Algorithm for correcting the image depth map based on the points brightness and their distance from the observation point

Objective. Modeling the human head is a significant problem that arises in a wide variety of fields of science and technology. Existing active technologies for reconstruction and modeling of the object under study require expensive equipment and trained personnel. Methods. An alternative is to use passive methods that perform image processing using special mathematical algorithms. One of these methods is the stereo vision, which is based on the use of paired images taken simultaneously with several cameras positioned and calibrated in a certain way. However, a common drawback of stereo vision methods is the possibility of obtaining erroneous depth maps due to poorquality source images or incorrect camera and lighting settings. Results. Procedures were developed that use additional parameters of image points, which can be used to correct depth maps to avoid the appearance of defects. To achieve this objective, the existing mathematical software for processing photo and video materials is analyzed; methods for suppressing noise in the image, obtaining an image contour, as well as a method for obtaining a 3D object matrix based on changing the direction of illumination are proposed; the algorithm is tested on a test example. Conclusion. The developed technique should improve the quality of the depth map of the processed image and thus make the modeling procedures more efficient.

1. Batseva D.A. Passivnyye tekhnologii modelirovaniya golovy cheloveka / D.A. Batseva, YU.S. Belov // Nauchnoye obozreniye. Tekhnicheskiye nauki. 2017. № 2. S. 11-14. [Batseva D.A. Passive technologies for modeling the human head / D.A. Batseva, Yu.S. Belov // Scientific Review. Technical science. 2017. No. 2. S. 11-14. (In Russ)]

2. Batseva D.A. Aktivnyye tekhnologii modelirovaniya golovy cheloveka / D.A. Batseva, YU.S. Belov // Mezhdunarodnyy studencheskiy nauchnyy vestnik. 2017. № 3.Rezhim dostupa: https://www.eduherald.ru/ru/article/view?id=17296. - (Data obrashcheniya: 21.11.2017). [Batseva D.A. Active technologies for modeling the human head. Batseva, Yu.S. Belov // International student scientific bulletin. 2017. No. 3. Access mode: https://www.eduherald.ru/ru/article/view?id=17296. (Date of access: 21.11.2017) (In Russ)]

3. Forsayt D. A. Komp'yuternoye zreniye: sovremennyy podkhod / D. A. Forsayt, ZH. Pons. - M.: Vil'yams, 2004. 928 s. [Foresight D.A. Computer vision: a modern approach / DA Forsyth, J. Pons. M .: Williams, 2004.928 p. (In Russ)]

4. Ul'yanov S.V. Razrabotka sistemy stereozreniya dlya mobil'nogo robota / S.V. Ul'yanov, A.G. Reshetnikov, K.V. Koshelev // Programmnyye produkty i sistemy. 2017. T. 3, № 30. S. 435-438. [Ulyanov S.V. Development of a stereo vision system for a mobile robot / S.V. Ulyanov, A.G. Reshetnikov, K.V. Koshelev // Software products and systems. 2017. T. 3, No. 30. pp. 435438. (In Russ)]

5. Scharstein D. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms / D. Scharstein, R. Szeliski // Int. Journal of Computer Vision. 2002. Vol. 47, No 1-3. pp. 7-42.

6. Vakhitov A.T. Obzor algoritmov stereozreniya / A.T. Vakhitov, L.C. Gurevich, D.V. Pavlenko // Stokhasticheskaya optimizatsiya v informatike. 2008. № 4. S. 151-169. [Vakhitov A.T. Review of stereovision algorithms / A.T. Vakhitov, L. S. Gurevich, D.V. Pavlenko // Stochastic optimization in computer science. 2008. No. 4. pp. 151-169. (In Russ)]

7. Kotyuzhanskiy L.A. Vychisleniye karty glubiny stereoizobrazheniya na graficheskom protsessore v real'nom vremeni / L.A. Kotyuzhanskiy // Fundamental'nyye issledovaniya. 2012. № 6-2. S. 444-449. [Kotyuzhansky L.A. Calculation of the depth map of a stereo image on a graphics processor in real time / L.A. Kotyuzhansky // Fundamental Research. 2012. No. 6-2. pp. 444-449. (In Russ)]

8. Voronin V.V. Vosstanovleniye karty glubiny na osnove kombinirovannoy obrabotki mnogokanal'nogo izobrazheniya / V.V. Voronin // Sovremennyye problemy nauki i obrazovaniya. 2014. № 6. Rezhim dostupa: http://science-education.ru/ru/article/view?id=16360. (Data obrashcheniya: 11.01.2019). [Voronin V.V. Reconstruction of the depth map based on combined processing of a multichannel image / V.V. Voronin // Modern problems of science and education. 2014. No. 6. Access mode: http://science-education.ru/ru/article/view?id=16360. (Date of access: 11.01.2019) (In Russ)]

