Multitask GLocal OBIA-Mamba for Sentinel-2 Landcover Mapping

TL;DR

This paper introduces a novel multitask GLocal OBIA-Mamba framework that enhances Sentinel-2 land cover classification by combining object-based analysis, dual-branch CNN architecture, and multitask optimization, achieving higher accuracy and finer details.

Contribution

It presents a new OBIA-Mamba model with superpixels, a dual-branch CNN architecture for local and global features, and a multitask loss framework for improved Sentinel-2 land cover classification.

Findings

Higher classification accuracy than state-of-the-art methods

Finer land cover details captured in results

Effective modeling of local and global information

Abstract

Although Sentinel-2 based land use and land cover (LULC) classification is critical for various environmental monitoring applications, it is a very difficult task due to some key data challenges (e.g., spatial heterogeneity, context information, signature ambiguity). This paper presents a novel Multitask Glocal OBIA-Mamba (MSOM) for enhanced Sentinel-2 classification with the following contributions. First, an object-based image analysis (OBIA) Mamba model (OBIA-Mamba) is designed to reduce redundant computation without compromising fine-grained details by using superpixels as Mamba tokens. Second, a global-local (GLocal) dual-branch convolutional neural network (CNN)-mamba architecture is designed to jointly model local spatial detail and global contextual information. Third, a multitask optimization framework is designed to employ dual loss functions to balance local precision with global consistency. The proposed approach is tested on Sentinel-2 imagery in Alberta, Canada, in comparison with several advanced classification approaches, and the results demonstrate that the proposed approach achieves higher classification accuracy and finer details that the other state-of-the-art methods.