Palm trees detecting and counting from high-resolution WorldView-3 satellite images in United Arab Emirates

A. AlMaazmi

doi:10.1117/12.2325733

10 October 2018 Palm trees detecting and counting from high-resolution WorldView-3 satellite images in United Arab Emirates

A. AlMaazmi

Author Affiliations +

Proceedings Volume 10783, Remote Sensing for Agriculture, Ecosystems, and Hydrology XX; 107831M (2018) https://doi.org/10.1117/12.2325733
Event: SPIE Remote Sensing, 2018, Berlin, Germany

Abstract

The United Arab Emirates (UAE) is one of the fastest agriculture economical growing country in the world. One aspect of this agriculture growth is the development of the date palm trees sector in the UAE. The date palm tree is considered one of the oldest and most widely cultivated tree, which is commercially the most important tree in the life of its people and their heritage. Moreover, the date palm tree was believed to be a part of the UAE strategy to control desertification. With this huge investment and interest in palm trees in the UAE, there is limited knowledge of the actual tree counts and their exact spatial locations, which is a requirement for any agricultural census. WorldView-3 satellite images were used to develop an algorithm to detect and count palm trees in the UAE. The processing was done in two steps: the first step is to detect palm trees which involved supervised classification using maximum likelihood with four feature classes: Red, Blue, Green and Near infrared (NIR) bands associated with palm trees objects taken by the labeling. The second step is to count palm trees which involved extracting local spatial maxima of Laplacian blob from Normalized Difference Vegetation Index (NDVI) masking. The algorithm was tested in different regions of interest in AlAin city, part of the capital Emirate Abu Dhabi. The algorithm and final results are compared with ground truth images for accuracy assessment. The results were satisfactory with an accuracy of 89% and higher and very minimum negligible misclassification.

Conference Presentation

Citation Download Citation

A. AlMaazmi "Palm trees detecting and counting from high-resolution WorldView-3 satellite images in United Arab Emirates", Proc. SPIE 10783, Remote Sensing for Agriculture, Ecosystems, and Hydrology XX, 107831M (10 October 2018); https://doi.org/10.1117/12.2325733

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