A mine environment change detection method based on high-score remote sensing image

Abstract

The invention discloses a mine environment change detection method based on a high-score remote sensing image, comprising the following steps: S1, determining a mine environment detection target and collecting a corresponding multi-temporal remote sensing image; S2, preprocessing the change detection data of the multi-temporal remote sensing image; S3, segmenting the multi-temporal remote sensingimage after preprocessing by means of mean shift image, extracting features according to the characteristics of the mine, and constructing the multi-source feature set at the object level; S4, takingthe constructed multi-source feature set as an input image, and automatically selecting a training sample by using the CVA model; 5, inputting the training sample, training the ELM model, obtaining the change detection diagram, and realizing the mine environment change detection. The invention solves the problems that the artificial ground investigation mode existing in the prior art leads to theblind area of monitoring, low efficiency, low detection precision and large influence on the detection result.

Description

technical field [0001] The invention belongs to the technical field of mine detection, and in particular relates to a mine environment change detection method based on high-resolution remote sensing images. Background technique [0002] Mine sites are mostly located in mountainous areas with rugged roads. In addition, mines are often large in scale and complex in structure. The method of manual ground survey is inefficient, and it is easy to form monitoring blind spots due to the constraints of manpower, material resources, and financial resources. Remote sensing technology is a comprehensive technology for earth observation, which has the characteristics of large-area synchronous observation, fast information acquisition, short cycle and strong comprehensiveness. It makes up for the defects of traditional mine monitoring technology and can be comprehensive, objective, effective, and Accurately and dynamically reflect the situation of the mine and surrounding areas, and is n...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a high-efficiency, high-accuracy detection method for mine environment changes based on high-resolution remote sensing images, which solves the problem of monitoring blind spots and efficiency problems caused by artificial ground survey methods in the prior art. Low, low detection accuracy and greatly affected detection results

Images