E.A. Semenishchev, I.V. Tolstova, I.A. Toropov

The modern systems video control and monitoring are widely used in various fields of engineering, so the development of a monitoring system areas, and protection systems can not be realized without the systems combining data into a single content. Combining Images into a single composition scene is complex and requires the solution of the problem. Most of the algorithms used in practice are not universal and in some cases requires attention in selecting parameters and reconfiguring the system. The combination of images of different scale (different focal length of the lens), and received from different directions the optical axis, change exposure, varying sensitivity, low percentage of overlapping frames, etc. imposes restrictions on the use of well-known algorithms, and in some cases makes it impossible to use. In this connection, the development of new methods and algorithms for the images together into a single composition is an important task. In this paper we present an algorithm combining images into a single composition. The resulting approach allows the creation of a mosaic image by combining photos and video data of different scales, different lighting and detail. Assessment of the degree of detail is performed using the search algorithm of highly detailed objects using «density». The examples of the images together into mosaics, the analysis of treatment results showed a high efficiency of the proposed algorithm.

 

1. Gary Bradski Learning OpenCV. Computer Vision with the OpenCV Library / G. Bradski, A. Kaehler // O-Reilly Media. 2008. P. 580.
2. Semenishhev E.A., Marchuk V.I., Toropov I.A., Tolstova I.V. Vydelenie lokalnykh uchastkov vysokodetalizirovannykh obektov na obshhem izobrazhenii sceny // Nelinejjnyjj mir. 2012. T.10. № 11. S. 796-800.
3. Semenishhev E.A., Tazetdinova D.I., Pisarev A.V., ZHuk S.V., Tarasov D.A. Razrabotka i issledovanie metodov vydelenija vysokodetalizirovannykh obektov na izobrazhenijakh // Nauchno-tekhnicheskijj vestnik Povolzhja. 2012. № 6. Kazan. S. 374-377.
4. Voronin V.V., Morozova T.V., Makhov D.S., Samojjlin E.A., Minasjan D.G. Poisk lokalnykh osobennostejj na izobrazhenijakh s ispolzovaniem teksturnykh kharakteristik //Nelinejjnyjj mir. 2012. T. 10. № 11. S. 744-850.
5. Fischler M.A., Bolles R.C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography // Comm. of the ACM. 1989. V. 24. R. 381-395.