Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 18) Show all publications
Alves, D. i., Palm, B., Hellsten, H., Machado, R., Vu, V. T., Pettersson, M. & Dammert, P. (2023). Change Detection Method for Wavelength-Resolution SAR Images Based on Bayes’ Theorem: An Iterative Approach. IEEE Access, 11, 84734-84743
Open this publication in new window or tab >>Change Detection Method for Wavelength-Resolution SAR Images Based on Bayes’ Theorem: An Iterative Approach
Show others...
2023 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 84734-84743Article in journal (Refereed) Published
Abstract [en]

This paper presents an iterative change detection (CD) method based on Bayes’ theorem for very high-frequency (VHF) ultra-wideband (UWB) SAR images considering commonly used clutter-plus-noise statistical models. The proposed detection technique uses the information of the detected changes to iteratively update the data and distribution information, obtaining more accurate clutter-plus-noise statistics resulting in false alarm reduction. The Bivariate Rayleigh and Bivariate Gaussian distributions are investigated as candidates to model the clutter-plus-noise, and the Anderson-Darling goodness-of-fit test is used to investigate three scenarios of interest. Different aspects related to the distributions are discussed, the observed mismatches are analyzed, and the impact of the distribution chosen for the proposed iterative change detection method is analyzed. Finally, the proposed iterative method performance is assessed in terms of the probability of detection and false alarm rate and compared with other competitive solutions. The experimental evaluation uses data from real measurements obtained using the CARABAS II SAR system. Results show that the proposed iterative CD algorithm performs better than the other methods. Author

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
Keywords
Bayes’ theorem, CARABAS II, Data models, Gaussian distribution, Histograms, iterative change detection, Iterative methods, Radar polarimetry, SAR, Stability analysis, Surveillance, wavelength-resolution SAR images, Change detection, Clutter (information theory), Errors, Image segmentation, Radar clutter, Radar imaging, Synthetic aperture radar, Ultra-wideband (UWB), Baye's theorem, CARABAS, Histogram, SAR Images, Stability analyze, Wavelength resolution, Wavelength-resolution SAR image
National Category
Signal Processing
Identifiers
urn:nbn:se:bth-25326 (URN)10.1109/ACCESS.2023.3303107 (DOI)001049927400001 ()2-s2.0-85167776056 (Scopus ID)
Available from: 2023-08-25 Created: 2023-08-25 Last updated: 2023-09-04Bibliographically approved
Berner, J., Moraes, A. L., Palm, B., Sanmartin Berglund, J. & Anderberg, P. (2023). Five-factor model, technology enthusiasm and technology anxiety. Digital Health, 9
Open this publication in new window or tab >>Five-factor model, technology enthusiasm and technology anxiety
Show others...
2023 (English)In: Digital Health, E-ISSN 2055-2076, Vol. 9Article in journal (Refereed) Published
Abstract [en]

Older adults need to participate in the digital society, as societal and personal changes and what they do with the remaining time that they have in their older years has an undeniable effect on motivation, cognition and emotion. Changes in personality traits were investigated in older adults over the period 2019–2021. Technology enthusiasm and technology anxiety are attitudes that affect the relationship to the technology used. The changes in the score of technology enthusiasm and technology anxiety were the dependent variables. They were investigated with personality traits, age, gender, education, whether someone lives alone, cognitive function, digital social participation (DSP) and health literacy as predictors of the outcome. The Edwards-Nunnally index and logistic regression were used. The results indicated that DSP, lower age, lower neuroticism and higher education were indicative of less technology anxiety. High DSP and high extraversion are indicative of technology enthusiasm. DSP and attitude towards technology seem to be key in getting older adults to stay active online. © The Author(s) 2023.

Place, publisher, year, edition, pages
Sage Publications, 2023
Keywords
digital social participation, five-factor model, older adults, personality, Technology anxiety, technology enthusiasm
National Category
Gerontology, specialising in Medical and Health Sciences
Identifiers
urn:nbn:se:bth-25426 (URN)10.1177/20552076231203602 (DOI)001069602300001 ()2-s2.0-85171753514 (Scopus ID)
Available from: 2023-10-02 Created: 2023-10-02 Last updated: 2023-10-30Bibliographically approved
Javadi, S., Palm, B., Vu, V. T., Pettersson, M. & Sjögren, T. (2023). Harbour Area Change Detection and Analysis Using SAR Images from a Recent Measurement Campaign. In: Proceedings of the IEEE Radar Conference 2023: . Paper presented at IEEE International Radar Conference, RADAR 2023, Sydney, 6 November through 10 November 2023. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Harbour Area Change Detection and Analysis Using SAR Images from a Recent Measurement Campaign
Show others...
2023 (English)In: Proceedings of the IEEE Radar Conference 2023, Institute of Electrical and Electronics Engineers (IEEE), 2023Conference paper, Published paper (Refereed)
Abstract [en]

