Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm

Y. G. Li, Guangqi Chen, C. Tang, L. Zheng, B. Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We developed a two-step detection approach to map landslides in Chenjiaba area, Beichuan County, Sichuan Province, China after the 2008 Wenchuan earthquake and a strong rainfall four months later. First, the variance information was assessed by image fusion technique. Different from traditional usage of image fusion technique, this paper aims to enhance the interesting features through combing multispectral image with high resolution and panchromatic image with relatively lower resolution. Four fusion technologies (PCA, Brovey, IHS and Wavelet) were tested. All the results contain the spectrum information of both earthquake and rainfall-induced landslides, except the one by wavelet transform based fusion method. The fusion results were assessed by visual inspection and IHS transform based fusion image shows the best performance. Second, fusion image was semi-automatically interpreted. The image interpretation was based on object-oriented analysis which not only the spectral information in pixel-based method was considered, but also the spatial and texture information of the image. Various landscape elements were classified by K Nearest Neighbor algorithm for landslide detection. Accuracy assessment was carried out by comparing those extracted ones with a manually prepared landslide inventory map. Results showed that this approach is capable of mapping different temporal landslides quickly and efficiently.

Original languageEnglish
Title of host publication46th US Rock Mechanics / Geomechanics Symposium 2012
Pages2830-2837
Number of pages8
Volume4
Publication statusPublished - Dec 1 2012
Event46th US Rock Mechanics / Geomechanics Symposium 2012 - Chicago, IL, United States
Duration: Jun 24 2012Jun 27 2012

Other

Other46th US Rock Mechanics / Geomechanics Symposium 2012
CountryUnited States
CityChicago, IL
Period6/24/126/27/12

Fingerprint

rainstorm
Landslides
Image fusion
landslide
Earthquakes
earthquake
Rain
wavelet
transform
panchromatic image
Sichuan earthquake 2008
rainfall
accuracy assessment
multispectral image
Wavelet transforms
Textures
Inspection
Pixels
automatic detection
pixel

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology

Cite this

Li, Y. G., Chen, G., Tang, C., Zheng, L., & Wang, B. (2012). Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm. In 46th US Rock Mechanics / Geomechanics Symposium 2012 (Vol. 4, pp. 2830-2837)

Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm. / Li, Y. G.; Chen, Guangqi; Tang, C.; Zheng, L.; Wang, B.

46th US Rock Mechanics / Geomechanics Symposium 2012. Vol. 4 2012. p. 2830-2837.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, YG, Chen, G, Tang, C, Zheng, L & Wang, B 2012, Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm. in 46th US Rock Mechanics / Geomechanics Symposium 2012. vol. 4, pp. 2830-2837, 46th US Rock Mechanics / Geomechanics Symposium 2012, Chicago, IL, United States, 6/24/12.
Li YG, Chen G, Tang C, Zheng L, Wang B. Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm. In 46th US Rock Mechanics / Geomechanics Symposium 2012. Vol. 4. 2012. p. 2830-2837
Li, Y. G. ; Chen, Guangqi ; Tang, C. ; Zheng, L. ; Wang, B. / Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm. 46th US Rock Mechanics / Geomechanics Symposium 2012. Vol. 4 2012. pp. 2830-2837
@inproceedings{4812e33be7064340994f96498707863f,
title = "Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm",
abstract = "We developed a two-step detection approach to map landslides in Chenjiaba area, Beichuan County, Sichuan Province, China after the 2008 Wenchuan earthquake and a strong rainfall four months later. First, the variance information was assessed by image fusion technique. Different from traditional usage of image fusion technique, this paper aims to enhance the interesting features through combing multispectral image with high resolution and panchromatic image with relatively lower resolution. Four fusion technologies (PCA, Brovey, IHS and Wavelet) were tested. All the results contain the spectrum information of both earthquake and rainfall-induced landslides, except the one by wavelet transform based fusion method. The fusion results were assessed by visual inspection and IHS transform based fusion image shows the best performance. Second, fusion image was semi-automatically interpreted. The image interpretation was based on object-oriented analysis which not only the spectral information in pixel-based method was considered, but also the spatial and texture information of the image. Various landscape elements were classified by K Nearest Neighbor algorithm for landslide detection. Accuracy assessment was carried out by comparing those extracted ones with a manually prepared landslide inventory map. Results showed that this approach is capable of mapping different temporal landslides quickly and efficiently.",
author = "Li, {Y. G.} and Guangqi Chen and C. Tang and L. Zheng and B. Wang",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9781622765140",
volume = "4",
pages = "2830--2837",
booktitle = "46th US Rock Mechanics / Geomechanics Symposium 2012",

}

TY - GEN

T1 - Automatic detection of landslides induced by the Wenchuan earthquake and subsequent rainstorm

AU - Li, Y. G.

AU - Chen, Guangqi

AU - Tang, C.

AU - Zheng, L.

AU - Wang, B.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We developed a two-step detection approach to map landslides in Chenjiaba area, Beichuan County, Sichuan Province, China after the 2008 Wenchuan earthquake and a strong rainfall four months later. First, the variance information was assessed by image fusion technique. Different from traditional usage of image fusion technique, this paper aims to enhance the interesting features through combing multispectral image with high resolution and panchromatic image with relatively lower resolution. Four fusion technologies (PCA, Brovey, IHS and Wavelet) were tested. All the results contain the spectrum information of both earthquake and rainfall-induced landslides, except the one by wavelet transform based fusion method. The fusion results were assessed by visual inspection and IHS transform based fusion image shows the best performance. Second, fusion image was semi-automatically interpreted. The image interpretation was based on object-oriented analysis which not only the spectral information in pixel-based method was considered, but also the spatial and texture information of the image. Various landscape elements were classified by K Nearest Neighbor algorithm for landslide detection. Accuracy assessment was carried out by comparing those extracted ones with a manually prepared landslide inventory map. Results showed that this approach is capable of mapping different temporal landslides quickly and efficiently.

AB - We developed a two-step detection approach to map landslides in Chenjiaba area, Beichuan County, Sichuan Province, China after the 2008 Wenchuan earthquake and a strong rainfall four months later. First, the variance information was assessed by image fusion technique. Different from traditional usage of image fusion technique, this paper aims to enhance the interesting features through combing multispectral image with high resolution and panchromatic image with relatively lower resolution. Four fusion technologies (PCA, Brovey, IHS and Wavelet) were tested. All the results contain the spectrum information of both earthquake and rainfall-induced landslides, except the one by wavelet transform based fusion method. The fusion results were assessed by visual inspection and IHS transform based fusion image shows the best performance. Second, fusion image was semi-automatically interpreted. The image interpretation was based on object-oriented analysis which not only the spectral information in pixel-based method was considered, but also the spatial and texture information of the image. Various landscape elements were classified by K Nearest Neighbor algorithm for landslide detection. Accuracy assessment was carried out by comparing those extracted ones with a manually prepared landslide inventory map. Results showed that this approach is capable of mapping different temporal landslides quickly and efficiently.

UR - http://www.scopus.com/inward/record.url?scp=84873243730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873243730&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781622765140

VL - 4

SP - 2830

EP - 2837

BT - 46th US Rock Mechanics / Geomechanics Symposium 2012

ER -