Application of the YOLOv6 Combining CBAM and CIoU in Forest Fire and Smoke Detection

Forest fires are a vulnerable and devastating disaster that pose a major threat to human property and life. Smoke is easier to detect than flames due to the vastness of the wildland scene and the obscuring vegetation. However, the shape of wind-blown smoke is constantly changing, and the color of smoke varies greatly from one combustion chamber to another. Therefore, the widely used sensor-based smoke and fire detection systems have the disadvantages of untimely detection and a high false detection rate in the middle of an open environment. Deep learning-based smoke and fire object detection can recognize objects in the form of video streams and images in milliseconds. To this end, this paper innovatively employs CBAM based on YOLOv6 to increase the extraction of smoke and fire features. In addition, the CIoU loss function was used to ensure that training time is reduced while extracting the feature effects. Automatic mixed-accuracy training is used to train the model. The proposed model has been validated on a self-built dataset containing multiple scenes. The experiments demonstrated that our model has a high response speed and accuracy in real-field smoke and fire detection, which provides intelligent support for forest fire safety work in social life.