Synthetic aperture radar (SAR) data are widely used for remote sensing applications, such as change detection and environmental monitoring. This paper presents a recent measurement campaign for SAR images using the LORA system and investigates the applicability of the collected data for change detection. The region of interest in this study is a busy commercial harbour area in the south of Sweden. During the measurements, there were significant changes on the ground in the parking lot as trucks were disembarking a ship. The obtained SAR images were first filtered to have similar regions of interest in the Fourier domain to increase the coherence magnitude. Then, a constant false alarm rate (CFAR) algorithm was employed to detect changes with respect to trucks. In addition, optical aerial images were collected during this measurement campaign and were utilized to adjust the CFAR detection threshold. As a result, all the changed and unchanged regions corresponding to the selected targets were detected successfully. Moreover, a pattern of trucks’ utilization of the harbour’s parking lot during this peak time was obtained. The results demonstrate the applicability of the data from the ongoing measurement campaign and the possibility of further algorithm development for target detection and classification.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
Series
IEEE International Conference on Radar (RADAR), ISSN 1097-5764, E-ISSN 2640-7736
Keywords
aerial images, CFAR detector, change detection, LORA system, SAR images
National Category
Remote Sensing
Identifiers
urn:nbn:se:bth-25853 (URN)10.1109/radar54928.2023.10371086 (DOI)2-s2.0-85182738528 (Scopus ID)
Conference
IEEE International Radar Conference, RADAR 2023, Sydney, 6 November through 10 November 2023
Available from: 2024-01-03 Created: 2024-01-03 Last updated: 2024-02-05Bibliographically approved
da Silva, F. G., Ramos, L. P., Palm, B. & Machado, R. (2023). Hyperparameters Analysis of Machine Learning Techniques for Classification of Marine Targets in SAR Images. In: Proceedings of the XX Brazilian Symposium on Remote Sensing: Anais do XX Simpósio Brasileiro de Sensoriamento Remoto. Paper presented at XX SBSR Brazilian Symposium on Remote Sensing, Florianopolis, 2-5 april, 2023 (pp. 1095-1098). , 20, Article ID 155793.
Open this publication in new window or tab >>Hyperparameters Analysis of Machine Learning Techniques for Classification of Marine Targets in SAR Images
2023 (English)In: Proceedings of the XX Brazilian Symposium on Remote Sensing: Anais do XX Simpósio Brasileiro de Sensoriamento Remoto, 2023, Vol. 20, p. 1095-1098, article id 155793Conference paper, Published paper (Refereed)
Abstract [en]

Due to the extensive coastal area of Brazil, pattern recognition techniques based on artificial intelligence can search for targets at sea faster for surveillance, rescue, or illicit combat activities. This article presents a hyperparameter analysis of machine learning techniques to classify targets in SAR images. We considered a data set with vertical horizontal polarization SAR images from Campos Basin, Rio de Janeiro, to classify oil platforms and ships. The classification attributes are extracted through a convolutional neural network VGG-16 pre-trained with the ImageNet data set. Then, four machine learning techniques are evaluated, random forest, decision tree, k-nearest-neighbors, and logistic regression. As a metric for assessing the classifiers, accuracy (Acc) and area under the curve (AUC) are used. The grid search technique is used to identify the best combination of parameters of the classifiers with the highest Acc and AUC. Finally, the best result is the logistic regression classifier.