9. Kovalev O.F. Povysheniye kachestva kart glubiny po dal'nosti / O.F. Kovalev // Informatsionnyye sistemy i tekhnologii: materialy mezhdunarodnogo nauchnogo kongressa. Minsk, 2016. - Minsk: Izd-vo Belorusskogo gosudarstvennogo universiteta. -2016. - S. 942-946. [Kovalev O.F. Improving the quality of depth maps by range / O.F. Kovalev // Information systems and technologies: materials of the international scientific congress. Minsk, 2016. Minsk: Publishing house of the Belarusian State University. 2016 . pp. 942-946. (In Russ)]

10. Gordon G.G. Face Recognition Based on DepthMaps and Surface Curvature / G.G. Gordon // Proceedings of the SPIE, Geometric Methods in Computer Vision, 1991. Vol. 1570. pp. 108-110.

11. Furman YA.A. Vvedeniye v konturnyy analiz i yego prilozheniya k obrabotke izobrazheniy i signalov / YA.A. Furman - M.: FIZMATLIT. 2002. 592 s. [Furman Ya.A. Introduction to contour analysis and its applications to image and signal processing / Ya.A. Furman M .: FIZMATLIT. 2002 . 592 p. (In Russ)]

12. Novakovskiy S.V. Novyye sistemy televideniya. Tsifrovyye metody obrabotki videosignalov / S.V. Novakovskiy - M.: Radio i svyaz'. 1992. 88s. [Novakovsky S.V. New television systems. Digital methods of video signal processing / S.V. Novakovsky -M .: Radio and communication. 1992. 88p. (In Russ)]

13. Starovoitov V.V. Metric basis for digital image processing / V.V. Starovoitov // Automation of image processing and recognition: collection of articles. scientific. tr. / Minsk. 1995 . pp. 7-14.

14. Kazanskiy N.L. Sravneniye ob"yekta i etalona po otkloneniyu konturov / N.L. Kazanskiy, R.V. Khmelev // Komp'yuternaya optika. 2000. Byp. 20. S. 128-133. [Kazansky N.L. Comparison of the object and the standard by the deviation of the contours / N.L. Kazansky, R.V. Khmelev // Computer Optics. 2000. Iss. 20. pp. 128-133. (In Russ)]

15. Ablameyko S.V. Selection of contours of objects of a halftone image based on local binarization / S.V. Ablameiko, D.M. Lagunovsky // Pattern recognition and image analysis: abstracts. report conf. Minsk. 1993 . p. 193-195.

16. Ablameyko S.V. Vector representation of the boundaries of grayscale objects and their processing in high-performance systems: instructional method. materials / S.V. Ablameiko, M.A. Samoshkin, A. Ya. Kuleshov - Minsk: ITK NSA. 1993 .123 p.

17. Zhang Yu-Jin. Advances in Image and Video Segmentation / Yu-Jin Zhang. Hershey: IRM Press. 2006 . 473 p.

18. Senthilkumaran N.A. Study on Edge Detection Methods for Image Segmentation / N.A. Senthilkumaran, R. Rajesh // Proceedings of the International Conference on Mathematics and Computer Science (ICMCS-2009). 2009. Vol. 1. pp. 255-259.

19. Buy T. T. CH. Analiz metodov vydeleniya krayev na tsifrovykh izobrazheniyakh / T. T. CH. Buy, V.G. Spitsyn // Doklady TUSUR. 2010. № 2 (22), ch. 2. S. 221-223. [Bui T. T. Ch. Analysis of edge detection methods on digital images / T. T. Ch. Bui, V. G. Spitsyn // Reports of TUSUR. 2010. No. 2 (22), part 2. pp. 221-223 (In Russ)]

20. Chellappa R. Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition / R. Chellappa et [others] // Foundations and Trends in Signal Processing. 2010. No. 1-2. pp. 128-151.

21. Reyad Y.A. Image Thresholding Using Split and Merge Techniques with Log-Normal Distribution / Y.A. Reyad, A. El-Zaart, H. Mathkour // Canadian Journal on Image Processing and Computer Vision. 2010. Vol.1, No.3. pp. 36-45.

22. Calderero F. Region Merging Techniques Using Information Theory Statistical Measures / F. Calderero, F. Marques // IEEE Transactions on Image Processing. 2010. Vol. 19, No. 6. pp. 1567-1586.