Mine and solid waste landfill automatic extraction method and device based on remote sensing data

Abstract

The invention discloses a mine and solid waste landfill automatic extraction method and device based on remote sensing data, and belongs to the field of environment monitoring. The method comprises the following steps: acquiring a sub-meter remote sensing image and a thermal infrared remote sensing image, calculating a normalized vegetation index and a specific value building index by using the sub-meter remote sensing image, and extracting a non-vegetation coverage area and a non-building area; inversing the surface temperature by using the thermal infrared remote sensing image, fitting a normal distribution curve based on a surface temperature value, and extracting a high-temperature abnormal region; based on the high-temperature abnormal area extraction result, removing vegetation coverage areas and building areas, and obtaining pattern spot information of mines and solid waste landfills; and establishing a classification model, carrying out secondary classification on the information of the mine and the solid waste landfill, and obtaining the mine and the solid waste landfill through grid vectorization processing. According to the invention, automatic extraction of the mine and the solid waste landfill is realized, the labor cost and the time cost are greatly reduced, the working efficiency is improved, and technical support is provided for environmental pollution source supervision.

Description

technical field [0001] The invention relates to the field of environmental monitoring, in particular to a method and device for automatically extracting mines and solid waste landfills based on remote sensing data. Background technique [0002] my country is a country rich in mineral resources, and rich mineral resources are one of the main factors that promote the automatic development of my country's economy, but at the same time, large-scale development has also caused a large number of ecological and environmental problems. Remote sensing monitoring data show that by the end of 2018, my country's mines occupied and damaged more than 54 million mu of land, and historical mines occupied and damaged more than 34 million mu. The destruction of mountains and vegetation caused by mining is often the main factor that induces landslides, mountain torrents and other disasters and subsidence accidents. Therefore, in order to thoroughly implement the idea of ​​ecological civilizat...

AI Technical Summary

Problems solved by technology

The ground survey method is costly and inefficient, and some illegal mines and landfills have not been registered, coupled with traffic, geographical and other constraints, making the investigation work extremely difficult

Remote sensing survey methods are mainly divided into artificial visual interpretation and machine learning extraction. Among them, although the artificial visual interpretation method can extract ground object information more accurately, it has a large workload and low efficiency, and the extraction accuracy depends on the solution. According to the experience of translators, machine learning extraction requires a large number of samples for training, and the labor cost is relatively high. Both methods are difficult to meet the needs of daily supervision and emergency response

Images