Unmanned aerial vehicle violation building inspection method and device, and storage medium

Abstract

The invention discloses an unmanned aerial vehicle violation building inspection method and device, and a storage medium, and the method comprises the steps: obtaining a violation building video photographed by an unmanned aerial vehicle, obtaining training data from the video, and processing and marking the training data; constructing a training neural network, and training the annotation data set to obtain a training model; controlling the unmanned aerial vehicle to start inspection; calculating an image shot by the unmanned aerial vehicle in real time through the training model to obtain aviolation building category in the image and a relative coordinate of the violation building in the image; planning an inspection route of the unmanned aerial vehicle according to the relative coordinates of each illegal building in the image, and controlling the unmanned aerial vehicle to inspect according to the inspection route; and judging whether the unmanned aerial vehicle completes the inspection of one building, and controlling the unmanned aerial vehicle to return when the unmanned aerial vehicle completes the inspection. The method can improve the recognition efficiency of illegal buildings, and discover illegal buildings in time.

Description

technical field [0001] The invention relates to the technical field of detection of illegal buildings, in particular to a method, equipment and storage medium for inspection of illegal buildings by drones. Background technique [0002] With the rapid development of urban construction, illegal construction phenomena emerge in endlessly, and illegal construction behaviors limit the rapid and harmonious development of cities. Therefore, it is of great significance to actively discover illegal buildings in cities as early as possible and implement demolition monitoring. At the same time, in demolition monitoring, it is also particularly important to be able to grasp the expansion and addition of urban buildings within a period of time in a timely, accurate and intuitive manner. [0003] In terms of technical means, the key to the identification of illegal buildings is to detect the changes of buildings. At present, most of the detection of building changes is through manual ana...

AI Technical Summary

Problems solved by technology

The main disadvantages of the urban building change detection method based on remote sensing images are: (1) low efficiency and easy to miss; (2) it is a comparison method, which requires the planning department to provide the original building planning data for comparison, and the planning data is difficult Easy to obtain; (3) The cost of remote sensing images is high and the resolution is low; (4) Many parameters and thresholds of the comparison algorithm need to be manually defined, and the bit error rate is high

Images