Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A Molecular Engineering Strategy to Fine-Tune Phototoxicity of AIE Probes for Super-Resolution Imaging of Mitochondrial Cristae Dynamics.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Retraction notice to "Effectiveness of prescription-based influenza vaccination services among older adults in Binzhou, China: A cluster-randomized controlled trial" [Vaccine 82 (2026) 128588].

Vaccine·2026

Same author

Functionalized SiO<sub>2</sub> nanoparticle-mediated release and transport of Cd through soil porous media: implications for their application in soil remediation.

Environmental geochemistry and health·2026

Same author

An In Situ Gelled PCA-Na/Gelatin Hydrogel Plant Wearable Sensor Patch Based on Synergistic Enhancement Strategy for Atrazine Detection.

Analytical chemistry·2026

Same author

Silencing miR-208a-3p promotes autophagy and attenuates high glucose-triggered podocyte injury by activating VAV3/AKT/mTOR pathway.

General physiology and biophysics·2026

Same author

The Caspase-1/GSDMD/PXN/VCAM-1 Cascade Mediates Cerebral Ischemia-Reperfusion Injury.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026

Search research articles

Related Experiment Video

Updated: Oct 13, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with

Yanjun Wang^1,2,3, Shaochun Li^1,2,3, Yunhao Lin^1,2,3

¹Hunan Provincial Key Laboratory of Geo-Information Engineering in Surveying, Mapping and Remote Sensing, Hunan University of Science and Technology, Xiangtan 411201, China.

Sensors (Basel, Switzerland)

|November 13, 2021

Summary

A new lightweight MobileNetV2 model efficiently extracts water bodies from high-resolution remote sensing images, outperforming traditional methods and deep learning models in complex environments. This advancement aids water resource management and disaster response.

Keywords:

MobileNetv2 deep learning lightweight deep neural network multisensor high-resolution image water body extraction

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

Related Experiment Videos

Last Updated: Oct 13, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

Area of Science:

Environmental Science
Remote Sensing
Computer Vision

Background:

Accurate water body extraction from remote sensing data is crucial for water management and disaster response.
Traditional methods and existing deep learning models face challenges with complex features, shadows, computational cost, and real-time processing.

Purpose of the Study:

To develop and validate an efficient water body extraction method using a lightweight deep learning model.
To assess the model's performance on multisensor high-resolution remote sensing images across diverse geographical conditions.

Main Methods:

A novel water body extraction approach utilizing the lightweight MobileNetV2 architecture.
Application and validation on GF-2, WorldView-2, and UAV orthoimages in complex urban and mountainous terrains.
Comparative analysis against Support Vector Machine, Random Forest, and U-Net models.

Main Results:

MobileNetV2 achieved superior F1-scores and Kappa coefficients (e.g., 0.98 for UAV, 0.86 for WorldView-2, 0.75 for GF-2) compared to other methods.
Significantly reduced training time, parameters, and computational load versus U-Net, enhancing extraction efficiency.
Consistent high accuracy in complex environments and demonstrated the benefit of combining multi-resolution imagery for training.

Conclusions:

The proposed MobileNetV2 method offers an efficient and accurate solution for water body extraction from high-resolution remote sensing data.
This approach provides a valuable reference for automated water classification in challenging geographical settings.
The findings support improved water resource investigation, management, and planning through advanced remote sensing techniques.