National Category
Signal Processing
Identifiers
urn:nbn:se:bth-25533 (URN)9786589159049 (ISBN)
Conference
XX SBSR Brazilian Symposium on Remote Sensing, Florianopolis, 2-5 april, 2023
Available from: 2023-11-01 Created: 2023-11-01 Last updated: 2023-11-01Bibliographically approved
Palm, B., Javadi, S., Vu, V. T., Pettersson, M. & Sjogren, T. (2023). Wavelength Resolution SAR Change Detection: New Measurement Campaign for New Research Data Set. In: Zelnio, E Garber, FD (Ed.), ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXX 2023: . Paper presented at Conference on Algorithms for Synthetic Aperture Radar Imagery XXX, MAY 02-03, 2023, Orlando, FL. SPIE - International Society for Optical Engineering, 12520, Article ID 1252009.
Open this publication in new window or tab >>Wavelength Resolution SAR Change Detection: New Measurement Campaign for New Research Data Set
Show others...
2023 (English)In: ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXX 2023 / [ed] Zelnio, E Garber, FD, SPIE - International Society for Optical Engineering, 2023, Vol. 12520, article id 1252009Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes a new measurement campaign for SAR images. The data consists of images collected by the Swedish LORA system associated with VHF-band (19-90 MHz). Due to the system frequency, detecting targets concealed in a forest is possible. Thus, this paper aims to share with the community the results of utilizing new VHF-band SAR data that allows the development of new methods for target and other change detection. In particular, to show the applicability of the new data set, a simple change detection method was performed to detect targets in a forest, resulting in 100% of detection, associated with no false alarm in a particular region of interest.

Place, publisher, year, edition, pages
SPIE - International Society for Optical Engineering, 2023
Series
Proceedings of SPIE, ISSN 0277-786X
Keywords
Change detection, SAR images, Wavelength resolution SAR data
National Category
Signal Processing
Identifiers
urn:nbn:se:bth-25246 (URN)10.1117/12.2663452 (DOI)001012855700008 ()2-s2.0-85167444680 (Scopus ID)9781510661547 (ISBN)
Conference
Conference on Algorithms for Synthetic Aperture Radar Imagery XXX, MAY 02-03, 2023, Orlando, FL
Available from: 2023-08-08 Created: 2023-08-08 Last updated: 2023-08-18Bibliographically approved
Palm, B., Bayer, F. M. & Cintra, R. J. (2022). 2-D Rayleigh autoregressive moving average model for SAR image modeling. Computational Statistics & Data Analysis, 171, Article ID 107453.
Open this publication in new window or tab >>2-D Rayleigh autoregressive moving average model for SAR image modeling
2022 (English)In: Computational Statistics & Data Analysis, ISSN 0167-9473, E-ISSN 1872-7352, Vol. 171, article id 107453Article in journal (Refereed) Published
Abstract [en]

Two-dimensional (2-D) autoregressive moving average (ARMA) models are commonly applied to describe real-world image data, usually assuming Gaussian or symmetric noise. However, real-world data often present non-Gaussian signals, with asymmetrical distributions and strictly positive values. In particular, SAR images are known to be well characterized by the Rayleigh distribution. In this context, the ARMA model tailored for 2-D Rayleigh-distributed data is introduced—the 2-D RARMA model. The 2-D RARMA model is derived and conditional likelihood inferences are discussed. The proposed model was submitted to extensive Monte Carlo simulations to evaluate the performance of the conditional maximum likelihood estimators. Moreover, in the context of SAR image processing, two comprehensive numerical experiments were performed comparing anomaly detection and image modeling results of the proposed model with traditional 2-D ARMA models and competing methods in the literature. © 2022 The Authors

Place, publisher, year, edition, pages
Elsevier B.V., 2022
Keywords
Anomaly detection, ARMA modeling, Rayleigh distribution, SAR images, Two-dimensional models, Gaussian distribution, Gaussian noise (electronic), Intelligent systems, Maximum likelihood estimation, Monte Carlo methods, Numerical methods, Synthetic aperture radar, Autoregressive Moving Average modeling, Gaussians, Image modeling, Rayleigh, Rayleigh distributions, Real-world image data, Two Dimensional (2 D), Two dimensional model, Radar imaging
National Category
Control Engineering
Identifiers
urn:nbn:se:bth-22734 (URN)10.1016/j.csda.2022.107453 (DOI)000820753700005 ()2-s2.0-85125357625 (Scopus ID)
Note

open access

Available from: 2022-03-10 Created: 2022-03-10 Last updated: 2022-08-11Bibliographically approved
da Silva, F. G., Ramos, L. P., Palm, B. & Machado, R. (2022). Assessment of Machine Learning Techniques for Oil Rig Classification in C-Band SAR Images. Remote Sensing, 14(13), Article ID 2966.
Open this publication in new window or tab >>Assessment of Machine Learning Techniques for Oil Rig Classification in C-Band SAR Images
2022 (English)In: Remote Sensing, E-ISSN 2072-4292, Vol. 14, no 13, article id 2966Article in journal (Refereed) Published
Abstract [en]

