研究者詳細 - 吉田　圭介

論文 - 吉田　圭介

分割表示 162 件中 1 - 20 件目／全件表示 >>

Local Low-Altitudes Drone-based Riparian Waste Benchmark Dataset (LAD-RWB): A Case Study on the Asahi River Basin 査読

Shijun PAN, Daichi SHIMOE, Keisuke YOSHIDA, Takashi KOJIMA

Intelligence, Informatics and Infrastructure 6 ( 1 ) 39 - 50 2025年5月

Crack Width Behaviour in a Concrete Retaining Wall Using Deep Learning and Image Processing Technique 査読

Afia Boney, Shosuke Akita, Satoshi Nishiyama, Osamu Murakami, Shijun Pan, Keisuke Yoshida

Intelligence, Informatics and Infrastructure 6 ( 1 ) 117 - 136 2025年5月

Integrating AI Tools into Sponge City Concepts for Enhanced Flood Prevention and Mitigation: A Case Study of the Asahi River 査読

Nicolas SEIBEL, Shijun PAN, Keisuke YOSHIDA, Satoshi NISHIYAMA

Intelligence, Informatics and Infrastructure 6 ( 1 ) 62 - 78 2025年5月

Utilising smartphone-derived photogrammetry 3Dmodel for AI-based top-surfaced asphalt-paved cracks-based instance segmentation and size measurement 査読

Shijun Pan, Keisuke Yoshida, Satoshi Nishiyama

Digital Water 3 ( 1 ) 1 - 20 2025年5月

UAVを活用した河川巡視時のペットボトル検出モデルにおける画像生成AIの応用査読

下江大地, 潘是均, 吉田圭介, 西山哲, 小島崇

土木学会論文集 81 ( 16 ) n/a - n/a 2025年2月

河川カメラ，物体検出AI及び大規模マルチモーダルモデルによる人の河川利用調査の検討査読

山田悠生, 吉田圭介, 潘是均, 小島崇

土木学会論文集 81 ( 16 ) n/a - n/a 2025年2月

Interchangeability of Cross-Platform Orthophotographic and LiDAR Data in DeepLabV3+-Based Land Cover Classification Method 査読

Shijun Pan, Keisuke Yoshida, Satoshi Nishiyama, Takashi Kojima, Yutaro Hashimoto

Land 14 ( 2 ) 217 - 217 2025年1月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：MDPI AG

Riverine environmental information includes important data to collect, and the data collection still requires personnel’s field surveys. These on-site tasks still face significant limitations (i.e., hard or danger to entry). In recent years, as one of the efficient approaches for data collection, air-vehicle-based Light Detection and Ranging technologies have already been applied in global environmental research, i.e., land cover classification (LCC) or environmental monitoring. For this study, the authors specifically focused on seven types of LCC (i.e., bamboo, tree, grass, bare ground, water, road, and clutter) that can be parameterized for flood simulation. A validated airborne LiDAR bathymetry system (ALB) and a UAV-borne green LiDAR System (GLS) were applied in this study for cross-platform analysis of LCC. Furthermore, LiDAR data were visualized using high-contrast color scales to improve the accuracy of land cover classification methods through image fusion techniques. If high-resolution aerial imagery is available, then it must be downscaled to match the resolution of low-resolution point clouds. Cross-platform data interchangeability was assessed by comparing the interchangeability, which measures the absolute difference in overall accuracy (OA) or macro-F1 by comparing the cross-platform interchangeability. It is noteworthy that relying solely on aerial photographs is inadequate for achieving precise labeling, particularly under limited sunlight conditions that can lead to misclassification. In such cases, LiDAR plays a crucial role in facilitating target recognition. All the approaches (i.e., low-resolution digital imagery, LiDAR-derived imagery and image fusion) present results of over 0.65 OA and of around 0.6 macro-F1. The authors found that the vegetation (bamboo, tree, grass) and road species have comparatively better performance compared with clutter and bare ground species. Given the stated conditions, differences in the species derived from different years (ALB from year 2017 and GLS from year 2020) are the main reason. Because the identification of clutter species includes all the items except for the relative species in this research, RGB-based features of the clutter species cannot be substituted easily because of the 3-year gap compared with other species. Derived from on-site reconstruction, the bare ground species also has a further color change between ALB and GLS that leads to decreased interchangeability. In the case of individual species, without considering seasons and platforms, image fusion can classify bamboo and trees with higher F1 scores compared to low-resolution digital imagery and LiDAR-derived imagery, which has especially proved the cross-platform interchangeability in the high vegetation types. In recent years, high-resolution photography (UAV), high-precision LiDAR measurement (ALB, GLS), and satellite imagery have been used. LiDAR measurement equipment is expensive, and measurement opportunities are limited. Based on this, it would be desirable if ALB and GLS could be continuously classified by Artificial Intelligence, and in this study, the authors investigated such data interchangeability. A unique and crucial aspect of this study is exploring the interchangeability of land cover classification models across different LiDAR platforms.

