scholarly journals Multiclass Non-Randomized Spectral–Spatial Active Learning for Hyperspectral Image Classification

2020 ◽  
Vol 10 (14) ◽  
pp. 4739 ◽  
Author(s):  
Muhammad Ahmad ◽  
Manuel Mazzara ◽  
Rana Aamir Raza ◽  
Salvatore Distefano ◽  
Muhammad Asif ◽  
...  
Keyword(s):  
Active Learning ◽  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Statistical Tests ◽  
Sample Selection ◽  
Support Vector ◽  
Selection Methods ◽  
Hyperspectral Image Classification ◽  
Stopping Criteria

Active Learning (AL) for Hyperspectral Image Classification (HSIC) has been extensively studied. However, the traditional AL methods do not consider randomness among the existing and new samples. Secondly, very limited AL research has been carried out on joint spectral–spatial information. Thirdly, a minor but still worth mentioning factor is the stopping criteria. Therefore, this study caters to all these issues using a spatial prior Fuzziness concept coupled with Multinomial Logistic Regression via a Splitting and Augmented Lagrangian (MLR-LORSAL) classifier with dual stopping criteria. This work further compares several sample selection methods with the diverse nature of classifiers i.e., probabilistic and non-probabilistic. The sample selection methods include Breaking Ties (BT), Mutual Information (MI) and Modified Breaking Ties (MBT). The comparative classifiers include Support Vector Machine (SVM), Extreme Learning Machine (ELM), K-Nearest Neighbour (KNN) and Ensemble Learning (EL). The experimental results on three benchmark hyperspectral datasets reveal that the proposed pipeline significantly increases the classification accuracy and generalization performance. To further validate the performance, several statistical tests are also considered such as Precision, Recall and F1-Score.

scholarly journals Spectral-Spatial Hyperspectral Image Classification Based on Homogeneous Minimum Spanning Forest

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
F. Poorahangaryan ◽  
H. Ghassemian
Keyword(s):  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Feature Space ◽  
Support Vector ◽  
Hyperspectral Image Classification ◽  
Spatial Classification ◽  
Spanning Forest ◽  
Minimum Spanning Forest ◽  
Initial Classification

The combination of spectral and spatial information is known as a suitable way to improve the accuracy of hyperspectral image classification. In this paper, we propose a spectral-spatial hyperspectral image classification approach composed of the following stages. Initially, the support vector machine (SVM) is applied to obtain the initial classification map. Then, we present a new index called the homogeneity order and, using that with K-nearest neighbors, we select some pixels in feature space. The extracted pixels are considered as markers for Minimum Spanning Forest (MSF) construction. The class assignment to the markers is done using the initial classification map results. In the final stage, MSF is applied to these markers, and a spectral-spatial classification map is obtained. Experiments performed on several real hyperspectral images demonstrate that the classification accuracies obtained by the proposed scheme are improved when compared to MSF-based spectral-spatial classification approaches.

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

2011 ◽  
Vol 5 (3) ◽  
pp. 618-628 ◽  
Author(s):  
Wei Di ◽  
Melba M. Crawford
Keyword(s):  
Active Learning ◽  
Image Classification ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Hyperspectral Data ◽  
Unlabeled Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Small Subset ◽  
Hyperspectral Image Classification

A novel co-regularization framework for active learning is proposed for hyperspectral image classification. The first regularizer explores the intrinsic multi-view information embedded in the hyperspectral data. By adaptively and quantitatively measuring the disagreement level, it focuses only on samples with high uncertainty and builds a contention pool which is a small subset of the overall unlabeled data pool, thereby mitigating the computational cost. The second regularizer is based on the “consistency assumption” and designed on a spatial or the spectral based manifold space. It serves to further focus on the most informative samples within the contention pool by penalizing rapid changes in the classification function evaluated on proximally close samples in a local region. Such changes may be due to the lack of capability of the current learner to describe the unlabeled data. Incorporating manifold learning into the active learning process enforces the clustering assumption and avoids the degradation of the distance measure associated with the original high-dimensional spectral features. One spatial and two local spectral embedding methods are considered in this study, in conjunction with the support vector machine (SVM) classifier implemented with a radial basis function (RBF) kernel. Experiments show excellent performance on AVIRIS and Hyperion hyperspectral data as compared to random sampling and the state-of-the-art SVMSIMPLE.

