Faculty Profiles - YOSHIDA Keisuke

Papers - YOSHIDA Keisuke

Division display 21 - 40 of about 158 ／ All the affair displays >>

旭川中原橋周辺の河道形状及び植生分布の違いが更正係数に与える影響に関する数値的検討 Reviewed

安達森, 梶川勇樹, 吉田圭介, 西山哲

土木学会論文B1(水工学) 78 ( 2 ) I_1153 - I_1158 2022.11

Drone-LiDAR-assisted Image Fusion methodology for Deep Learning-based Land Cover Classification Reviewed

Shijun PAN, Keisuke YOSHIDA, Takashi KOJIMA, Satoshi NISHIYAMA

Intelligence, Informatics and Infrastructure 3 ( 3 ) 15 - 25 2022.11

Authorship：Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：Japan Society of Civil Engineers

This study uses an unmanned aircraft mounted green Light Detection and Ranging (LiDAR) system to verify the learnability associated with deep learning regarding land cover classification (i.e., evaluated by the average and the absolute difference value of label-based F1, overall accuracy or Macro F1 under the premise of cross-seasonal mutual-prediction). Image fusion method in this study mainly attempts to superimpose the visualized LiDAR data with the aerial photographs to provide new features. LiDAR data are visualized using high contrast color scale (default), average high contrast color scale (same color, different split points as default), and high contrast gray color scale (different color, same split points as default). The reason of setting these methods is to compare the impact of split points and point-associated color in the color scale on learnability of cross-seasonal data. It is worth noting, however from the view of the results, that relying solely on aerial photographs is not sufficient, comparing with image fusion method, especially when training and predicting using cross-seasonal data. From the comparison of the label-based F1, this study has proved the necessary impact of LiDAR on vegetation label-based land cover classification.

DOI： 10.11532/jsceiii.3.3_15

researchmap

YoloV5 analysis for juvenile ayu detection in underwater images of fishway Reviewed

Shijun Pan, Ryo Furutani, Keisuke Yoshida

Proc. of the 2022 Int. Symp. on Ecohydraulics 2022.10

Using airborne lidar bathymetry-aided transfer learning method in riverine land cover classification Reviewed

Shijun Pan, Keisuke Yoshida, Takashi Kojima

Proc. of the 2022 Int. Symp. on Ecohydraulics 2022.10

Developing 3-D numerical flood flow model for vegetated rivers: A case study for lower Asahi River flooding in Japan Reviewed

Md. Touhidul Islam, Keisuke Yoshida, Yuki Kajikawa, Satoshi Nishiyama

Proc. of 39th IAHR World Congress 2022.6

Novel UAV-borne green LiDAR versus traditional airborne LiDAR: A case study to characterize hydraulic and riparian vegetation attributes Reviewed

Md. Touhidul Islam, Keisuke Yoshida, Satoshi Nishiyama, Koichi Sakai

Proc. of 39th IAHR World Congress 2022.6

Airborne LiDAR-assisted deep learning methodology for riparian land cover classification using aerial photographs and its application for flood modelling Reviewed

Keisuke Yoshida, Shijun Pan, Junichi Taniguchi, Satoshi Nishiyama, Takashi Kojima, Md. Touhidul Islam

Journal of Hydroinformatics 24 ( 1 ) 179 - 201 2022.1

Authorship：Lead author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：IWA Publishing

<title>Abstract</title>
In response to challenges in land cover classification (LCC), many researchers have experimented recently with classification methods based on artificial intelligence techniques. For LCC mapping of the vegetated Asahi River in Japan, the current study uses deep learning (DL)-based DeepLabV3+ module for image segmentation of aerial photographs. We modified the existing model by concatenating data on its resultant output port to access the airborne laser bathymetry (ALB) dataset, including voxel-based laser points and vegetation height (i.e. digital surface model data minus digital terrain model data). Findings revealed that the modified approach improved the accuracy of LCC greatly compared to our earlier unsupervised ALB-based method, with 25 and 35% improvement, respectively, in overall accuracy and the macro F1-score for November 2017 dataset (no–leaf condition). Finally, by estimating flow-resistance parameters in flood modelling using LCC mapping-derived data, we conclude that the upgraded DL methodology produces better fit between numerically analyzed and observed peak water levels.

