Efficient Semantic Segmentation of Hyperspectral Images Using Adaptable Rectangular Convolution

García, José Manuel Menéndez; Paoletti, Mercedes E.; Jiménez, Luis Ignacio; Haut, Juan M.

doi:10.1109/lgrs.2022.3140950

Cited by 13 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They explored different spatial granularities of the HSI data and compared it with RGB data and processed HSI data. In [245] authors introduced a novel technique called Adaptable Rectangular Convolutions (ARCs) to address challenges in hyperspectral image semantic segmentation using convolutional neural networks (CNNs). In [246] authors present a novel approach called Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for material discrimination in hyperspectral images.…”

Section: B Recent Algorithmsmentioning

confidence: 99%

Hyperspectral Imaging Algorithms and Applications: A Review

Akewar,

Chandak

2023

Preprint

View full text Add to dashboard Cite

<p>The paper covers topics ranging from hyperspectral imaging applications to innovative algorithms that have enhanced the analysis of hyperspectral data. We delve into the practical applications, including Agriculture, Food Quality and Safety, Earth Sciences, Exploration and Monitoring, Healthcare, Pharmaceuticals, Medical Imaging, Industrial Manufacturing, Management, Conservation, Safety and Security. Our goal is to provide a holistic understanding of how hyperspectral imaging is transforming these fields and driving new possibilities. We also discussed detailed algorithmic development in Hyperspectral Imaging including Supervised and Unsupervised algorithms. We reviewed algorithmic development from the early 1980’s to recent developments including Artificial Intelligence involving algorithms from Machine Learning to Deep Learning. We believe our paper will be of particular interest to your readers for those who wish to study algorithm development from simple image processing procedures to AI based approaches and how these algorithms are used in diverse applications to make intelligent decisions for increasing productivity and efficiency in Agriculture, Exploration and Management and identification of diseases and natural resources. Our paper is well organized into various sections as per algorithms and applications. We reviewed more than 250 papers with proper citations and authors' research work.</p>

show abstract

Section: B Recent Algorithmsmentioning

confidence: 99%

Hyperspectral Imaging Algorithms and Applications: A Review

Akewar,

Chandak

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Between climate change, invasive species, and logging enterprises, it is important to know which ground types are where on a large scale. Recently, due to the widespread use of satellite imagery, big data hyperspectral images (HSI) are available to be utilized on a grand scale in ground-type semantic segmentation [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering

Soucy

Sekeh

2023

J Big Data

View full text Add to dashboard Cite

Most semantic segmentation approaches of big data hyperspectral images use and require preprocessing steps in the form of patching to accurately classify diversified land cover in remotely sensed images. These approaches use patching to incorporate the rich spatial neighborhood information in images and exploit the simplicity and segmentability of the most common datasets. In contrast, most landmasses in the world consist of overlapping and diffused classes, making neighborhood information weaker than what is seen in common datasets. To combat this common issue and generalize the segmentation models to more complex and diverse hyperspectral datasets, in this work, we propose a novel flagship model: Clustering Ensemble U-Net. Our model uses the ensemble method to combine spectral information extracted from convolutional neural network training on a cluster of landscape pixels. Our model outperforms existing state-of-the-art hyperspectral semantic segmentation methods and gets competitive performance with and without patching when compared to baseline models. We highlight our model’s high performance across six popular hyperspectral datasets including Kennedy Space Center, Houston, and Indian Pines, then compare them to current top-performing models.

show abstract

“…Using the patch-based method, one can only classify a single feature point at a time, and the data set needs to be cut into pieces before testing, which leads to low efficiency and complicates data-processing. Recently, a large number of hyperspectral object classification methods based on semantic segmentation have been introduced [11,[19][20][21]. We attempted to perform a direct segmentation of hyperspectral images and achieved satisfactory results.…”

Section: Introductionmentioning

confidence: 99%

Shallow-Guided Transformer for Semantic Segmentation of Hyperspectral Remote Sensing Imagery

et al. 2023

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have achieved great progress in the classification of surface objects with hyperspectral data, but due to the limitations of convolutional operations, CNNs cannot effectively interact with contextual information. Transformer succeeds in solving this problem, and thus has been widely used to classify hyperspectral surface objects in recent years. However, the huge computational load of Transformer poses a challenge in hyperspectral semantic segmentation tasks. In addition, the use of single Transformer discards the local correlation, making it ineffective for remote sensing tasks with small datasets. Therefore, we propose a new Transformer layered architecture that combines Transformer with CNN, adopts a feature dimensionality reduction module and a Transformer-style CNN module to extract shallow features and construct texture constraints, and employs the original Transformer Encoder to extract deep features. Furthermore, we also designed a simple Decoder to process shallow spatial detail information and deep semantic features separately. Experimental results based on three publicly available hyperspectral datasets show that our proposed method has significant advantages compared with other traditional CNN, Transformer-type models.

show abstract

Efficient Semantic Segmentation of Hyperspectral Images Using Adaptable Rectangular Convolution

Cited by 13 publications

References 18 publications

Hyperspectral Imaging Algorithms and Applications: A Review

Hyperspectral Imaging Algorithms and Applications: A Review

CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering

Shallow-Guided Transformer for Semantic Segmentation of Hyperspectral Remote Sensing Imagery

Contact Info

Product

Resources

About