CCTV TASVIRLARINI SEGMENTLASH VA OBYEKTLARNI ANIQLASH UCHUN CHUQUR O‘QITISHGA ASOSLANGAN MODELLAR VA ALGORITMLAR TAHLILI

Temurbek Kuchkorov; Farrux Baxritdinov; Jamshid Hamzayev

Авторы

Temurbek Kuchkorov Muhammad al-Xorazmiy nomidagi TATU
Farrux Baxritdinov Kimyo International University in Tashkent
Jamshid Hamzayev Muhammad al-Xorazmiy nomidagi TATU

Ключевые слова:

YOLO, R-CNN, AlexNet, Computer Vision, CCTV, Deep Learning, VGG16

Аннотация

Ushbu maqolada CCTV kameralaridan olingan tasvirlarini segmentatsiyalash va obyektni aniqlash uchun turli modellar va algoritmlarning tahlili keltirib o‘tilgan. Maqolada chuqur o‘rganish (Deep Learning) orqali hozirda keng foydalaniladigan R-CNN, AlexNet va YOLO modellarining xususiyatlari, ustun jihatlari, kamchiliklari va o‘ziga xos afzalliklari tahlil qilingan. Modellardan olingan natijalarni baholash - aniqlilik, F1 baholash, mAP50 kabi ko‘rsatkichlarga asoslanadi. CCTV kameralaridan foydalangan holda obyektlarni aniqlash uchun chuqur o’qitishga asoslangan modellardan eng samaralisi YOLO modeli aniqlik bo‘yicha yuqori natija ko‘rsatdi va tahlil natijasida YOLOv8 modeli amaliy dasturiy loyihalarda yaxshi samaradorlikka ega ekanligi aniqlandi. Maqoladan olingan natijalar va xulosalar asosida tadqiqotchilar o‘zlarining ilovalari uchun eng mos modelni tanlab olishlari uchun tavsiyalar keltirilgan.

Биография автора

Farrux Baxritdinov, Kimyo International University in Tashkent

Master's student

Библиографические ссылки

Weishan Zhanga, Xia Liua, Jiangru Yuan, Liang Xu, Haoyun Suna, Jiehan Zhou, Xin Liu. 2018 International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2018. 331-337 p.

Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014.

Manolis Loukadakis, Jose Cano, Michael Oboyle. 11th International Workshop on Programmability and Architectures for Heterogeneous Multicores (MULTIPROG-2018). Conference: 11th International Workshop on Programmability and Architectures for Heterogeneous Multicores.

Olga R., Jia D., Hao Su, Jonathan K., Sanjeev S., Sean Ma, Zhiheng and others. ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015.

Shiva Asadianfam, Mahboubeh Shamsi, Abdolreza Rasouli Kenari. Hadoop Deep Neural Network for offending drivers. Journal of Ambient Intelligence and Humanized Computing 13(2). 2022.

Ling Ding, Hongyi Li, Changmiao Hu, Wei Zhang, Shumin Wang. AlexNet Feature Extraction And Multi-Kernel Learning For Objectoriented Classification. The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences XLII-3:277-281.

Muhammad Hussain. YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection. Machines and Tooling. 2023.

Juan R. Tervan, Diana M. Cordova-Esparaza. A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. Under review in ACM Computing Surveys. 2023.

Maria Kalinina, Pavel Nikolaev. Research of YOLO Architecture Models in Book Detection. 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020).

Shiron Thalagala, Chamila Walgampaya. Application of AlexNet convolutional neural network architecture-based transfer learning for automated recognition of casting surface defects. 2021 International Research Conference on Smart Computing and Systems Engineering (SCSE). 2021

Temurbek Kuchkorov, Jamshid Khamzaev, Zamira Allamuratova, Temur Ochilov. “Traffic and road sign recognition using deep convolutional neural network”. 2021 International Conference on Information Science and Communications Technologies (ICISCT).

Alpamis Kutlimuratov, Jamshid Khamzaev, Temur Kuchkorov, Muhammad Shahid Anwar, Ahyoung Choi. “Applying Enhanced Real-Time Monitoring and Counting Method for Effective Traffic Management in Tashkent”. Sensors 23 (11), 5007 .

T.A.Kuchkorov, Sh.N.Urmanov, Kh.Kh.Nosirov, K.Kyamakya. “Perspectives of deep learning based satellite imagery analysis and efficient training of the U-Net architecture for land-use classification” . Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference (FLINS 2020). 2020.

Furkat Safarov, Kuchkorov Temurbek, Djumanov Jamoljon, Ochilov Temur, Jean Chamberlain Chedjou, Akmalbek Bobomirzaevich Abdusalomov, Young-Im Cho. “Improved Agricultural Field Segmentation in Satellite Imagery Using TL-ResUNet Architecture”. Sensors 22 (24), 9784 .