STPM_SAHI: A Small-Target Forest Fire Detection Model Based on Swin Transformer and Slicing Aided Hyper Inference

Abstract

Forest fires seriously destroy the world’s forest resources and endanger biodiversity. The traditional forest fire target detection models based on convolutional neural networks (CNNs) lack the ability to deal with the relationship between visual elements and objects. They also have low detection accuracy for small-target forest fires. Therefore, this paper proposes an improved small-target forest fire detection model, STPM_SAHI. We use the latest technology in the field of computer vision, the Swin Transformer backbone network, to extract the features of forest fires. Its self-attention mechanism can capture the global information of forest fires to obtain larger receptive fields and contextual information. We integrated the Swin Transformer backbone network into the Mask R-CNN detection framework, and PAFPN was used to replace the original FPN as the feature fusion network, which can reduce the propagation path of the main feature layer and eliminate the impact of down-sampling fusion. After the improved model was trained, the average precision (AP0.5) of forest fire target detection at different scales reached 89.4. Then, Slicing Aided Hyper Inference technology was integrated into the improved forest fire detection model, which solved the problem that small-target forest fires pixels only account for a small proportion and lack sufficient details, which are difficult to be detected by the traditional target detection models. The detection accuracy of small-target forest fires was significantly improved. The average precision (AP0.5) increased by 8.1. Through an ablation experiment, we have proved the effectiveness of each module of the improved forest fire detection model. Furthermore, the forest fire detection accuracy is significantly better than that of the mainstream models. Our model can also detect forest fire targets with very small pixels. Our model is very suitable for small-target forest fire detection. The detection accuracy of forest fire targets at different scales is also very high and meets the needs of real-time forest fire detection.

An Improved Wildfire Smoke Detection Based on YOLOv8 and UAV Images

“…Insights garnered from pertinent literature [55,56] underscore the significance of geometric modifications, encompassing flips and rotations, as valuable techniques for enhancing image data. By employing strategies such as rotation and horizontal flips [57,58], the forest fire smoke detection dataset was augmented experimentally, leading to an increase in the number of images. The performance of CNN models is notably responsive to the quantity and quality of image datasets utilized for training purposes.…”

“…In this study, a quantitative assessment of the proposed approach's effectiveness was conducted using the well-established Microsoft COCO benchmarks (presented in Table 5), aligning with previous research endeavors [5,9,12,[58][59][60]. A common metric for evaluating a classifier's accuracy involves tallying the instances in which it correctly classifies an object.…”

An Efficient Forest Fire Target Detection Model Based on Improved YOLOv5

“…Deep-learning-based object-detection approaches exhibit distinct benefits when applied to identifying forest fires [18][19][20]. These advantages include high accuracy, fast detection speed, flexible installation and the ability to adapt to various fire features [21][22][23]. Mohnish et al (2022) [24] preprocessed the images in the dataset and input them into a convolutional neural network (CNN) for feature extraction and detection.…”

FBC-ANet: A Semantic Segmentation Model for UAV Forest Fire Images Combining Boundary Enhancement and Context Awareness

“…This allows firefighters and forestry managers to quickly monitor the forest fire without blind space by operating UAVs without delving deep into the forest, thereby reducing the risks that firefighters and forestry managers face. With the rapid development of machine vision and deep learning, real-time classification and detection based on images are widely applied in this field of forest fires [10][11][12][13][14][15]. Modern UAVs can be equipped with small CPUs and GPUs, as well as pre-trained deep network models onboard [16,17], in order to detect fires as early as possible.…”