Building Recognition Based on Indirect Location of Planar Landmark in FLIR Image Sequences

A novel method is proposed to deal with the problem of building recognition in forward-looking infrared (FLIR) image sequences. Two computational models are deduced in this paper: one is the perspective transformation model, through which an image is transformed perspectively from downward-looking state to forward-looking state; the other is the indirect location model, through which the position of a building is computed in an FLIR image. In addition, in order to illustrate the application scope of our method, the error analysis is presented. The proposed approach is validated by extensive experiments, with images taken in different weather conditions, seasons and at different times. Superior recognition results were obtained on three FLIR image sequences we collected.

[1]  Wei Zhang,et al.  Hierarchical building recognition , 2007, Image Vis. Comput..

[2]  Ramakant Nevatia,et al.  Detection and Modeling of Buildings from Multiple Aerial Images , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Yi Li,et al.  Consistent line clusters for building recognition in CBIR , 2002, Object recognition supported by user interaction for service robots.

[4]  Allen R. Hanson,et al.  Recognition and reconstruction of buildings from multiple aerial images , 2003, Comput. Vis. Image Underst..

[5]  Jingjing Hu,et al.  Building Detection and Recognition for an Automated Tour Guide , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[6]  Wei Zhang,et al.  Localization Based on Building Recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[7]  Taejung Kim,et al.  Development of a graph-based approach for building detection , 1999, Image Vis. Comput..

[8]  Ramakant Nevatia,et al.  Detection of buildings using perceptual grouping and shadows , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Dae-Nyeon Kim,et al.  Supervised training database by using SVD-based method for building recognition , 2008, 2008 International Conference on Control, Automation and Systems.