Weakly supervised building segmentation method taking reliable region as attention mechanism supervision

Abstract

The invention discloses a weak supervision building segmentation method taking a reliable region as attention mechanism supervision, and the method comprises the following steps: constructing a weak supervision semantic segmentation network which comprises a first classification network and a reliable region synthesis module, a second classification network, a pixel attention module, a class activation mapping calculation module, a twin network structure and a loss function design module; building images and manually-marked classification labels are obtained to serve as a training set, the training set is used for training the classification network to obtain initial seeds, and the initial seeds are input into a reliable region synthesis module to obtain reliable labels; training a class activation mapping module based on the pixel attention module and the twin network structure by using the training set to obtain class activation mapping; and finally, taking the generated reliable label as supervision of class activation mapping to obtain a pseudo label, and training an existing network by using the pseudo label to obtain a final building segmentation result. According to the method, pixel-level semantic segmentation is realized only through classification labels.

Description

technical field [0001] The invention belongs to the field of image segmentation, and in particular relates to a weakly supervised building segmentation method in which a reliable region is supervised by an attention mechanism. Background technique [0002] With the development of sensor technology and UAV technology, the use of UAVs to obtain building footprints has become an important research direction in high-resolution image segmentation and target detection in recent years. It is widely used in digital cities, military reconnaissance, disaster assessment and other fields. In recent years, with the development of deep neural networks, the task of semantic segmentation has made great progress, but a big challenge in this field is the lack of large-scale pixel-level segmentation labels. At present, the task of semantic segmentation mainly faces low However, there are few researches in the field of remote sensing. The main reason is that the transformation from natural sce...

AI Technical Summary

Problems solved by technology

Although CAM can identify the most salient regions of the target object, CAM has three main obstacles that prevent it from being directly used as a pseudo-label for segmentation network training: (1) Underactivation: CAM usually only covers the most salient part of the object instead of responding to the entire area of ​​the object

Images