Determining surface magnetic susceptibility of loess-paleosol sections based on spectral features: Application to a UHD 185 hyperspectral image

2016 ◽  
Vol 50 ◽  
pp. 159-169 ◽  
Author(s):  
Jing Cui ◽  
Shimin Zhang ◽  
Jingfa Zhang ◽  
Xudong Liu ◽  
Rui Ding ◽  
...  
Keyword(s):  
Magnetic Susceptibility ◽  
Hyperspectral Image ◽  
Spectral Features

scholarly journals A Novel Hyperspectral Image Classification Pattern Using Random Patches Convolution and Local Covariance

2019 ◽  
Vol 11 (16) ◽  
pp. 1954 ◽  
Author(s):  
Yangjie Sun ◽  
Zhongliang Fu ◽  
Liang Fan
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Qualitative Evaluation ◽  
Support Vector ◽  
Spectral Features ◽  
Hyperspectral Image Classification ◽  
Spectral Bands ◽  
Public Data ◽  
Local Covariance ◽  
Classification Pattern

Today, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, such approaches are still hampered by long training times. Traditional spectral–spatial hyperspectral image classification only utilizes spectral features at the pixel level, without considering the correlation between local spectral signatures. Our article has tested a novel hyperspectral image classification pattern, using random-patches convolution and local covariance (RPCC). The RPCC is an effective two-branch method that, on the one hand, obtains a specified number of convolution kernels from the image space through a random strategy and, on the other hand, constructs a covariance matrix between different spectral bands by clustering local neighboring pixels. In our method, the spatial features come from multi-scale and multi-level convolutional layers. The spectral features represent the correlations between different bands. We use the support vector machine as well as spectral and spatial fusion matrices to obtain classification results. Through experiments, RPCC is tested with five excellent methods on three public data-sets. Quantitative and qualitative evaluation indicators indicate that the accuracy of our RPCC method can match or exceed the current state-of-the-art methods.

scholarly journals Spectral-Spatial Hyperspectral Image Classification with Superpixel Pattern and Extreme Learning Machine

2019 ◽  
Vol 11 (17) ◽  
pp. 1983 ◽  
Author(s):  
Yongshan Zhang ◽  
Xinwei Jiang ◽  
Xinxin Wang ◽  
Zhihua Cai
Keyword(s):  
Remote Sensing ◽  
Extreme Learning Machine ◽  
Spatial Patterns ◽  
Hyperspectral Image ◽  
Classification Model ◽  
Image Texture ◽  
Spatial Characteristic ◽  
Spectral Features ◽  
Sensing Applications ◽  
Learning Machine

Spectral-spatial classification of hyperspectral images (HSIs) has recently attracted great attention in the research domain of remote sensing. It is well-known that, in remote sensing applications, spectral features are the fundamental information and spatial patterns provide the complementary information. With both spectral features and spatial patterns, hyperspectral image (HSI) applications can be fully explored and the classification performance can be greatly improved. In reality, spatial patterns can be extracted to represent a line, a clustering of points or image texture, which denote the local or global spatial characteristic of HSIs. In this paper, we propose a spectral-spatial HSI classification model based on superpixel pattern (SP) and kernel based extreme learning machine (KELM), called SP-KELM, to identify the land covers of pixels in HSIs. In the proposed SP-KELM model, superpixel pattern features are extracted by an advanced principal component analysis (PCA), which is based on superpixel segmentation in HSIs and used to denote spatial information. The KELM method is then employed to be a classifier in the proposed spectral-spatial model with both the original spectral features and the extracted spatial pattern features. Experimental results on three publicly available HSI datasets verify the effectiveness of the proposed SP-KELM model, with the performance improvement of 10% over the spectral approaches.

scholarly journals A Lightweight Spectral–Spatial Feature Extraction and Fusion Network for Hyperspectral Image Classification

2020 ◽  
Vol 12 (9) ◽  
pp. 1395
Author(s):  
Linlin Chen ◽  
Zhihui Wei ◽  
Yang Xu
Keyword(s):  
Classification Accuracy ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Spectral Features ◽  
Classification Methods ◽  
Hyperspectral Image Classification ◽  
Spatial Feature ◽  
Deep Network ◽  
Spatial Features ◽  
Reduced Parameters

Hyperspectral image (HSI) classification accuracy has been greatly improved by employing deep learning. The current research mainly focuses on how to build a deep network to improve the accuracy. However, these networks tend to be more complex and have more parameters, which makes the model difficult to train and easy to overfit. Therefore, we present a lightweight deep convolutional neural network (CNN) model called S2FEF-CNN. In this model, three S2FEF blocks are used for the joint spectral–spatial features extraction. Each S2FEF block uses 1D spectral convolution to extract spectral features and 2D spatial convolution to extract spatial features, respectively, and then fuses spectral and spatial features by multiplication. Instead of using the full connected layer, two pooling layers follow three blocks for dimension reduction, which further reduces the training parameters. We compared our method with some state-of-the-art HSI classification methods based on deep network on three commonly used hyperspectral datasets. The results show that our network can achieve a comparable classification accuracy with significantly reduced parameters compared to the above deep networks, which reflects its potential advantages in HSI classification.

scholarly journals A Multi-Scale and Multi-Level Spectral-Spatial Feature Fusion Network for Hyperspectral Image Classification

2020 ◽  
Vol 12 (1) ◽  
pp. 125 ◽  
Author(s):  
Mu ◽  
Guo ◽  
Liu
Keyword(s):  
Neural Network ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Hyperspectral Images ◽  
Spectral Features ◽  
Hyperspectral Image Classification ◽  
Spatial Feature ◽  
Multi Scale ◽  
Spatial Features ◽  
Multi Level