DOI： 10.3390/land14020217

researchmap

Trials of Night-Time 4K-Camera-based Human Action Recognition in Riverine Environments with Multimodal and Object Detection Technologies 査読

Shijun PAN, Keisuke YOSHIDA, Yuki YAMADA, Takashi KOJIMA

Intelligence, Informatics and Infrastructure 5 ( 1 ) 89 - 97 2024年11月

Generating 3D Models for UAV-Based Detection of Riparian PET Plastic Bottle Waste: Integrating Local Social Media and InstantMesh 査読

Shijun PAN, Keisuke YOSHIDA, Daichi SHIMOE, Takashi KOJIMA, Satoshi NISHIYAMA

Drones 8 ( 9 ) 471 2024年9月

Assessment of spawning habitat suitability for Amphidromous Ayu (Plecoglossus altivelis) in tidal Asahi River sections in Japan: Implications for conservation and restoration 査読

Keisuke Yoshida, Hiroshi Yajima, Md. Touhidul Islam, Shijun Pan

River Research and Applications 40 ( 8 ) 1497 - 1511 2024年6月

担当区分：筆頭著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Wiley

Abstract

The Amphidromous Ayu (Plecoglossus altivelis), vital for Japan's riverine commercial fisheries, is experiencing population decline due to habitat degradation. In response, Japan is implementing restoration efforts by releasing juvenile fish and cultivating spawning habitats. This study, focusing on the Asahi River's Heidan area, evaluates Ayu spawning habitat suitability, especially in tidal zones, and its conservation implications. Through field surveys and numerical analysis, the research identifies optimal conditions for spawning amid dwindling numbers. Observations from the 2020 peak spawning season showed that water temperatures below 20°C are conducive to spawning, with the best sites producing up to 48,817 eggs/m². Gravel sizes between 0.85 and 53.0 mm were identified as crucial for effective spawning. Notably, artificial spawning grounds established in 2019 showed no spawning activity, likely due to saline intrusion from tides. Using the three‐dimensional hydrodynamic‐aquatic ecosystem numerical model, the study assesses flow, substrate, and water quality's impact on spawning, corroborated by sensor data. A key finding is the negative correlation between salinity and egg density in tidal sections of the Asahi River. Furthermore, an artificial intelligence (AI)‐based YOLOv5 model, trained on underwater images, effectively detected Ayu aggregations, demonstrating an F1‐score of 0.757 in differentiating Ayu from other coexisting fish species in the same aquatic environment. This AI approach provides a nonintrusive method for monitoring Ayu populations and habitat preferences. The research underlines that successful spawning habitats require minimal saline intrusion, with optimal salinity and flow conditions. These insights are critical for spawning ground development, emphasizing the management of tidal effects and riverbed conditions to bolster Ayu populations and preserve aquatic ecosystems.

DOI： 10.1002/rra.4329

researchmap

Monitoring Human Activities in Riverine Space using 4K Camera Images with YOLOv8 and LLaVA: A Case Study from Ichinoarate in the Asahi River 査読

Shijun PAN, Keisuke YOSHIDA, Yuki YAMADA, Takashi KOJIMA

Intelligence, Informatics and Infrastructure 5 89 - 97 2024年5月

Comprehensive Analysis of On-Site Riparian Waste Pollution: A Case Study on the Hyakken River Basin 査読

