Published Paper Details:

The performance of Yolo V8 when compared to traditional approaches such as infrared imaging has been thoroughly studied and documented. Studies have found that the algorithm is more accurate in detecting fires before they become too severe or spread too far, allowing for quicker response times from firefighting units. For solving this problem, we developed a detection model called upgraded-YOLO based on the state-of-the-art object detection method of YOLOv8. The proposed model is able to perform real-time object detection. Firstly, the data will be collected and data labelling is performed. Unlike other objects detection models that divide image into multiple regions and perform object detection on multiple regions, YOLOv8 performs object detection on entire image in one forward pass through the network. This makes it fast and efficient for real time applications. A comparative study with several contemporary object detectors proved that the Upgraded-YOLO performed better. Therefore, the proposed detection technology can be deployed in a monitoring center in order to protect a strategic installation even in low-visibility conditions.