IEEE Int. Conf. on Robotics and Automation (ICRA), 1742-1747, 2005.
    Google ScholarLocate open access versionFindings
  • Mendes, A., Nunes, U., “Situation-based multi-target detection and tracking with laserscanner in outdoor semi-structured environment” Proc. Conf. on Intelligent Robots and Systems, 2004.
    Google ScholarLocate open access versionFindings
  • Nuchter, A., Surmann, H., Hertzberg, J., “Planning robot motion for 3d digitization of indoor environment” Proc. 11th Int. Conf. on Advanced Robotics (ICAR), 2003.
    Google ScholarLocate open access versionFindings
  • Nuchter, A., Lingemann, K., Hertzberg, J., Surmann, H., “6D SLAM - 3D mapping outdoor environments” J. Field Robotics, 24(8-9):699722, 2009.
    Google ScholarLocate open access versionFindings
  • Porway, J., Wange, K., Zhu, S.C., “A hierarchical and contextual model for aerial image understanding” Proc. Computer Vision and Pattern Recognition (CVPR), 2008.
    Google ScholarLocate open access versionFindings
  • Posner, I., Cummins, M., Newman, P., “A generative framework for fast urban labeling using spatial and temporal context” Autonomous Robots, 26(2-3):153-170. April 2009.
    Google ScholarLocate open access versionFindings
  • Posner, I., Cummins, M., Newman, P., “Online generation of scene descriptions in urban environments” Robotics and Autonomous Systems, 56(11):901 - 914. 2008.
    Google ScholarLocate open access versionFindings
  • Rosin, P.L., West, G.A.W., “Nonparametric segmentation of curves into various representations” IEEE Trans. Pattern Analysis and Machine Intelligence, 17:1140-1153, 1995. Software available at http://users.cs.cf.ac.uk/Paul.Rosin
    Locate open access versionFindings
  • Triebel, R., Kersting, K., Burgard, W., “Robust 3D scan point classification using associative Markov Networks” IEEE Int. Conf. on Robotics and Automation (ICRA), 2006.
    Google ScholarLocate open access versionFindings
  • Thrun, S., Burgard, W., Fox, D., “A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping” IEEE Int. Conf. on Robotics and Automation (ICRA), 2000.
    Google ScholarLocate open access versionFindings
  • Tu, Z., Chen, X., Yuille, A., Zhu, S.C., “Image parsing: unifying segmentation, detection and recognition” Int. J. Computer Vision, 63(2):113-140, 2005.
    Google ScholarLocate open access versionFindings
  • Weingarten, J., Siegwart, R., “EKF-based 3D SLAM for structured environment” IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 2089-2094, 2005.
    Google ScholarLocate open access versionFindings
  • Zhao, H., Chiba, M., Shibasaki, R., Shao, X., Cui, J., Zha, H., “SLAM in a Dyanmic Large Outdoor Environment using a Laser Scanner” IEEE Int. Conf. on Robotics and Automation (ICRA), 2008.
    Google ScholarLocate open access versionFindings
  • Zhao, H., Xiong, L., Jiao, Z., Cui, J., Zha, H., “Sensor alignment towards an omni-directional measurement using an intelligent vehicle” IEEE Intelligent Vehicle Symposium, 292-298, 2009.
    Google ScholarLocate open access versionFindings
0
Your rating :

No Ratings

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn