Skip to Main content Skip to Navigation
Conference papers

Semantic segmentation of remote sensing images combining hierarchical probabilistic graphical models and deep convolutional neural networks

Abstract : In this paper, a novel method to deal with the semantic segmentation of very high resolution remote sensing data is presented. Recent advances in deep learning (DL), especially convolutional neural networks (CNNs) and fully convolutional networks (FCNs), have shown outstanding performances in this task. However, the map accuracy depends on the quantity and quality of ground truth (GT) used to train them. At the same time, probabilistic graphical models (PGMs) have sparked even more interest in the past few years, because of the ever-growing need for structured predictions. The novel method proposed in this paper combines DL and PGMs to perform remote sensing image classification. FCNs can be exploited to deal with multiscale data through the integration with a hierarchical Markov model. The marginal posterior mode (MPM) criterion for inference is used in the proposed framework. Experimental validation is conducted on the ISPRS 2D Semantic Labeling Challenge Vaihingen dataset. The results are significant, as the proposed method has a higher recall than the standard FCNs considered and allows mitigating the impact of incomplete or suboptimal GT, especially with regard to the discrimination of minoritary classes.
Complete list of metadata

https://hal.inria.fr/hal-03253006
Contributor : Jules Mabon Connect in order to contact the contributor
Submitted on : Tuesday, June 8, 2021 - 9:52:55 AM
Last modification on : Thursday, June 10, 2021 - 3:44:56 AM
Long-term archiving on: : Thursday, September 9, 2021 - 6:17:17 PM

File

Pastorino-IGARSS-2021.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03253006, version 1

Citation

Martina Pastorino, Gabriele Moser, Sebastiano Serpico, Josiane Zerubia. Semantic segmentation of remote sensing images combining hierarchical probabilistic graphical models and deep convolutional neural networks. IGARSS 2021 - IEEE International Geoscience and Remote Sensing Symposium, Jul 2021, Brussels / Virtual, Belgium. ⟨hal-03253006⟩

Share

Metrics

Record views

70

Files downloads

148