A METHOD OF SELECTIVE PROCESSING OF VIDEO SEGMENTS TO IMPROVE THE QUALITY OF VIDEO IMAGES IN INTELLIGENT ANALYSIS SYSTEMS
DOI:
https://doi.org/10.18372/2310-5461.66.20332Keywords:
video images, selective methods, segment classification, image processing, intelligent systemsAbstract
The world is currently experiencing the fourth industrial revolution, marked by the emergence and development of production automation technologies. One of the technology groups that is increasingly being utilized in various industrial and service sectors is intelligent image processing technologies. However, tools developed using these technologies have a number of limitations that restrict their effectiveness. One such limitation is the existing dependence of the performance of intelligent image processing systems on the quality of the input images. It has been demonstrated that the advancement of modern technologies for processing and compressing video images imposes new requirements on the quality of the images received by intelligent information processing systems. This study investigates the features of selective video segment processing aimed at enhancing their informativeness and adaptation to intelligent technologies. It has been concluded that traditional processing methods, such as noise filtering or artifact removal, do not address the problem of image quality loss during the initial compression stages. A novel approach has been proposed, based on analyzing the intensity and range of color changes in image segments. To achieve this goal, a combination of statistical methods, spectral analysis, and computer modeling was employed. An innovative method for selectively identifying significant segments has been developed, relying on their informational and semantic load. The study presents a metric for evaluating segment informativeness, which enables effective classification of segments into informative, mixed, and non-informative blocks. This approach improves the quality of critical image areas, reduces noise impact, and ensures processing adaptability to the specificity of input data. The selective processing methodology enhances the efficiency of intelligent systems by preserving the quality of significant regions during compression and adapting to specific processing requirements. The results of this work can be applied in video surveillance systems, autonomous transportation, medical diagnostics, and other fields where image quality is of critical importance.
References
Бараннік В. В., Тарнополов Р. В., Власов А. В. Модель загроз безпеки відеоінформаційного ресурсу систем відеоконференцзв’язку. Наукоємні технології. 2014. № 1 (21). С. 55–60.
Barannik V. V., Komolov Dm., Musienko A. P., Tarnopolov R. V. Methodological basis for determining the energy significance of the structural unit of a video frame based on the estimation of low-frequency components of the matrices of the DCT blocks of the luminance component. Modern problems of radio engineering, telecommunications and computer science (TCSET’2016): materials of the XIV Internat. сonf., (Lviv –Slavske, Ukraine, February, 22–26, 2016). Lviv–Slavske, 2016. P. 572–574.
Babenko Yurii, Barannik Dmitry, Balzhan Smailova, Hahanova Anna, Yroshenko Valerii, shmakov Vitalii, Shaikhanova Aigul, Veselska Olga, Karpiinski Mikolaj The Technology of Structural Classification of Video Frames in Intelligent Info-Communication Systems. “Development of technology analys for the content semantics,” in Engineer of XXI Century - We Design the Future, Bielsko-Biała, Poland: ATH, 2020. Р.122 – 132.
Бараннік В. В., Комолов Д. І. Методологія селективного захисту відеопотоку по базовим кадрам. Інформаційно-управляючі системи на залізничному транспорте. 2014. № 6. С. 69–77.
Бараннік В. В., Королева Н. А. Структурно-комбінаторне представлення даних в АСУ. Харків: ХУПС, 2009. 252 с.
Бараннік В. В., Тарнополов Р. В. Метод ефективного кодування розділених за комбинованою схемою аерофотознімків. Радіоелектроніка та інформатика. 2016. № 2 (73). С. 33–37.
Uri Gadot, Assaf Shocher, Shie Mannor, Gal Chechik, Assaf Hallak RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression URL: https://www.researchgate.net/publication/388318023_RL-RC-DoT_A_Block-level_RL_agent_for_Task-Aware_Video_Compression
Aro Kim, Seung-taek Woo, Minho Park, Dong-hwi Kim, Hanshin Lim, Soon-heung Jung, Sangwoon Kwak & Sang-hyo Park Deep learning-guided video compression for machine vision tasks URL: https://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-024-00649-w
Lisha Gao, Zhoujun Ma, Shuo Han, Tiancheng Zhao, Qingcheng Liu, Zhangjie Fu ROI‑aware video compressive sensing for surveillance URL: https://www.mdpi.com/2078-2489/15/9/555
Xiongkuo Min, Huiyu Duan, Wei Sun, Yucheng Zhu, Guangtao Zhai Perceptual Video Quality Assessment: A Survey URL: https://arxiv.org/abs/2402.03413
Stefan Winkler, Praveen Mohandas The Evolution of Video Quality Measurement: From PSNR to Hybrid Metrics URL: https://www.researchgate.net/publication/ 3042136_The_Evolution_of_Video_Quality_Measurement_From_PSNR_to_Hybrid_Metrics
Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Susan Liang, , Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali Vosoughi, , Chao Huang, Zeliang Zhang, Pinxin Liu, Mingqian Feng, Feng Zheng, , Jianguo Zhang, , Ping Luo, Jiebo Luo, and Chenliang Xu Video Understanding with Large Language Models: A Survey URL: https://arxiv.org/html/2312.17432v5
Бараннік В. В., Власов А. В. Модель загроз безпеки відеоінформаційного ресурсу систем відеоконференцзв'язку. Наукоємні технології. 2014. № 3 (19). С. 299–304.
