Forest smoke and fire detection method based on video understanding, storage medium and equipment

Abstract

The invention discloses a forest smoke and fire detection method based on video understanding, a storage medium and equipment, and belongs to the field of computer vision video understanding and forest smoke and fire video monitoring. The method comprises: obtaining a forest smoke and fire image; performing forward calculation on the forest smoke and fire image by adopting a neural network model comprising a 2D network layer and a 3D network layer; the confidence coefficient of the forest smoke and fire area is obtained, whether a forest fire occurs or not is judged by comparing the confidencecoefficient with a set confidence coefficient threshold value, when the confidence coefficient is larger than the confidence coefficient threshold value, it is considered that the fire occurs in theforest, and when the confidence coefficient is smaller than or equal to the confidence coefficient threshold value, it is considered that the fire does not occur in the forest. According to the method, network model parameters can be reduced, and the precision and efficiency of forest smoke and fire detection are effectively improved, so that forest smoke and fire can be efficiently and accuratelyidentified. Meanwhile, the invention discloses a storage medium and equipment comprising the storage medium, and the equipment can directly carry out engineering deployment and is used for efficiently and accurately detecting forest smoke and fire.

Description

technical field [0001] The invention belongs to the fields of computer vision video understanding and forest firework video monitoring, and in particular relates to a forest firework detection method, storage medium and equipment based on video understanding. Background technique [0002] Forest fires are a common natural disaster. The casualties and property losses caused by forest fires in the world are huge every year. For example, the recent California forest fires, Indonesian forest fires, and Amazon forest fires have not only caused a large number of Casualties and property losses have also caused serious impacts on the natural environment. In the fire fighting process, a lot of manpower and material resources have been invested, but it is still difficult to effectively extinguish forest fires. Forest fires have caused serious threats to the survival of humans and animals. my country is a country with many forests. Every year, tens of thousands of casualties and hundr...

AI Technical Summary

Problems solved by technology

However, when using a 3D convolutional neural network, the network model has many parameters and is prone to overfitting, so this method is slow and has low precision.

Images