Investigation of the effect of gamma image correction in the problem of object recognition at a pedestrian crossing

Purpose of research. Improving the reliability of object recognition in an image by investigating the effect of gamma correction of the input image on the quality coefficient of object recognition on it.

Methods. Pre-processing of images obtained using the complex of video recording of traffic violations installed in the city of Kursk includes gamma correction, conversion from RGB to grayscale, blurring with a Gauss filter, highlighting the boundaries of objects based on the Canny algorithm, classification of objects using the YOLO algorithm.

Results. The main advantages of adaptive control traffic control systems are considered. The structural scheme of the pedestrian crossing control system and the stages of input image preprocessing, including gamma correction, and their effect on the reliability of object detection are described. The Recall indicator was calculated to quantify the detection efficiency at different gamma correction values for each of the classes under consideration: pedestrians (Recall = 0.46), cars (Recall =0.824), traffic lights (Recall =0.60).

Conclusion. The results of a series of experimental studies prove the positive effect of gamma correction on the recognition efficiency of only certain classes of objects, such as traffic lights, requiring a minimum value of γ ≈ 1.5 (gamma 100) to start recognition. The detection of other classes considered, such as pedestrians and cars, remains stable at any gamma values from the range [0; 200]. The largest number of detections was recorded at ranges of 20 and 80 for pedestrians and at ranges of 60, 100 and 120 for cars.

1. Beklaryan A. L., Beklaryan L. A., Akopov A. S. Simulation model of an intelligent transport system of a "smart city" with adaptive traffic light control based on fuzzy clustering. Biznes-informatika = Business Informatics. 2023; 17(3): 70-86. (In Russ.).

2. Myasnikov V. V., Agafonov A. A., Yumaganov A. S. Deterministic predictive model of traffic light signal control in intelligent transport and geoinformation systems. Komp'yuternaya optika = Computer Optics. 2021; 45(6): 917-925. (In Russ.).

3. Zhankaziev S. V., Vorobyov A. I., Bachmanov M. D. Optimization of adaptive traffic light control in the framework of directive traffic flow management. Vestnik Moskovskogo avtomobil'no-dorozhnogo gosudarstvennogo tekhnicheskogo universiteta (MADI) = Bulletin of the Moscow Automobile and Road State Technical University (MADI). 2016; (4): 138-143. (In Russ.).

4. Andronov S. A. Comparison of the effectiveness of adaptive traffic light control algorithms in the AnyLogic environment. Programmnye produkty i sistem = Software products and systems. 2019; (1): 150-158. (In Russ.).

5. Bobyr M.V., Khrapova N. I., Lamonov M. A. Smart Traffic Light Control System Based on Fuzzy Logic. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2021; 25(4): 162-176 (In Russ.). https://doi.org/10.21869/2223-1560-2021-25-4-162-176.

6. Bobyr M. V., Khrapova N. I. A Two-Level Information and Analytical Control System for Intelligent Traffic Lights. Automatic Documentation and Mathematical Linguistics. 2024; 58(S5): S269-S278.

7. Bobyr M. V., Emelyanov S. G., Khrapova N. I. Ontological model for managing waiting time for traffic light signals by road users in a pedestrian crossing zone. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2024; 28(4): 124-137 (In Russ.). https://doi.org/10.21869/2223-1560-2024-28-4-124-137.

8. Emaletdinova L. Y., Nazarov M. A. Neural network algorithm for recognizing an object in an image based on a reference contour. Matematicheskie metody v tekhnike i tekhnologiyakh - MMTT = Mathematical methods in engineering and technology - MMTT. 2020; 4: 137-141. (In Russ.).

9. Vazaev A.V., Noskov V. P., Rubtsov I. V., Tsarichenko S. G. Recognition of objects and types of the bearing surface according to the integrated vision system. Izvestiya YuFU. Tekhnicheskie nauki = Izvestiya SFU. Technical sciences. 2016; (2): 127-139. (In Russ.).

