Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain)
A workflow headed up to identify crops growing under plastic-covered greenhouses (PCG) and based on multi-temporal and multi-sensor satellite data is developed in this article. This workflow is made up of four steps: (i) data pre-processing, (ii) PCG segmentation, (iii) binary pre-classification bet...
Main Authors: | , , , , |
---|---|
Format: | info:eu-repo/semantics/article |
Language: | English |
Published: |
MDPI
2020
|
Subjects: | |
Online Access: | http://hdl.handle.net/10835/7499 |
_version_ | 1789406326906945536 |
---|---|
author | Nemmaoui, Abderrahim Aguilar Torres, Manuel Ángel Aguilar Torres, Fernando José Novelli, Antonio García Lorca, Andrés Miguel |
author_facet | Nemmaoui, Abderrahim Aguilar Torres, Manuel Ángel Aguilar Torres, Fernando José Novelli, Antonio García Lorca, Andrés Miguel |
author_sort | Nemmaoui, Abderrahim |
collection | DSpace |
description | A workflow headed up to identify crops growing under plastic-covered greenhouses (PCG) and based on multi-temporal and multi-sensor satellite data is developed in this article. This workflow is made up of four steps: (i) data pre-processing, (ii) PCG segmentation, (iii) binary pre-classification between greenhouses and non-greenhouses, and (iv) classification of horticultural crops under greenhouses regarding two agronomic seasons (autumn and spring). The segmentation stage was carried out by applying a multi-resolution segmentation algorithm on the pre-processed WorldView-2 data. The free access AssesSeg command line tool was used to determine the more suitable multi-resolution algorithm parameters. Two decision tree models mainly based on the Plastic Greenhouse Index were developed to perform greenhouse/non-greenhouse binary classification from Landsat 8 and Sentinel-2A time series, attaining overall accuracies of 92.65% and 93.97%, respectively. With regards to the classification of crops under PCG, pepper in autumn, and melon and watermelon in spring provided the best results (Fβ around 84% and 95%, respectively). Data from the Sentinel-2A time series showed slightly better accuracies than those from Landsat 8. |
format | info:eu-repo/semantics/article |
id | oai:repositorio.ual.es:10835-7499 |
institution | Universidad de Cuenca |
language | English |
publishDate | 2020 |
publisher | MDPI |
record_format | dspace |
spelling | oai:repositorio.ual.es:10835-74992023-10-10T11:07:36Z Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) Nemmaoui, Abderrahim Aguilar Torres, Manuel Ángel Aguilar Torres, Fernando José Novelli, Antonio García Lorca, Andrés Miguel Landsat 8 Sentinel-2 WorldView-2 time series object-based classification greenhouse mapping crop types classification A workflow headed up to identify crops growing under plastic-covered greenhouses (PCG) and based on multi-temporal and multi-sensor satellite data is developed in this article. This workflow is made up of four steps: (i) data pre-processing, (ii) PCG segmentation, (iii) binary pre-classification between greenhouses and non-greenhouses, and (iv) classification of horticultural crops under greenhouses regarding two agronomic seasons (autumn and spring). The segmentation stage was carried out by applying a multi-resolution segmentation algorithm on the pre-processed WorldView-2 data. The free access AssesSeg command line tool was used to determine the more suitable multi-resolution algorithm parameters. Two decision tree models mainly based on the Plastic Greenhouse Index were developed to perform greenhouse/non-greenhouse binary classification from Landsat 8 and Sentinel-2A time series, attaining overall accuracies of 92.65% and 93.97%, respectively. With regards to the classification of crops under PCG, pepper in autumn, and melon and watermelon in spring provided the best results (Fβ around 84% and 95%, respectively). Data from the Sentinel-2A time series showed slightly better accuracies than those from Landsat 8. 2020-01-17T08:19:21Z 2020-01-17T08:19:21Z 2018-11-06 info:eu-repo/semantics/article 2072-4292 http://hdl.handle.net/10835/7499 en https://www.mdpi.com/2072-4292/10/11/1751 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess MDPI |
spellingShingle | Landsat 8 Sentinel-2 WorldView-2 time series object-based classification greenhouse mapping crop types classification Nemmaoui, Abderrahim Aguilar Torres, Manuel Ángel Aguilar Torres, Fernando José Novelli, Antonio García Lorca, Andrés Miguel Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title | Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title_full | Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title_fullStr | Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title_full_unstemmed | Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title_short | Greenhouse Crop Identification from Multi-Temporal Multi-Sensor Satellite Imagery Using Object-Based Approach: A Case Study from Almería (Spain) |
title_sort | greenhouse crop identification from multi-temporal multi-sensor satellite imagery using object-based approach: a case study from almería (spain) |
topic | Landsat 8 Sentinel-2 WorldView-2 time series object-based classification greenhouse mapping crop types classification |
url | http://hdl.handle.net/10835/7499 |
work_keys_str_mv | AT nemmaouiabderrahim greenhousecropidentificationfrommultitemporalmultisensorsatelliteimageryusingobjectbasedapproachacasestudyfromalmeriaspain AT aguilartorresmanuelangel greenhousecropidentificationfrommultitemporalmultisensorsatelliteimageryusingobjectbasedapproachacasestudyfromalmeriaspain AT aguilartorresfernandojose greenhousecropidentificationfrommultitemporalmultisensorsatelliteimageryusingobjectbasedapproachacasestudyfromalmeriaspain AT novelliantonio greenhousecropidentificationfrommultitemporalmultisensorsatelliteimageryusingobjectbasedapproachacasestudyfromalmeriaspain AT garcialorcaandresmiguel greenhousecropidentificationfrommultitemporalmultisensorsatelliteimageryusingobjectbasedapproachacasestudyfromalmeriaspain |