HUMAN LIFE DETECTION DURING FIRE (YOLOV8 and V9)

This project focuses on designing and evaluating an advanced detection system capable of identifying humans, fire, and smoke in real-time. Using cutting-edge deep learning algorithms such as YOLOv8 and YOLOv9, the system will analyse and classify these elements accurately in both uploaded images and live camera feeds. The project leverages a diverse dataset from Roboflow, featuring images of humans, fire, and smoke, to train and validate the models. Development will take place in Python, utilizing Google Colab as the primary development environment. The system will be designed to work with images captured from a laptop camera, though potential challenges related to resolution and image clarity may impact detection performance. A key part of this study will involve comparing YOLOv8 and YOLOv9 to assess their effectiveness in terms of accuracy, processing speed, and reliability across different scenarios. The ultimate goal is to create a real-time application that provides alerts and visual feedback when detecting fire, smoke, or human presence. This capability has the potential to significantly improve safety and response measures in critical situations. Through this project, we aim to make a meaningful contribution to the field of computer vision, particularly in the development of systems for safety and security.