Exploring a Deep Convolutional Neural Network and Geobia for Automatic Recognition of Brazilian Palm Swamps (Veredas) Using Sentinel-2 Optical Data

The Brazilian Palm Swamps (Veredas) are a vegetation physiognomy of the Cerrado biome. It has a critical importance for biodiversity and also for groundwater sources conservation. With the irrigated agriculture intensification, it's been significantly impacted. Mapping this physiognomy is impor...

Full description

Saved in:

Bibliographic Details
Published in:	2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS pp. 5401 - 5404
Main Authors:	Bendini, Hugo N., Fonseca, Leila M. G., Maretto, Raian V., Matosak, Bruno M., Taquary, Evandro C., Simoes, Philipe S., Haidar, Ricardo F., Valeriano, Dalton De M.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 11-07-2021
Subjects:	Cerrado Convolutional neural networks Digital Processing Image Image segmentation Optical computing Optical fiber networks Optical imaging Peat-lands Remote Sensing Semantic Segmentation Training Vegetation mapping
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The Brazilian Palm Swamps (Veredas) are a vegetation physiognomy of the Cerrado biome. It has a critical importance for biodiversity and also for groundwater sources conservation. With the irrigated agriculture intensification, it's been significantly impacted. Mapping this physiognomy is important to delimit this vegetation type to provide subsides for public policy and monitoring programs. Pixel-based methods do not succeed, since the spatial context is important for this physiognomy. Object-based methods are a great potential on this sense. Deep Learning methods, particularly the convolutional neural networks (CNN), are increasing considerably as a solution for these challenges. We applied both methods in two regions of the Cerrado and evaluated the model transferability. The results are promising, with training model overall accuracies higher than 90% for both methods. The CNN performed better when transferred a different region. We discussed some advantages and limitations, and pointed out to improvements that can still be done.
ISSN:	2153-7003
DOI:	10.1109/IGARSS47720.2021.9554050