P.O. Arkhipov – Ph.D.(Eng.), Senior Research Scientist, 

Orel Branch of the FRC «Computer Science and Control» of RAS

E-mail: arpaul@mail.ru

M.V. Tsukanov – Research Engineer, 

Orel Branch of the FRC «Computer Science and Control» of RAS E-mail: tsukanov.m.v@yandex.ru

The development of automatic methods for creating panoramic images from a variety of images is currently an urgent and popular task. Images used in creating panoramas often differ in the color palette and light levels, regardless of the camera model. Such differences may also be caused by weather conditions or the angle of the camera relative to the surface being shot. Therefore, it is necessary to use brightness and color correction technologies to minimize differences between the images being stitched.

To investigate the correction technology of brightness and color. Propose a proprietary information model of brightness and color correction technology that eliminates the disadvantages of the technologies considered and improves the operation of the anomaly detection algorithm.

A new information model of brightness and color correction technology for creating panoramic images using the Lab color space has been developed. The results before and after applying the proposed information model are presented. Based on the analysis of the results obtained, it is concluded that this correction technology can improve the quality of the final panoramic image.

The developed information model was able to reduce the difference in illumination between the cross-linked panorama images. We also managed to normalize the areas with excessive and insufficient brightness, which led to a more accurate selection of the borders of objects in the cross-linked panorama, making them more distinguishable. Such improvements had a positive impact on the operation of the anomaly detection algorithm and its effectiveness.n information model of brightness and color correction technology for creating panoramas is proposed. This article will review the existing methods of brightness and color correction in images and identify the features of each of them. The developed information model is based on normalization of the original array of captured frames through the intermediate color space Lab, which allows you to directly control the brightness of each pixel of the image, changing the current values in accordance with the brightness indicators of the reference image. An algorithm has been developed for stitching such normalized images into a seamless panorama based on the comparison of selected key points and their descriptors.

Arkhipov P.O., Tsukanov M.V. Information model of brightness and color correction technology for creating panoramic images. Highly Available Systems. 2020. V. 16. № 3. P. 46−51. DOI: 10.18127/j20729472-202003-04. (In Russian).

1. Arkhipov P.O., Sidorkin I.I., Tsukanov M.V. Algoritmicheskaya model tekhnologii minimizatsii iskazhenii pri sshivanii snimkov, poluchennykh s BPLA. Sistemy vysokoi dostupnosti. 2018. № 5. S. 30−35. DOI: 10.18127/j20729472-201805-04. (In Russian).
2. Limare Nicolas, Lisani Jose-Luis, Morel Jean-Michel, Petro Ana Belen, Sbert Catalina Simplest Color Balance. Image Processing On Line. 2011. P. 297−315.
3. Nosov A.V., Buzaev D.V., Zotin A.G. Sravnenie algoritmov vyravnivaniya osveshchennosti na izobrazhenii. Reshetnevskie chteniya. Krasnoyarsk. 2012. Ch. 2. S. 623−624. (In Russian).
4. Voeikova A.V., Sakharova M.A. Algoritmy korrektsii tsvetovogo balansa izobrazhenii. Voprosy nauki i obrazovaniya. 2017. № 10(11). S. 43−45. (In Russian).
5. Voeikova A.V., Sakharova M.A. Algoritmy korrektsii osveshchennosti izobrazhenii Single-Scale Retinex i Multi-Scale Retinex. Dostizheniya nauki i obrazovaniya. 2018. № 1(23). S. 24−25. (In Russian).
6. Petro Ana Belen, Sbert Catalina, Morel Jean-Michel Multiscale Retinex. Image Processing On Line. 2014. № 4. P. 71−88.
7. Jobson D., Rahman Z., Woodell G. A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes. IEEE Trans. Image Processing. 1997. V. 6. № 7. P. 965−976.
8. Chen Guanghua, Zhang Xiaolong A Method to Improve Robustness of the Gray World Algorithm. 4th International Conference on Computer, Mechatronics, Control and Electronic Engineering. 2015. P. 250−255.
9. Kanaeva I.A., Bolotova Yu.A. Metody korrektsii tsveta i yarkosti pri sozdanii panoramnykh izobrazhenii. Kompyuternaya optika. 2018. № 42(5). S. 885−897. DOI: 10.18287/2412-6179-2018-42-5-885-897. (In Russian).
10. Bibikov S.A., Fursov V.A. Tsvetovaya korrektsiya na osnove identifikatsii modelei po testovym fragmentam izobrazhenii. Kompyuternaya optika. 2008. № 32(3). S. 302−306. (In Russian).
11. Gonsales R., Vuds R. Tsifrovaya obrabotka izobrazhenii. M.: Tekhnosfera. 2006. 110 s. (In Russian).
12. Tsyganov A.V. Algoritmy mashinnoi grafiki. 2010. URL = http://cph.phys.spbu.ru/documents/First/JPEG.pdf. (In Russian).
13. Useful Color Equations. URL = http://www.brucelindbloom.com.