Abstract
The algorithm for detecting cars in color images obtained by aerophotography has been presented. The approach is as follows: the majority of cars are painted in one color and have similar sizes. This makes possible to separate cars in the background as areas with color characteristics that differ from the background and have a certain size and form. The areas are generated by integrating hierarchically the smaller areas according to similarity of color and space characteristics. The algorithm is tested on a set of images containing 2226 cars in all.
Similar content being viewed by others
References
V. G. Bondur and S. A. Starchenkov, “Methods and software for processing and classifying aerospace images,” Izv. Vyssh. Uchebn. Zaved. Geodez. Aerofotos”emka, No. 3, 118–143 (2001).
M. A. Sotelo, J. Nuevo, L. M. Bergasa, et al., “Road vehicle recognition in monocular images,” Proc. IEEE ISIE 4, 1471–1476 (2005).
T. Zhao and R. Nevatia, “Car detection in low resolution aerial image,” Proc. IEEE ICCV 1, 710–717 (2001).
P. Negri, X. Clady, S. M. Hanif, et al., “A cascade of boosted generative and discriminative classifiers for vehicle detection,” EURASIP J. Adv. Signal Processing, Art. ID 782432 (2008).
L.-W. Tsai, J.-W. Hsieh, and K.-C. Fan, “Vehicle detection using normalized color and edge map,” IEEE Trans. Image Processing 16 (3), 850–864 (2007).
R. Mejía-Inigo, M. E. Barilla-Pérez, and H. A. Montes-Venegas, Color-based Texture Image Segmentation for Vehicle Detection. www.intechopen.com/download/pdf/15388
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper uses the materials of the report submitted at the 11th International Conference “Pattern Recognition and Image Analysis: New Information Technologies,” Samara, Russia, September 23–28, 2013.
Ivan Alekseevich Matveev. Born in 1973. Graduated from Moscow Institute of Physics and Technology in 1997, received PhD in 1999 and SciD in 2014. Since 2004, he is the head of the intelligence system sector, Computing Center of Russian Academy of Science. Fields of interests: image processing and recognishion, biometrical identification. He is the author of 80 published works.
Aleksandr Borisovich Murynin. Born in 1960. Graduated from Moscow Institute of Physics and Technology in 1984, received PhD in 1992. Since 1993 he has been a senior researcher of the Computing Center of Russian Academy of Science and a senior scientist at the Aerospace Research Institute. Fields of interest: mathematical simulation, machine vision, aerophotos processing, remote probing. He is the author of 100 published works.
Aleksei Nikolaevich Trekin. Born in 1989. Graduated from Moscow Institute of Physics and Technology in 2012, currently a postgraduate student. Fields of interest: aerophoto processing, remote probing. He is the author of ten published works.
Rights and permissions
About this article
Cite this article
Matveev, I.A., Murynin, A.B. & Trekin, A.N. Method for detecting cars in aerospace photos. Pattern Recognit. Image Anal. 25, 669–673 (2015). https://doi.org/10.1134/S1054661815040161
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661815040161