Development of an Algorithm for Improving the Quality of Images of the Input Video Stream for Controlling Nuclear Vehicles
DOI:
https://doi.org/10.22213/2410-9304-2021-2-90-95Keywords:
intelligent transport systems, algorithms and methods of uniformed histogram, digital video image processingAbstract
The main goal of the research work is to develop and analyze a method and algorithm for digital image processing to improve the quality of the resulting output video streaming sequences based on histogram processing. A graphical representation of the quantitative characteristic of the probability distribution of the intensity of pixels in the selected area of the image is a histogram. The most common way to improve an image is to flatten the histogram. The purpose of this method is to equalize the brightness levels of pixels and normalize the frequency, and the histogram must conform to a uniform distribution law. To achieve this goal, an algorithm for uniform alignment of the histogram of the processed image has been developed. An analysis of directions of the development of control systems is presented, which showed that currently there are four levels of intelligent autonomous vehicles: control of the braking system and the vehicle speed control system, control of the acceleration system (taxiing, automatic parking), the autopilot system, and the advanced autopilot system. An analytical description of the method for improving the image quality of a video stream based on the calculation of contrast is presented. An algorithm for calculating the contrast of an image based on the search for the luminosity of pixels and an algorithm for calculating the total average color of individual channels are presented. Modeling of functions of the considered algorithms and the process of improving the quality of images in the MATLAB program using the Image Processing Toolbox has been implemented. The results obtained are a binary image with a uniform pixel brightness histogram. On the basis of the experiment carried out, it can be concluded that the presented algorithms make it possible to increase the contrast of the resulting images, as well as to align the histogram of pixel brightness.References
Choi J., Chun D., Lee H.-J., Kim H. 2020. Uncertainty-based Object Detector for Autonomous Driving Embedded Platforms. Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020, 9073907, pp. 16-20.
Muthalagu R., Bolimera A., Kalaichelvi V. 2020. Lane detection technique based on perspective transformation and histogram analysis for self-driving cars. Computers and Electrical Engineering, 85, 106653.
Kouris A., Venieris S.I., Rizakis M., Bouganis C.-S. 2020. Approximate LSTMs for Time-Constrained Inference: Enabling Fast Reaction in Self-Driving Cars. IEEE Consumer Electronics Magazine. 9(4),9109418, pp. 11-26.
Дегтярев Г. Л., Сагдатуллин А. М. Модель интеллектуальной поддержки управления процессами добычи и транспорта нефти в условиях неопределенности // Математические методы в технике и технологиях - ММТТ. 2020. Т. 1. С. 11-17.
Ni J. et al. 2020. A survey on theories and applications for self-driving cars based on deep learning methods. Applied Sciences (Switzerland). 10 (8), 2749.
Сагдатуллин А. М. Разработка операторского интерфейса удаленного телеуправления для монитора реального времени заполнения смеси // Вестник Казанского государственного технического университета им. А. Н. Туполева. 2020. Т. 76, № 1. С. 99-103.
Isa K., Jantan A. 2005. An Autonomous Vehicle Driving Control System. Int. J. Engng Ed. 21 (5), pp. 855-866.
Сагдатуллин А. М. Применение новой информационной модели при обучении моделированию производственных объектов машиностроения в условиях аддитивного производства // Вестник Казанского государственного технического университета им. А.Н. Туполева. 2020. Т. 76. № 1. С. 94-98.
Zhuravel I.M., 1999. A short course in image processing theory: Electronic resource, Access mode: http://matlab.exponenta.ru/imageprocess/book2/ - Access date: 25/07/2020.
Russ J., 2006. The Image Processing Handbook, Fifth Edition. Taylor&Francis, pp. 832.
Blanchet G., Charbit M. 2006. Digital Signal and Image Processing using MATLAB. ISTE Ltd, pp. 764.
Cai F., Koutsoukos X. 2020. Real-time out-of-distribution detection in learning-enabled cyber-physical systems. Proceedings - 2020 ACM/IEEE 11th International Conference on Cyber-Physical Systems, ICCPS 2020, 9095995, pp. 174-183.
Dorj B., Hossain S., Lee D.-J. 2020. Highly curved lane detection algorithms based on Kalman filter. Applied Sciences (Switzerland). 10 (7), 2372.
Gonzalez R., Woods R. and Eddins S. 2009. Digital Image Processing using Matlab. Gatesmark Publishing. pp: 845.
