Detection of Windows in IR Building Textures Using Masked Correlation

Infrared (IR) images depict thermal radiation of physical objects. Imaging the building hull with an IR camera allows thermal inspections. Mapping these images as textures on 3D building models, 3D georeferencing of each pixel can be carried out. This is helpful for large area inspections. In IR images glass reflects the surrounding and shows false results for the temperature measurements. Consequently, the windows should be detected in IR images and excluded for the inspection. In this paper, an algorithm for window detection in textures extracted from terrestrial IR images is proposed. First, a local dynamic threshold is used to extract candidates for windows in the textures. Assuming a regular grid of windows masked correlation is used to find the position of windows. Finally, gaps in the window grid are replaced by hypothetical windows. Applying the method for a test dataset, 79% completeness and 80% correctness was achieved.

[1]  K. Jacobsen,et al.  Direct Sensor Orientation for Large Scale Mapping—Potential, Problems, Solutions , 2005 .

[2]  Uwe Stilla,et al.  WINDOW DETECTION IN SPARSE POINT CLOUDS USING INDOOR POINTS , 2013, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[3]  P. Waide,et al.  Hurdling Financial Barriers to Low Energy Buildings: Experiences from the USA and Europe on Financial Incentives and Monetizing Building Energy Savings in Private Investment Decisions , 2006 .

[4]  Avideh Zakhor,et al.  Automated texture mapping of 3D city models with oblique aerial imagery , 2004 .

[5]  Uwe Stilla,et al.  Detection of windows and doors from thermal images by grouping geometrical features , 2011, 2011 Joint Urban Remote Sensing Event.

[6]  Roberto Cipolla,et al.  Modelling and Interpretation of Architecture from Several Images , 2004, International Journal of Computer Vision.

[7]  Andrew Zisserman,et al.  New Techniques for Automated Architectural Reconstruction from Photographs , 2002, ECCV.

[8]  Uwe Stilla,et al.  Automatic extraction and database integration of textures of 3D building models acquired from infrared image sequences , 2007 .

[9]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[10]  Susanne Becker,et al.  Generation and application of rules for quality dependent façade reconstruction , 2009 .

[11]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[12]  Uwe Stilla,et al.  Thermal leakage detection on building facades using infrared textures generated by mobile mapping , 2009, 2009 Joint Urban Remote Sensing Event.

[13]  Uwe Stilla,et al.  Texture mapping of 3D building models with oblique direct geo-referenced airborne IRimage sequences , 2009 .

[14]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[15]  Stephan Nebiker,et al.  REAL-TIME GEOREGISTRATION OF VIDEO STREAMS FROM MINI OR MICRO UAS USING DIGITAL 3D CITY MODELS , 2009 .

[16]  Uwe Stilla,et al.  Matching of 3D wire-frame building models with image features from infrared video sequences taken by helicopters , 2010 .

[17]  Rongxing Li,et al.  Mobile Mapping: An Emerging Technology for Spatial Data Acquisition , 1997 .