10. Medvedev M. V., Kirpichnikov A. P. An unmanned aerial vehicle control system based on wavelet methods for detecting and recognizing objects in images. Vestnik Kazanskogo tekhnologicheskogo universiteta = Bulletin of Kazan Technological University. 2014; 17(19): 359-362. (In Russ.).

11. Solovyov F. S., Tarasov I. E., Petrov A. B. Pattern recognition and detection of contours of an object in an image. Innovatsii v nauke = Innovations in science. 2019; (4): 4-9. (In Russ.).

12. Choudhary P., Dey S. Choudhary P. FAIERDet: Fuzzy-based Adaptive Image Enhancement for Real-time Traffic Sign Detection and Recognition Under Varying Light Conditions. Expert Systems with Applications. 2023; 295: 128795.

13. Bobyr M. V., Kulabukhov S. A. Modeling the process of controlling the temperature regime in the cutting zone based on fuzzy logic. Problemy mashinostroeniya i nadezhnosti mashin = Problems of mechanical engineering and machine reliability. 2017; (3): 76-82. (In Russ.).

14. Bobyr M. V., Milostnaya N. A. Analysis of the use of soft arithmetic operations in the structure of fuzzy logic.logical inference. Vestnik komp'yuternykh i informatsionnykh tekhnologii = Bulletin of Computer and Information Technologies. 2015; (7): 7-15. (In Russ.).

15. Dai X., Lan J., Chen Z., Wang B., Wen X. Multi-exposure image enhancement and YOLO integration for nighttime pedestrian detection. Signal Processing: Image Communication, 2025; 140: 117421.

16. Trofimenko Ya. M., Vinogradova L. N., Ershov E. V. Algorithms of image preprocessing in the face identification system in the video stream. Vestnik Cherepovetskogo gosudarstvennogo universiteta = Bulletin of Cherepovets State University. 2019; (4): 21-29. (In Russ.).

17. Dancing G. M., Maikov K. A. A study of algorithms for preprocessing the image of the hand, applicable to the recognition of gesture symbols. Cloud of Science. 2020; 7(1): 61-74. (In Russ.).

18. Shagalova P. A., Yerofeyeva A.D., Orlova M. M., et al. Investigation of image preprocessing algorithms to improve the efficiency of recognition of medical images. Trudy NGTU im. R.E. Alekseeva = Proceedings of the Alekseev Russian State Technical University. 2020; (1): 25-32. (In Russ.).

19. Lagunov N. A., Mezentseva O. S. The influence of image preprocessing on the quality of neural network learning for their recognition. Vestnik Severo-Kavkazskogo federal'nogo universiteta = Bulletin of the North Caucasus Federal University. 2015; (1): 51-58. (In Russ.).

20. Deng G. A generalized gamma correction algorithm based on the SLIP model. Eurasip Journal on Advances in Signal Processing. 2016; 2016(1): 69.

21. Tomakova R.A., Dzyubin I.A., Brezhnev A.V. A Method and Algorithm for Training a Convolutional Neural Network Designed for an Intelligent Melanoma Recognition System. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computing Engineering, Information Science. Medical Instruments Engineering. 2022;12(1):65-83. (In Russ.). https://doi.org/10.21869/2223-1536-2022-12-1-65-83

22. Ryabinov A. V., Uzdiaev M. Yu., Vatamaniuk I.A. Applying Multitask Deep Learning to Emotion Recognition in Speech. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2021; 25(1): 82-109 (In Russ.). https://doi.org/10.21869/2223-1560-2021-25-1-82-109.

23. Oparin E.S., Dzus M.A., Davydov N.N., Khorkov K.S. Automatic Particle Recognition Based on Digital lmage Processing. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computing Engineering, Information Science. Medical Instruments Engineering. 2024;14(1):50-66. (In Russ.). https://doi.org/10.21869/2223-1536-2024-14-1-50-66.

24. Abrosimov V. K., Matveeva Yu. N. Formation of synthetic data for machine learning to recognize underwater objects. Robototekhnika i tekhnicheskaya kibernetika = Robotics and technical cybernetics. 2023; 11(4): 256-266. (In Russ.).

25. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. P. 779-788.