Land use type identification on the basis of drone imagery and object-oriented methods

Demao Sun; Mengqiao He; Dongying Zhang

doi:10.1117/12.3007579

30 August 2023 Land use type identification on the basis of drone imagery and object-oriented methods

Demao Sun, Mengqiao He, Dongying Zhang

Proceedings Volume 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023); 127971S (2023) https://doi.org/10.1117/12.3007579
Event: 2nd International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 2023, Qingdao, China

Abstract

This paper takes part of Wulian County, Rizhao City, Shandong Province as the study area, and utilizes UAV image data for land use classification research. The object-oriented random forest (RF) algorithm, logistic regression (LR) algorithm and support vector machine (SVM) algorithm combined with spectral features, index features and texture features are used to classify the land use and compare the classification effects of different algorithms. The results show that the object-oriented random forest algorithm performs better than the other algorithms, achieving an overall accuracyof89.74% and a Kappa coefficient of 0.872. The combination of object-oriented and machine learning methods can be effective for land use classification, and the classification accuracy is also higher.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Demao Sun, Mengqiao He, and Dongying Zhang "Land use type identification on the basis of drone imagery and object-oriented methods", Proc. SPIE 12797, Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), 127971S (30 August 2023); https://doi.org/10.1117/12.3007579

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available