New method for video stream brightness stabilization: algorithms and performance evaluation

Vladyslav Bilozerskyi, Kostyantyn Dergachov, Leonid Krasnov, Anatolii Zymovin, Anatoliy Popov

Abstract


Subject of study. In this paper, for the first time, an original method for estimating the change in the brightness of video data under the influence of changes in the lighting conditions of the scene and external noise is proposed. Algorithms for stabilizing the brightness of video data are also proposed. An objective assessment of the quality of video data pre-processed is given. The purpose of the research is to create a methodology for analyzing the variability of video data parameters under the influence of negative factors and to develop effective algorithms for stabilizing the parameters of the received video stream. The reliability of the method is tested using real video recordings pictured through various conditions. Objectives: To determine the most universal, resistant to external influences, and informative indicator necessary for an objective assessment of the quality of video data under various shooting conditions and scene lighting features; develop and programmatically implement algorithms for stabilizing video parameters based on modern programming tools. Research methods. Statistical analysis and pre-processing of video stream parameters as a random spatio-temporal process, algorithms for processing video data by digital filtering, and adaptive stabilization of video stream parameters. Research results. It has been proposed and experimentally proven that the optimal indicator of video stream quality is the average frame brightness (AFB). An algorithm for spatiotemporal processing of video data is proposed that generates a sequence of AFB values from the original video stream. The paper also proposes digital algorithms for filtering and stabilizing the brightness of a video stream and investigates the effectiveness of their application. Conclusions. The scientific novelty of the results obtained lies in a new method for analyzing and evaluating the parameters of video surveillance data and algorithms for filtering and stabilizing the brightness of the video stream. The performance of the proposed algorithms has been tested on real data. The algorithms are implemented in the Python software environment using the functions of the OpenCV library.

Keywords


video stream; average frame brightness; video brightness trend; trend digital filtering; brightness stabilization algorithms

Full Text:

PDF

References


Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 1998, vol. 86, no. 11, pp. 2278–2324. DOI: 10.1109/5.726791.

Information about the ImageNet library [Electronic resource]. Available at: https://en.wiki-pedia.org/wiki/ImageNet (аccessed 17.04.2023).

Krizhevsky, A., Sutskever, I., & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems, 2012, vol. 25, pp. 1097–1105.

Krizhevsky, A., Sutskever, I., & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, vol. 60, no. 6, pp. 84–90. DOI:10.1145/3065386.

Software Caffe [Electronic resource]. Available at: http://caffe.berkeleyvision.org (аccessed 17.04.2023).

TensorFlow library [Electronic resource]. Available at: https://www.tensorflow.org (аccessed 17.04.2023).

Scientific computing platform Torch [Electronic resource]. Available at: http://torch.ch (аccessed 17.04.2023).

Keras library [Electronic resource]. Available at: https://keras.io (аccessed 17.04.2023).

OpenCV DNN library [Electronic resource]. Available at: https://github.com/opencv/opencv/tree/master/samples/dnn (аccessed 17.04.2023).

Skadins, A., Ivanovs, M., Rava, R., & Nesenbergs, K. Edge pre-processing of traffic surveillance video for bandwidth and privacy optimization in smart cities. 2020 17th Biennial Baltic Electronics Conference (BEC), Tallinn, Estonia, 2020, pp. 1-6. DOI: 10.1109/BEC49624.2020.9276799.

Zaharia, P., Bigioi, P., & Corcoran, P. M. Hybrid video-frame pre-processing architecture for HD-video. 2011 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 2011, pp. 89-90. DOI: 10.1109/ICCE.2011.5722927.

Guilluy, W., Oudre, L., & Beghdadi A. Video stabilization: overview, challenges and perspectives. Signal Processing: Image Communication, 2021, vol. 90, article no. 116015. DOI: 10.1016/j.image.2020.116015.

Egiazarian, K., Ponomarenko, M., Lukin, V., & Ieremeiev, O. Statistical Evaluation of Visual Quality Metrics for Image Denoising. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018, pp. 6752-6756. DOI: 10.1109/ICASSP.2018.8462294.

Lukin, V. V., Zriakhov, M. S., Ponomarenko, N. N., Krivenko, S. S., & Zhenjiang, M. Lossy compression of images without visible distortions and its application. IEEE 10th international conference on signal processing proceedings, Beijing, China, 2010, pp. 698-701. DOI: 10.1109/ICOSP.2010.5655751.

Dergachov, K., Krasnov, L., Bilozerskyi, V., & Zymovin, A. Data pre-processing to increase the quality of optical text recognition systems. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2021, no. 4, pp. 183-198. DOI: 10.32620/reks.2021.4.15.

Bilozerskyi, V., Dergachov, K., & Кrasnov, L. Analiz i poperednya obrobka videodanykh dlya pidvyshchennya yakosti roboty system tekhnichnoho zoru [Analysis and pre-processing of video data to improve the quality of computer vision systems]. Problemy keruvannya ta informatyky – Problems of control and informatics, 2023, vol. 68, no. 2, pp. 50–66. DOI: 10.34229/1028-0979-2023-2-4. (In Ukrainian).

Perek, P., Mielczarek, A., & Makowski, D. High-Performance Image Acquisition and Processing for Stereoscopic Diagnostic Systems with the Application of Graphical Processing Units. Sensors, 2022, vol. 22(2), article no. 471. DOI: 10.3390/s22020471.

Wang, T-s., Kim, G. T., Kim, M., & Jang, J. Contrast Enhancement-Based Preprocessing Process to Improve Deep Learning Object Task Performance and Results. Applied Sciences, 2023, vol. 13(19), article no. 10760. DOI: 10.3390/app131910760.

Cho, S-Y., Kim, D.-Y., Oh, S-Y., & Sohn, C-B. Reducing System Load of Effective Video Using a Network Model. Applied Sciences, 2021, vol. 11(20), article no. 9665. DOI: 10.3390/app11209665.

Guo, H., Tian, B., Yang, Z., Chen, B., Zhou, Q., Liu, S., Nahrstedt, K., & Danilov, C. DeepStream: Bandwidth Efficient Multi-Camera Video Streaming for Deep Learning Analytics. arXiv − CS − Networking and Internet Architecture, 2023. DOI: 10.48550/arXiv.2306.15129.




DOI: https://doi.org/10.32620/reks.2023.3.10

Refbacks

  • There are currently no refbacks.