There are major problems in the field of image-based forest fire smoke detection, including the low recognition rate caused by the changeable and complex state of smoke in the forest environment and the high false alarm rate caused by various interferential objects in the recognition process. Here, a forest fire smoke identification method based on the integration of environmental information is proposed. The model uses (1) the Faster R-CNN as the basic framework, (2) a component perception module to generate a receptive field of integrated environmental information through separable convolution to improve recognition accuracy, and (3) a multi-level Region of Interest (ROI)pooling structure to reduce the deviation caused by rounding in the ROI pooling process. The results showed that the model achieved a recognition accuracy rate of 96.72%, an Intersection Over Union (IOU) of 78.96%, and an average recognition speed for each picture of 1.5 ms; the false alarm rate was 2.35% and the false-negative rate was 3.28%. Compared with other models, the proposed model can effectively enhance the recognition accuracy and recognition speed of forest fire smoke, which provides a technical basis for the real-time and accurate detection of forest fires.
Early wildfire smoke detection faces challenges such as limited datasets, small target sizes, and interference from smoke-like objects. To address these issues, we propose a novel approach leveraging Efficient Channel and Dilated Convolution Spatial Attention (EDA). Specifically, we develop an experimental dataset, Smoke-Exp, consisting of 6016 images, including real-world and Cycle-GAN-generated synthetic wildfire smoke images. Additionally, we introduce M-YOLO, an enhanced YOLOv5-based model with a 4× downsampling detection head, and MEDA-YOLO, which incorporates the EDA mechanism to filter irrelevant information and suppress interference. Experimental results on Smoke-Exp demonstrate that M-YOLO achieves a mean Average Precision (mAP) of 96.74%, outperforming YOLOv5 and Faster R-CNN by 1.32% and 3.26%, respectively. MEDA-YOLO further improves performance, achieving an mAP of 97.58%, a 2.16% increase over YOLOv5. These results highlight the potential of the proposed models for precise and real-time early wildfire smoke detection.
About Me
A graduate student from School of Technology, Beijing Forestry University.
A graduate student from School of Technology, Beijing Forestry University.