Combining spectral and spatial information into hidden Markov models for unsupervised image classifciation
MetadataShow full item record
Unsupervised classification methodology applied to remote sensing image processing can provide benefits in automatically converting the raw image data into useful information so long as higher classification accuracy is achieved. The traditional k-means clustering scheme using spectral data alone does not perform well in general as far as accuracy is concerned. This is partly due to the failure to take the spatial inter-pixels dependencies (i.e. the context) into account, resulting in a â busyâ visual appearance to the output imagery. To address this, the hidden Markov models (HMM) are introduced in this study as a fundamental framework to incorporate both the spectral and contextual information in analysis. This helps generate more patch-like output imagery and produces higher classification accuracy in an unsupervised scheme. The newly developed unsupervised classification approach is based on observation-sequence and observation-density adjustments, which have been proposed for incorporating 2D spatial information into the linear HMM. For the observation-sequence adjustment methods, there are a total of five neighbourhood systems being proposed. Two neighbourhood systems were incorporated into the observationdensity methods for study. The classification accuracy is then evaluated by means of confusion matrices made by randomly chosen test samples. The classification obtained by k-means clustering and the HMM with commonly seen strip-like and Hilbert-Peano sequence fitting methods were also measured. Experimental results showed that the proposed approaches for combining both the spectral and spatial information into HMM unsupervised classification mechanism present improvements in both classification accuracy and visual qualities.
Showing items related by title, author, creator and subject.
McIver, Charles A. (Monterey, California: Naval Postgraduate School, 2017-03);Remote-sensing analysis is conducted for the Naval Postgraduate School campus, containing buildings, impervious surfaces (asphalt and concrete), natural ground, and vegetation. Data is from the Optech Titan, providing ...
Spectral dependence of texture features integrated with hyperspectral data for area target classification improvement Bangs, Corey F.; Kruse, Fred A.; Olsen, Chris R. (SPIE, 2013);Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture feature data on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were ...
Improving Identification of Area Targets by Integrated Analysis of Hyperspectral Data and Extracted Texture Features Bangs, Corey F. (Monterey, California. Naval Postgraduate School, 2012-09);Hyperspectral data were assessed to determine the effect of integrating spectral data and extracted texture features on classification accuracy. Four separate spectral ranges (hundreds of spectral bands total) were used ...