Multispectral data UAV for rice growth phase: a comparison of pixel-based and object-based approach

Rohmad Sasongko; M. Faozi Nasrulloh; Abeer Firdaus Adiva Hadi; Ferry Febrian; Francisca Nova Puspatiyaningrum; Fitria Khojanni; Adienda Rayhan Salsabilla; Barandi Sapta Widartono; Sanjiwana Arjasakusuma

doi:10.1117/12.3009686

29 January 2024 Multispectral data UAV for rice growth phase: a comparison of pixel-based and object-based approach

Rohmad Sasongko, M. Faozi Nasrulloh, Abeer Firdaus Adiva Hadi, Ferry Febrian, Francisca Nova Puspatiyaningrum, Fitria Khojanni, Adienda Rayhan Salsabilla, Barandi Sapta Widartono, Sanjiwana Arjasakusuma

Author Affiliations +

Proceedings Volume 12977, Eighth Geoinformation Science Symposium 2023: Geoinformation Science for Sustainable Planet; 129770G (2024) https://doi.org/10.1117/12.3009686
Event: 8th Geoinformation Science Symposium 2023: Geoinformation Science for Sustainable Planet, 2023, Yogyakarta, Indonesia

Abstract

The advancement of remote sensing image acquisition through Unmanned Aerial Vehicles (UAVs) has seen rapid growth in the last five years, particularly in the field of agricultural mapping. The inclusion of multispectral sensors on UAVs holds potential and capabilities for distinguishing different growth stages of rice crops. However, with respect to this objective, there has been limited research investigating pixel-based and object-based classification approaches using multispectral UAV data. This study aims to assess the capabilities of multispectral aerial photos in identifying rice crop growth stages through both pixel-based and object-based classification methods within a portion of the Banyubiru Subdistrict, Semarang Regency. The Support Vector Machine (SVM) method is employed for pixel-based classification, while the object-based classification (OBIA) process employs the Segment Mean Shift algorithm for segmentation. Training samples and data accuracy are obtained through visual interpretation based on the developed orthomosaic data. Four rice crop growth stages are mapped, namely vegetative, reproductive, ripening, and bare-land phases. The two approaches yield differing accuracy performance. The pixel based approach using support vector machine (SVM) achieves an accuracy of 45% with a kappa coefficient of 0.28, whereas the Object Based Image Analysis (OBIA) approach attains an accuracy of 37% with a kappa coefficient of 0.24. The results indicate that, in this case, the pixel-based approach (SVM) demonstrates higher accuracy compared to the Object Based Image Analysis (OBIA) approach. However, the low accuracy indicates the limitations of pixel based image analysis using spectrometer inputs for mapping using UAV datasets.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Rohmad Sasongko, M. Faozi Nasrulloh, Abeer Firdaus Adiva Hadi, Ferry Febrian, Francisca Nova Puspatiyaningrum, Fitria Khojanni, Adienda Rayhan Salsabilla, Barandi Sapta Widartono, and Sanjiwana Arjasakusuma "Multispectral data UAV for rice growth phase: a comparison of pixel-based and object-based approach", Proc. SPIE 12977, Eighth Geoinformation Science Symposium 2023: Geoinformation Science for Sustainable Planet, 129770G (29 January 2024); https://doi.org/10.1117/12.3009686

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image classification

Image processing

Visualization

Unmanned aerial vehicles

Reflectivity

3D modeling

Support vector machines

Show All Keywords

Keywords/Phrases

Search In:

Publication Years