Coal mining subsidence ground crack identification and extraction method and device and storage medium

Abstract

The invention provides a coal mining subsidence ground crack identification and extraction method and device and a storage medium. The method comprises the steps of acquiring multiple pieces of mining area unmanned aerial vehicle image data A containing coal mining subsidence ground fissures; preprocessing the mining area unmanned aerial vehicle image data A to obtain mining area unmanned aerial vehicle image data B; calculating ground feature statistical characteristics; by using a K-means clustering method and combining ground feature statistical characteristics, extracting ground fissures from the mining area unmanned aerial vehicle image B, and generating binary image data B3; performing optimization processing on the binary image data B3 to obtain binary image data C; performing hit-miss transformation processing on the binary image data C until the width of the ground crack in the binary image data C does not change any more, and obtaining final binary image data D containing the ground crack; and calculating the actual area, length and width of the ground crack according to the binary image data D. The crack extraction precision is higher, automation is achieved, and a large number of training samples are not needed.

Description

technical field [0001] The disclosure belongs to the field of ground fissure monitoring, and in particular relates to a method, device and storage medium for identifying and extracting ground fissures in coal mining subsidence. Background technique [0002] The ecologically fragile loess gully area in western my country is characterized by arid climate, surface water shortage and low vegetation coverage. The problem of ground fissures caused by coal mining is particularly prominent. At the same time, it has also caused a series of environmental problems such as deformation of surface buildings, damage to underground pipelines, loss of groundwater, ground subsidence, damage to cultivated land, reduction of water content in the soil surface, degradation of vegetation, and soil erosion. Mining area management workers have brought great difficulties, which is the key work of land reclamation in mining areas. Therefore, it is necessary to obtain real-time and high-precision dist...

AI Technical Summary

Problems solved by technology

[0003] At present, ground fissures have become the most important geological disaster in the western mining area. The monitoring of ground fissures is mainly to use ground fissure monitoring devices to directly measure them on the spot, which requires a lot of manpower, material and financial resources. At the same time, the monitoring range is limited and universal poor

At present, the identification and extraction of ground fissures are mainly object-oriented, edge detection, threshold segmentation and manual visual interpretation, which require a large number of training samples, and all have many restrictive factors and conditions, which cannot be widely used. use

Images