Introduction of Spatio-Spectral Indices for Using Spatial Data in Multispectral Image Classification
- PDF / 3,116,068 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 98 Downloads / 220 Views
RESEARCH ARTICLE
Introduction of Spatio-Spectral Indices for Using Spatial Data in Multispectral Image Classification Hamed Ashoori1
•
Mohamad Javad Valadan Zoej1 • Mahmod Reza Sahebi1
Received: 9 July 2018 / Accepted: 28 January 2019 Ó Indian Society of Remote Sensing 2019
Abstract Different methods of using spatial information in image classification are presented. One approach is to quantify image texture to produce features for use in classifiers, and there are various methods with adjustable parameters for texture quantification. The produced features are numerous and are in different discriminating image classes. Therefore, there is a need for selecting their optimum combination, or to alternatively create a set of features that abstract their class discernibility. Inspired by spectral normalized difference indices, the concept of the spatio-spectral index is introduced in this article to produce indices from a series of spatial features created from image spectral bands. In the proposed method, the produced spatio-spectral indices for each class are used as the abstract of spatial features. Along with the image spectral bands, they are used as new feature forms for supervised classification. Features with maximum and minimum values in each class were selected after production of the average vector in the feature space, and the removal of features with a small variation range. Next, non-repetitive band pairs were selected and spatio-spectral indices were produced. Using this method, the number of selected spatial features was at most twice the number of classes and was used to produce spatiospectral indices. Use of the produced features in classification improves classification accuracy significantly (about 30% and 6% in the two test images used here) by enhancing class discrimination and decreasing computational time. This method is also explicit and direct, with no need to use iterative optimization processes. Keywords Spatio-spectral index Supervised classification Image texture quantization
Introduction Classification is one of the most common methods of information extraction from satellite images used in academic and industrial research projects. In conventional classification methods, the gray values of image pixels in different spectral bands are used as input. These features exhibit limitations when dealing with complicated scenes, and class separation is only possible for well-distinguished & Hamed Ashoori [email protected] Mohamad Javad Valadan Zoej [email protected] Mahmod Reza Sahebi [email protected] 1
Photogrammetry and Remote Sensing Department, Geomatics Faculty, K.N. Toosi University of Technology, Tehran, Iran
ground features. When identifying image objects, the operator uses spatial features as important tools to distinguish between different objects. These features are detectable and can be used for object identification in spatially high-resolution images. As high-resolution images become more readily available, optimized methods are being developed to maximize t
Data Loading...
