A modified neural network model based on Yolo V5 was developed and the quality metrics of object classification on video images built on the basis of existing known basic neural network architectures were compared. The application of convolutional neural networks for processing images from video surveillance cameras is considered in order to develop an optimized algorithm for detecting and classifying objects on video images. The existing models and architectures of neural networks for image analysis were analyzed and compared. The possibilities of optimizing the process of image analysis using neural networks are considered.
[1] Farmaha I., Salo Y. Medical object detection using computer vision tools and methods only // САПР у проектуванні машин. Питання впровадження та навчання : матеріали ХХХ Міжнародної польсько- української науково-технічної конференції (Львів, Україна, 1–2 грудня 2022 р.). – 2022. – C. 18.
[2] Y.-L. Tian, L. Brown, A. Hampapur, M. Lu, A. Senior and C.-F. Shu, "IBM smart surveillance system (S3): Event based video surveillance system with an open and extensible framework", Mach. Vis. Appl., vol. 19, no. 5, pp. 315-327, Oct. 2008. https://doi.org/10.1007/s00138-008-0153-z
[3] J. Fernández, L. Calavia, C. Baladrón, J. Aguiar, B. Carro, A. Sánchez-Esguevillas, et al., "An intelligent surveillance platform for large metropolitan areas with dense sensor deployment", Sensors, vol. 13, no. 6, pp. 7414-7442, Jun. 2013. https://doi.org/10.3390/s130607414
[4] R. Baran, T. Rusc and P. Fornalski, "A smart camera for the surveillance of vehicles in intelligent transportation systems", Multimedia Tools Appl., vol. 75, no. 17, pp. 10471-10493, Sep. 2016. https://doi.org/10.1007/s11042-015-3151-y
[5] D. Eigenraam and L. J. M. Rothkrantz, "A smart surveillance system of distributed smart multi cameras modelled as agents", Proc. Smart Cities Symp. Prague (SCSP), pp. 1-6, May 2016. https://doi.org/10.1109/SCSP.2016.7501018
[6] Bosch Intelligent Video Analysis, May 2023, [Електронний ресурс] // Режим доступу: https://www.boschsecurity.com/xc/en/.
[7] Bhubaneswar’s Smart Safety City Surveillance Project Powered By Honeywell Technologies, May 2023, [Електронний ресурс] // Режим доступу: https://buildings.honeywell.com/content/dam/hbtbt/en/documents/ downloads/Bhubaneswar-CS_0420_V2.pdf.
[8] Hitachi: Data Integration Helps Smart Cities Fight Crime Iot-hitachi-smart Communities-solution, May 2023, [online] Available: https://www.intel.com/content/dam/www/public/emea/xe/en/documents/.
[9] Iomniscient, May 2023, [Електронний ресурс] // Режим доступу: https://iomni.ai/oursolutions/.
[10] E. B. Varghese and S. M. Thampi, "A cognitive IoT smart surveillance framework for crowd behavior analysis", Proc. Int. Conf. Commun. Syst. Netw. (COMSNETS), pp. 360-362, Jan. 2021. https://doi.org/10.1109/COMSNETS51098.2021.9352910
[11] V. Sharma, M. Gupta, A. Kumar and D. Mishra, "Video processing using deep learning techniques: A systematic literature review", IEEE Access, vol. 9, pp. 139489-139507, 2021. https://doi.org/10.1109/ACCESS.2021.3118541
[12] New trends in production engineering : колективна монографія. – Warszawa, Poland: Sciendo, 2019. Farmaha I. Wound image segmentation using clustering based algorithms / I. Farmaha, M. Banaś, V. Savchyn, B. Lukashchuk, T. Farmaha. – c.217–225.
[13]. Jaworski Nazariy, Farmaha Ihor, Farmaha Taras, Savchyn Vasyl, Marikutsa Uliana. Implementation features of wounds visual comparison subsystem // Перспективні технології і методи проектування МЕМС : матеріали XIV Міжнародної науково-технічної конференції, 18–22 квітня, 2018 р., Поляна, Україна. – 2018. – P. 114–117. (Google Scholar, SciVerse SCOPUS, Web of Science). https://doi.org/10.1109/MEMSTECH.2018.8365714
[14] C. Dhiman and D. K. Vishwakarma, "A review of state-of-the-art techniques for abnormal human activity recognition", Eng. Appl. Artif. Intell., vol. 77, pp. 21-45, Jan. 2019. https://doi.org/10.1016/j.engappai.2018.08.014
[15] Yang, R., Yu, J., Yin, J., Liu, K., & Xu, S. (2022). A dense r-CNN multi-target instance segmentation model and its application in medical image processing. IET image processing(9), 16.
[16] Szajna, A., Kostrzewski, M., Ciebiera, K., Stryjski, R., & Sciubba, E. (2021). Application of the deep cnn-based method in industrial system for wire marking identification. Energies(12). https://doi.org/10.3390/en14123659
[17] Took, C. C., & Mandic, D. (2022). Weight sharing for lms algorithms: convolutional neural networks inspired multichannel adaptive filtering. Digital Signal Processing.
[18] Weiller, C., Reisert, M., Glauche, V., Musso, M., & Rijntjes, M. (2022). The dual-loop model for combining external and internal worlds in our brain. NeuroImage, 263, 119583. https://doi.org/10.1016/j.neuroimage.2022.119583
[19] Tremeau A., Borel N. A. region growing and merging algorithm to color segmentation [J]. Pattern Recognition, 1997, 30(7):1191-1203.R. https://doi.org/10.1016/S0031-3203(96)00147-1
[20] Levinshtein A., Stere A., Kutulakos K. N., etal. TurboPixels: Fast superpixels using geometric ows [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297.D. https://doi.org/10.1109/TPAMI.2009.96
[21] Bazgir O, Zhang R, Dhruba S R, et al. Representation of features as image with neighborhood dependencies for compatibility with convolutional neural networks [J]. Nature communications, 2020, 11(1): 4391. https://doi.org/10.1038/s41467-020-18197-y
[22] Chen L C, Papandreou G, Kokkinos I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848. https://doi.org/10.1109/TPAMI.2017.2699184