Pole-Like Objects (PLOs) in the road environment located nearby the road boundary are important roadway assets. They play vital role in the road safety inspection and road planning. In present study a novel automated method for the detection of PLOs from Mobile Laser Scanner (MLS) point cloud data has been proposed. Proposed method includes four basic steps. Initially ground points are roughly filtered out from the input dataset to reduce the processing of un-necessary points; formerly local window search is performed at non-ground points to find out the concentrated point distribution. Principal Component Analysis (PCA) has been implemented at such concentrated distributed points for the identification of PLOs. In last step of proposed method knowledge based information are used for suppressing the false positives and rectifying the output. Proposed method has been tested on a MLS point cloud data of complex road environment and corresponding PLOs are detected having completeness and correctness of 91.48 % and 86.00 % respectively.

LiDAR, Pole Like Objects, PCA

[1] K.S. Yen, B. Ravani, T.A. Lasky, “LiDAR for Data Efficiency”, WSDOT Research Report, WA-RD 778.1, 2011.
[2] S.I. El-Halawany, D.D. Lichti, “Detection of road poles from mobile terrestrial laser scanner point cloud”, International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), pp.1–6, 2011.
[3] C. Brenner, “Extraction of features from mobile laser scanning data for future driver assistance systems”, Advances in GIScience, Lecture Notes in Geoinformation and Cartography, Springer, pp.25-42, 2009.
[4] H. Yokoyama, H. Date, S. Kanai, H. Takeda, “Detection and Classification of Pole-like Objects from Mobile Laser Scanning Data of Urban Environments”, International Journal of CAD/CAM, Vol. 13, No. 2, pp.31-40, 2013.
[5] S. Pu, M. Rutzinger, G. Vosselman, S.O. Elberink, “Recognizing basic structures from mobile laser scanning data for road inventory studies”, ISPRS Journal of Photogrammetry and Remote Sensing 6(66), S28–S39, 2011.
[6] D. Li, S.O. Elberink, “Optimizing Detection of Road Furniture (Pole-Like Objects) in
Mobile Laser Scanner Data”, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial
Information Sciences II-5/W2: pp. 163–168, 2013.
[7] Y.Z. Chen, H.J. Zhao, R. Shibasaki, “A mobile system combining laser scanners and cameras for urban spatial objects extraction”, Proceedings of the Sixth International Conference on Machine Learning and Cybernetics 2, pp.1729-1733, 2007.
[8] A. Kukko, A. Jaakkola, M. Lehtomki, H. Kaartinen, Y. Chen, “Mobile mapping system and computing methods for modeling of road environment” Proceeding of the Urban Remote Sensing Joint Event , pp.331–338, 2009.
[9] M. Lehtomäki, A. Jaakkola, J. Hyyppa, A. Kukko, H. Kaartinen, “Detection of vertical pole-like objects in a road environment using vehicle-based laser scanning data”, Remote Sensing 2 (3), pp.641–664, 2010.
[10] K. Ishikawa, F. Tonomura, Y. Amano, T. Hashizume, “Recognition of Road Objects from 3D Mobile Mapping Data”, Proc. International Journal of CAD/CAM, vol. 13, No.2, pp.41-48, 2013.
[11] A. Golovinskiy, V. Kim, A. Funkhouser, “Shape-based recognition of 3D point clouds in urban environments”, Proceedings of the international conference on computer vision (ICCV), pp.2154–2161, 2009.
[12] S. Pu, M. Rutzinger, G. Vosselman, S.O. Elberink, “Recognizing basic structures from mobile laser scanning data for road inventory studies”, ISPRS Journal of Photogrammetry and Remote Sensing 6(66), S28–S39, 2011.