Environmental soil detection method and device

Abstract

The embodiment of the invention provides an environmental soil detection method and device. An environment soil image set shot by an unmanned aerial vehicle is acquired, and an initial soil area of each environment soil image in the environment soil image set is extracted; extracting key feature points of the soil boundary in the initial soil area according to a pre-trained neural network model; removing the environmental soil image in the mistakenly detected soil area when it is detected that the mistakenly detected soil area exists in the initial soil area according to the depth characteristic of the area corresponding to each key characteristic point; and carrying out detection marking on the environmental soil image and the shooting information when the environmental soil image is shot, so as to obtain an environmental soil image set after false detection optimization. Therefore, the misunderstanding rate of soil detection can be effectively controlled, the influence on the subsequent soil boundary area comparison and recognition functions when a large number of soil images are mistakenly detected is avoided, and the manual troubleshooting cost is reduced.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an environmental soil detection method and device. Background technique [0002] At present, it is necessary to strengthen the detection of environmental soil. Environmental soil detection can guide farmers to choose suitable fertilizers to make saplings and crops grow better. It can also develop unknown sites for planting, so that soil resources can be fully utilized. use. In areas with serious soil pollution, it is necessary to strengthen management and pollution prevention and control to gradually alleviate soil pollution. [0003] At present, in the process of soil detection, how to control the false detection rate of soil detection has always been a major problem. When a large number of false detection soil images appear, it will greatly affect the subsequent comparison and identification of soil boundary areas, and increase the cost of manual inspection. Contents of th...

AI Technical Summary

Problems solved by technology

[0003] At present, in the process of soil detection, how to control the false detection rate of soil detection has always been a major problem. When a large number of false detection soil images appear, it will greatly affect the subsequent comparison and identification of soil boundary areas, and increase the cost of manual investigation.

Images