Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Apr 17;20(8):2286.
doi: 10.3390/s20082286.

An Image Registration Method for Multisource High-Resolution Remote Sensing Images for Earthquake Disaster Assessment

Xin Zhao  1   2 , Hui Li  2   3 , Ping Wang  1 , Linhai Jing  2   3
Affiliations

An Image Registration Method for Multisource High-Resolution Remote Sensing Images for Earthquake Disaster Assessment

Xin Zhao et al. Sensors (Basel). .

Abstract

For earthquake disaster assessment using remote sensing (RS), multisource image registration is an important step. However, severe earthquakes will increase the deformation between the remote sensing images acquired before and after the earthquakes on different platforms. Traditional image registration methods can hardly meet the requirements of accuracy and efficiency of image registration of post-earthquake RS images used for disaster assessment. Therefore, an improved image registration method was proposed for the registration of multisource high-resolution remote sensing images. The proposed method used the combination of the Shi_Tomasi corner detection algorithm and scale-invariant feature transform (SIFT) to detect tie points from image patches obtained by an image partition strategy considering geographic information constraints. Then, the random sample consensus (RANSAC) and greedy algorithms were employed to remove outliers and redundant matched tie points. Additionally, a pre-earthquake RS image database was constructed using pre-earthquake high-resolution RS images and used as the references for image registration. The performance of the proposed method was evaluated using three image pairs covering regions affected by severe earthquakes. It was shown that the proposed method provided higher accuracy, less running time, and more tie points with a more even distribution than the classic SIFT method and the SIFT method using the same image partitioning strategy.

Keywords: SIFT; Shi_Tomasi corner detection algorithm; earthquake damage assessment; image registration; multisource high-resolution remote sensing image.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Flowchart of the proposed method.
Figure 2
Figure 2
Tie points obtained using the original multispectral image (a) and the enhanced image obtained using the 2% linear stretch method (b).
Figure 3
Figure 3
Schematic of the image partitioning strategy based on a geographical information constraint: (a) an input image and the image partition of the input image; (b) an image patch F2N (with corners A1, A2, A3, and A4) of the input image; (c) the corresponding reference image patch (with corners B1, B2, B3, and B4) in a pre-earthquake image covering the input image patch.
Figure 4
Figure 4
Schematic of the Shi_Tomasi algorithm.
Figure 5
Figure 5
The orientation histogram of a feature point.
Figure 6
Figure 6
The feature descriptor of a feature point.
Figure 7
Figure 7
Comparison of the spatial distribution of the initial matched tie points (a) and the remaining tie points after removing some tie points with high density (b).
Figure 8
Figure 8
The Wenchuan earthquake dataset. The left (a) is the post-earthquake image (the input image), whereas the right (b) is the reference image in the pre-earthquake database. The points in red are the verification points used for calculating the accuracy of the rectified image.
Figure 9
Figure 9
The Yaan earthquake dataset. The left (a) is the post-earthquake image (the input image), and the right (b) is the reference image in the pre-earthquake database. The points in red are the verification points used for calculating the accuracy of the rectified image.
Figure 10
Figure 10
The Jiuzhaigou earthquake dataset. The left (a) is the post-earthquake image (the input image), and the right (b) is the reference image in the pre-earthquake database. The points in red are the verification points used for calculating the accuracy of the rectified image.
Figure 11
Figure 11
Matched tie points obtained from the Wenchuan dataset. (a) The proposed method; (b) Patch- scale-invariant feature transform (SIFT); and (c) SIFT.
Figure 12
Figure 12
Registered images of the Wenchuan dataset. (a) The original image; (b) registered image using the proposed method; (c) registered image using Patch-SIFT; and (d) registered image using SIFT.
Figure 13
Figure 13
Matched tie points of the GF-1 image. (a) The proposed method, (b) Patch-SIFT, and (c) SIFT.
Figure 14
Figure 14
Registration results of the Yaan dataset. (a) The original image; (b) registered image of the proposed method; (c) registered image of Patch-SIFT; and (d) registered image of SIFT.
Figure 15
Figure 15
Matched tie points of the GF-2 image. (a) The proposed method; (b) Patch-SIFT; and (c) SIFT.
Figure 16
Figure 16
Registered images for the Jiuzhaigou dataset. (a) The original image; (b) the registered image of the proposed method; (c) the registered image of the Patch-SIFT method; and (d) the registered image of the SIFT method.
See this image and copyright information in PMC

References

    1. Dong L., Shan J. A comprehensive review of earthquake-induced building damage detection with remote sensing techniques. ISPRS J. Photogramm. Remote Sens. 2013;84:85–99. doi: 10.1016/j.isprsjprs.2013.06.011. - DOI
    1. Li B., Liu J. Use of shadows for detection of earthquake-induced collapsed buildings in high-resolution satellite imagery. ISPRS J. Photogramm. Remote Sens. 2013;79:53–67.
    1. Corbane C., Carrion D., Lemoine G., Broglia M. Comparison of damage assessment maps derived from very high spatial resolution satellite and aerial imagery produced for Haiti 2010 earthquake. Earthq. Spectra. 2011;27:199–218. doi: 10.1193/1.3630223. - DOI
    1. Pan G., Tang D. Damage information derived from multi-sensor data of the Wenchuan Earthquake of May 2008. Int. J. Remote Sens. 2010;31:3509–3519. doi: 10.1080/01431161003730865. - DOI
    1. Russo F., Rindone C. The planning process and logical framework approach in road evacuation: A coherent vision. Wit Trans. Built Environ. 2011;117:415–425.

LinkOut - more resources