Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images

02/22/2021
by   Lei Ding, et al.
13

Building extraction in VHR RSIs remains to be a challenging task due to occlusion and boundary ambiguity problems. Although conventional convolutional neural networks (CNNs) based methods are capable of exploiting local texture and context information, they fail to capture the shape patterns of buildings, which is a necessary constraint in the human recognition. In this context, we propose an adversarial shape learning network (ASLNet) to model the building shape patterns, thus improving the accuracy of building segmentation. In the proposed ASLNet, we introduce the adversarial learning strategy to explicitly model the shape constraints, as well as a CNN shape regularizer to strengthen the embedding of shape features. To assess the geometric accuracy of building segmentation results, we further introduced several object-based assessment metrics. Experiments on two open benchmark datasets show that the proposed ASLNet improves both the pixel-based accuracy and the object-based measurements by a large margin. The code is available at: https://github.com/ggsDing/ASLNet

READ FULL TEXT

page 1

page 3

page 4

page 7

page 8

page 10

research
07/21/2020

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

Semi-supervised learning has attracted much attention in medical image s...
research
08/10/2020

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Convolutional Neural Networks (CNNs) are known to rely more on local tex...
research
07/10/2020

Quantization in Relative Gradient Angle Domain For Building Polygon Estimation

Building footprint extraction in remote sensing data benefits many impor...
research
08/01/2022

Accurate Polygonal Mapping of Buildings in Satellite Imagery

This paper studies the problem of polygonal mapping of buildings by tack...
research
04/12/2022

Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape Model

Designing implants for large and complex cranial defects is a challengin...
research
11/07/2018

GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images

Automatic extraction of buildings in remote sensing images is an importa...
research
05/18/2023

Scribble-Supervised Target Extraction Method Based on Inner Structure-Constraint for Remote Sensing Images

Weakly supervised learning based on scribble annotations in target extra...

Please sign up or login with your details

Forgot password? Click here to reset