PSSNet: An Optimized High-Accuracy Method for Forest Fire Smoke Detection

Abstract

In the field of early automatic detection of smoke from forest fires, there is the issue of the small size and interference of smoke detection by clouds. The conventional nonmaximum suppression (NMS) requires manual adjustment of the threshold, which may result in missed or erroneous detection. This article proposes a high-accuracy anti-interference forest fire smoke detection network for small objects. First, a window feature extractor based on singular value decomposition (SVD-STR) is designed. This extractor is capable of extracting more representative features, of capturing small and inconspicuous features in the image, and of reducing the complexity and computation of the model. Second, a sinthreshold screening attention mechanism (SinAttention) is proposed, which can filter interference information and enhance the discriminative power of the features, thereby facilitating the accurate recognition and distinction of smoke and clouds. Subsequently, a variational particle swarm soft suppression optimization (PGS) is proposed as a means of further enhancing the optimization effect. This is achieved by adjusting the suppression strategy and incorporating a Gaussian variational particle swarm algorithm. In conclusion, an Internet of Things forest fire detection system based on PSSNet has been constructed. The experimental results demonstrate that the mAP50 value of the method is 98.2%, the value of mAP50-95 is 80.4%, and the FPS value is 35.7. These values are superior to those of current forest fire smoke detection methods and can be utilized for the precise detection of forest fire smoke, thereby providing technical support for forest ecological protection.