Object Based Unsupervised Classification of VHR Panchromatic and Multispectral Satellite Images by Combining the HDP, IBP and K-Mean on Multiple Scenes

Abstract

In this paper Bayesian hierarchical model (HDP_IBPs) to classify very high resolution panchromatic as well as multispectral satellite images in an unsupervised way, in which the hierarchical Dirichlet process (HDP) and Indian buffet process (IBP) are combined on multiple scenes. The main contribution of this paper is a novel application framework to solve the problems of traditional probabilistic topic models and achieve the effective unsupervised classification of very high resolution (VHR) panchromatic and multispectral satellite images. The hierarchical structure of our model transmits the spatial information from the original image to the scene layer implicitly and provides useful cues of classification by using clustering technique, clustering is a popular tool for exploratory data analysis, such as K-means clustering technique .Automatic determination of the initialization number of clusters in K-means clustering application is often needed in advance as an input parameter to the algorithm. K-mean clustering algorithm is used to partition and analyze the data which used the required cluster. Initially this number of clusters is taken as starting values. Sometime images which are captures are blur or unclear so they do not return proper return but now with the help of multiple satellite it captures the multiple satellite images and splits them separately.

Authors and Affiliations

Dipika R. Parate, Prof. N. M. Dhande

Keywords

Related Articles

Optical Character Recognition.

Character Recognition (CR) is the process of recognizing handwritten characters. It is an active area of research and it is used in various applications such as reading license plate numbers, document processing, readin...

Study about the Behaviour of Concrete Filled Tubular Column with GFRP Wrapping

In this paper, the tubular columns are filled with normal and replacement concrete under M25 grade. The replacement involves 5 % of metakaolin replaced for cement and 25 % of green sand replaced for fine aggregate. The...

Designing Of MPLS Network and Ensuring Fast Convergence and Security Performance through Layer2 and Layer3 VPN

Need of global networking is increasing day by day and is a primary need. There has been a rapid growth of the routing protocols in the area of communication. A routing protocol is a protocol which is responsible to det...

A Novel Enhanced Image Denoising Algorithm Combining DWT and Curvelet Techniques with Image Fusion

Image denoising is a well-studied subject and used in a variety of applications from surveillance, satellite imagery to forensic sciences. This algorithm is aimed to achieve further knowledge and information to the subj...

A Survey on Routing Protocols and Vulnerabilities in Mobile Ad-Hoc Network (MANETs)

Mobile ad hoc network (MANET) is composed of a collection of mobile nodes which are movable. Therefore, dynamic topology, unstable links, limited energy capacity and absence of fixed infrastructure are special features...

Download PDF file
  • EP ID EP23219
  • DOI http://doi.org/10.22214/ijraset.2017.3022
  • Views 218
  • Downloads 7

How To Cite

Dipika R. Parate, Prof. N. M. Dhande (2017). Object Based Unsupervised Classification of VHR Panchromatic and Multispectral Satellite Images by Combining the HDP, IBP and K-Mean on Multiple Scenes. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(3), -. https://europub.co.uk/articles/-A-23219