Spatial Techniques for Image Classification

Aksoy, Selim

doi:10.1201/9781420003130.ch22

Cited by 17 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification accuracy using the complete set of spectral bands without feature selection/extraction is 66.02% for the HYDICE data and 64.72% for the AVIRIS data. These results are lower than the published results when feature extraction was conducted [26], [27] showing the strong need for feature reduction. For each method and data set, the overall classification accuracies are given in Fig.…”

Section: Classification Resultscontrasting

confidence: 84%

Subspace Detection Using a Mutual Information Measure for Hyperspectral Image Classification

Hossain

Jia

Pickering

2014

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Finding a subspace which consists of the most informative features for reliable hyperspectral image classification is a challenging task. Feature reduction is often achieved via feature selection and feature extraction techniques. In this letter, a hybrid approach which combines both treatments is proposed. Principal Component Analysis (PCA) is applied as a preprocessing step so that each of the new features is generated from the complete set of the original spectral bands. Feature selection is then performed effectively using a normalized Mutual Information (nMI) measure with two constraints to maximize general relevance and minimize redundancy in the selected subspace. The proposed algorithm (PCA-nMI) is tested on hyperspectral images and the experimental results show that the modifications give significant improvement in terms of classification accuracy.

show abstract

Section: Classification Resultscontrasting

confidence: 84%

Subspace Detection Using a Mutual Information Measure for Hyperspectral Image Classification

Hossain

Jia

Pickering

2014

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…In the EO field, the texture descriptors are based on the statistical properties or structure of the texture. The cooccurrence matrix is the basis for the texture descriptor in [26], while in [27] the Gabor features are obtained by filtering the first principal component image with Gabor kernels at 4 different scales and 4 different directions. In [28], the Wavelet features are used for object-based retrieval in EO archives.…”

Section: A Existing Methods and Algorithms For Eo Data Analysis Featmentioning

confidence: 99%

Multispectral Data Analysis for Semantic Assessment—A SNAP Framework for Sentinel-2 Use Case Scenarios

Grivei

Neagoe

Georgescu

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Sentinel-2 satellites provide systematic global coverage of land surfaces, measuring physical properties within 13 spectral intervals at a temporal resolution of 5 days. Computer-based data analysis is highly required to extract similarity by processing and to assist human understanding and semantic annotation in support of mapping Earth's surface. This paper proposes a data mining concept that uses advanced data visualization and explainable features to enhance relevant aspects in the Sentinel-2 data and enable semantic analysis. There is a two-stage process. At first, spectral, texture, and physical parameters related features are extracted from the data and included in a learning process that models the data content according to statistical similarities. In parallel, the second processing stage maximizes the data impact on the human visual system to help image understanding and interpretation. Target classes are subject to exploratory visual analysis, such that both visual and latent characteristics are revealed to the user. The concept is further implemented as Sentinel-2 dedicated data analysis (DAS-Tool) plugin for the Sentinel Application Platform (SNAP) and deployed as an open-source tool empowering the Earth Observation (EO) community with fast and reliable results. Accommodating multiple solutions for each processing phase, the plugin enables flexibility in information extraction and knowledge discovery that will bring the best accuracy in mapping applications. For demonstration purposes, the authors focus on a detailed benchmark against reference data (ground truth) for the Southern region of Romania, then use the selected algorithms in a forest fires scenario analysis for the Sydney region in Australia. The processing involves full-size Sentinel-2 images.

show abstract

“…Although better results have been achieved by MRF, it may suffer from time issue for the iterative optimization step and the high dimensionality of hyperspectral images [2]. Another approach to use the spatial information is to extract the contextual features in the neighborhood [24]- [26]. These additional features benefit the classification process and thus improve the classification accuracy.…”

Section: A Related Workmentioning

confidence: 97%

A Probabilistic Framework for Spectral–Spatial Classification of Hyperspectral Images

Liu

2016

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Classification of hyperspectral images usually suffers from high dimensionality and few reference data, which limits the performance of the pixelwise classifiers. The spectral-spatial classifiers, which integrate the spectral data and the spatial information during the classification, perform impressively in terms of the high classification accuracy and the homogeneous appearance of the classification map. In this paper, we propose a new probabilistic framework for spectral-spatial classification (PFSSC), which integrates the spectral data and the spatial information from the probabilistic point of view. Both the spectral data and the spatial information are used to estimate the per-pixel probability, which gives the likelihood that one pixel belongs to one class, respectively. The classification map can then be directly derived from the joint probability. In the proposed framework, a pixelwise probabilistic classifier can be extended as a spectral-spatial one since it can integrate spatial information easily. Furthermore, these spectral-spatial classifiers in the proposed framework are realized in an iterative way to avoid the problem caused by the limited reference data to some extent. In each iterative step, some unassigned pixels are classified by considering the pixels assigned in previous iterative steps. In this iterative process, pixels are assigned to specific labels step by step gradually. In the proposed framework, the probabilistic support vector machine (SVM) and random forest (RF) are extended to be two spectral-spatial classifiers. In short, we denote them as SVM-PFSSC and RF-PFSSC, respectively. The experimental results show that SVM-PFSSC and RF-PFSSC outperform some pixelwise and spectral-spatial classifiers.

show abstract

Spatial Techniques for Image Classification

Cited by 17 publications

References 22 publications

Subspace Detection Using a Mutual Information Measure for Hyperspectral Image Classification

Subspace Detection Using a Mutual Information Measure for Hyperspectral Image Classification

Multispectral Data Analysis for Semantic Assessment—A SNAP Framework for Sentinel-2 Use Case Scenarios

A Probabilistic Framework for Spectral–Spatial Classification of Hyperspectral Images

Contact Info

Product

Resources

About