Forest fire smoke root node detection method based on dynamic and static grid fusion strategy

Abstract

The invention discloses a forest fire smoke root node detection method based on a dynamic and static grid fusion strategy. In order to solve the problem that an existing smog root node detection method cannot obtain a complete smog contour through motion detection and gray scale detection, the invention provides a forest fire smoke root node detection method based on a dynamic and static grid fusion strategy. According to the algorithm, firstly, smoke static characteristics are extracted through a Sobel algorithm, then smoke dynamic characteristics are extracted through a Vibe algorithm, extracted characteristic images are fused through a grid strategy, a smoke image is obtained, bones and bone endpoints are extracted, and smoke root candidate points are obtained. According to the algorithm, by fusing dynamic and static features of smoke, the problem that smoke edges and smoke roots are difficult to recognize by a dynamic extraction algorithm is improved, meanwhile, the smoke area extraction process is simplified, and the detection efficiency is greatly improved.

Description

Technical field [0001] The invention belongs to the field of forest fire prevention and video target detection, and particularly relates to a forest fire smoke root node detection method based on a dynamic and static grid fusion strategy. Background technique [0002] Due to the particularity of the forest, once a forest fire is triggered, it is easy to spread rapidly under the drive of the wind. Due to the large area of ​​the forest, the fire may not be detected in time when the fire is discovered, and the fire has often spread a considerable distance. There are also considerable difficulties in fighting forest fires. Forest fires often cause huge resource damage. Therefore, early recognition of forest fires is very important. Smoke is an obvious feature of early forest fires. In early forest fires, smoke is often an irregular shape that drifts upward. The more upward, the thinner the smoke and the harder it is to be detected. However, the location of the source of early smoke i...

AI Technical Summary

Problems solved by technology

This method can neither make up for the shortcomings that the gradient algorithm will bring a lot of background interference, nor can it make up for the shortcomings that the dynamic extraction cannot extract the complete outline of the moving object, and it cannot be used for forest fire smoke detection, and the direct fusion method is even more incapable. Extract the correct smoke area

[0008] The School of Computer and Control Engineering, University of Chinese Academy of Sciences proposed a motion detection algorithm based on optimized Sobel and Vibe (ZHANG Yujia, ZHAO Xiaoguang, TAN Min, Motion Detection Based on Improved Sobel and Vibe Algorithm, Proceeding of the 35 th Chinese Control Conference, July 27-29, 2016, Chnegdu, China: 4144-4148.), this article extracts and fills the edges based on Otsu’s improved Sobel algorithm to fill the gaps in the foreground pixels to achieve the accuracy of driving on the highway Vehicle detection, the algorithm has a good detection effect on moving vehicles, but the algorithm has great requirements for the accuracy and clarity of the early dynamic extraction and edge extraction. The vehicle has clear edges and motion features, while the forest The smoke in the early stage of the fire has neither obvious edge outline nor clear motion trajectory. It is impossible to detect the complete smoke area through the dynamic detection algorithm, and the complete outline cannot be detected through the gradient detection algorithm. Therefore, this algorithm is also not suitable for forest fires. Early Smoke Detection

Images