Multimodal and Multitemporal Land Use/Land Cover Semantic Segmentation on Sentinel-1 and Sentinel-2 Imagery: An Application on a MultiSenGE Dataset

Wenger, Romain; Puissant, A.; Weber, Jonathan; Idoumghar, Lhassane; Forestier, Germain

doi:10.3390/rs15010151

Cited by 9 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work, the reference data [14], initially in 14 classes, was reclassified into 10 classes by merging the least represented classes (Table I). Indeed, these classes represented less than 0.1% of the total area of the region and were not spatially homogeneous over the territory, which causes problems for the training and classification, even when applying a weighted loss.…”

Section: A Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Exploring inference of a land use and land cover model trained on MultiSenGE dataset

Wenger

Puissant

Weber

et al. 2023

2023 Joint Urban Remote Sensing Event (JURSE)

Self Cite

View full text Add to dashboard Cite

Land use and land cover and Urban Fabric (UF) mapping are very useful for urban modeling and simulation (growth, pollution, noise, micro-climate, mobility) in a context of global change. In recent years, due to the increase of Earth Observation data researchers built and shared datasets to the machine learning scientific community to apply and test their models for semantic segmentation. Few works have trained their deep learning model based on a geographic region and applied it to another geographical area of the same country. In this study, we explore the inference of a deep learning model pretrained on a multitemporal and multimodal dataset named 'MultiSenGE' dataset (based on a region in the East of France representing one fifth of the area of France) on five different cities over France (Toulouse, Dijon, Orléans, Lille, Rennes) away from the trained area. Results are encouraging and achieve F1-Score between 0.70 and 0.80 for the five urban fabric classes.

show abstract

Section: A Datasetsmentioning

confidence: 99%

“…In previous work [14], it has been shown that the contribution of multitemporal and multimodal imagery improve UF semantic segmentation. Thus, a convolution network has been developed and trained on the MultiSenGE [15] dataset which was built for the entire Grand-Est region in France.…”

Section: Introductionmentioning

confidence: 98%

Exploring inference of a land use and land cover model trained on MultiSenGE dataset

Wenger

Puissant

Weber

et al. 2023

2023 Joint Urban Remote Sensing Event (JURSE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The electronic and technological advancements of both these platforms and their onboard sensors, as well as the numerous applications where remote sensing provides valuable information for decision-making, particularly in the determination of more precise land cover classifications, have seen significant advancements in recent years [24,25] Satellite images can now be obtained from a variety of platforms located across the globe [25]. The development of indicators to track and comprehend anthropogenic and natural processes necessitated using high-resolution and frequently updated land cover maps [26].…”

Section: Introductionmentioning

confidence: 99%

“…The development of novel approaches for producing LULC maps based on classification techniques, and more specifically, deep learning, has been made possible by the evolution of cloud computing [33]. For LULC mapping, many studies have employed deep learning methods, particularly convolutional neural networks (CNN), either in conjunction with pixel categorization [34] or semantic segmentation [26,35,36].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of DL-based Models for LULC segmentation using SAR time series data of regions in Gujarat

Jain

Varghese²,

Joshi

et al. 2023

Preprint

View full text Add to dashboard Cite

Both spatial and non-spatial data are critical to a country's social and economic development. Land use and land cover (LULC) maps are data that can be used to retrieve land information and detect environmental changes. Several recent studies have used deep learning approaches to generate LULC maps from various remote-sensing image formats. They have correctly recognized several land cover elements such as built-up areas, forests, water, etc. On the other hand, spaceborne radar images must be used to test deep learning methods because radar sensors operate in all weather and lighting circumstances and have diverse image characteristics depending on the wavelength. Although many researchers have applied deep learning techniques to classify the land cover features, most of them need to do more by taking less or more several land cover features and taking proper evaluation metrics to justify the classification techniques. The current research shows segmentation on Sentinel-1 C-band synthetic aperture radar (SAR) images of Gujarat's Ahmedabad, Anand, and Kheda regions using four deep-learning models. U-Net, SegNet, FCN, and DeepLabV3+ have primarily been employed in prior research to classify SAR and other satellite image formats and showed excellent results in identifying different land cover features. Training samples of five primary classes for ground-truth data were obtained using Google Earth and Sentinel-2 images as reference maps. For segmenting the Sentinel-1 image, above mentioned four deep-learning semantic segmentation models were chosen and fine-tuned. All models did exceptionally well, with overall accuracy ranging from 76% to 90%. U-Net fared well, followed by DeepLabV3+ in classifying all five land cover features, with mean intersection over union (IoU) of 0.67 and 0.55, respectively. The results reveal that using a self-generated reference map, the Sentinel-1 dual-pol images can categorize the primary land cover features.

show abstract

“…CNN-based methods have been continuously proposed, such as the more mature and popular VGG [ 12 ], ResNet [ 13 ], UNet [ 14 ], SegNet [ 15 ], and DeepLab series [ 16 , 17 , 18 , 19 ]. Due to the advantage of automatically learning discriminative features, CNNs have been widely used in remote sensing image processing, including change detection [ 20 , 21 ], scene recognition [ 22 , 23 ], and land-use classification [ 24 , 25 ]. Transformer [ 26 ] is a later-emerged deep learning model that was first proposed for natural language processing (NLP) tasks.…”

Section: Introductionmentioning

confidence: 99%

AGDF-Net: Attention-Gated and Direction-Field-Optimized Building Instance Extraction Network

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Building extraction from high-resolution remote sensing images has various applications, such as urban planning and population estimation. However, buildings have intraclass heterogeneity and interclass homogeneity in high-resolution remote sensing images with complex backgrounds, which makes the accurate extraction of building instances challenging and regular building boundaries difficult to maintain. In this paper, an attention-gated and direction-field-optimized building instance extraction network (AGDF-Net) is proposed. Two refinements are presented, including an Attention-Gated Feature Pyramid Network (AG-FPN) and a Direction Field Optimization Module (DFOM), which are used to improve information flow and optimize the mask, respectively. The AG-FPN promotes complementary semantic and detail information by measuring information importance to control the addition of low-level and high-level features. The DFOM predicts the pixel-level direction field of each instance and iteratively corrects the direction field based on the initial segmentation. Experimental results show that the proposed method outperforms the six state-of-the-art instance segmentation methods and three semantic segmentation methods. Specifically, AGDF-Net improves the objective-level metric AP and the pixel-level metric IoU by 1.1%~9.4% and 3.55%~5.06%

show abstract

Multimodal and Multitemporal Land Use/Land Cover Semantic Segmentation on Sentinel-1 and Sentinel-2 Imagery: An Application on a MultiSenGE Dataset

Cited by 9 publications

References 49 publications

Exploring inference of a land use and land cover model trained on MultiSenGE dataset

Exploring inference of a land use and land cover model trained on MultiSenGE dataset

Performance Evaluation of DL-based Models for LULC segmentation using SAR time series data of regions in Gujarat

AGDF-Net: Attention-Gated and Direction-Field-Optimized Building Instance Extraction Network

Contact Info

Product

Resources

About