scholarly journals Improved Fusion of Spatial Information into Hyperspectral Classification through the Aggregation of Constrained Segment Trees: Segment Forest

2021 ◽  
Vol 13 (23) ◽  
pp. 4816
Author(s):  
Jianmei Ling ◽  
Lu Li ◽  
Haiyan Wang
Keyword(s):  
Dimension Reduction ◽  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Principal Component ◽  
Support Vector ◽  
Hyperspectral Image Classification ◽  
Segment Tree ◽  
Public Data ◽  
Initial Classification

Compared with traditional optical and multispectral remote sensing images, hyperspectral images have hundreds of bands that can provide the possibility of fine classification of the earth’s surface. At the same time, a hyperspectral image is an image that coexists with the spatial and spectral. It has become a hot research topic to combine the spatial spectrum information of the image to classify hyperspectral features. Based on the idea of spatial–spectral classification, this paper proposes a novel hyperspectral image classification method based on a segment forest (SF). Firstly, the first principal component of the image was extracted by the process of principal component analysis (PCA) data dimension reduction, and the data constructed the segment forest after dimension reduction to extract the non-local prior spatial information of the image. Secondly, the images’ initial classification results and probability distribution were obtained using support vector machine (SVM), and the spectral information of the images was extracted. Finally, the segment forest constructed above is used to optimize the initial classification results and obtain the final classification results. In this paper, three domestic and foreign public data sets were selected to verify the segment forest classification. SF effectively improved the classification accuracy of SVM, and the overall accuracy of Salinas was enhanced by 11.16%, WHU-Hi-HongHu by 15.89%, and XiongAn by 19.56%. Then, it was compared with six decision-level improved space spectrum classification methods, including guided filtering (GF), Markov random field (MRF), random walk (RW), minimum spanning tree (MST), MST+, and segment tree (ST). The results show that the segment forest-based hyperspectral image classification improves accuracy and efficiency compared with other algorithms, proving the algorithm’s effectiveness.

scholarly journals Approaches for Hyperspectral Image Classification Detailed Review

2021 ◽  
Vol 11 (1) ◽  
pp. 13-22
Author(s):  
Kushalatha M R ◽  
◽  
Prasantha H S ◽  
Beena R. Shetty ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Support Vector ◽  
Electromagnetic Spectrum ◽  
Hyperspectral Image Classification ◽  
Sensing Applications ◽  
Remote Sensing Applications

Hyperspectral Image (HSI) processing is the new advancement in image / signal processing field. The growth over the years is appreciable. The main reason behind the successful growth of the Hyperspectral imaging field is due to the enormous amount of spectral and spatial information that the imagery contains. The spectral band that the HSI which contains is also more in number. When an image is captured through the HSI cameras, it contains around 200-250 images of the same scene. Nowadays HSI is used extensively in the fields of environmental monitoring, Crop-Field monitoring, Classification, Identification, Remote sensing applications, Surveillance etc. The spectral and spatial information content present in Hyperspectral images are with high resolutions.Hyperspectral imaging has shown significant growth and widely used in most of the remote sensing applications due to its presence of information of a scene over hundreds of contiguous bands In. Hyperspectral Image Classification of materials is the critical application of HSI using Hyperspectral sensors. It collects hundreds of spectrum channels, where each channel consists of a sharp point of Electromagnetic Spectrum. The paper mainly focuses on Deep Learning techniques such as Convolutional Neural Network (CNN), Artificial Neural Network (ANN), and Support Vector machines (SVM), K-Nearest Neighbour (KNN) for the accuracy in classification. Finally in the summary the current state-of-the-art scheme, a critical discussion after reviewing the research work by other professionals and organizing it into review-based paper, also implying about the present status on classification accuracy using neural networks is carried out.

Sign in / Sign up

Export Citation Format

Share Document