How to Identify Good Superpixels for Deforestation Detection on Tropical Rainforests
This work addresses deforestation detection for conservation efforts, but it is incremental as it applies existing superpixel methods to a new domain without introducing novel techniques.
The paper tackled the problem of identifying deforested regions in satellite images of tropical rainforests by evaluating 16 superpixel segmentation methods, finding that ERS, GMMSP, and DISF performed best on specific metrics like UE, BR, and SIRS, with ERS offering the best trade-off in delineation and regularity.
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.