MAN-MADE OBJECT EXTRACTION FROM REMOTE SENSING IMAGES USING GABOR ENERGY FEATURES AND PROBABILISTIC NEURAL NETWORKS
Abstract
vioft2nntf2t|tblJournal|Abstract_paper|0xf4ffb5b42e000000b252100001000700
This paper presents a novel approach for man-made object extraction in remote sensing images. This paper focuses on the design and implementation of a system that allows a user to extract multiple objects such as buildings or roads from an input image without much user intervention. The framework includes five main stages: 1) Pre-processing Stage. 2) Extraction of Local energy features using edge information and Gabor filter followed by down sampling to reduce the redundant information. 3) Further reduction of the size of feature vectors using Wavelet decomposition. 4) Classification and recognition of man-made structures using Probabilistic Neural Network (PNN) 5) NDVI based post-classification refinement. Experiments are conducted on a dataset of 200 RS images. The proposed framework yields overall accuracy of 93%. Experimental results validate the effective performance of the suggested technique for extracting man-made objects from RS images. Compared with other methods; the proposed framework exhibits significantly improved accuracy results and computationally much more efficient. Most notably, it has a much smaller input size, which makes it more feasible in practical applications.

Authors
Md. Abdul Alim Sheikh1, Tanmoy Maity2, Alok Kole3
Aliah University, India1, Indian Institute of Technology, Dhanbad, India2, RCC Institute of Information Technology, India3

Keywords
Remote Sensing Image, Man-Made Object Extraction, Gabor Wavelets, Probabilistic Neural Network
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
100000000000
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 13 , Issue: 2 , Pages: 2849 - 2859 )
Date of Publication :
November 2022
Page Views :
307
Full Text Views :
2

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.