Real-time object detection and recognition in video streams is one of the most important tasks in modern computer vision. This paper compares the performance of modern deep learning models such as YOLOv8, Faster R-CNN, and EfficientDet in object detection in video data. Experiments on the COCO and MOT17 open datasets showed that the YOLOv8 model has the highest speed (145 FPS) and sufficient accuracy (mAP@0.5 = 53.9%), which is superior in real-time applications. At the same time, EfficientDet-D7 (mAP@0.5 = 55.1%) performed best in cases where high accuracy was required.
| Mualliflar | Зулунов, Равшанбек, Мухторов, Асадбек |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2025-12-05 |
| Son | 4 |
| Betlar | 68-70 |
| Til | Rus |
обнаружение объектов, видеоанализ, YOLO, Faster R-CNN, EfficientDet, глубокое обучение, системы реального времени, YOLOv8, object detection, video analysis, YOLO, Faster R-CNN, EfficientDet, deep learning, real-time systems, YOLOv8, obyektlarni aniqlash, video tahlil, Faster R-CNN, EfficientDet, chuqur o‘quv, real vaqt tizimlari, YOLOv8
The textile industry relies on high-speed rotating and thermally loaded equipment such as spinning frames, carding cylinders, and weaving looms. To enhance reliability and reduce unplanned stoppages, this study develops…
This research is devoted to developing a novel type of composite three-dimensional geometric model constructed on the basis of one of the fundamental objects of fractal geometry - the Sierpinski tetrahedron (Sierpinski…
This paper presents methods for filtering spam messages using machine learning models in artificial intelligence. Machine learning algorithms are widely used for automatic spam detection because they can learn from…
This article proposes an artificial immune system, based on the principles of the biological immune system, for detecting anomalies in information systems. Anomaly detection utilizes an adverse selection algorithm to…
Deepfake technology has become a growing threat to information integrity and digital trust. This study examines how accurately humans can identify deepfake videos through an empirical survey conducted among 492 students…
This article analyzes the field of post-quantum cryptography, the threats posed by quantum computing technologies to traditional cryptographic systems, and the early developments of post-quantum cryptography. It…
This paper presents the development of an adaptive control system for an electric cotton dryer based on the ESP32 microcontroller with power regulation via a dimmer. An empirical model for calculating the coolant…
This article analyzes methods for improving the mechanical properties of Hadfield steels, such as hardness, wear resistance, strength, and impact toughness. Various modification and heat treatment methods were analyzed…
Ush tadqiqotining tadqiqot usullarini kompyuter tizimlarining ishonchli tahlil qilish va uni qayta ishlab chiqilmagan bilan, ular qurilmani saqlab qolishning holatini tekshirishni yoki uning faqat uni saqlab qolishini…
This article presents the results of a computational study of the thermal and physical parameters of an autonomous photovoltaic-thermal device. The device is based on a mobile solar energy system and consists of two…