Spectral-Spatial Classification of Hyperspectral Images Using Joint Bilateral Filter and Graph Cut Based Model

Wang, Yi; Song, Haiwei; Zhang, Yan

doi:10.3390/rs8090748

Cited by 32 publications

(12 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tian et al [20] applied the random forest classifier to classify wetland land covers from multi-sensor data. Wang et al [21] used the SVM-based joint bilateral filter to classify hyperspectral images. Das et al [22] presented a probabilistic SVM to detect roads from VHR multispectral images with the aid of two salient features of roads and the design of a leveled structure.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

Zhang

et al. 2019

Remote Sensing

177

View full text Add to dashboard Cite

Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks-FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement.

show abstract

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

Zhang

et al. 2019

Remote Sensing

177

View full text Add to dashboard Cite

show abstract

“…In computer vision, image segmentation tries to simplify any image by assigning to each pixel a label (here equivalent to a cluster) from a small set of labels. Image segmentation has been successfully applied for applications such as cancer detection and automated driving (López and Malpica 2008;Tarabalka and Charpiat 2013;Tarabalka and Rana 2014;Wang et al 2016).…”

Section: Spatial Correctionmentioning

confidence: 99%

Fuzzy Clustering with Spatial Correction and Its Application to Geometallurgical Domaining

Sepúlveda

Dowd

2018

Math Geosci

View full text Add to dashboard Cite

Self-archiving for articles in subscription-based journals Springer journals' policy on preprint sharing. By signing the Copyright Transfer Statement you still retain substantial rights, such as self-archiving: Author(s) are permitted to self-archive a pre-print and an author's accepted manuscript version of their Article. ………. b. An Author's Accepted Manuscript (AAM) is the version accepted for publication in a journal following peer review but prior to copyediting and typesetting that can be made available under the following conditions: (i) Author(s) retain the right to make an AAM of their Article available on their own personal, selfmaintained website immediately on acceptance, (ii) Author(s) retain the right to make an AAM of their Article available for public release on any of the following 12 months after first publication ("Embargo Period"): their employer's internal website; their institutional and/or funder repositories. AAMs may also be deposited in such repositories immediately on acceptance, provided that they are not made publicly available until after the Embargo Period.

show abstract

“…Then, a final classification map is obtained by combining its pixel-wise classification map and its segmentation map by employing a majority voting algorithm. The segmentation map can be obtained by using the most popular unsupervised algorithms, such as mean-shift [38], watershed [39], hierarchical segmentation [23,40], minimum spanning forest [41], and graph cut [42]. The main challenge is to obtain accurate object-based segmentation results of HSIs.…”

Section: Introductionmentioning

confidence: 99%

Multiple Kernel-Based SVM Classification of Hyperspectral Images by Combining Spectral, Spatial, and Semantic Information

Wang

Fang

2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

In this study, we present a hyperspectral image classification method by combining spectral, spatial, and semantic information. The main steps of the proposed method are summarized as follows: First, principal component analysis transform is conducted on an original image to produce its extended morphological profile, Gabor features, and superpixel-based segmentation map. To model spatial information, the extended morphological profile and Gabor features are used to represent structure and texture features, respectively. Moreover, the mean filtering is performed within each superpixel to maintain the homogeneity of the spatial features. Then, the k-means clustering and the entropy rate superpixel segmentation are combined to produce semantic feature vectors by using a bag of visual-words model for each superpixel. Next, three kernel functions are constructed to describe the spectral, spatial, and semantic information, respectively. Finally, the composite kernel technique is used to fuse all the features into a multiple kernel function that is fed into a support vector machine classifier to produce a final classification map. Experiments demonstrate that the proposed method is superior to the most popular kernel-based classification methods in terms of both visual inspection and quantitative analysis, even if only very limited training samples are available.

show abstract

Spectral-Spatial Classification of Hyperspectral Images Using Joint Bilateral Filter and Graph Cut Based Model

Cited by 32 publications

References 52 publications

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

Fuzzy Clustering with Spatial Correction and Its Application to Geometallurgical Domaining

Multiple Kernel-Based SVM Classification of Hyperspectral Images by Combining Spectral, Spatial, and Semantic Information

Contact Info

Product

Resources

About