Clustering Feature Constraint Multiscale Attention Network for Shadow Extraction From Remote Sensing Images

Xie, Yakun; Feng, Dejun; Shen, Xingyu; Liu, Yangge; Zhu, Jun; Hussain, Tanveer; Baik, Sung Wook

doi:10.1109/tgrs.2022.3151901

Cited by 13 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature fusion-based approaches [5,[17][18][19][20][21][22][23][24][25][26] enhance the representation of cropland information by supplementing additional feature information to the model. Considering the difficulty in labeling the existing high-resolution remote sensing image samples, [17] utilized the existing medium-resolution remote sensing images as a priori knowledge to provide cross-scale relocatable samples for HR images, thus obtaining more effective high-resolution farmland samples.…”

Section: Methods Based On Features Fusionmentioning

confidence: 99%

“…Specifically, this inaccuracy is usually caused by factors such as complex boundary morphology and feature recognition errors, as illustrated in Figure 1. In practical applications, this inaccuracy will be manifested in the phenomenon of boundary error and omission, which will have certain impacts on fields such as land use planning and agricultural production [5]. To alleviate the problem of inaccurate cropland boundary segmentation, it is urgent to enhance the model's perception ability of edge features to improve the recognition accuracy and reliability of segmentation results [6].…”

Section: Introductionmentioning

confidence: 99%

“…However, most of them focus on specific geographic regions or a single cropland type, ignoring the regional differences of cropland parcels, and failing to achieve the purpose of generalized extraction. (2) Feature-based approaches [5,[17][18][19][20][21][22][23][24][25][26] enhance the representation and understanding of cropland information by supplementing the model with additional features. However, some redundant feature representations do not provide positive images to the model while increasing the computational burden of the model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

Li,

Wang,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland illustrates diverse morphologies and degrees of fragmentation on the Earth’s surface, underscoring the importance of accurately perceiving the complex boundaries of cropland which are crucial for effective segmentation. This paper introduces a UNet-like boundary-aware compensation model BAFormer. Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote-sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Deep Wide Large Kernel Multi-Layer Perceptron (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM adaptively mixes high-frequency and low-frequency features through the advantages of convolution and self-attention; DWLK-MLP expands the convolutional receptive field by deeply decomposing large kernel convolutions. The efficacy of BAFormer has been evaluated on the Vaihingen, Potsdam, and LoveDA public datasets, as well as the Mapcup dataset. It has demonstrated advanced performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets respectively. Notably, BAFormer-T, the lightweight iteration of the model, surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. The source code is available at https://github.com/WangYouM1999/BAFormer.

show abstract

Section: Methods Based On Features Fusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

Li,

Wang,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The flexibility and robustness of the transfer learning of LSTM have been proven in several studies ( Bashar et al., 2020 ; Jung et al., 2019 ; Ma et al., 2020a , b ). Moreover, attention networks have been applied to improve the feature extraction of deep learning models ( Xie et al., 2022 ). The selective refinement of the learnable parameters-weights in the attention mechanism emphasizes the important features of the data, contributing to the improvement of the LSTM model performance ( Kumar et al., 2020 ; Shen et al., 2020 ; Zhang et al., 2020a ).…”

Section: Introductionmentioning

confidence: 99%

Long short-term memory models of water quality in inland water environments

Pyo,

Pachepsky,

Kim

et al. 2023

Water Research X

View full text Add to dashboard Cite

“…A large number of studies have been conducted to use these images for the extraction of crop plantation areas [9][10][11][12], among which the most extensively used remote sensing images are derived from the Gaofen satellites of China, the Sentinel satellites within the European Copernicus program, and the Landsat satellites within the Landsat Project of the United States. With rich spectral, spatial, and temporal information, many crops can be classified, effectively avoiding interference by the phenomenon of "different body with the same spectrum" and "same body with different spectra" [13]. Consequently, remote sensing technology is conducive to monitoring the planting area of many kinds of crops quickly, accurately, and efficiently to provide a reference for planting area statistics, spatial distribution mapping, etc.…”

Section: Introductionmentioning

confidence: 99%

Extracting Tea Plantations from Multitemporal Sentinel-2 Images Based on Deep Learning Networks

et al. 2022

View full text Add to dashboard Cite

Tea is a special economic crop that is widely distributed in tropical and subtropical areas. Timely and accurate access to the distribution of tea plantation areas is crucial for effective tea plantation supervision and sustainable agricultural development. Traditional methods for tea plantation extraction are highly dependent on feature engineering, which requires expensive human and material resources, and it is sometimes even difficult to achieve the expected results in terms of accuracy and robustness. To alleviate such problems, we took Xinchang County as the study area and proposed a method to extract tea plantations based on deep learning networks. Convolutional neural network (CNN) and recurrent neural network (RNN) modules were combined to build an R-CNN model that can automatically obtain both spatial and temporal information from multitemporal Sentinel-2 remote sensing images of tea plantations, and then the spatial distribution of tea plantations was predicted. To confirm the effectiveness of our method, support vector machine (SVM), random forest (RF), CNN, and RNN methods were used for comparative experiments. The results show that the R-CNN method has great potential in the tea plantation extraction task, with an F1 score and IoU of 0.885 and 0.793 on the test dataset, respectively. The overall classification accuracy and kappa coefficient for the whole region are 0.953 and 0.904, respectively, indicating that this method possesses higher extraction accuracy than the other four methods. In addition, we found that the distribution index of tea plantations in mountainous areas with gentle slopes is the highest in Xinchang County. This study can provide a reference basis for the fine mapping of tea plantation distributions.

show abstract

Clustering Feature Constraint Multiscale Attention Network for Shadow Extraction From Remote Sensing Images

Cited by 13 publications

References 46 publications

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

BAFormer: A Novel Boundary-Aware Compensation UNet-like Transformer for High-Resolution Cropland Extraction

Long short-term memory models of water quality in inland water environments

Extracting Tea Plantations from Multitemporal Sentinel-2 Images Based on Deep Learning Networks

Contact Info

Product

Resources

About