Post-classification building change detection method based on a semantic edge

Abstract

The invention discloses a post-classification building change detection method based on a semantic edge, and the method comprises the steps: carrying out the learning of a building sample through a semantic edge detection model based on a convolutional neural network, obtaining the building edge information of two corresponding images through model prediction, and carrying out the synthesis of the two edge images, and obtaining a binary image containing all building edge information. In this way, more details of the building edge contour are reserved through mutual complementation of the building edges of the two stages, the difference of image sources is neglected, and therefore building change detection on remote sensing images with different resolutions and different sources is achieved. At present, all algorithms related to change detection have the problems of high registration requirements, capability of being only used on specific data and low accuracy, and according to the method, the registration requirements are reduced to a certain extent through an image registration algorithm, and due to a post-classification mode, the adaptability to the data is higher.

Description

technical field [0001] The invention belongs to the technical field of change detection for buildings in remote sensing images, and in particular relates to a change detection method for post-classified buildings based on semantic edges. Background technique [0002] With the increase of urban construction, higher requirements are placed on the level of government governance of the city. The change detection of buildings in the city can not only detect illegal buildings in time, but also play an important role in maintaining the sustainable development of the city. However, traditional building change detection is often achieved through manual labeling. This method is not only very time-consuming and labor-intensive, but also cannot manually label large areas of the city. With the research of change detection algorithm, it also provides the possibility for the realization of building change detection in a large area of ​​the city. [0003] Today's algorithms for building c...

Images