DOI： 10.2166/hydro.2022.134

Scopus

researchmap

Characterizing vegetated rivers using novel unmanned aerial vehicle‐borne topo‐bathymetric green lidar: Seasonal applications and challenges Reviewed

Md. Touhidul Islam, Keisuke Yoshida, Satoshi Nishiyama, Koichi Sakai, Tomoyuki Tsuda

River Research and Applications 38 ( 1 ) 44 - 58 2022.1

UAVレーザ点群と航空写真を併用した深層学習による河道の地被分類法の検討 Reviewed

野村碧都, 吉田圭介, 谷口純一

土木学会論文B1(水工学) 77 ( 2 ) I_913 - I_918 2021.12

旭川の感潮域におけるアユの好適な産卵場の検討 Reviewed

足立真綾, 吉田圭介, 矢島啓, 山下泰司

土木学会論文B1(水工学) 77 ( 2 ) I_1429 - I_1434 2021.12

Flood risk assessment in vegetated lower Asahi River of Okayama Prefecture in Japan using airborne topo-bathymetric LiDAR and depth-averaged flow model Reviewed

Keisuke Yoshida, Kimihisa nagata, Shiro maeno, Koji mano, Satoshi nishiyama, Md. Touhidul Islam

Journal of Hydro-environment Research 39 39 - 59 2021.10

Authorship：Lead author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：Elsevier BV

This paper describes application of airborne LiDAR bathymetry (ALB) with near-infrared and green pulsed lasers for gathering distributed vegetation conditions and topo-bathymetric data for rivers. For the lower Asahi River of Okayama Prefecture in Japan, the ALB data validity was verified using field observation data. This study also examined the applicability of ALB data for numerical simulations of the lower Asahi River flooding in early July 2018 in Japan, comparing simulated and observed data. Results demonstrated that the methodology for this study works well for parameterization of distributed vegetation on a reach scale. This study also applied numerical tests to investigate the effects of vegetation establishment on flood control plans for the lower Asahi River using parameters validated for flood flow simulations. Results demonstrate that the predicted water level markedly exceeds the high water level because of thick vegetation presently established along few-kilometerlong upstream sections of the targeted river reach. Therefore, we conclude that the present findings can support cost-effective management tasks for vegetated rivers.

DOI： 10.1016/j.jher.2021.06.005

Web of Science

researchmap

平成30 年7月豪雨時の旭川分流堰周辺の植生分布を考慮した3次元洪水流解析 Reviewed

吉田圭介,梶川勇樹,永田貴美久,西山哲,間野耕司,堺浩一,Md. Touhidul ISLAM,児子真也

土木学会論文集B1(水工学) 76 ( 2 ) I_985 - I_990 2020.12

Model-induced comparative study of ALB and UAV-borne green LiDAR systems on vegetated lower Asahi river assessment in Japan Reviewed

Md. Touhidul ISLAM, Keisuke YOSHIDA, Koichi SAKAI, Satoshi NISHIYAMA, Tomoyuki TSUDA, Kimishisa NAGATA and Shiro MAENO

土木学会論文集B1(水工学) 76 ( 2 ) I_529 - I_534 2020.12

ALB-ASSISTED DEEP LEARNING OF AERIAL PHOTOGRAPHS FOR LAND-COVER CLASSIFICATION IN RIVERS Reviewed

YOSHIDA Keisuke, TANIGUCHI Junichi, PAN Shijun, KOJIMA Takashi, NAGATA Kimihisa, WATANABE Akihide

Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering) 76 ( 2 ) I_1003 - I_1008 2020.12

Authorship：Lead author,　Corresponding author Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Japan Society of Civil Engineers

