Abstract

The identification and monitoring of buildings from remotely sensed imagery are of considerable value for urbanization monitoring. Two outstanding issues in the detection of changes in buildings with composite structures and relief displacements are heterogeneous appearances and positional inconsistencies. In this paper, a novel patch-based matching approach is developed using densely connected conditional random field (CRF) optimization to detect building changes from bi-temporal aerial images. First, the bi-temporal aerial images are combined to obtain change information using an object-oriented technique, and then semantic segmentation based on a deep convolutional neural network is used to extract building areas. With the change information and extracted buildings, a graph-cuts-based segmentation algorithm is applied to generate the bi-temporal changed building proposals. Next, in the bi-temporal changed building proposals, corner and edge information are integrated for feature detection through a phase congruency (PC) model, and the structural feature descriptor, called the histogram of orientated PC, is used to perform patch-based roof matching. We determined the final change in buildings by gathering matched roof and bi-temporal changed building proposals using co-refinement based on CRF, which were further classified as “newly built,” “demolished”, or “changed”. Experiments were conducted with two typical datasets covering complex urban scenes with diverse building types. The results confirm the effectiveness and generality of the proposed algorithm, with more than 85% and 90% in overall accuracy and completeness, respectively.

Highlights

  • Automatic building change detection (BCD) from aerial images is a relevant research area in the remote sensing field, as the results are required for a range of applications such as urbanization monitoring, identification of illegal or unauthorized buildings, land use change detection, digital map updating, and route planning [1]

  • The two columns on the left show the bi-temporal aerial images, the third column depicts the results of the proposed method, and the last column provides the building change truths

  • During the process of co-refinement based on conditional random field (CRF), the corresponding roofs representing the unchanged areas are obtained using an effective patch-based matching approach, matching the roofs lacking structure information is fairly difficult and may result in poor performance and even pseudo changes

Read more

Summary

Introduction

Automatic building change detection (BCD) from aerial images is a relevant research area in the remote sensing field, as the results are required for a range of applications such as urbanization monitoring, identification of illegal or unauthorized buildings, land use change detection, digital map updating, and route planning [1]. With the development of remote sensing techniques, an ever-growing number of remote sensing images need to be processed [3]. BCD involves two main procedures: building change generation (BCG) and segmentation of the building change map. As the core part of BCD, BCG aims to highlight changes in the buildings, and it directly affects the accuracy. Segmentation is used to distinguish the changed from unchanged pixels by transforming the building change map into a binary map, which facilitates the evaluation of the accuracy of the BCD

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call