Masashi Matsuoka

Prof. Masashi Matsuoka

Tokyo Institute of Technology
orcid

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2004 in Earthquake Spectra
Verified
Journal Article
Closed access
MMMasashi Matsuoka
Masashi Matsuoka
Fumio YamazakiFumio Yamazaki
Fumio Yamazaki
Synthetic aperture radar (SAR) is remarkable for its capability to record the backscattering coefficient, the physical value of the earth's surface, regardless of weather condition or sun illumination. Therefore, SAR is a powerful tool that can be utilized to develop a universal method to comprehend damaged areas in disasters such as earthquakes, forest fires, and floods. We performed a feasibility study on backscattering characteristics of damaged areas in the 1995 Hyogoken‐Nanbu (Kobe), Japan, earthquake using the pre‐ and post‐event ERS images, revealing that the backscattering coefficient and intensity correlation between the two attained values were significantly lowered in hard‐hit areas. The evaluation, however, was performed without speckle noise reduction. We also investigated the effects of speckle noise reduction and pixel‐window size in evaluating building damage using the difference in the backscattering coefficient and correlation coefficient of the pre‐ and post‐event ERS images. From the analysis, an optimum window size for the damage evaluation was obtained. It was also found that the accuracy of damage detection is not significantly improved for speckle‐reduction filtering of window size larger than 21×21 pixels. We developed an automated method to detect hard‐hit areas based on the discriminant analysis, and compared the detected distribution with a damage survey result.

1 May 2021 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Open access
BABruno Adriano
Bruno Adriano
Naoto YokoyaNaoto Yokoya
Naoto Yokoya
JXJunshi Xia
Junshi Xia
Hiroyuki MiuraHiroyuki Miura
Hiroyuki Miura
WLWen Liu
Wen Liu
SKShunichi Koshimura
Shunichi Koshimura

1 July 2017
Verified
Conference Paper
Closed access
KEKenji Enomoto
Kenji Enomoto
KSKen Sakurada
Ken Sakurada
WWWeimin Wang
Weimin Wang
HFHiroshi Fukui
Hiroshi Fukui
MMMasashi Matsuoka
Masashi Matsuoka
NKNobuo Kawaguchi
Nobuo Kawaguchi
In this paper, we propose a method for cloud removal from visible light RGB satellite images by extending the conditional Generative Adversarial Networks (cGANs) from RGB images to multispectral images. Satellite images have been widely utilized for various purposes, such as natural environment monitoring (pollution, forest or rivers), transportation improvement and prompt emergency response to disasters. However, the obscurity caused by clouds makes it unstable to monitor the situation on the ground with the visible light camera. Images captured by a longer wavelength are introduced to reduce the effects of clouds. Synthetic Aperture Radar (SAR) is such an example that improves visibility even the clouds exist. On the other hand, the spatial resolution decreases as the wavelength increases. Furthermore, the images captured by long wavelengths differs considerably from those captured by visible light in terms of their appearance. Therefore, we propose a network that can remove clouds and generate visible light images from the multispectral images taken as inputs. This is achieved by extending the input channels of cGANs to be compatible with multispectral images. The networks are trained to output images that are close to the ground truth using the images synthesized with clouds over the ground truth as inputs. In the available dataset, the proportion of images of the forest or the sea is very high, which will introduce bias in the training dataset if uniformly sampled from the original dataset. Thus, we utilize the t- Distributed Stochastic Neighbor Embedding (t-SNE) to improve the problem of bias in the training dataset. Finally, we confirm the feasibility of the proposed network on the dataset of four bands images, which include three visible light bands and one near-infrared (NIR) band.

1 September 2007 in Journal of Earthquake and Tsunami
Verified
Journal Article
Closed access
FYFumio Yamazaki
Fumio Yamazaki
MMMasashi Matsuoka
Masashi Matsuoka

1 December 2005 in Earthquake Spectra
Verified
Journal Article
Closed access
Fumio YamazakiFumio Yamazaki
Fumio Yamazaki
YYYoshihisa Yano
Yoshihisa Yano
MMMasashi Matsuoka
Masashi Matsuoka
A strong earthquake struck the city of Bam in southeast Iran on 26 December 2003. The earthquake brought massive destruction to the city and its surrounding rural areas. QuickBird, a high‐resolution satellite, captured a clear image of Bam on 03 January 2004, eight days after the event. The city was also observed by QuickBird on 30 September 2003, about three months before the event. In this paper, using the pre‐event image, the location of individual buildings was registered on GIS and the city blocks surrounded by major roads were assigned. Then, the visual damage interpretation based on the European Macroseismic Scale (EMS‐98) was carried out building by building, comparing the pre‐event and post‐event images. The result of the damage inspection was compared with field survey data, and the accuracy and usefulness of the high‐resolution satellite images in damage detection was demonstrated.

1 August 2009 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Closed access
TVT. Thuy Vu
T. Thuy Vu
Fumio YamazakiFumio Yamazaki
Fumio Yamazaki
MMMasashi Matsuoka
Masashi Matsuoka