15 November 2007 Building detection from LIDAR and images in urban areas
Author Affiliations +
Proceedings Volume 6788, MIPPR 2007: Pattern Recognition and Computer Vision; 67880V (2007) https://doi.org/10.1117/12.748448
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Rapid texture mapping of buildings is a key aspect for reconstruction of 3D city landscapes. An effective approach by the way of coarse-to-fine 3D building model generation by integration of LIDAR and multiple overlap images is proposed. Classification and segmentation can be processed by combined multi-spectral information which is provided by color aerial image and geometric information from multi-return laser scanned data. A connected graph of the segment label image has to be created to derive the neighborhood relation of the planar segments. A line segment matching, based on geometry and chromatic constraint, is applied for automatically getting the corresponding line features in multi target images. Hypotheses for polyhedral surfaces are selected using topological relations and verified using geometry.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Haiyan Guan, Haiyan Guan, Fei Deng, Fei Deng, Jianqing Zhang, Jianqing Zhang, } "Building detection from LIDAR and images in urban areas", Proc. SPIE 6788, MIPPR 2007: Pattern Recognition and Computer Vision, 67880V (15 November 2007); doi: 10.1117/12.748448; https://doi.org/10.1117/12.748448


Highway 3D model from image and lidar data
Proceedings of SPIE (May 21 2014)
Graph-based segmentation of airborne lidar point clouds
Proceedings of SPIE (October 17 2016)
Focusing and reconstruction of building from DSM
Proceedings of SPIE (November 03 2005)
Three-dimensional feature extraction using data fusion method
Proceedings of SPIE (September 02 1993)
Building extraction from multiple images and LIDAR data
Proceedings of SPIE (November 03 2005)

Back to Top