Method and system for detecting change to structure by using drone

Abstract

Disclosed herein is a method for an image analysis server to detect a change to a structure by using a drone. The method for an image analysis server to detect a change to a structure by using a drone includes: receiving images of a specific inspection target structure taken at different time points by a drone; detecting the difference between an image taken at a first time point and an image taken at a second time point based on the received images; and detecting a change to the inspection target structure via the detected difference, and generating a risk signal and then transmitting it to an administrator terminal.

1 . A method for an image analysis server to detect a change to a structure by using a drone, the method comprising:
 receiving images of a specific inspection target structure taken at different time points by a drone;   detecting a difference between an image taken at a first time point and an image taken at a second time point based on the received images; and   detecting a change to the inspection target structure via the detected difference, and generating a risk signal and then transmitting it to an administrator terminal,   wherein detecting the difference comprises acquiring feature maps for respective images by learning an image taken first for the specific inspection target structure and images taken at different time points thereafter by using a machine learning algorithm, and   acquiring a difference between the feature map acquired based on the image taken first and the feature map acquired based on each of the images taken thereafter by using a Euclidean distance analysis method.   
     
     
         2 . (canceled) 
     
     
         3 . The method of  claim 1 , further comprising predicting a change pattern of the specific inspection target structure in a future based on a plurality of images of the specific inspection target structure taken at different time points. 
     
     
         4 . The method of  claim 1 , wherein generating the risk signal and then transmitting it comprises generating a risk signal when an area of a detected change area or an area value of a change per unit time is equal to or larger than a preset value. 
     
     
         5 . A system for detecting a change to a structure by using a drone, the system comprising:
 an image acquisition unit configured to receive images of a specific inspection target structure taken at different time points by a drone;   an image learning unit configured to detect a difference between an image taken at a first time point and an image taken at a second time point based on the received images; and   a change detection unit configured to detect a change to the inspection target structure via the detected difference, and generating a risk signal and then transmitting it to an administrator terminal,   wherein the image learning unit is further configured to acquire feature maps for respective images by learning an image taken first for the specific inspection target structure and images taken at different time points thereafter by using a machine learning algorithm, and acquire a difference between the feature map acquired based on the image taken first and the feature map acquired based on each of the images taken thereafter by using a Euclidean distance analysis method.