How to Identify Good Superpixels for Deforestation Detection on Tropical Rainforests
- 5 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Abstract
The conservation of tropical forests is a topic of significant social and ecological relevance due to their crucial role in the global ecosystem. Unfortunately, deforestation and degradation impact millions of hectares annually, requiring government or private initiatives for effective forest monitoring. However, identifying deforested regions in satellite images is challenging due to data imbalance, image resolution, low-contrast regions, and occlusion. Superpixel segmentation can overcome these drawbacks, reducing workload and preserving important image boundaries. However, most works for remote sensing images do not exploit recent superpixel methods. In this work, we evaluate 16 superpixel methods in satellite images to support a deforestation detection system in tropical forests. We also assess the performance of superpixel methods for the target task, establishing a relationship with segmentation methodological evaluation. According to our results, ERS, GMMSP, and DISF perform best on UE, BR, and SIRS, respectively, whereas ERS has the best trade-off with CO and Reg. In classification, SH, DISF, and ISF perform best on RGB, UMDA, and PCA compositions, respectively. According to our experiments, superpixel methods with better trade-offs between delineation, homogeneity, compactness, and regularity are more suitable for identifying good superpixels for deforestation detection tasks.Keywords
All Related Versions
Funding Information
- Pontifícia Universidade Católica de Minas Gerais
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (Finance Code 001)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (407242/2021-0)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (306573/2022-9)
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais (APQ-01079-23)
- Instituto Nacional de Ciência e Tecnologia (INCT) Future Internet for Smart Cities through CNPq (465446/2014-0)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2014/50937-1)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2015/24485-9)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2017/25908-6)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2018/23908-1)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2019/26702-8)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2023/00811-0)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2023/00782-0)
This publication has 32 references indexed in Scilit:
- Unsupervised segmentation of hyperspectral remote sensing images with superpixelsRemote Sensing Applications: Society and Environment, 2022
- ForestEyes Project: Conception, enhancements, and challengesFuture Generation Computer Systems, 2021
- Rooted Spanning SuperpixelsInternational Journal of Computer Vision, 2020
- Robust superpixels using color and contour features along linear pathComputer Vision and Image Understanding, 2018
- Superpixels and Polygons Using Simple Non-iterative Clustering2017
- Real-time coarse-to-fine topologically preserving segmentation2015
- Eikonal based region growing for superpixels generation: Application to semi-supervised real time organ segmentation in CT imagesIRBM, 2014
- Entropy rate superpixel segmentation2011
- Superpixel lattices2008
- From recombination of genes to the estimation of distributions I. Binary parameters1996