Система розпізнавання об’єктів на основі моделі YOLO

dc.citation.epage126
dc.citation.issue1
dc.citation.journalTitleУкраїнський журнал інформаційних технологій
dc.citation.spage120
dc.citation.volume6
dc.contributor.affiliationНаціональний університет “Львівська політехніка”
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorНазаркевич, М. А.
dc.contributor.authorОлексів, Н. Т.
dc.contributor.authorNazarkevych, M. A.
dc.contributor.authorOleksiv, N. T.
dc.coverage.placenameЛьвів
dc.coverage.placenameLviv
dc.date.accessioned2025-05-21T08:02:09Z
dc.date.created2024-02-28
dc.date.issued2024-02-28
dc.description.abstractПобудовано систему розпізнавання об’єктів, знятих у режимі реального часу на відеокамеру в зашумленому та змінному щодо навколишніх умов середовищі. Досліджено методику наповнення бази даних для мобільних військових об’єктів. Для розпізнавання об’єктів використано нейромережу YOLO v8, яка дає змогу відстежувати рухомі та ідентифікувати об’єкти, які потрапляють на відео із відеокамери. Ця нейромережа дає змогу відстежувати об’єкти зі зміною масштабу, під час руху з перешкодами. З’ясовано, що розпізнавання об’єктів здійснюється на основі контурного аналізу, зіставлення із шаблоном та виявлення і встановлення відповідності ознакам. Використано методи штучного інтелекту на основі YOLO v8 для розпізнавання військової техніки. Здійснено навчання для різних моделей YOLO із використанням оптимізаторів Adam W, Adam, SGD та роздільної здатності 512×512, 640×640, 1024×1024 px зображень. Поліпшення розпізнавання об’єктів досягається завдяки аналізу контурів, порівнянню шаблонів і введених особливих точок. Різні роздільні здатності зображень та оптимізатори по-різному впливали на продуктивність моделі, а стандартні метрики оцінки не надають найточнішого вигляду. Найефективнішим оптимізатором є метод градієнтного спуску (SGD), який показав найкращі показники точності для розпізнавання бойових машин. Градієнт зазвичай розглядають як суму градієнтів, зумовлених кожним елементом навчання, і використовують для коригування параметрів моделі. Внаслідок розроблення системи сформовано показники із точністю розпізнавання (accuracy) 92 %, F1-оцінка (F1 score) – 89 %, середній показник точності (mAP) – 90 %. Запропоновано спосіб наповнення набору даних та створення класифікатора. Побудовано модель розпізнавання бойових машин. Наведено графіки, результати розпізнавання рухомих об’єктів у нейромережі Yolo8 x.
dc.description.abstractA system for recognizing objects that are captured in real time on a video camera in a noisy environment that changes to the surrounding conditions has been built. The method of filling the database for mobile military objects was studied. For object recognition, the YOLO v8 neural network is used, which allows you to track moving and identify objects that fall into the video from the video camera. This neural network makes it possible to track objects with a change in scale, during movement with obstacles. It has been analyzed that the recognition of objects is carried out on the basis of contour analysis, comparison with a template and detection and matching of features. Artificial intelligence methods based on YOLO v8 were used to recognize military equipment. Trained for different YOLO models using Adam W, Adam, SGD optimizers and 512x512, 640x640, 1024x1024 px image resolution. Improved object recognition is achieved by analyzing contours, comparing patterns, and comparing entered special points. Different image resolutions and optimizers have shown different effects on model performance, and standard evaluation metrics do not provide the most accurate view. The most effective optimizer is gradient descent (SGD), which has shown the best accuracy for combat vehicle recognition. The gradient is usually considered as the sum of the gradients caused by each training element and is used to adjust the model parameters. As a result of the development of the system, indicators with recognition accuracy (accuracy) of 92%, F1-estimate (F1 score) – 89%, average indicator of accuracy (mAP) – 90% were formed. A method of filling the data set and creating a classifier is proposed. A model of combat vehicle recognition was built. Graphs, results of recognition of moving objects in the Yolo8 x neural network are presented.
