THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE

Due to the forward scattering and block of radar signal, the water, bare soil, shadow, named low backscattering objects (LBOs), often present low backscattering intensity in polarimetric synthetic aperture radar (PolSAR) image. Because the LBOs rise similar backscattering intensity and polarimetric...

Full description

Bibliographic Details
Main Authors: L. Yang, L. Shi, P. Li, J. Yang, L. Zhao, B. Zhao
Format: Article
Language:English
Published: Copernicus Publications 2018-04-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/2089/2018/isprs-archives-XLII-3-2089-2018.pdf
_version_ 1818548981128495104
author L. Yang
L. Shi
P. Li
J. Yang
L. Zhao
B. Zhao
author_facet L. Yang
L. Shi
P. Li
J. Yang
L. Zhao
B. Zhao
author_sort L. Yang
collection DOAJ
description Due to the forward scattering and block of radar signal, the water, bare soil, shadow, named low backscattering objects (LBOs), often present low backscattering intensity in polarimetric synthetic aperture radar (PolSAR) image. Because the LBOs rise similar backscattering intensity and polarimetric responses, the spectral-based classifiers are inefficient to deal with LBO classification, such as Wishart method. Although some polarimetric features had been exploited to relieve the confusion phenomenon, the backscattering features are still found unstable when the system noise floor varies in the range direction. This paper will introduce a simple but effective scene classification method based on Bag of Words (BoW) model using Support Vector Machine (SVM) to discriminate the LBOs, without relying on any polarimetric features. In the proposed approach, square windows are firstly opened around the LBOs adaptively to determine the scene images, and then the Scale-Invariant Feature Transform (SIFT) points are detected in training and test scenes. The several SIFT features detected are clustered using K-means to obtain certain cluster centers as the visual word lists and scene images are represented using word frequency. At last, the SVM is selected for training and predicting new scenes as some kind of LBOs. The proposed method is executed over two AIRSAR data sets at C band and L band, including water, bare soil and shadow scenes. The experimental results illustrate the effectiveness of the scene method in distinguishing LBOs.
first_indexed 2024-12-12T08:27:29Z
format Article
id doaj.art-22b1afdbbbd84d2d887b58b6561b542e
institution Directory Open Access Journal
issn 1682-1750
2194-9034
language English
last_indexed 2024-12-12T08:27:29Z
publishDate 2018-04-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj.art-22b1afdbbbd84d2d887b58b6561b542e2022-12-22T00:31:13ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342018-04-01XLII-32089209110.5194/isprs-archives-XLII-3-2089-2018THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINEL. Yang0L. Shi1P. Li2J. Yang3L. Zhao4B. Zhao5State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, ChinaDue to the forward scattering and block of radar signal, the water, bare soil, shadow, named low backscattering objects (LBOs), often present low backscattering intensity in polarimetric synthetic aperture radar (PolSAR) image. Because the LBOs rise similar backscattering intensity and polarimetric responses, the spectral-based classifiers are inefficient to deal with LBO classification, such as Wishart method. Although some polarimetric features had been exploited to relieve the confusion phenomenon, the backscattering features are still found unstable when the system noise floor varies in the range direction. This paper will introduce a simple but effective scene classification method based on Bag of Words (BoW) model using Support Vector Machine (SVM) to discriminate the LBOs, without relying on any polarimetric features. In the proposed approach, square windows are firstly opened around the LBOs adaptively to determine the scene images, and then the Scale-Invariant Feature Transform (SIFT) points are detected in training and test scenes. The several SIFT features detected are clustered using K-means to obtain certain cluster centers as the visual word lists and scene images are represented using word frequency. At last, the SVM is selected for training and predicting new scenes as some kind of LBOs. The proposed method is executed over two AIRSAR data sets at C band and L band, including water, bare soil and shadow scenes. The experimental results illustrate the effectiveness of the scene method in distinguishing LBOs.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/2089/2018/isprs-archives-XLII-3-2089-2018.pdf
spellingShingle L. Yang
L. Shi
P. Li
J. Yang
L. Zhao
B. Zhao
THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
title_full THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
title_fullStr THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
title_full_unstemmed THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
title_short THE LOW BACKSCATTERING OBJECTS CLASSIFICATION IN POLSAR IMAGE BASED ON BAG OF WORDS MODEL USING SUPPORT VECTOR MACHINE
title_sort low backscattering objects classification in polsar image based on bag of words model using support vector machine
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-3/2089/2018/isprs-archives-XLII-3-2089-2018.pdf
work_keys_str_mv AT lyang thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT lshi thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT pli thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT jyang thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT lzhao thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT bzhao thelowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT lyang lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT lshi lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT pli lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT jyang lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT lzhao lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine
AT bzhao lowbackscatteringobjectsclassificationinpolsarimagebasedonbagofwordsmodelusingsupportvectormachine