Бараннік В. В., Комолов Д. І. Метод суміщення кодової конструкції енергетично значимої структурної складової з вимогою методу блокового симетричного шифрування для закриття потокових відеоданих на основі технології внутрікадрової селекції. Наукоємні технології. 2016. № 1. С. 39–47.
Бараннік В. В., Комолов Д. І., Селективний метод шифрування видеопотоку в телекомунікаційних системах на основі приховування базового I-кадру. Наукоємні технології. 2015. № 2. С. 69–77.
Бараннік В. В., Тарнополов Р. В., Власов А. В. Модель загроз безпеки відеоінформаційного ресурсу систем відеоконференцзв’язку. Наукоємні технології. 2014. № 1 (21). С. 55–60.
Barannik V. V., Komolov Dm., Musienko A. P., Tarnopolov R. V. Methodological basis for determining the energy significance of the structural unit of a video frame based on the estimation of low-frequency components of the matrices of the DCT blocks of the luminance component. Modern problems of radio engineering, telecommunications and computer science (TCSET’2016): materials of the XIV Internat. сonf., (Lviv –Slavske, Ukraine, February, 22–26, 2016). Lviv–Slavske, 2016. P. 572–574.
L. Torres, "The Lena image: The most widely used test image in image processing," IEEE Signal Processing Magazine, vol. 20, no. 5, pp. 105-107, 2003.
Bitstream-based JPEG Encryption in Real-time [Text] / S. Auer, A. Bliem, D. Engel, A. Uhl, A. Unterweger. International Journal of Digital Crime and Forensics. 2013. Vol. 5, Iss. 3. P. 1–14. DOI: 10.4018/jdcf.2013070101, 17.03.2023
Cryptographic and Information Security Approaches for Images and Videos [Text] / S. Ramakrishnan, et al. – CRC Press, 2018. – 962 p. DOI: 10.1201/9780429435461.
Cartooning for Enhanced Privacy in Lifelogging and Streaming Videos [Text] / E. T. Hassan, R. Hasan, P. Shaffer, D. Crandall, A. Kapadia. Computer Vision and Pattern Recognition Workshops: proc. IEEE Conf. (CVPRW). 21-26 July 2017. Honolulu, USA, 2017. Р. 1333–1342. DOI: 10.1109/CVPRW.2017.175.
Gonzalez R., Woods R. Digital Image Processing. Pearson Education. 2018. pp. 310–315.
ITU-T Recommendation H.264. International Telecommunication Union. 2017. pp. 45–48.
ITU-T Recommendation H.265. International Telecommunication Union. 2021. pp. 50–55.
AV1 Documentation. Alliance for Open Media. 2020. pp. 15–20.
Steve Göring, Alexander Raake Evaluation of Intra-Coding Based Image Compression; 2018. URL: https://ieeexplore.ieee.org/document/8946162 (Дата зверення: 12.11.2024)
Miroslav Uhrina, Lukas Sevcik et al. Performance Comparison of VVC, AV1, HEVC, and AVC for High Resolutions URL: https://www.mdpi.com/2079- 9292/13/5/953
Dan Grois , Tung Nguyen, Detlev Marpe Coding efficiency comparison of AV1/VP9, H.265/MPEG-HEVC, and H.264/MPEG-AVC encoders URL: https://ieeexplore.ieee.org/document/7906321
Dan Grois, Detlev Marpe, Amit Mulayoff, Benaya Itzhaky, Ofer Hadar Performance comparison of H.265/MPEG-HEVC, VP9, and H.264/MPEG-AVC encoders URL: https://ieeexplore.ieee.org/abstract/document/6737766/authors#authors
Shannon C. A Mathematical Theory of Communication. Bell System Technical Journal. 1948. Vol. 27. pp. 379–423.
Haralick R. M., Shanmugam K., Dinstein I. Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics. 1973. Vol. 3.pp. 610–621.
Szeliski R. Computer Vision: Algorithms and Applications. Springer. 2020. pp. 225–230.
Daugman J. Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation. Journal of the Optical Society of America. 1985. Vol. 2. pp. 1160–1170.
Navidi W. Statistics for Engineers and Scientists. McGraw-Hill Education. 2019. pp. 145–150.
Poynton C. Digital Video and HD: Algorithms and Interfaces. Elsevier. 2012. pp. 130–135.
Bishop C. Pattern Recognition and Machine Learning. Springer. 2006. pp. 256–260.
Gonzalez R., Woods R. Digital Image Processing. Pearson Education. 2018. pp. 400–405.
ITU-T Recommendation JPEG. International Telecommunication Union. 1992. pp. 22–25.
Poynton C. Digital Video and HD: Algorithms and Interfaces. Elsevier. 2012. pp. 140–145.
Shannon C. A Mathematical Theory of Communication. Bell System Technical Journal. 1948. Vol. 27. pp. 423–425.