Land cover classification (LCC) map in rivers is one of the important fundamental materials for hydraulic research works and practical tasks in terms of both flood control and water environment conservation. Recently, massive flooding because of heavy rainfall motivates hydraulic engineers to estimate the flow capacity at local river sections accurately by re-evaluating the LCC map of the cross-sectional area, vegetation height, and vegetation density, using useful remote sensing methods such as airborne laser bathymetry (ALB). For this work, we developed a new methodology for land cover classification (water area, bare ground, herbaceous species, arborous species, and bamboo grove) in rivers. We used an image processing technique of deep convolutional neural networks (DCNNs) for aerial photographs taken during ALB measurements in conjunction with the dataset of laser point cloud and vegetation height (digital surface model data minus digital terrain model data). We applied our method to two flights of ALB measurement data (in March 2017 and November 2017) for the 4.5 km-long lower reach of the Asahi River. Results showed that our method predicts the LCC map more accurately in case of support of the ALB dataset, especially for detection of herbaceous species, compared with predictions using aerial photographs only. However, if we use different season dataset for learning and prediction processes, classification performance is degraded largely for arborous species because of defoliation.

DOI： 10.2208/jscejhe.76.2_i_1003

CiNii Article

researchmap

Verification of STIV analysis of flood discharge at Nakano observatory in the Ota River by flow analysis using ALB data Reviewed

K. Yoshida, S. Nigo, S. Maeno, K. Mano, M. Nakano

Proc. 22nd IAHR-APD Congress 2020.9

Flood simulation model coupled with woody vegetation wash-out in the lower Asahi River Reviewed

K. Nagata, K. Yoshida, S. Maeno, S. Nigo, MD. T. Islam

Proc. 22nd IAHR-APD Congress 2020.9

Estimation of distributed flow resistance in vegetated rivers using airborne topo-bathymetric LiDAR and its application to risk management tasks for Asahi River flooding Reviewed

Keisuke Yoshida, Shiro Maeno, Shuhei Ogawa, Koji Mano and Shinya Nigo

Journal of Flood Risk Management 13 ( 1 ) e12584 2020.3

植生高分布と限界掃流力を考慮した植生流出を伴う洪水流解析モデルの検討 Reviewed

吉田圭介,前野詩朗,永田貴美久,児子真也,赤穗良輔

土木学会論文集B1(水工学) 75 ( 4 ) I_325 - I_330 2019.12

2018 年7 月西日本豪雨時の岡山県での降雨特性と旭川水系での洪水被害の調査解析 Reviewed

吉田圭介,前野詩朗,工藤亮治,近森秀高,赤穗良輔,小川修平,永田貴美久

土木学会論文集B1(水工学) 75 ( 1 ) 172 - 183 2019.12

FLOOD DISASTER CHARACTERISTICS IN MABI DISTRICT OF KURASHIKI CITY DUE TO HEAVY RAIN IN 2018 AND INVESTIGATION OF FLOODING SCENARIO USING RIVER FLOOD FLOW COMBINED INUNDATION FLOW MODEL Reviewed

MAENO Shiro, AKOH Ryosuke, NIHEI Yasuo, AKAMATSU Yoshihisa, YOSHIDA Keisuke

Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering) 75 ( 1 ) 387 - 402 2019.12

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：Japan Society of Civil Engineers

<p> Due to the heavy rain of July in 2018, several levees of the Oda River flowing through the Mabi district of Kurashiki City and its tributaries, the Suemasa River, the Takama River, and the Madani River, were breached. Inundation area reached 1,200 ha in Mabi district and maximum inundation depth was more than 5 m, and eventually 51 people died there. First, in this study, the inundation state was clarified by the field survey. And flooding scenario was examined using an integrated flooding simulation model that analyzes the flood flow of rivers and the inundation flow from the breaching points. At first, the analysis was performed without breaching condition of levee to estimate the time to start overflowing the levee. Then simulations under breaching condition was carried out to clarify the inundation process. Numerical results of inundation depth show in good agreement with the field surveyed results.</p>

DOI： 10.2208/jscejhe.75.1_387

CiNii Article

researchmap

　 PREV - NEXT 　

< YOSHIDA Keisuke >

Papers - YOSHIDA Keisuke