GEOMETRIC FEATURE SELECTION OF BUILDING SHAPE FOR URBAN CLASSIFICATION
DOI:
https://doi.org/10.17770/etr2017vol2.2613Keywords:
feature selection, LiDAR, remote sensing, urban classificationAbstract
The proposed research is related with building detection in airborne laser scanning data. The result of geospatial surface segmentation provides a vector layer of unclassified shapes. Geometric features of shapes can be applied to classify urban objects and to detect buildings among them. The goal of this research is to select the appropriate geometric features considering their importance for building recognition. The feature selection is completed using random forest algorithm. The obtained list of features and their influence weights can be used to improve building recognition methods and to filter noise objects.Downloads
References
Y. Wang, L. Cheng, Y. Chen, Y. Wu and M. Li, “Building Point Detection from Vehicle-Borne LiDAR Data Based on Voxel Group and Horizontal Hollow Analysis,” Remote Sensing, vol. 8, no. 5, p. 25, May 2016 [Online]. Available: www.mdpi.com/2072-4292/8/5/419/pdf. [Accessed March 3, 2017].
S. Kodors, A. Ratkevics, A. Rausis and J. Buls, “Building Recognition Using LiDAR and Energy Minimization Approach,” Procedia Computer Science. Vol. 3, pp. 109-117, December 2014 [Online]. Available: http://www.sciencedirect.com/science/article/pii/S187705091401583X. [Accessed March 3, 2017].
C. Nesrine, G. Li and C. Mallet, “Airborne LiDAR Features Selection for Urban Classification Using Random Forests,” Laser scanning 2009, IAPRS, Vol. XXXVIII, pp. 207-212, September 2009 [Online]. Available: www.isprs.org/proceedings/XXXVIII/3-W8/papers/p207.pdf. [Accessed March 3, 2017].
F.Y. Manik, Y. Herdiyeni and E.N. Herliyana, “Leaf Morphological Feature Extraction of Digital Image Anthocephalus Cadamba,” TELKOMNIKA, vol.14, no. 2, pp. 630-637, June 2016.
A. Bardossy and F. Schmidt, “GIS approach to scale issues of perimeter-based shape indices for drainage basins,” Hydrological Sciences-Journal-des Sciences Hydrologiques, vol. 47, no. 6, pp. 931-942, December 2002 [Online]. Available: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.2607&rank=1. [Accessed March 3, 2017].
N. Jamil and Z.A. Bakar, Shape-Based Image Retrieval of Songket Motifs, Proceedings of the 19th Annual Conference of the National Advisory Committee on Computing Qualifications, July 7-10, 2006, pp. 213-219.
R. Genuer, J.-M. Poggi and C. Tuleau-Malot, “Variable selection using Random Forests,” Pattern Recognition Letters, vol. 31, no. 14, pp. 2225-2236, October 2010.
S. Cinaroglu, “Comparison of Performance of Decision Tree Algorithms and Random Forest: An Application on OECD Countries Health Expenditures,” International Journal of Computer Applications, vol. 138, no. 1, pp. 37-41, March 2016 [Online]. Available: www.ijcaonline.org/research/volume138/number1/cinaroglu-2016-ijca-908704.pdf. [Accessed March 3, 2017].