dc.format.extent120-126
dc.format.pages7
dc.identifier.citationНазаркевич М. А. Система розпізнавання об’єктів на основі моделі YOLO / М. А. Назаркевич, Н. Т. Олексів // Український журнал інформаційних технологій. — Львів : Видавництво Львівської політехніки, 2024. — Том 6. — № 1. — С. 120–126.
dc.identifier.citationenNazarkevych M. A. Object recognition system based on the YOLO model and database formation / M. A. Nazarkevych, N. T. Oleksiv // Ukrainian Journal of Information Tecnology. — Lviv : Lviv Politechnic Publishing House, 2024. — Vol 6. — No 1. — P. 120–126.
dc.identifier.doidoi.org/10.23939/ujit2024.01.120
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/64850
dc.language.isouk
dc.publisherВидавництво Львівської політехніки
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofУкраїнський журнал інформаційних технологій, 1 (6), 2024
dc.relation.ispartofUkrainian Journal of Information Tecnology, 1 (6), 2024
dc.relation.references1. Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems.
dc.relation.references2. Zhang, Y., Zhang, H., Huang, Q., Han, Y., & Zhao, M. (2024). DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects. Expert Systems with Applications, 241, 122669. https://doi.org/10.1016/j.eswa.2023.122669
dc.relation.references3. Patel, M., Liu, X. C., Yang, K., Tassone, C., Escott, B., & Thometz, J. (2024). 3D Back Contour Metrics in Predicting Idiopathic Scoliosis Progression: Retrospective Cohort Analysis, Case Series Report and Proof of Concept. Children, 11(2), 159. https://doi.org/10.3390/children11020159
dc.relation.references4. Wang, Q., Lu, C., Gao, L., & He, G. (2024). Transformer-Based Multiple-Object Tracking via Anchor-Based-Query and Template Matching. Sensors (Basel, Switzerland), 24(1). https://doi.org/10.3390/s24010229
dc.relation.references5. Lu, H., Nie, J. (2024). Coarse registration of point cloud base on deep local extremum detection and attentive description. Multimedia Systems, 30(1), 23. https://doi.org/10.1007/s00530-023-01203-w
dc.relation.references6. Moksyakov A, Wu Y, Gadsden SA, Yawney J, AlShabi M. Object Detection and Tracking with YOLO and the Sliding Innovation Filter. Sensors. 2024; 24(7):2107. https://doi.org/10.3390/s24072107
dc.relation.references7. Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023). Object detection using YOLO: Challenges, architectural successors, datasets and applications. multimedia Tools and Applications, 82(6), 9243-9275. https://doi.org/10.1007/s11042-022-13644-y
dc.relation.references8. Du, J. (2018, April). Understanding of object detection based on CNN family and YOLO. In Journal of Physics: Conference Series (Vol. 1004, p. 012029). IOP Publishing. https://doi.org/10.1088/1742-6596/1004/1/012029
dc.relation.references9. Shafiee, M. J., Chywl, B., Li, F., & Wong, A. (2017). Fast YOLO: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943. https://doi.org/10.15353/vsnl.v3i1.171
dc.relation.references10. Zhang, Z., Lu, X., Cao, G., Yang, Y., Jiao, L., & Liu, F. (2021). ViT-YOLO: Transformer-based YOLO for object detection. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 2799-2808). https://doi.org/10.1109/ICCVW54120.2021.00314
dc.relation.references11. S. Li, Y. Li, Y. Li, M. Li and X. Xu, "YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection," in IEEE Access, vol. 9, pp. 141861-141875, 2021. https://doi.org/10.1109/ACCESS.2021.3120870
dc.relation.references12. Malik, J., Belongie, S., Leung, T., Shi, J. (2001). Contour and texture analysis for image segmentation. International journal of computer vision, 43, 7-27. https://doi.org/10.1023/A:1011174803800
dc.relation.references13. Hashemi, N. S., Aghdam, R. B., Ghiasi, A. S. B., Fatemi, P. (2016). Template matching advances and applications in image analysis. arXiv preprint arXiv:1610.07231.
dc.relation.references14. Cox, G. S. (1995). Template matching and measures of match in image proce-ssing. University of Cape Town, South Africa.