Shijun PAN, Keisuke YOSHIDA, Takashi KOJIMA

Intelligence, Informatics and Infrastructure 5 98 - 103 2024年5月

航空レーザ計測と洪水解析による植生抗力の３次元分布推定と竹林倒伏・木本流失の再現計算査読

古谷崚, 吉田圭介, 岡田拓巳, 梶川勇樹, 西山哲

土木学会論文集 80 ( 16 ) 23-16161 2024年

ランダムフォレストを用いた多波長励起蛍光光度計による植物プランクトンの組成分類査読

矢島啓, 藤井陽, 管原庄吾, 吉田圭介

土木学会論文集 80 ( 16 ) 23-16032 2024年

ノリ養殖漁場でのクロダイの食害把握に向けた水中画像の深層学習と教師データ基準の検討査読

吉田圭介, 潘是均, 横山貴洋, 山下泰司, 上田勇輝, 杉野博之, 小島崇

土木学会論文集 80 ( 16 ) 23-16150 2024年

Mutual validation of remote hydraulic estimates and flow model simulations using UAV-borne LiDAR and deep learning-based imaging techniques 査読

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

Results in Engineering 20 101415 - 101415 2023年12月

Detection and Segmentation of Riparian Asphalt Paved Cracks Using Drone and Computer Vision Algorithms 査読

Shijun PAN, Keisuke YOSHIDA, Satoshi NISHIYAMA

Intelligence, Informatics and Infrastructure 4 ( 2 ) 35 - 49 2023年12月

Application of the Prompt Engineering-assisted Generative AI for the Drone-based Riparian Waste Detection 査読

Shijun PAN, Keisuke YOSHIDA, Takashi KOJIMA

Intelligence, Informatics and Infrastructure 4 ( 2 ) 50 - 59 2023年12月

Three-dimensional numerical modelling of floods in river corridor with complex vegetation quantified using airborne LiDAR imagery 査読

Keisuke Yoshida, Yuki Kajikawa, Satoshi Nishiyama, Md. Touhidul Islam, Shin Adachi, Koichi Sakai

Journal of Hydraulic Research 61 ( 1 ) 88 - 108 2023年1月

Promises and uncertainties in remotely sensed riverine hydro‐environmental attributes: Field testing of novel approaches to unmanned aerial vehicle‐borne lidar and imaging velocimetry 査読

Md. Touhidul Islam, Keisuke Yoshida, Satoshi Nishiyama, Koichi Sakai, Shin Adachi, Shijun Pan

River Research and Applications 38 ( 10 ) 1757 - 1774 2022年12月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Wiley

Recent advancements in remotely sensed techniques have markedly expanded data acquisition potential in riverine studies, but the techniques' applicability must be validated and improved because of uncertainties associated with diverse field conditions. This study is the first experimental evidence of using a newly designed unmanned aerial vehicle (UAV)-borne green lidar system (GLS) and deep learning-automated space–time image velocimetry (STIV) for remote investigation of hydraulic and vegetation quantities of the gravel-bed Asahi River in Okayama Prefecture, Japan. In addition to identifying bed deformation in waters shallower than 2 m, the GLS point clouds characterized the submerged infrastructure with block detailing patterns, thereby identifying positional displacement and severely damaged parts. This paper also presents a noncontact method of estimating incremental river discharge. Compared to benchmarked flow model estimates, remotely sensed discharges for three transects covering shallower, deeper, and partially submerged woody vegetation areas were overestimated by 1–11%, with 4% underestimation for another cross-section. The STIV analysis also showed complicated flow patterns that were reasonably confirmed by flow vectors from depth-averaged modeling. Ultimately, depth-averaged flow model estimates validated hydraulic parameters derived remotely from GLS and STIV, and vice versa. In addition to approximating vegetation growth rates, the study using GLS attributes accurately identified riparian vegetation types as herbaceous (70%), woody (86%), and bamboo groves (65%). Finally, our findings provide insight into the management of shallow clear-flowing vegetated rivers and remote sensing of streamflow to validate hydrodynamic-numerical methods.

DOI： 10.1002/rra.4042

Scopus

researchmap

その他リンク： https://onlinelibrary.wiley.com/doi/full-xml/10.1002/rra.4042

　前のページ - 次のページ　

<吉田 圭介>

論文 - 吉田 圭介

<吉田　圭介>

論文 - 吉田　圭介