This article aims at performing maritime target classification in SAR images using machine learning (ML) and deep learning (DL) techniques. In particular, the targets of interest are oil platforms and ships located in the Campos Basin, Brazil. Two convolutional neural networks (CNNs), VGG-16 and VGG-19, were used for attribute extraction. The logistic regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbours (kNN), decision tree (DT), naive Bayes (NB), neural networks (NET), and AdaBoost (ADBST) schemes were considered for classification. The target classification methods were evaluated using polarimetric images obtained from the C-band synthetic aperture radar (SAR) system Sentinel-1. Classifiers are assessed by the accuracy indicator. The LR, SVM, NET, and stacking results indicate better performance, with accuracy ranging from 84.1% to 85.5%. The Kruskal–Wallis test shows a significant difference with the tested classifier, indicating that some classifiers present different accuracy results. The optimizations provide results with more significant accuracy gains, making them competitive with those shown in the literature. There is no exact combination of methods for SAR image classification that will always guarantee the best accuracy. The optimizations performed in this article were for the specific data set of the Campos Basin, and results may change depending on the data set format and the number of images. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Place, publisher, year, edition, pages
MDPI, 2022
Keywords
classification algorithms, deep learning, machine learning, oil rig classification, SAR, ship classification, Adaptive boosting, Classification (of information), Convolutional neural networks, Decision trees, Image classification, Learning systems, Nearest neighbor search, Radar imaging, Ships, Support vector machines, C-bands, Campos Basin, Classification algorithm, Machine-learning, Oil-rigs, Synthetic aperture radar images, Target Classification, Synthetic aperture radar
National Category
Remote Sensing
Identifiers
urn:nbn:se:bth-23505 (URN)10.3390/rs14132966 (DOI)000825692700001 ()2-s2.0-85132981546 (Scopus ID)
Note

open access

Available from: 2022-08-11 Created: 2022-08-11 Last updated: 2023-08-28Bibliographically approved
Vinholi, J. G., Palm, B., Silva, D., Machado, R. & Pettersson, M. (2022). Change Detection Based on Convolutional Neural Networks Using Stacks of Wavelength-Resolution Synthetic Aperture Radar Images. IEEE Transactions on Geoscience and Remote Sensing, 60, Article ID 5236414.
Open this publication in new window or tab >>Change Detection Based on Convolutional Neural Networks Using Stacks of Wavelength-Resolution Synthetic Aperture Radar Images
Show others...
2022 (English)In: IEEE Transactions on Geoscience and Remote Sensing, ISSN 0196-2892, E-ISSN 1558-0644, Vol. 60, article id 5236414Article in journal (Refereed) Published
Abstract [en]

This article presents two supervised change detection algorithms (CDA) based on convolutional neural networks (CNN) that use stacks of co-registered wavelength-resolution synthetic aperture radar (SAR) images to detect changes in an image under monitoring. The additional information of a scene of interest provided by SAR image stacks can be explored to enhance the performance of change detection algorithms. In particular, stacks of images with similar statistics can be obtained for ultra-wideband (UWB) very high frequency (VHF) SAR systems, as they produce images highly stable in time. The proposed CDAs can be summed up into four stages: difference image formation, semantic segmentation, clustering, and change classification. The CNN-GSP algorithm is based on a ground scene prediction (GSP) image, which is used as a reference to form a difference image (DI). A CNN-based model then analyzes the DI. The CNN-MDI algorithm feeds multiple DIs with identical monitored images to a CNN-based model, which will concurrently analyze their features. Tests with CARABAS-II data show that the proposed CDAs can outperform other state-of-the-art algorithms that also use stacks of WR-SAR images. Beyond that, the proposed algorithms outperformed a CNN-based CDA that does not use image stacks, which shows that CNN-based algorithms can use the additional information provided by stacks of SAR images to reduce false alarm occurrences while increasing the probability of detection of changes. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022
Keywords
Change detection, Convolution, Deep learning, Image enhancement, Neural networks, Radar imaging, Remote sensing, Semantic Segmentation, Semantics, Signal detection, Tracking radar, CARABAS, CARABAS-II, Complexity theory, Convolutional neural network, Detection algorithm, Radar polarimetry, Remote-sensing, Ultra-wideband technology, Synthetic aperture radar, Classification, CNN, Convolutional neural networks, Detection algorithms, Monitoring, Ultra wideband technology
National Category
Signal Processing
Identifiers
urn:nbn:se:bth-23775 (URN)10.1109/TGRS.2022.3211010 (DOI)000874066100016 ()2-s2.0-85139463271 (Scopus ID)
Note

