Yusuke Adachi

Mr. Yusuke Adachi


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
8 May 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YAYusuke Adachi
Yusuke Adachi
RKRyota Kikuchi
Ryota Kikuchi
KOKenta Obata
Kenta Obata
HYHiroki Yoshioka
Hiroki Yoshioka
This study introduced a data screening method for comparing the reflectances in middle latitude forest regions collected by a Geostationary Earth Observing (GEO) satellite and a Low Earth Orbit (LEO) satellite. This method attempts to reduce the differences between the relative azimuth angles of the GEO and LEO observations. The method, called relative azimuthal-angle matching (RAM), takes advantage of the high temporal resolution of the GEO satellites, which enables collection of a wide range of relative azimuth angles within a day. The performance of the RAM method was evaluated using data in the visible and near-infrared bands collected by the Himawari-8/Advanced Himawari Imager (AHI) and the Terra/Moderate Resolution Imaging Spectroradiometer (MODIS). The consistency of the reflectance pairs of MODIS and AHI selected by the RAM method was compared with the consistency of the reflectance pairs acquired simultaneously by the two sensors. The data were matched pixel-by-pixel after applying atmospheric corrections and cloud screening. The results show that RAM improved the reflectance ratio by approximately 10% for the red and NIR bands on average relative to the simultaneous observations. Significant improvements in the two bands were observed (20%), especially among data collected in the fall and winter. Performance of RAM depends largely on season. Especially in summer, the reflectance pair chosen by RAM showed less consistency than solar zenith-angle matching (SZM). The results also indicated the relatively large influence of the spectral response functions on the green and red bands of the two sensors.

19 July 2019 in Robotics
Verified
Journal Article
Open access
PDF file
YAYusuke Adachi
Yusuke Adachi
MIMasahide Ito
Masahide Ito
TNTadashi Naruse
Tadashi Naruse
This paper addresses a strategy learning problem in the RoboCupSoccer Small Size League (SSL). We propose a novel method based on action sequences to cluster an opponent’s strategies online. Our proposed method is composed of the following three steps: (1) extracting typical actions from geometric data to make action sequences, (2) calculating the dissimilarity of the sequences, and (3) clustering the sequences by using the dissimilarity. This method can reduce the amount of data used in the clustering process; handling action sequences instead of geometric data as data-set makes it easier to search actions. As a result, the proposed clustering method is online feasible and also is applicable to countering an opponent’s strategy. The effectiveness of the proposed method was validated by experimental results.

19 May 2017
Verified
Conference Paper
Open access
PDF file
YAYusuke Adachi
Yusuke Adachi
NONaoya Onimura
Naoya Onimura
TYTakanori Yamashita
Takanori Yamashita
SHSachio Hirokawa
Sachio Hirokawa

1 November 2017
Verified
Book Chapter
Closed access
PDF file
YAYusuke Adachi
Yusuke Adachi
MIMasahide Ito
Masahide Ito
TNTadashi Naruse
Tadashi Naruse

22 October 2018
Verified
Conference Paper
Closed access
PDF file
HYHiroki Yoshioka
Hiroki Yoshioka
YAYusuke Adachi
Yusuke Adachi
RKRyota Kikuchi
Ryota Kikuchi
MMMasayuki Matsuoka
Masayuki Matsuoka
KIKazuhito Ichii
Kazuhito Ichii
The combinatorial use of geostationary and polar-orbiting satellites is expected to provide a new approach to Earth observation with a wide range of applications; however, differences in the observation conditions and sensor specifications can introduce biases into the outputs of the various satellites. These differences are also known to depend on the land cover type, and this feature of the data requires thorough investigation. This study compared the solar reflective bands measured by the Advanced Himawari Imager (AHI) and an established sensor MODIS onboard Terra satellite. The comparison was made using data collected over a forested region on the Shikoku Island (30 km by 140 km) located in the south of Japan under similar view zenith angles of approximately 40 degrees. The reflectances of the visible and near-infrared bands (four bands) were processed to correct the molecular scattering and ozone absorption effect. A comparison was made before and after the atmospheric correction. Our results showed that the reflectance differences over the region fell mainly within the relevant standard deviations (reflectance variations within the relevant region), except for the green band. The larger difference between the green band reflectances measured by the two sensors was attributed to differences in the band positions. The band-4 of MODIS (green) covers 545-565 nm, whereas the AHI counterpart (band-2) covers 490-530 nm, providing little overlap with MODIS. These results suggested that special caution is needed when using data collected from these two sensors simultaneously or continuously if the green band is involved in the algorithm.

1 July 2018
Verified
Conference Paper
Closed access
KTKenta Taniguchi
Kenta Taniguchi
YAYusuke Adachi
Yusuke Adachi
KOKenta Obata
Kenta Obata
HYHiroki Yoshioka
Hiroki Yoshioka
Estimation of soil brightness from a reflectance spectrum involves a radiative transfer model that describes a canopy-soil system of layers. An assumption of soil line in the model becomes a source of error for the estimation of soil brightness. This study investigates the influences of soil line parameters (slope and NIR intercept) on estimation of soil brightness underneath the vegetation canopy. The investigation was carried out based on a theory of inter-band relationship under the constant soil brightness, which is known as the soil `isoline' equations. Simulation datasets from EO-l/Hyperion hyperspectral data were used to compare inversion results by varying the intercept and slope of the soil line. The result indicates several trends of the brightness estimation caused by the variations of soil line parameters. Since the soil line is known to be varied sensor by sensor, the trends clarified in this study would be beneficial to calibration of multiple soil isoline equations for inter-sensor calibration of the satellite sensors in the context of mega satellite constellation.