APPLICATION OF VGG16 AND YOLOV10 IN OBJECT CLASSIFICATION AND DETECTION

Abstract

The application of artificial intelligence in education and scientific research is becoming an increasingly prominent trend in the digital age. Leveraging deep learning models such as VGG16 and YOLOv10 has opened up numerous opportunities for developing intelligent systems that support teaching and monitoring. In an effort to enhance the quality of teaching and learning in the field of image processing and computer vision, the student has developed a system for object classification and recognition by integrating two models: VGG16 for image classification and YOLOv10 for real-time object detection. The system focuses on identifying traffic vehicles, flying devices, and violations such as the absence of helmets. The dataset was trained, tested, and evaluated using performance metrics including accuracy, mAP, and F1-score. Results indicate that the model performs well on both still images and video streams, demonstrating strong potential for deployment in traffic monitoring and public safety systems. This represents a concrete step toward integrating digitized learning materials, endogenous resources, and modern AI technologies into teaching and research practices at universities today.