Coal mine goaf crack identification method and detection system based on unmanned aerial vehicle

Abstract

The invention discloses a coal mine goaf crack identification method and detection system based on an unmanned aerial vehicle. The detection system comprises a camera, an unmanned aerial vehicle, an unmanned aerial vehicle ground station and a data server. The coal mine goaf crack identification method is characterized in that a deep semantic segmentation model is constructed through data augmentation processing in combination with deep semantic information of an image; a dense deep separable convolution unit is adopted, and image features are fully utilized, and multi-scale feature extractionof cracks is achieved in combination with a spatial pyramid; a loss function is adaptively set according to the weight of the crack in the training sample in the image, thereby accelerating the training process; and dense classification is adopted to finally obtain a pixel-level detection result. The coal mine goaf crack identification method has high crack detection precision and high training speed, can effectively reduce the inspection time and improve the detection reliability, is suitable for coal mine goaf surface crack detection under large-scale complex backgrounds, and can be popularized and applied to geological anomaly detection in other industries.

Description

technical field [0001] The invention relates to a coal mine goaf crack detection system based on an unmanned aerial vehicle and a crack recognition method thereof, belonging to the field of computer vision. Background technique [0002] In the process of coal mining, with the continuous transportation of underground coal and gangue, coal mine goafs will be formed, and cracks will gradually form in the corresponding surface areas, and eventually surface subsidence will occur, which will seriously damage the environment and even cause life-threatening. Therefore, it is very important to detect the development of cracks in time, which directly affects the economic benefits and personnel safety of coal mining enterprises. [0003] At present, crack detection in coal mine goaf mainly relies on manual inspection. Workers inspect the goaf, and when cracks are found, they take photos and archive them to complete the crack detection. Literature (Zhang Juan, Sha Aimin, Sun Chaoyun, ...

AI Technical Summary

Problems solved by technology

At the same time, combined with the depth semantic information of the image, according to the weight of the image occupied by the cracks in the training data, the loss function is adaptively set, so as to effectively extract image features, improve the efficiency of model training, and effectively solve the problem of surface crack detection in coal mine goafs in complex scenarios , significantly improving the accuracy of surface crack detection

Based on this, this patent is aimed at the coal mine goaf surface with complex background and inconsistent cracks, constructs a crack detection system for drones, designs a crack detection method combined with image depth semantic information, and solves the problem of drones looking down on the aerial perspective The problem of surface crack detection in coal mine goaf

Images