Typical battlefield infrared background detection method based on multi band fusion DOI Creative Commons
Bentian Hao, Weidong Xu, Xin Yang

и другие.

Deleted Journal, Год журнала: 2024, Номер 6(12)

Опубликована: Дек. 2, 2024

Intelligent battlefield environment recognition is crucial for active camouflage technology. Enhancing detection capabilities various environments essential target survival. Traditional systems, relying on single visible light or infrared bands, face challenges like low performance and limited information use due to lighting conditions, making them inadequate all-weather detection. This study presents a multi-modal feature fusion network model using typical background database. It employs coordinated attention mechanism spatial optimizes dense dual-path networks improve the of optical images. The achieves 97.57% accuracy, 4.16% higher than best single-modal results. boosts accuracy by 2.68%. Thus, effectively integrates data, showing strong in classifying detecting backgrounds.

Язык: Английский

Development of a HAND-based flood risk assessment tool in Google Earth Engine for a data-scarce region in the US DOI Creative Commons
Jobin Thomas,

S. Sujatha Mohan,

Saumik Mallik

и другие.

Journal of Great Lakes Research, Год журнала: 2025, Номер unknown, С. 102510 - 102510

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

1

Challenges of earth remote sensing data during geological exploration DOI
Andrey Samsonov,

Yu. A. Churikov,

A. R. Ibragimov

и другие.

International Journal of Environmental Science and Technology, Год журнала: 2025, Номер unknown

Опубликована: Май 10, 2025

Язык: Английский

Процитировано

0

An Integrated Framework for Actionable Flood Warnings on Road Structures Using High Resolution Satellite Imagery DOI Creative Commons
Zhouyayan Li, Bekir Zahit Demiray, Marian Muste

и другие.

EarthArXiv (California Digital Library), Год журнала: 2024, Номер unknown

Опубликована: Авг. 17, 2024

Floods rank among the most devastating natural hazards globally. Unlike many other calamities, floods typically occur in densely populated regions, resulting immediate and long-term adverse impacts on communities, including fatalities, injuries, health risks, significant economic environmental losses annually. Traditional flood models, while useful, are constrained by simplifying assumptions, numerical approximations, a lack of sufficient data for accurate simulations. Recent advancements data-efficient Digital Elevation Model (DEM) Terrain (DTM) based models show promise overcoming some these limitations. However, models' reliance DEM or DTM renders them sensitive to dynamic nature Earth's surface. This study investigates effectiveness remote sensing imagery inundation mapping, focusing role high-resolution commercial optical PlanetScope images data-limited scenarios. To address early-stage reflectance issues attributed on-board calibration constellations, we introduced novel post-processing workflow, Quantile-based Filling Refining (QFR). Our results indicate that initial extent maps produced using widely adopted Normalized Difference Water Index (NDWI) were inferior manual delineations comparable those generated only Near-Infrared (NIR) band, which also suffers from flaws. NIR band processed with QFR significantly outperformed delineations. research demonstrates potential precise particularly at smaller scales, such as urban areas. Additionally, it underscores workflow's enhancing prediction accuracy, offering streamlined scalable method improving modeling outcomes.

Язык: Английский

Процитировано

0

CataEx: a multi-task export tool for the Google Earth Engine data catalog DOI Creative Commons
Gisela Domej, Kacper Pluta, Marek Ewertowski

и другие.

Environmental Modelling & Software, Год журнала: 2024, Номер unknown, С. 106227 - 106227

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

0

Typical battlefield infrared background detection method based on multi band fusion DOI Creative Commons
Bentian Hao, Weidong Xu, Xin Yang

и другие.

Deleted Journal, Год журнала: 2024, Номер 6(12)

Опубликована: Дек. 2, 2024

Intelligent battlefield environment recognition is crucial for active camouflage technology. Enhancing detection capabilities various environments essential target survival. Traditional systems, relying on single visible light or infrared bands, face challenges like low performance and limited information use due to lighting conditions, making them inadequate all-weather detection. This study presents a multi-modal feature fusion network model using typical background database. It employs coordinated attention mechanism spatial optimizes dense dual-path networks improve the of optical images. The achieves 97.57% accuracy, 4.16% higher than best single-modal results. boosts accuracy by 2.68%. Thus, effectively integrates data, showing strong in classifying detecting backgrounds.

Язык: Английский

Процитировано

0