Affiliation:
1. University of Waterloo, Waterloo, Ontario
2. Ryerson University, Toronto, Ontario
Abstract
This paper presents an effective approach to integrating airborne lidar data and colour imagery acquired simultaneously for urban mapping. Texture and height information extracted from lidar point cloud is integrated with spectral channels of aerial imagery into an image segmentation process. Then, the segmented polygons are integrated with the extracted geometric features (height information between first- and lastreturn, eigenvalue-based local variation and filtered height data) and spectral features (line segments) into a supervised classifier. The results for two different urban areas in Toronto, Canada, demonstrated that a satisfactory overall accuracy of 84.96% and Kappa of 0.76 were achieved in Scene I, while a building detection rate of 92.11%, comission error of 2.10% and omission error of 9.25% were obtained in Scene II.
Publisher
Canadian Science Publishing
Subject
Earth-Surface Processes,Geography, Planning and Development
Reference40 articles.
1. Integrating earth observation and GIScience for high resolution spatial and functional modeling of urban land use
2. Automatic detection of residential buildings using LIDAR data and multispectral imagery
3. Axelsson, P. 2000. DEM generation from laser scanner Archives of the Photogrammetry and Remote Sensing, 33(B4/1): 110-117.
4. Bartels, M., and H. Wei. 2006. Maximum likelihood classification of lidar data incorporating multiple coregistered bands. Proceedings of 4th International Workshop on Pattern Recognition in Remote Sensing/18th International Conference on Pattern Recognition, 20 August, Hong Kong, China, pp.17-20.
5. Object based image analysis for remote sensing
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献