Related Experiment Video
Updated: Aug 11, 2025
08:25
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
9.1K
Mapping Pu'er tea plantations from GF-1 images using Object-Oriented Image Analysis (OOIA) and Support Vector Machine
Lei Liang1,2,3, Jinliang Wang1,2,3, Fei Deng1,2,3
1Faculty of Geography, Yunnan Normal University, Kunming, China.
Plos One
|February 7, 2023
Summary
Mapping China's tea plantations using remote sensing is crucial for management. A new method integrating spectral, textural, and geometrical features achieved 93.14% accuracy, outperforming other techniques and showing significant area increase.
Area of Science:
- Agricultural Science
- Remote Sensing
- Geographic Information Systems (GIS)
Background:
- Tea is a globally popular beverage and a significant commercial crop in China, necessitating accurate plantation mapping for effective management and market analysis.
- Accurate and timely mapping of tea plantation distribution is vital for plantation management and informed decision-making in China, the world's largest tea producer.
Purpose of the Study:
- To develop and validate a novel method for mapping tea plantation areas using remote sensing data.
- To assess the accuracy and efficiency of the proposed mapping method compared to existing techniques.
Main Methods:
- Utilized GF-1 satellite data from 2014-2017 for the Menghai region in Yunnan Province, China.
- Integrated image texture, spectral, and geometrical features, building feature space using SEparability and THresholds (SEaTH) algorithms.
- Employed Object-Oriented Image Analysis (OOIA) with a Support Vector Machine (SVM) algorithm for tea plantation classification.
Main Results:
- The proposed method achieved an overall accuracy of 93.14% and a Kappa coefficient of 0.81.
- Demonstrated superior performance compared to CART, Maximum Likelihood, and Convolutional Neural Network (CNN) based methods, with accuracy improvements of 3.61% to 6.99%.
- Indicated a tea plantation area increase of 4,095.36 acres between 2014 and 2017, with the fastest growth observed from 2015 to 2016.
Conclusions:
- The novel integrated feature and OOIA-SVM approach provides a highly accurate and effective method for mapping tea plantations.
- The study highlights the significant expansion of tea cultivation areas in the region, emphasizing the need for continuous monitoring.