dc.relation.references15. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60, 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
dc.relation.references16. Mukherjee, D., Jonathan Wu, Q. M., Wang, G. (2015). A comparative experimental study of image feature detectors and descriptors. Machine Vision and Applications, 26, 443-466. https://doi.org/10.1007/s00138-015-0679-9
dc.relation.references17. Liu, Q., Ye, H., Wang, S., & Xu, Z. (2024). YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera. Electronics, 13(1), 236. https://doi.org/10.3390/electronics13010236
dc.relation.references18. Koga, S., Hamamoto, K., Lu, H., & Nakatoh, Y. (2024). Optimizing Food Sample Handling and Placement Pattern Recognition with YOLO: Advanced Techniques in Robotic Object Detection. Cognitive Robotics. https://doi.org/10.1016/j.cogr.2024.01.001
dc.relation.references19. Wang, Y., Wang, B., Huo, L., & Fan, Y. (2024). GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images. Journal of Marine Science and Engineering, 12(2), 213. https://doi.org/10.3390/jmse12020213
dc.relation.references20. Wang, Z., Hua, Z., Wen, Y., Zhang, S., Xu, X., & Song, H. (2024). E-YOLO: Recognition of estrus cow based on improved YOLOv8 n model. Expert Systems with Applications, 238, 122212. https://doi.org/10.1016/j.eswa.2023.122212
dc.relation.references21. Giudici, P., Centurelli, M., & Turchetta, S. (2024). Artificial Intelligence risk measurement. Expert Systems with Applications, 235, 121220. https://doi.org/10.1016/j.eswa.2023.121220
dc.relation.references22. Shinde, S., Khoje, S., Raj, A., Wadhwa, L., & Shaikha, A. S. (2024). Artificial intelligence approach for terror attacks prediction through machine learning. Multidisciplinary Science Journal, 6(1), 2024011-2024011. https://doi.org/10.31893/multiscience.2024011
dc.relation.references23. Dogan, A., Okatan, A., & Cetinkaya, A. (2021). Vehicle Classification and Tracking Using Convolutional Neural Network Based on Darknet Yolo with Coco Dataset. AI and Big Data in Engineering Applications, 179.
dc.relation.references24. Nazarkevych, M., Oliarnyk, R., Troyan, O., & Nazarkevych, H. (2016, September). Data protection based on encryption using Ateb-functions. In 2016 XIth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT) (pp. 30-32). IEEE. https://doi.org/10.1109/STC-CSIT.2016.7589861
dc.relation.references25. Medykovskyy, M., Lipinski, P., Troyan, O., & Nazarkevych, M. (2015, September). Methods of protection document formed from latent element located by fractals. In 2015 Xth International Scientific and Technical Conference" Computer Sciences and Information Technologies"(CSIT) (pp. 70-72). IEEE. https://doi.org/10.1109/STC-CSIT.2015.7325434
dc.relation.references26. Sheketa, V., Zorin, V., Chupakhina, S., Kyrsta, N., Pasyeka, M., & Pasieka, N. (2020, November). Empirical method of evaluating the numerical values of metrics in the process of medical software quality determination. In 2020 International Conference on Decision Aid Sciences and Application (DASA) (pp. 22-26). IEEE. https://doi.org/10.1109/DASA51403.2020.9317218
dc.relation.referencesen1. Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems.