Open access

Available from: 2022-10-24 Created: 2022-10-24 Last updated: 2022-12-13Bibliographically approved
da Silva, F. G., Ramos, L. P., Palm, B., Alves, D. I., Pettersson, M. & Machado, R. (2022). Hybrid Feature Extraction Based on PCA and CNN for Oil Rig Classification in C-Band SAR Imagery. In: Dijk J. (Ed.), Proceedings of SPIE - The International Society for Optical Engineering: . Paper presented at Artificial Intelligence and Machine Learning in Defense Applications IV 2022, Berlin, 6 September through 7 September 2022. SPIE - International Society for Optical Engineering, Article ID 122760G.
Open this publication in new window or tab >>Hybrid Feature Extraction Based on PCA and CNN for Oil Rig Classification in C-Band SAR Imagery
Show others...
2022 (English)In: Proceedings of SPIE - The International Society for Optical Engineering / [ed] Dijk J., SPIE - International Society for Optical Engineering, 2022, article id 122760GConference paper, Published paper (Refereed)
Abstract [en]

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.

Place, publisher, year, edition, pages
SPIE - International Society for Optical Engineering, 2022
Series
Proceedings of SPIE, the International Society for Optical Engineering, ISSN 0277-786X, E-ISSN 1996-756X ; 12276
Keywords
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
National Category
Remote Sensing
Identifiers
urn:nbn:se:bth-24195 (URN)10.1117/12.2636274 (DOI)000906230300013 ()2-s2.0-85145216918 (Scopus ID)
Conference
Artificial Intelligence and Machine Learning in Defense Applications IV 2022, Berlin, 6 September through 7 September 2022
Note

open access

Available from: 2023-01-12 Created: 2023-01-12 Last updated: 2023-02-16Bibliographically approved
Palm, B., Javadi, S., Bayer, F. M., Vu, V. T. & Pettersson, M. (2022). Inflated Rayleigh Distribution for SAR Imagery Modeling. In: International Geoscience and Remote Sensing Symposium (IGARSS 2022): . Paper presented at 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022, Kuala Lumpur, 17 July 2022 through 22 July 2022 (pp. 44-47). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Inflated Rayleigh Distribution for SAR Imagery Modeling
Show others...
2022 (English)In: International Geoscience and Remote Sensing Symposium (IGARSS 2022), Institute of Electrical and Electronics Engineers (IEEE), 2022, p. 44-47Conference paper, Published paper (Refereed)
Abstract [en]

Synthetic aperture radars (SAR) data plays an important role in remote sensing applications. It is common knowledge that SAR image amplitude pixels can be approximately modeled by the Rayleigh distribution. However, this model is contin-uous and does not accommodate points with non-zero prob-ability, such as a null pixel amplitude value. Thus, in this paper, we propose an inflated Rayleigh distribution for SAR image modeling that is based on a mixed continuous-discrete distribution and can be used to fit signals with observed values on [0, infty). The maximum likelihood approach is considered to estimate the parameters of the proposed distribution. An empirical experiment with a SAR image is also presented and discussed. © 2022 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022
Series
IEEE International Symposium on Geoscience and Remote Sensing (IGARSS), ISSN 2153-6996, E-ISSN 2153-7003
Keywords
Maximum likelihood estimation, Null amplitude value, Rayleigh distribution, SAR images
National Category
Signal Processing
Identifiers
urn:nbn:se:bth-23833 (URN)10.1109/IGARSS46834.2022.9883264 (DOI)000920916600012 ()2-s2.0-85140359332 (Scopus ID)9781665427920 (ISBN)
Conference
2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022, Kuala Lumpur, 17 July 2022 through 22 July 2022
Note

open access

Available from: 2022-11-03 Created: 2022-11-03 Last updated: 2023-05-09Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-0423-9927

Search in DiVA

Show all publications