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
Optimized Reinforcement Learning-Driven Model for Remote Sensing Change Detection.
Journal of imaging·2026
Same author
A Feature Extraction Algorithm of Brain Network of Motor Imagination Based on a Directed Transfer Function.
Computational intelligence and neuroscience·2022
Related Experiment Video
Updated: May 14, 2025

08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.3K
Typical Crop Classification of Agricultural Multispectral Remote Sensing Images by Fusing Multi-Attention Mechanism
Zongpu Li1,2,3, Zhiyun Xiao1,2,3, Yulong Zhou1,2,3
1Inner Mongolia Key Laboratory of Electrical and Mechanical Control, Inner Mongolia University of Technology, Hohhot 010080, China.
Sensors (Basel, Switzerland)
|April 12, 2025
Summary
This study introduces an improved deep learning model for crop classification using multispectral images from unmanned aerial vehicles (UAVs). The enhanced ResNet model achieves 97.8% accuracy, supporting precision agriculture.
Area of Science:
- Agricultural Science
- Computer Science
- Remote Sensing
Background:
- Traditional crop classification relies on labor-intensive, subjective field surveys, limiting spatial coverage and spectral detail.
- Existing methods struggle with fine-grained spectral variations crucial for accurate crop identification.
Purpose of the Study:
- To develop an enhanced crop classification model using deep learning and multispectral remote sensing data.
- To improve the accuracy and efficiency of identifying complex crop planting structures.
Main Methods:
- Utilized multispectral remote sensing images acquired from unmanned aerial vehicles (UAVs).
- Developed an improved ResNet50 model incorporating ACmix self-attention and coordinate attention mechanisms.
- Focused on classifying four key crops: sunflower, corn, beet, and pepper.
Main Results:
- The enhanced ResNet model achieved a classification accuracy of 97.8% on multispectral images.
- The model significantly outperformed classification using RGB images and traditional methods.
- Demonstrated superior performance in accurately classifying complex crop structures.
Conclusions:
- Combining UAV multispectral remote sensing with deep learning offers a powerful approach for precise crop classification.
- The developed model provides valuable technical support for effective precision agriculture management.
- Highlights the potential for advanced remote sensing and AI in agricultural monitoring.