dc.relation.referencesen2. Zhang, Y., Zhang, H., Huang, Q., Han, Y., & Zhao, M. (2024). DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects. Expert Systems with Applications, 241, 122669. https://doi.org/10.1016/j.eswa.2023.122669
dc.relation.referencesen3. Patel, M., Liu, X. C., Yang, K., Tassone, C., Escott, B., & Thometz, J. (2024). 3D Back Contour Metrics in Predicting Idiopathic Scoliosis Progression: Retrospective Cohort Analysis, Case Series Report and Proof of Concept. Children, 11(2), 159. https://doi.org/10.3390/children11020159
dc.relation.referencesen4. Wang, Q., Lu, C., Gao, L., & He, G. (2024). Transformer-Based Multiple-Object Tracking via Anchor-Based-Query and Template Matching. Sensors (Basel, Switzerland), 24(1). https://doi.org/10.3390/s24010229
dc.relation.referencesen5. Lu, H., Nie, J. (2024). Coarse registration of point cloud base on deep local extremum detection and attentive description. Multimedia Systems, 30(1), 23. https://doi.org/10.1007/s00530-023-01203-w
dc.relation.referencesen6. Moksyakov A, Wu Y, Gadsden SA, Yawney J, AlShabi M. Object Detection and Tracking with YOLO and the Sliding Innovation Filter. Sensors. 2024; 24(7):2107. https://doi.org/10.3390/s24072107
dc.relation.referencesen7. Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023). Object detection using YOLO: Challenges, architectural successors, datasets and applications. multimedia Tools and Applications, 82(6), 9243-9275. https://doi.org/10.1007/s11042-022-13644-y
dc.relation.referencesen8. Du, J. (2018, April). Understanding of object detection based on CNN family and YOLO. In Journal of Physics: Conference Series (Vol. 1004, p. 012029). IOP Publishing. https://doi.org/10.1088/1742-6596/1004/1/012029
dc.relation.referencesen9. Shafiee, M. J., Chywl, B., Li, F., & Wong, A. (2017). Fast YOLO: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943. https://doi.org/10.15353/vsnl.v3i1.171
dc.relation.referencesen10. Zhang, Z., Lu, X., Cao, G., Yang, Y., Jiao, L., & Liu, F. (2021). ViT-YOLO: Transformer-based YOLO for object detection. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 2799-2808). https://doi.org/10.1109/ICCVW54120.2021.00314
dc.relation.referencesen11. S. Li, Y. Li, Y. Li, M. Li and X. Xu, "YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection," in IEEE Access, vol. 9, pp. 141861-141875, 2021. https://doi.org/10.1109/ACCESS.2021.3120870
dc.relation.referencesen12. Malik, J., Belongie, S., Leung, T., Shi, J. (2001). Contour and texture analysis for image segmentation. International journal of computer vision, 43, 7-27. https://doi.org/10.1023/A:1011174803800
dc.relation.referencesen13. Hashemi, N. S., Aghdam, R. B., Ghiasi, A. S. B., Fatemi, P. (2016). Template matching advances and applications in image analysis. arXiv preprint arXiv:1610.07231.
dc.relation.referencesen14. Cox, G. S. (1995). Template matching and measures of match in image proce-ssing. University of Cape Town, South Africa.
dc.relation.referencesen15. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60, 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
dc.relation.referencesen16. Mukherjee, D., Jonathan Wu, Q. M., Wang, G. (2015). A comparative experimental study of image feature detectors and descriptors. Machine Vision and Applications, 26, 443-466. https://doi.org/10.1007/s00138-015-0679-9
dc.relation.referencesen17. Liu, Q., Ye, H., Wang, S., & Xu, Z. (2024). YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera. Electronics, 13(1), 236. https://doi.org/10.3390/electronics13010236
dc.relation.referencesen18. Koga, S., Hamamoto, K., Lu, H., & Nakatoh, Y. (2024). Optimizing Food Sample Handling and Placement Pattern Recognition with YOLO: Advanced Techniques in Robotic Object Detection. Cognitive Robotics. https://doi.org/10.1016/j.cogr.2024.01.001
dc.relation.referencesen19. Wang, Y., Wang, B., Huo, L., & Fan, Y. (2024). GT-YOLO: Nearshore Infrared Ship Detection Based on Infrared Images. Journal of Marine Science and Engineering, 12(2), 213. https://doi.org/10.3390/jmse12020213
dc.relation.referencesen20. Wang, Z., Hua, Z., Wen, Y., Zhang, S., Xu, X., & Song, H. (2024). E-YOLO: Recognition of estrus cow based on improved YOLOv8 n model. Expert Systems with Applications, 238, 122212. https://doi.org/10.1016/j.eswa.2023.122212
dc.relation.referencesen21. Giudici, P., Centurelli, M., & Turchetta, S. (2024). Artificial Intelligence risk measurement. Expert Systems with Applications, 235, 121220. https://doi.org/10.1016/j.eswa.2023.121220
dc.relation.referencesen22. Shinde, S., Khoje, S., Raj, A., Wadhwa, L., & Shaikha, A. S. (2024). Artificial intelligence approach for terror attacks prediction through machine learning. Multidisciplinary Science Journal, 6(1), 2024011-2024011. https://doi.org/10.31893/multiscience.2024011
dc.relation.referencesen23. Dogan, A., Okatan, A., & Cetinkaya, A. (2021). Vehicle Classification and Tracking Using Convolutional Neural Network Based on Darknet Yolo with Coco Dataset. AI and Big Data in Engineering Applications, 179.
