Научная электронная библиотека ULRICH'S Periodicals Directory

Сибирский государственный университет
науки и технологий имени академика М.Ф. Решетнева

Сибирский аэрокосмический журнал
ISSN 2712-8970 (Print) ISSN 2782-5760 (on-line)

Сведения об образовательной организации

UDK 004.932.2
VIDEO BASED DYNAMIC TEXTURE RECOGNITION UNDER SPECIFIC ILLUMINATION CONDITIONS
A. V. Pyataeva*, Y. D. Kulikova
Siberian Federal University, School of Space and Information Technology 26, Kirensky Str., Krasnoyarsk, 660074, Russian Federation
Nowadays dynamic textures recognition is particularly important in different computer vision community tasks in a variety of fields such as urban scenes and forest scenes. The goal of the dynamic textures recognition can be different. Real scenes may include the objects with dynamic behavior because of possible varying illumination, blurring, or weather conditions. Under bad weather conditions the imaging system is degraded to produce low visibility images. Such effects may significantly degrade the performance of outdoor vision systems which relies on image/video. For illumination effects compensation and visual quality enhancement images it is necessary to average pixel intensity increase, expand the range of brightness, image contrast increase and eliminate influence of the additive noise. For the images obtained in adverse lighting conditions imitation in this work Gamma correction, additive Gaussian noise and impulse noise was applied successively. The proposed algorithm employs Multi Scale Retinex with Color Restoration, Laplacian, Gaussian and median filters. For experimental researches of the databases of Bilkent University, Video Smoke Detection, Wildfilmsindia, V-MOTE were used. In addition, the representativeness of the test set is increased by a video sequence, which the authors themselves recorded at night. Experiments on video based smoke detection system based on spatio-temporal local binary pattern were computed. True recognition for smoke in adverse lighting conditions is degraded to 65 %. False rare rejection and false alert errors significantly increase to 34.2 % and 27.2 % respectively. After adverse lighting compensation algorithm work true recognition of smoke regions increases to 94.41 %. This accuracy provides the influence of adverse lighting on a quality of smoke detection is studied. Experimental results show that the proposed method is feasible and effective for video-based dynamic texture analysis in varying illumination conditions.
Keywords: varying illumination, noise, dynamic textures, video sequence, smoke.
References

1. Favorskaya M. N. Pyataeva A. V. [Verification of smoke detection in video sequences based on spatiotemporal local binary patterns in outdoor spaces with different weather conditions]. Informatsionnoupravlyayushchie sistemy. 2016, Vol. 1(80), P. 16–25 (In Russ.).

2. Madhav V. Chitturi, Juan C. Medina, Rahim (Ray) F. Benekohal. Effect of Shadows and Time of Day on Performance of Video Detection Systems at Signalized Intersections. Transportation Research Part C: Emerging Technologies. 2010, Vol. 18, Iss. 2, P. 176–186.

3. Goncharov A. V., Karakishchenko A. N. [Influence of Illumination on a Quality of Frontal Face Recognition]. Izvestiya YUFU. Tekhnicheskie nauki. 2008, No. 4, P. 88– 924 (In Russ.).

4. Adnin Y., Moses Y., Ullman S. Face recognition: The problem of compensating for changes in illumination direction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, Vol. 19, No. 7, P. 712–732.

5. Ramamoorthi R. Analytic PCA Construction for Theoretical Analysis of Lighting Variability in Images of a Lambertian Object. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002, Vol. 24, No. 10, P. 10–21.

6. Riklin-Raviv T., Shashua A. The Quotient image: Class based recognition and synthesis under varying illumination. In Proceedings of the 1999 Conference on Computer Vision and Pattern Recognition. 1999, P. 566–571.

7. Georghiades A. S., Belhumeur P. N. Illumination cone models for Faces recognition under variable lighting and Pose. IEEE Trans. Pattern Anal. Mach. Intelligence. 1998, No. 23(6), P. 643–660.

8. Shashua A., Riklin-Raviv T. The quotient image: Class-based re-rendering and recognition with varying illuminations. Transactions on Pattern Analysis and Machine Intelligence. 2001, Vol. 23, No. 2, P. 129–139.

9. Faraji M. R., Qi X. Face recognition under varying illuminations using logarithmic fractal dimension-based complete eight local directional patterns. Neurocomputing. 2016, Vol. 99, P. 16–30.

10. Zhou S. K., Zhao W., Tang X., Gong S. Analysis and Modeling of Faces and Gestures. Proc. of the Third International Workshop, AMFG Rio de Janeiro. 2007, Vol. 2688, P. 10–18.

11. Goncalves W. N., Machado B. B., Bruno O. M. A complex network approach for dynamic texture recognition. Neurocomputing. 2015, Vol. 153, P. 211–220.

12. Hu, W., Xie N., Li L., Zeng X., Maybank S. J. A survey on visual 316 content-based video indexing and retrieval. IEEE Transactions on Systems, Man, and Cybernetics. 2011, Part C 41 (6), P. 797–819.

13. Xu Y., Quan Y., Ling H., Ji H. Dynamic Texture Classification Using Dynamic Fractal Analysis. 2011 International Conference on Computer Vision. 2011, P. 1219–1226.

14. Lin H., Shi Z. Multi-scale retinex improvement for nighttime image enhancement. Optik - International Journal for Light and Electron Optics. 2014, Vol. 125, Iss. 24, P. 7143–7148.

15. Khryashchev D. A. [On a method of the analysis of digital image using histograms]. Vestnik Astrahanskogo Gosudarstvennogo Tekhnicheskogo Universiteta, seriya Upravlenie, vychislitel’naya tekhnika i informatika. 2010, No. 1, P. 109–113 (In Russ.).

16. Pyataeva A. V., Favorskaya M. N. Sistema obnaruzhenija oblastej zadymlenija na videoposledovatel’nosti s primeneniem lokal’nyh binarnyh shablonov [Videobased smoke detection system based on spatio-temporal local binary patterns (DKL 3.15)]. Patent RF, No. 2015615904, 2015.

17. Video smoke detection. Available at: http://staff. ustc.edu.cn/~yfn/vsd.html (accessed: 01.04.2017).

18. Database of Wildfilmsindia. Available at: www wildfilmsindia com (accessed: 01.04.2017).

19. V-MOTE Database. Available at: http://www.2.imse-cnm.csic.es/vmote/english_version/index.php (accessed: 01.04.2017).

20. Database of Bilkent University. Available at: http://signal.ee.bilkent.edu.tr/VisiFire/Demo/ (accessed 08.03.2016).

21. Youtube/firenight. Available at: https://www. youtube.com/watch?v=tmBG_ v23zbk&t=12s (accessed: 01.04.2017).


Pyataeva Anna Vladimirovna – senior teacher, School of Space and Information Technology, Siberian Federal

University. Е-mail: anna4u@list.ru.

Kulikova Yuliya Dmitrievna – student, School of Space and Information Technology, Siberian Federal University

Siberian Federal University. Е-mail: anna4u@list.ru.