Universidad de Granada Digibug
 

Repositorio Institucional de la Universidad de Granada >
1.-Investigación >
Departamentos, Grupos de Investigación e Institutos >
Departamento de Botánica >
DBot - Artículos >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10481/49111

Title: Deep-learning Versus OBIA for Scattered Shrub Detection with Google Earth Imagery: Ziziphus lotus as Case Study
Authors: Guirado, Emilio
Tabik, Siham
Alcaraz Segura, Domingo
Cabello, Javier
Herrera, Francisco
Issue Date: 26-Nov-2017
Abstract: There is a growing demand for accurate high-resolution land cover maps in many fields, e.g., in land-use planning and biodiversity conservation. Developing such maps has been traditionally performed using Object-Based Image Analysis (OBIA) methods, which usually reach good accuracies, but require a high human supervision and the best configuration for one image often cannot be extrapolated to a different image. Recently, deep learning Convolutional Neural Networks (CNNs) have shown outstanding results in object recognition in computer vision and are offering promising results in land cover mapping. This paper analyzes the potential of CNN-based methods for detection of plant species of conservation concern using free high-resolution Google Earth TM images and provides an objective comparison with the state-of-the-art OBIA-methods. We consider as case study the detection of Ziziphus lotus shrubs, which are protected as a priority habitat under the European Union Habitats Directive. Compared to the best performing OBIA-method, the best CNN-detector achieved up to 12% better precision, up to 30% better recall and up to 20% better balance between precision and recall. Besides, the knowledge that CNNs acquired in the first image can be re-utilized in other regions, which makes the detection process very fast. A natural conclusion of this work is that including CNN-models as classifiers, e.g., ResNet-classifier, could further improve OBIA methods. The provided methodology can be systematically reproduced for other species detection using our codes available through (https://github.com/EGuirado/CNN-remotesensing).
Sponsorship: Siham Tabik was supported by the Ramón y Cajal Programme (RYC-2015-18136).
The work was partially supported by the Spanish Ministry of Science and Technology under the projects: TIN2014-57251-P, CGL2014-61610-EXP, CGL2010-22314 and grant JC2015-00316, and ERDF and Andalusian Government under the projects: GLOCHARID, RNM-7033, P09-RNM-5048 and P11-TIC-7765.
This research was also developed as part of project ECOPOTENTIAL, which received funding from the European Union Horizon 2020 Research and Innovation Programme under grant agreement No. 641762, and by the European LIFE Project ADAPTAMED LIFE14 CCA/ES/000612.
Publisher: MDPI
Keywords: Ziziphus lotus
Plant species detection
Land cover mapping
Convolutional Neural Networks (CNNs)
Object-Based Image Analysis (OBIA)
Remote sensing
URI: http://hdl.handle.net/10481/49111
ISSN: 2072-4292
Rights : Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License
Citation: Guirado, E.; et al. Deep-learning Versus OBIA for Scattered Shrub Detection with Google Earth Imagery: Ziziphus lotus as Case Study. Remote Sensing, 9(12): 1220 (2017). [http://hdl.handle.net/10481/49111]
Appears in Collections:DBot - Artículos
OpenAIRE (Open Access Infrastructure for Research in Europe)

Files in This Item:

File Description SizeFormat
Guirado_DeepLearning.pdf9.79 MBAdobe PDFView/Open
Recommend this item

This item is licensed under a Creative Commons License
Creative Commons

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! OpenAire compliant DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard - Feedback

© Universidad de Granada