dc.relation.referencesen24. Nazarkevych, M., Oliarnyk, R., Troyan, O., & Nazarkevych, H. (2016, September). Data protection based on encryption using Ateb-functions. In 2016 XIth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT) (pp. 30-32). IEEE. https://doi.org/10.1109/STC-CSIT.2016.7589861
dc.relation.referencesen25. Medykovskyy, M., Lipinski, P., Troyan, O., & Nazarkevych, M. (2015, September). Methods of protection document formed from latent element located by fractals. In 2015 Xth International Scientific and Technical Conference" Computer Sciences and Information Technologies"(CSIT) (pp. 70-72). IEEE. https://doi.org/10.1109/STC-CSIT.2015.7325434
dc.relation.referencesen26. Sheketa, V., Zorin, V., Chupakhina, S., Kyrsta, N., Pasyeka, M., & Pasieka, N. (2020, November). Empirical method of evaluating the numerical values of metrics in the process of medical software quality determination. In 2020 International Conference on Decision Aid Sciences and Application (DASA) (pp. 22-26). IEEE. https://doi.org/10.1109/DASA51403.2020.9317218
dc.relation.urihttps://doi.org/10.1016/j.eswa.2023.122669
dc.relation.urihttps://doi.org/10.3390/children11020159
dc.relation.urihttps://doi.org/10.3390/s24010229
dc.relation.urihttps://doi.org/10.1007/s00530-023-01203-w
dc.relation.urihttps://doi.org/10.3390/s24072107
dc.relation.urihttps://doi.org/10.1007/s11042-022-13644-y
dc.relation.urihttps://doi.org/10.1088/1742-6596/1004/1/012029
dc.relation.urihttps://doi.org/10.15353/vsnl.v3i1.171
dc.relation.urihttps://doi.org/10.1109/ICCVW54120.2021.00314
dc.relation.urihttps://doi.org/10.1109/ACCESS.2021.3120870
dc.relation.urihttps://doi.org/10.1023/A:1011174803800
dc.relation.urihttps://doi.org/10.1023/B:VISI.0000029664.99615.94
dc.relation.urihttps://doi.org/10.1007/s00138-015-0679-9
dc.relation.urihttps://doi.org/10.3390/electronics13010236
dc.relation.urihttps://doi.org/10.1016/j.cogr.2024.01.001
dc.relation.urihttps://doi.org/10.3390/jmse12020213
dc.relation.urihttps://doi.org/10.1016/j.eswa.2023.122212
dc.relation.urihttps://doi.org/10.1016/j.eswa.2023.121220
dc.relation.urihttps://doi.org/10.31893/multiscience.2024011
dc.relation.urihttps://doi.org/10.1109/STC-CSIT.2016.7589861
dc.relation.urihttps://doi.org/10.1109/STC-CSIT.2015.7325434
dc.relation.urihttps://doi.org/10.1109/DASA51403.2020.9317218
dc.rights.holder© Національний університет “Львівська політехніка”, 2024
dc.subjectрозпізнавання
dc.subjectYOLO
dc.subjectштучний інтелект
dc.subjectвідстеження об’єктів
dc.subjectнейронна мережа
dc.subjectrecognition
dc.subjectYOLO
dc.subjectartificial intelligence
dc.subjectdecision support
dc.subjectneural network
dc.subject.udc004.8
dc.subject.udc[623.438
dc.subject.udc623.55.021]
dc.titleСистема розпізнавання об’єктів на основі моделі YOLO
dc.title.alternativeObject recognition system based on the YOLO model and database formation
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
2024v6n1_Nazarkevych_M_A-Object_recognition_120-126.pdf
Size:
1.2 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
2024v6n1_Nazarkevych_M_A-Object_recognition_120-126__COVER.png
Size:
1.65 MB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.81 KB
Format:
Plain Text
Description: