Real-Time Object Detection Using Yolov5: A Transfer Learning Approach

Abstract: Real-time object detection is essential in areas like surveillance, autonomous vehicles, and smart cities.This project uses YOLOv5, a fast and accurate one-stage deep learning model, for object detection.Transfer learning is applied by fine-tuning pre-trained weights on a custom dataset of 5,000 images.The model includes CSPDarknet53 and PANet to improve feature extraction and multi-scale detection.It effectively detects small, occluded, and multiple objects in complex scenes.Trained over 50 epochs, it achieved high accuracy using precision, recall, and mAP metrics.Deployment was done using OpenCV DNN for real-time CPU-based inference.The system shows strong real-world potential, with future scope in edge and IoT applications. Index Terms: YOLOv5, Real-Time Object Detection, Deep Learning, Transfer Learning, CNN, CSPDarknet53, PANet, Pascal VOC, Bounding Box, Data Augmentation, OpenCV, Edge Deployment, Object Classification, Precision, Recall, mAP, F1-Score, Smart Surveillance, Autonomous Vehicles, Lightweight Model