Method for detection of vehicles in digital aerial
and space remote sensed images
V.V. Myasnikov
Full text of article: Russian language.
Abstract:
In this paper we propose a method for automatic detection of the location of automobiles in the aerial images and images of advanced space-based Earth remote sensing means (ERS). The proposed method uses various groups of features (geometric, textural, structural) for a description of objects depicted in the images and their preliminary analysis, as well as solving list as an algorithm of testing of hypothesis of the presence of an object. The final positioning of objects in the image is performed with the original consecutive procedure. The proposed method on real urban area photographs provides a high quality score of vehicles correct detection with a slight (a few) number of falsely detected objects.
Key words:
images, Earth remote sensing, vehicle, detection.
References:
- Forsyth, D.A. Computer Vision: A Modern Approach / D.A. Forsyth, J. Ponce. – New Jersey: Prentice Hall, 2002. – 693 p.
- Shapiro, L.G. Computer Vision / L.G.Shapiro, G.C.Stockman. – New Jersey: Prentice Hall, 2001. – 608 p.
- Methods of computer image processing. Part II: Methods and algorithm;, Ed. V.A. Soifer. – Moskow. Fizmatlid, – 2009. – 784 p. – (in Russian)
- Mallat, S. A Wavelet Tour of Signal Processing / S. Mallat. – New York: Academic Press, 1999. – 620 p.
- Vapnik, V.N. Statistical Learning Theory / V.N. Vapnik, // – New York: Wiley-Interscience, 1998. – 736 p.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20