Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification

Feng, Fan; Zhang, Yongsheng; Zhang, Jin; Liu, Bing

doi:10.3390/rs15020304

Cited by 9 publications

(6 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the performance of the HSSF-MLDSVM based hyper-spectral image object classification using HSI has been compared with the other existing feature fusion-based object classification techniques spectral-spatial dependent global learning (SSDGL) [10], central attention network (CAN) [11], convolution neural network -active learning-Markov random field (CNN-Al-MNF) [12], enhanced-multiscale feature-fusion network (EMFFN) [24], 3-dimension self-attention multiscale feature-fusion network (3DSA-MFN) [25], adaptive spectral-spatial feature fusion network (ASSFFN) [26], low-rank attention multiple feature-fusion network (LMAFN) [27], and deep support vector machine (DSVM) [28]. For evaluating the proposed HSSF-MLDSVM and other existing HSI object classification techniques, the Indian Pines dataset has been used.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral object classification using hybrid spectral-spatial fusion and noise tolerant soft-margin technique

Mani,

Raguttapalli Chowdareddy

2024

IJECE

View full text Add to dashboard Cite

Because of its spectral-spatial and temporal resolution of greater areas, hyperspectral imaging (HSI) has found widespread application in the field of object classification. The HSI is typically used to accurately determine an object's physical characteristics as well as to locate related objects with appropriate spectral fingerprints. As a result, the HSI has been extensively applied to object identification in several fields, including surveillance, agricultural monitoring, environmental research, and precision agriculture. However, because of their enormous size, objects require a lot of time to classify; for this reason, both spectral and spatial feature fusion have been completed. The existing classification strategy leads to increased misclassification, and the feature fusion method is unable to preserve semantic object inherent features; This study addresses the research difficulties by introducing a hybrid spectral-spatial fusion (HSSF) technique to minimize feature size while maintaining object intrinsic qualities; Lastly, a soft-margins kernel is proposed for multi-layer deep support vector machine (MLDSVM) to reduce misclassification. The standard Indian pines dataset is used for the experiment, and the outcome demonstrates that the HSSF-MLDSVM model performs substantially better in terms of accuracy and Kappa coefficient.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Next, small, medium, and large-scale features are spatially captured using PMN. In the end, a hierarchical fusion of features ensures improved high-level semantic features even with insufficient training data [26], [27]…”

Section: Literature Surveymentioning

confidence: 99%

Hyperspectral object classification using hybrid spectral-spatial fusion and noise tolerant soft-margin technique

Mani,

Raguttapalli Chowdareddy

2024

IJECE

View full text Add to dashboard Cite

show abstract

“…Then, PMN is used for capturing small, medium, and large-scale features spatially. Finally, feature are fused in hierarchical manner assuring better high-level semantic features considering limited training samples [25], [26].…”

Section: Literature Surveymentioning

confidence: 99%

A hybrid spectral-spatial fusion technique for hyperspectral object classification

Mani,

Raguttapalli Chowdareddy

2024

IJEECS

View full text Add to dashboard Cite

<span>In the field of object classification, hyperspectral imaging (HSI) has been widely used, due to its spectral-spatial, and temporal resolution of larger areas. The HSI is generally used to identify the objects physical properties in accurate manner and as well as to identify similar object with acceptable spectral signatures. Thus, the HSI has been widely used for object identification applications in different fields such as precision agriculture, environmental study, crop monitoring, and surveillance. However, the object classification is time consuming due to extremely large size; thus, the feature fusion of both spectral and spatial have been done. The current feature fusion method fails to retain semantic object intrinsic feature; further, current classification technique induces higher misclassification. In addressing the research issues this paper introduces a hybrid spectral-spatial fusion (HSSF) technique to reduce feature size and retains object intrinsic properties. Finally, in reducing misclassification a soft-margins kernel is introduced in support vector machine (SVM). Experiment is conducted on standard Indian Pines dataset; the result shows the HSSF-SVM model attain much higher accuracy and Kappa coefficient performance.</span>

show abstract

“…A Linear transformation is performed to adjust the feature dimensions and increase the nonlinear expressiveness, and another Linear transformation is performed. Finally, the Shape of the resultant tensor is re-substituted to the initial format for subsequent processing [16].…”

Section: Modelingmentioning

confidence: 99%

Hyperspectral Image Study based on Deep Learning Model HSI-ConvNext

Bian,

Zhao,

Wang

et al. 2023

TCSISR

View full text Add to dashboard Cite

In recent years, deep learning techniques have made significant research progress in the field of hyperspectral image processing. Hyperspectral images are widely used in agriculture, environmental monitoring, geological exploration and other fields due to their richness in material and spectral information about objects. Deep learning models play an important role in hyperspectral image research and are able to learn feature representations from large-scale high-dimensional data, improving the performance of tasks such as classification, segmentation, and detection. In the study, researchers usually improve and optimize for the features of hyperspectral images by constructing deep learning models such as HSI-ConvNext. It is able to capture the correlation between different bands, thus realizing semantic segmentation and target detection for hyperspectral images. Data augmentation can effectively expand the limited hyperspectral dataset, and migration learning is able to migrate the knowledge of models trained in other domains to hyperspectral image tasks. Realistic hyperspectral images can be generated for data enhancement and model training. In conclusion, the study of hyperspectral images based on the deep learning model HSI-ConvNext provides new methods and techniques for the analysis and application of hyperspectral data. In the future, with the continuous development of deep learning technology, we can expect more innovations and breakthroughs in the field of hyperspectral image processing.

show abstract

Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification

Cited by 9 publications

References 59 publications

Hyperspectral object classification using hybrid spectral-spatial fusion and noise tolerant soft-margin technique

Hyperspectral object classification using hybrid spectral-spatial fusion and noise tolerant soft-margin technique

A hybrid spectral-spatial fusion technique for hyperspectral object classification

Hyperspectral Image Study based on Deep Learning Model HSI-ConvNext

Contact Info

Product

Resources

About