Specific Shape Building Detection from Aerial Imagery in Infrared Range
DOI:
https://doi.org/10.14529/cmse170306Keywords:
image processing, object detection, contour analysis, mathematical morphologyAbstract
This paper describes an approach to detection of specific shape buildings from the aerial imagery in the infrared range. The proposed algorithm uses contour analysis and is based on a modification of the generalized Hough transform that allows to detect curves defined by a small number of parameters. The main idea is to build a two-dimensional accumulator array for each possible parameter set of the specified curve, and to combine obtained arrays into the resultant accumulator array whose local maxima correspond to the positions of the sought objects. The gradient magnitudes of the original image are used to fill the arrays. The closeness of the found contours to the predefined curve is determined by the morphological analysis of the values calculated by the Canny edge detector. Filtering detected objects relies on the density of boundaries in their internal area with the ratio of the average intensity inside and outside the contour that provides high sensitivity to the specified types of objects and reduces the number of false alarms of the algorithm. The proposed approach was tested on the problem of localization of rectangular buildings and showed the appropriate quality for practical use.References
Gonzalez R.C., Woods R.E. Digital image processing. 2nd edition, 2001. 1072 p.
Sirota A.A., Solomatin A.I. Statistical and neural network algorithms of allocation of objects border in images. Proceedings of Voronezh State University. Series: Systems analysis and information technologies, № 1, 2008. P. 58–64. (in Russian)
Vizilter Y.V., Zheltov S.Y., Bondarenko A.V., Ososkov M.V., Morzhin A.V. Image processing and analysis in computer vision: A course of lectures and practical exercises — Moscow, Publishing Fizmatkniga, 2010. 672 p. (in Russian)
Leukhin A.N. Multidimensional hypercomplex contour analysis and its applications to image and signal processing / A.N. Leukhin — Yoshkar-Ola, Publishing Mari State Technical University, 2004. 36 p. (in Russian)
Furman Y.A. Introduction to contour analysis / Y.A. Furman, A.V. Krevetsky, A.K. Peredreev. — 2nd edition — Moscow, Publishing FIZMATLIT, 2003. 592 p. (in Russian)
Hough P.V.C. Methods, Means for Recognizing Complex Patterns / U.S., Patent 3069654, 1962.
Heikkila M., Pietikainen M. A texture-based method for modeling the background and detecting moving objects // IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, № 4, 2006. P. 657–662. DOI: 10.1109/TPAMI.2006.68.
Tomasi C., Manduchi R. Bilateral Filtering for Gray and Color Images // IEEE Proceedings of the 6-th International Conference on Computer Vision, Bombay, India, 1998. P. 839–846. DOI: 10.1109/ICCV.1998.710815.
K. He, J. Sun, X. Tang Guided Image Filtering // IEEE Transactions on Software Engineering, Vol. 35(6), June 2013. P. 1397–1409. DOI: 10.1109/TPAMI.2012.213.
Duda R., Hart P. Pattern Classification and Scene Analysis. John Wiley and Sons, 1973. P. 271–272. DOI: 10.2307/1573081.
Canny J. A Computational Approach to Edge Detection // IEEE Transactions on pattern analysis and machine intelligence, Vol. PAMI-8, №. 6, 1986. P. 679–698. DOI: 10.1109/TPAMI.1986.4767851.
L. Xu, E. Oja Randomized Hough Transform (RHT): Basic Mechanisms, Algorithms, and Computational Complexities // CVGIP: Image Understanding, Vol. 57, № 2, 1993. P. 131–154. DOI: 10.1006/ciun.1993.10091.
Harris C., Stephens M. A combined corner and edge detector // Proceedings of the 4th Alvey Vision Conference, 1988. P. 147–151. DOI: 10.5244/C.2.23.
Rosten E., Porter R., Drummond T. Faster and Better: A Machine Learning Approach to Corner Detection // IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, № 1, 2010. P. 105–119. DOI: 10.1109/CIT.2010.109.
Noronha S., Nevatia R. Detection and modeling of buildings from multiple aerial images // IEEE Transactions on pattern analysis and machine intelligence, Vol. 23, № 5, 2001. P. 501–518. DOI: 10.1109/34.922708.
Kornilov F.A. Using the Hough transform to detect rectangular contours on images // Sovremennye problemy matematiki i ee prilozhenii. Trudy 45-i Mezhdunarodnoj molodezhnoj shkoly-konferentsii (Yekaterinburg, 2 fevralya – 8 fevralya 2014)[Actual problems of mathematics and its applications. Proceedings of International (45-th National) Youth School-Conference]. Yekaterinburg, Publishing IMM UB RAS, 2014. P. 195–198. (in Russian)
Vegetation indiсes: URL: https://earthobservatory.nasa.gov/Features/MeasuringVegetation/ (accessed: 18.05.2017)
Boreskov A.V. and others. Parallel computing on GPU. Architectural and software model CUDA. Moscow, Publishing Lomonosov Moscow State University. Series: Supercomputer education, 2012. 336 p. (in Russian)
The library of computer vision, image processing and computational mathematics algorithms with opened source code: URL: http://www.opencv.org/ (accessed: 18.05.2017)