Extracting spatial and spectral features through deep neural networks has become an effective means of classification of hyperspectral images. However, most networks rarely consider the extraction of multi-scale spatial features and cannot fully integrate spatial and spectral features. In order to solve these problems, this paper proposes a multi-scale and multi-level spectral-spatial feature fusion network (MSSN) for hyperspectral image classification. The network uses the original 3D cube as input data and does not need to use feature engineering. In the MSSN, using different scale neighborhood blocks as the input of the network, the spectral-spatial features of different scales can be effectively extracted. The proposed 3D–2D alternating residual block combines the spectral features extracted by the three-dimensional convolutional neural network (3D-CNN) with the spatial features extracted by the two-dimensional convolutional neural network (2D-CNN). It not only achieves the fusion of spectral features and spatial features but also achieves the fusion of high-level features and low-level features. Experimental results on four hyperspectral datasets show that this method is superior to several state-of-the-art classification methods for hyperspectral images.

Hyperspectral image compression based on online learning spectral features dictionary

2017 ◽  
Vol 76 (23) ◽  
pp. 25003-25014 ◽  
Author(s):  
Worku Jifara ◽  
Feng Jiang ◽  
Bing Zhang ◽  
Huapeng Wang ◽  
Jinsong Li ◽  
...  
Keyword(s):  
Online Learning ◽  
Image Compression ◽  
Hyperspectral Image ◽  
Spectral Features ◽  
Hyperspectral Image Compression

scholarly journals Spatial–Spectral Feature Refinement for Hyperspectral Image Classification Based on Attention-Dense 3D-2D-CNN

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5191
Author(s):  
Jin Zhang ◽  
Fengyuan Wei ◽  
Fan Feng ◽  
Chunyang Wang
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Spectral Feature ◽  
Small Sample ◽  
Training Data ◽  
Spectral Features ◽  
Training Samples ◽  
Proposed Model ◽  
Limited Training Samples ◽  
Hyperspectral Classification

Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). In our proposed model, a dense block was used to reuse shallow features and aimed at better exploiting hierarchical spatial–spectral features. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial–spectral features was realized by the channel attention method and spatial attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer, respectively. Experiment results indicate that our proposed model can learn more discriminative spatial–spectral features using very few training data. In Indian Pines, Salinas and the University of Pavia, AD-HybridSN obtain 97.02%, 99.59% and 98.32% overall accuracy using only 5%, 1% and 1% labeled data for training, respectively, which are far better than all the contrast models.

scholarly journals The Potential of Multi- and HyperSpectral Air- and Spaceborne Sensors to Detect Crude Oil Hydrocarbon in Soils Long after a Contamination Event

2019 ◽  
Vol 9 (23) ◽  
pp. 5151 ◽  
Author(s):  
Ran Pelta ◽  
Eyal Ben-Dor
Keyword(s):  
Crude Oil ◽  
Hyperspectral Image ◽  
Spectral Characteristics ◽  
Spectral Features ◽  
Basic Premise ◽  
Promising Tool ◽  
Quality Classification ◽  
Spatial Configurations ◽  
Contamination Event ◽  
Original Size

Crude oil contamination is hazardous to health, negatively impacts vital life sources, and causes land and ecological degradation. The basic premise of the prevalent spectroscopic analyses for detecting such contamination is that crude oil spectral features are observable in the spectrum. Such analyses, however, have failed to address instances where the expected spectral features are not visible in the spectrum. Hence, a more refined method was recently published, which accounts for such cases. This method was successfully applied to a hyperspectral image over an arid area long after a contamination event. This study aimed to determine whether that same method could be successfully applied using a variety of other operational and future instruments, both air- and spaceborne, with different spatial and spectral characteristics. To that end, a series of simulation experiments was performed, including various spectral and spatial resolutions. Quantitative and qualitative evaluations of the classification are reported. The results indicate that the hyperspectral information can be reduced to one-third of its original size, while maintaining high accuracy and a quality classification map. A ground sampling distance of 7.5 m seems to be the boundary of an acceptable classification outcome. The overall conclusion of this study was that the method is robust enough to perform under various spectral and spatial configurations. Therefore, it could be a promising tool to be integrated into environmental protection and resource management programs.

scholarly journals A hyperspectral image classification algorithm based on atrous convolution

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Xiaoqing Zhang ◽  
Yongguo Zheng ◽  
Weike Liu ◽  
Zhiyong Wang
Keyword(s):  
Neural Networks ◽  
Receptive Field ◽  
High Efficiency ◽  
Hyperspectral Image ◽  
Hyperspectral Images ◽  
Spectral Features ◽  
Hyperspectral Image Classification ◽  
Deep Convolutional Neural Networks ◽  
Multi Level ◽  
Spatial Size

AbstractHyperspectral images not only have high spectral dimension, but the spatial size of datasets containing such kind of images is also small. Aiming at this problem, we design the NG-APC (non-gridding multi-level concatenated Atrous Pyramid Convolution) module based on the combined atrous convolution. By expanding the receptive field of three layers convolution from 7 to 45, the module can obtain a distanced combination of the spectral features of hyperspectral pixels and solve the gridding problem of atrous convolution. In NG-APC module, we construct a 15-layer Deep Convolutional Neural Networks (DCNN) model to classify each hyperspectral pixel. Through the experiments on the Pavia University dataset, the model reaches 97.9% accuracy while the parameter amount is only 0.25 M. Compared with other CNN algorithms, our method gets the best OA (Over All Accuracy) and Kappa metrics, at the same time, NG-APC module keeps good performance and high efficiency with smaller number of parameters.

Sign in / Sign up

Export Citation Format

Share Document