A Shallow-to-Deep Feature Fusion Network for VHR Remote Sensing Image Classification

Liu, Sicong; Zheng, Yongjie; Du, Qian; Bruzzone, Lorenzo; Samat, Alim; Tong, Xiaohua; Jin, Yanmin; Wang, Chao

doi:10.1109/tgrs.2022.3179288

Cited by 24 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the feature map normalization, LFAGCU incorporates a mechanism for introducing nonlinearity. VHR remote sensing images often exhibit intricate terrain boundaries, textures, and distinctive features, necessitating the network's capability to capture diverse nonlinear characteristics inherent in the data 34 . In Fig.…”

Section: Methodsmentioning

confidence: 99%

Local feature acquisition and global context understanding network for very high-resolution land cover classification

Li,

Hu,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Very high-resolution remote sensing images hold promising applications in ground observation tasks, paving the way for highly competitive solutions using image processing techniques for land cover classification. To address the challenges faced by convolutional neural network (CNNs) in exploring contextual information in remote sensing image land cover classification and the limitations of vision transformer (ViT) series in effectively capturing local details and spatial information, we propose a local feature acquisition and global context understanding network (LFAGCU). Specifically, we design a multidimensional and multichannel convolutional module to construct a local feature extractor aimed at capturing local information and spatial relationships within images. Simultaneously, we introduce a global feature learning module that utilizes multiple sets of multi-head attention mechanisms for modeling global semantic information, abstracting the overall feature representation of remote sensing images. Validation, comparative analyses, and ablation experiments conducted on three different scales of publicly available datasets demonstrate the effectiveness and generalization capability of the LFAGCU method. Results show its effectiveness in locating category attribute information related to remote sensing areas and its exceptional generalization capability. Code is available at https://github.com/lzp-lkd/LFAGCU.

show abstract

Section: Methodsmentioning

confidence: 99%

Local feature acquisition and global context understanding network for very high-resolution land cover classification

Li,

Hu,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Fusion of shallow artificial features and deep features has shown its effectiveness in multi-source image classification [48,49]. In order to offer a more comprehensive representation for Martian landforms from the single-band and gray-scale images, the extracted abstract convolutional features from scene-level view and the multi-texture features from local landform view are fused.…”

Section: ) Multi-view Features Fusion and Classificationmentioning

confidence: 99%

MarsMapNet: A Novel Superpixel-Guided Multiview Feature Fusion Network for Efficient Martian Landform Mapping

Zhao,

Liu,

Tong

et al. 2024

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Abstract-Landform classification and mapping of the Martian surface using Mars orbiter images can provide an important reference for landing site selection and rovers' traversability evaluation in Mars exploration. Moreover, specific Martian landforms are closely associated with the evidences of water-related activities and Martian life, thus have crucial research importance. This article proposes a novel superpixelguided multi-view feature fusion network (MarsMapNet) for efficient mapping of the Martian landforms. In particular, the proposed MarsMapNet first generates the superpixel-level segments from Mars orbiter images by considering local morphological homogeneity of landforms. Then a multi-view feature extraction and fusion (MVF) network is developed, where abstract convolutional features are extracted based on scene-level patches, and multi-textures are extracted based on local landform from shallow-to-deep feature learning. After the network being trained on scene-level samples and guided by the superpixel segmentation, Martian landforms can be correctly classified in an efficient way, whose mapping time cost sharply decreased when compared to the reference methods. The proposed MarsMapNet has been validated on three real landing sites from several Mars missions (i.e., the Jezero Crater, the Southern Utopia Planitia, the Oxia Planum) by using the Mars Reconnaissance Orbiter's Context Camera (CTX) images. Qualitative and quantitative analysis on the obtained experimental results confirm the effectiveness and efficiency of the proposed MarsMapNet when compared with the state-of-theart methods, demonstrating its potential for supporting a Martian global landform mapping in the future.

show abstract

“…The proposed FGMCN and SPP methods are compared with some algorithms for performance validation, including ResNet-34 [20], SSRN [39], MSPSSRN [40], AMDF [3], CANet [41], and SDF 2 N [42] to ascertain the efficacy of the proposed approach, which are all CNN-based. Among them, ResNet-34 is a standard residual network, CANet is a residual network with an attention mechanism, SSRN is for hyperspectral images, while MSPSSRN, AMDF and SDF 2 N are specifically designed for multispectral images.…”

Section: Parameter Settingmentioning

confidence: 99%

Land Use Classification of High-Resolution Multispectral Satellite Images With Fine-Grained Multiscale Networks and Superpixel Postprocessing

Deng

Wei

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Land use recognition from multispectral satellite images is fundamentally critical for geological applications, but the results are not satisfied. The scale dimension of current multiscale learning is too coarse to account for rich scales in multispectral images, and pixel-wise classification tends to produce "salt-and-pepper" labels due to possible misclassification in heterogeneous regions. In this paper, these issues are addressed by proposing a new pixel-wise classification model with finer scales for convolutional neural networks. The model is designed to extract multiscale contextual information using multiscale networks at a fine-grained level, addressing the issue of insufficient multiscale learning for classification. Furthermore, a smallscale segmentation-combination method is introduced as a postprocessing solution to smooth fragmented classification results. The proposed method is tested on GF-1, GF-2, DEIMOS-2, GeoEye-1, and Sentinel-2 satellite images, and compared with six neural-network-based algorithms. The results demonstrate the effectiveness of the proposed model in finding objects of large scale difference, improving classification accuracy, and reducing classified fragments. The discussion also illustrates that convolutional neural networks and pixel-wise inference are more practical than Transformer and patch-wise recognition.

show abstract

A Shallow-to-Deep Feature Fusion Network for VHR Remote Sensing Image Classification

Cited by 24 publications

References 44 publications

Local feature acquisition and global context understanding network for very high-resolution land cover classification

Local feature acquisition and global context understanding network for very high-resolution land cover classification

MarsMapNet: A Novel Superpixel-Guided Multiview Feature Fusion Network for Efficient Martian Landform Mapping

Land Use Classification of High-Resolution Multispectral Satellite Images With Fine-Grained Multiscale Networks and Superpixel Postprocessing

Contact Info

Product

Resources

About