Real-Time Object Detection System Using YOLO-Based Vision Models

Abstract: Object detection plays an important role in many real-time applications such as surveillance, traffic monitoring, smart automation. In recent years, deep learning techniques have significantly improved the accuracy and speed of object detection systems. This project presents the implementation of a real-time object detection system. Using YOLO integrated with CNN. The proposed system processes video frames, extracts features using CNN layers, and detects objects. By predicting bounding boxes and class labels in a single step. YOLO enables fast detection while maintaining acceptable accuracy, making it suitable for real-time environments. Experimental results show that the system performs efficiently on live video streams with good accuracy and real-time speed. Proving its suitability for practical applications.

Keywords: Real-time object detection, YOLOv8, CNN, Python, OpenCV, Smart monitoring.