Method and device for rapidly detecting coal gangue based on multispectral technology

Abstract

The invention discloses a method and a device for rapidly detecting coal gangue based on a multispectral technology. According to the invention, a multispectral imaging technology is used for coal gangue detection, a coal and gangue multispectral image acquisition system is constructed, a coal gangue multispectral image is acquired, the multispectral image is processed by using an image fusion technology, and the coal and gangue multispectral image after image fusion is used for coal gangue detection. YOLO-V3 is improved, a coal gangue rapid detection model is designed, and the fused multispectral image is labeled and used for training the detection model. Finally, the trained detection model is applied to coal gangue detection. The coal gangue is detected based on the multispectral imaging technology, and compared with a visible light image, richer characteristics of the coal and the gangue can be obtained through a multispectral image, and higher accuracy is achieved. In addition, the designed improved detection model has higher detection speed, and online detection of coal gangue can be realized.

Description

technical field [0001] The invention belongs to the field of multi-spectral image detection of coal gangue, in particular to a method and device for rapid detection of coal gangue based on multi-spectral technology. Background technique [0002] Coal has played an important role in human energy since the first industrial revolution. According to the "BP Statistical Yearbook of World Energy", in 2018, global coal consumption increased by 1.4%, and output increased by 4.3%, and their growth rates both hit five-year highs; in addition, the proportion of coal consumption in primary energy is still as high as 27.2%. This means that under the current energy model, people will be engaged in coal mining for a long time. In the process of coal mining, it is inevitable to add stones with low calorific value or non-combustible stones. It not only reduces the combustion efficiency of coal, but also increases air pollution (the gangue contains positive metals). Therefore, separating g...

AI Technical Summary

Problems solved by technology

At present, although there have been some reports on the detection of coal gangue, they are all based on visible light imaging, which is easily affected by environmental optical fibers and dust, and the detection accuracy needs to be improved.

For example, patent 201910715211.6 detects coal gangue based on video images. Although it realizes the detection of gangue, but based on video detection, it only uses part of the visible light band, and the detection accuracy needs to be improved.

Images