Search: onr:"swepub:oai:DiVA.org:bth-24195" >
Hybrid Feature Extr...
Hybrid Feature Extraction Based on PCA and CNN for Oil Rig Classification in C-Band SAR Imagery
-
- da Silva, Fabiano G. (author)
- Aeronautics Institute of Technology, BRA
-
- Ramos, Lucas P. (author)
- Aeronautics Institute of Technology, BRA
-
- Palm, Bruna (author)
- Blekinge Tekniska Högskola,Institutionen för matematik och naturvetenskap
-
show more...
-
- Alves, Dimas I. (author)
- Aeronautics Institute of Technology, BRA
-
- Pettersson, Mats, 1966- (author)
- Blekinge Tekniska Högskola,Institutionen för matematik och naturvetenskap
-
- Machado, Renato (author)
- Aeronautics Institute of Technology, BRA
-
show less...
-
(creator_code:org_t)
- SPIE - International Society for Optical Engineering, 2022
- 2022
- English.
-
In: Proceedings of SPIE - The International Society for Optical Engineering. - : SPIE - International Society for Optical Engineering.
- Related links:
-
https://bth.diva-por... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Feature extraction techniques play an essential role in classifying and recognizing targets in synthetic aperture radar (SAR) images. This article proposes a hybrid feature extraction technique based on convolutional neural networks and principal component analysis. The proposed method is used to extract features of oil rigs and ships in C-band synthetic aperture radar polarimetric images obtained with the Sentinel-1 satellite system. The extracted features are used as input in the logistic regression (LR), support vector machine (SVM), random forest (RF), naive Bayes (NB), decision tree (DT), and k-nearest-neighbors (kNN) classification algorithms. Furthermore, the statistical tests of Kruskal-Wallis and Dunn were considered to show that the proposed extraction algorithm has a significant impact on the performance of the classifiers. © 2022 SPIE.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Naturresursteknik -- Fjärranalysteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Environmental Engineering -- Remote Sensing (hsv//eng)
Keyword
- C-Band
- CNN
- Feature Extraction
- Machine Learning
- PCA
- SAR
- Sentinel-1
- Target Classification
- Classification (of information)
- Convolutional neural networks
- Decision trees
- Extraction
- Image classification
- Logistic regression
- Nearest neighbor search
- Principal component analysis
- Radar imaging
- Remote sensing
- Support vector regression
- C-bands
- Feature extraction techniques
- Features extraction
- Hybrid-feature extraction
- Machine-learning
- Oil-rigs
- Synthetic Aperture Radar Imagery
- Synthetic aperture radar
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database