Band Selection of Hyperspectral Images Based on Bhattacharyya Distance

نویسندگان

  • CAI SIMIN
  • ZHANG RONGQUN
  • CHENG WENLING
  • YUAN HUI
چکیده

With the development of sensor technology, the spectral resolution of remote sensing image is continuously improved. The appearance of the hyperspectral remote sensing is a tremendous leap in the field of remote sensing. The increasing availability of hyperspectral data and image has enriched us with better and finer data and it also enable us a much stronger ability to identify features. However the approaches in the feature identify of hyperspectral images are not as successful as we thought. Too many bands and a large amount of data not only bring difficulties in data storage and transmission, but also bring new challenges in hyperspectral image processing technology, especially the hyperspectral image feature recognize. Band selection aims to recognize the features effectively. We should distinguish the features by utilizing their spectral curve properties. These curves are found to have important information to recognize the different land cover types. So it makes great sense to choose the best combination of many bands and form a new hyperspectral image space. This procedure is usually called features selection. Bhattacharyya-Distance is one of the commonly used methods. It is one kind of statistic distance. It can more reasonably measure the distance between different land types in super multi-dimensional space. The hyperspectral data used in this paper is obtained by the sensors OMIS (Operational Modular Imaging Spectrometer). In this paper, we propose a band selection method based on the Bhattacharyya distance. In the proposed method, we try to find the optimize band combination. We divide land types in the research area into five classes (the five classes are seawater, fishery, building, vegetation and crops); calculate the Bhattacharyya distance between the five class pairs. According the optimal band subset selected by the Bhattacharyya distance, we make a classification and evaluate the classification accuracy. Experimental results show that the proposed band selection method compares favorably with conventional methods. Key-Words: Hyperspectral images; Band selection; Bhattacharyya distance; Coincident spectral plot

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Method on Feature Selection of Hyperspectral Images Based on Bhattacharyya Distance

Band selection aims to recognize the objects effectively. We should distinguish the objects by utilizing their spectral curve properties. B-Distance is one of the commonly used standards. It is one kind of statistic distance. It can more reasonably measure the distance between different categories in super multi-dimensional space. The hyperspectral data used in this paper is obtained by the sen...

متن کامل

Visualization, Band Ordering and Compression of Hyperspectral Images

Air-borne and space-borne acquired hyperspectral images are used to recognize objects and to classify materials on the surface of the earth. The state of the art compressor for lossless compression of hyperspectral images is the Spectral oriented Least SQuares (SLSQ) compressor (see [1–7]). In this paper we discuss hyperspectral image compression: we show how to visualize each band of a hypersp...

متن کامل

A Band Selection Method for Hyperspectral Image Classification based on Improved Particle Swarm Optimization

With the development of spectral imaging technology, it makes hyperspectral imagery widely used. According to the features of multiple bands and the strong mutual correlation among these bands, this paper presents a band selection method for hyperspectral imagery classification based on improved PSO (Particle Swarm Optimization). First of all, we use information divergence to describe the corre...

متن کامل

Overlap-based feature weighting: The feature extraction of Hyperspectral remote sensing imagery

Hyperspectral sensors provide a large number of spectral bands. This massive and complex data structure of hyperspectral images presents a challenge to traditional data processing techniques. Therefore, reducing the dimensionality of hyperspectral images without losing important information is a very important issue for the remote sensing community. We propose to use overlap-based feature weigh...

متن کامل

Analysis of Band Selection Algorithms for Endmember Extraction in Hyperspectral Images

This paper presents a novel approach of band selection for dimensionality reduction in Hyperspectral images (HSI). There are several methods of dimensionality reduction which can be further categorized into two groups; feature extraction and feature or band selection. Due to transformation in feature extraction, the critical information may have been distorted. Hence feature selection is prefer...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009