Semi-Supervised Learning for Joint SAR and Multispectral Land Cover Classification

Montanaro, Antonio; Valsesia, Diego; Fracastoro, Giulia; Magli, Enrico

doi:10.1109/lgrs.2022.3195259

Cited by 17 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The potential of SSL in Synthetic Aperture Radar (SAR) applications, a field closely related to SAS, has been demonstrated in several studies [19][20][21][22][23][24][25][26][27]. These studies have shown that SSL can effectively leverage the vast amounts of unlabeled SAR data to achieve meaningful results.…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Learning for Improved Sas Target Recognition

SHEFFIELD

2023

Synthetic Aperture Sonar and Synthetic Aperture Radar 2023

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Self-Supervised Learning for Improved Sas Target Recognition

SHEFFIELD

2023

Synthetic Aperture Sonar and Synthetic Aperture Radar 2023

View full text Add to dashboard Cite

“…Existing PolSAR land cover classification methods can be categorized into traditional approaches [5,6] and deep learning methods [7][8][9]. Traditional classification methods are predominantly designed based on statistical features of PolSAR data, such as the Wishart distribution [10], etc.…”

Section: Introductionmentioning

confidence: 99%

BSDSNet: Dual-Stream Feature Extraction Network Based on Segment Anything Model for Synthetic Aperture Radar Land Cover Classification

Wang,

Zhang,

Chen

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Land cover classification using high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images obtained from satellites is a challenging task. While deep learning algorithms have been extensively studied for PolSAR image land cover classification, the performance is severely constrained due to the scarcity of labeled PolSAR samples and the limited domain acceptance of models. Recently, the emergence of the Segment Anything Model (SAM) based on the vision transformer (VIT) model has brought about a revolution in the study of specific downstream tasks in computer vision. Benefiting from its millions of parameters and extensive training datasets, SAM demonstrates powerful capabilities in extracting semantic information and generalization. To this end, we propose a dual-stream feature extraction network based on SAM, i.e., BSDSNet. We change the image encoder part of SAM to a dual stream, where the ConvNext image encoder is utilized to extract local information and the VIT image encoder is used to extract global information. BSDSNet achieves an in-depth exploration of semantic and spatial information in PolSAR images. Additionally, to facilitate a fine-grained amalgamation of information, the SA-Gate module is employed to integrate local–global information. Compared to previous deep learning models, BSDSNet’s impressive ability to represent features is akin to a versatile receptive field, making it well suited for classifying PolSAR images across various resolutions. Comprehensive evaluations indicate that BSDSNet achieves excellent results in qualitative and quantitative evaluation when performing classification tasks on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset. Compared to the suboptimal results, our method improves the Kappa metric by 3.68% and 0.44% on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset, respectively.

show abstract

“…The Dynamic World dataset achieved near-real-time capability with an accuracy ranging from about 77% to 88%, depending on the validation method [ 33 ]. SAR, multispectral, elevation, and/or lidar imagery fusion combined with advanced deep neural network methods have also been applied in select regions, with overall accuracies ranging from 75% to 95% [ 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 ], including studies with automatically generated training data for self-supervised classification on select study sites [ 44 , 45 ]. The studies leveraging deep learning methods generally exceed the accuracy of shallow machine learning methods due to deep learning’s ability to better represent texture, morphology, and objects [ 46 , 47 , 48 ], but the accuracy can be poor when training data are of low quality or not geographically transferable [ 49 , 50 , 51 ].…”

Section: Introductionmentioning

confidence: 99%

Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data

Lasko,

O’Neill,

Sava

2024

Sensors

View full text Add to dashboard Cite

A near-global framework for automated training data generation and land cover classification using shallow machine learning with low-density time series imagery does not exist. This study presents a methodology to map nine-class, six-class, and five-class land cover using two dates (winter and non-winter) of a Sentinel-2 granule across seven international sites. The approach uses a series of spectral, textural, and distance decision functions combined with modified ancillary layers (such as global impervious surface and global tree cover) to create binary masks from which to generate a balanced set of training data applied to a random forest classifier. For the land cover masks, stepwise threshold adjustments were applied to reflectance, spectral index values, and Euclidean distance layers, with 62 combinations evaluated. Global (all seven scenes) and regional (arid, tropics, and temperate) adaptive thresholds were computed. An annual 95th and 5th percentile NDVI composite was used to provide temporal corrections to the decision functions, and these corrections were compared against the original model. The accuracy assessment found that the regional adaptive thresholds for both the two-date land cover and the temporally corrected land cover could accurately map land cover type within nine-class (68.4% vs. 73.1%), six-class (79.8% vs. 82.8%), and five-class (80.1% vs. 85.1%) schemes. Lastly, the five-class and six-class models were compared with a manually labeled deep learning model (Esri), where they performed with similar accuracies (five classes: Esri 80.0 ± 3.4%, region corrected 85.1 ± 2.9%). The results highlight not only performance in line with an intensive deep learning approach, but also that reasonably accurate models can be created without a full annual time series of imagery.

show abstract

Semi-Supervised Learning for Joint SAR and Multispectral Land Cover Classification

Cited by 17 publications

References 11 publications

Self-Supervised Learning for Improved Sas Target Recognition

Self-Supervised Learning for Improved Sas Target Recognition

BSDSNet: Dual-Stream Feature Extraction Network Based on Segment Anything Model for Synthetic Aperture Radar Land Cover Classification

Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data

Contact Info

Product

Resources

About