Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Flood Inundation Mapping of Krishnaraja Nagar, Mysore Using Sentinel-1 Sar Images(Springer Science and Business Media Deutschland GmbH, 2024) Sahu, M.K.; Shwetha, H.R.; Dwarakish, G.S.Floods cause physical damage and impact the availability of food, water, and crops. Effective disaster management and disaster risk reduction strategies require a quick and accurate mapping of these phenomena. The study area selected is the Krishnaraja Nagar taluk, Mysore districts, Karnataka having an area of 608 Km2. In this study, the analysis of a flood event was conducted using the temporal GRDH SAR pictures in C-band from Sentinel-1. Additionally, the co-polarized Vertical transmit, and Vertical received (VV) Synthetic Aperture Radar (SAR) images were utilized to map the extent of the flooded area. Two methods of change detection are applied to the temporal SAR images: Otsu's Automatic thresholding method using Matlab R2020a, utilizing a pre-flood image dated 02 August 2018 that shares identical image characteristics with the flood images captured on 14 August 2018; and flood mapping based on Normalized Difference Flood Index (NDFI) using Sentinel Application Platform (SNAP) software. By dividing the SAR image's non-water and open-water regions, the threshold approach was used to extract the flooded areas. In order to identify the actual flooded region, permanent water bodies were later removed from the open water. An analysis of the overlay flood maps was conducted to determine the total area inundated. After processing the SAR data and conducting threshold operations, the flooded area estimates from NDFI is 28.10 km2, and by Otsu's method flooded area is 21.92 km2. It is concluded from the study that the SAR information, sideways with GIS, can be used efficiently for floodwater plotting, real-time analysis, and analysing the spread of floodwater in a flood-prone zone. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Guided SAR image despeckling with probabilistic non local weights(Elsevier Ltd, 2017) Gokul, J.; Nair, M.S.; Rajan, J.SAR images are generally corrupted by granular disturbances called speckle, which makes visual analysis and detail extraction a difficult task. Non Local despeckling techniques with probabilistic similarity has been a recent trend in SAR despeckling. To achieve effective speckle suppression without compromising detail preservation, we propose an improvement for the existing Generalized Guided Filter with Bayesian Non-Local Means (GGF-BNLM) method. The proposed method (Guided SAR Image Despeckling with Probabilistic Non Local Weights) replaces parametric constants based on heuristics in GGF-BNLM method with dynamically derived values based on the image statistics for weight computation. Proposed changes make GGF-BNLM method adaptive and as a result, significant improvement is achieved in terms of performance. Experimental analysis on SAR images shows excellent speckle reduction without compromising feature preservation when compared to GGF-BNLM method. Results are also compared with other state-of-the-art and classic SAR depseckling techniques to demonstrate the effectiveness of the proposed method. © 2017 Elsevier LtdItem Non-local total variation regularization models for image restoration(Elsevier Ltd, 2018) Padikkal, P.; Holla Kayyar, S.H.Restoration of images corrupted by data-correlated Rayleigh noise distribution has not been studied much extensively in the literature, unlike the other noise distributions. In this paper, we analyze the degradations due to a data-correlated Rayleigh noise and a linear blurring artifact. This work employs a variance stabilization approach and two variational approaches for restoring images from their noisy and blurred observations. The split-Bregman iterative scheme is used for numerically solving the models to improve their convergence rates. Furthermore, non-local total variation and non-local total bounded variation priors are being used as regularizers in these models to improve their restoration efficiency. Various synthetic and real images (such as ultrasound and synthetic aperture radar images) are tested to show the performance of these models. © 2018 Elsevier LtdItem Image despeckling with non-local total bounded variation regularization(Elsevier Ltd, 2018) Padikkal, P.; Banothu, B.A non-local total bounded variational (TBV) regularization model is proposed for restoring images corrupted with data-correlated speckles and linear blurring artifacts. The energy functional of the model is derived using maximum a posteriori (MAP) estimate of the noise probability density function (PDF). The non-local total bounded variation prior regularizes the model while the data fidelity is derived using the MAP estimator of the noise PDF. The computational efficiency of the model is improved using a fast numerical scheme based on the Augmented Lagrange formulation. The proposed model is employed to restore ultrasound (US) and synthetic aperture radar (SAR) images, which are usually speckled and blurred. The numerical results are presented and compared. Furthermore, a detailed theoretical study of the model is performed in addition to the experimental analysis. © 2017 Elsevier LtdItem Adaptive non-local level-set model for despeckling and deblurring of synthetic aperture radar imagery(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2018) Padikkal, P.; Banothu, B.In this article, we modify Mumford–Shah level-set model to handle speckles and blur in synthetic aperture radar (SAR) imagery. The proposed model is formulated using a non-local regularization framework. Hence, the model duly cares about local gradient oscillations (corresponding to the fine details/textures) during the evolution process. It is assumed that the speckle intensity is gamma distributed, while designing a maximum a posteriori estimator of the functional. The parameters of the gamma distribution (i.e. scale and shape) are estimated using a maximum likelihood estimator. The regularization parameter of the model is evaluated adaptively using these (estimated) parameters at each iteration. The split-Bregman iterative scheme is employed to improve the convergence rate of the model. The proposed and the state-of-the-art despeckling models are experimentally verified and compared using a large number of speckled and blurred SAR images. Statistical quantifiers are used to numerically evaluate the performance of various models under consideration. © 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.Item Hierarchical clustering approaches for flood assessment using multi-sensor satellite images(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2019) Senthilnath, J.; Shreyas, P.B.; Rajendra, R.; Sundaram, S.; Kulkarni, S.; Benediktsson, J.A.In this paper, hierarchical clustering methods are used on synthetic aperture radar (SAR) (during the flood) and LISS-III (before the flood) data to analyse damage caused by floods. The flooded and non-flooded regions are extracted from the SAR image while different land cover regions are extracted from the LISS-III image. Initially, the Bayesian information criterion (BIC) is implemented to obtain the constraints for the number of clusters. The optimal cluster centres are then computed using hierarchical clustering approach (i.e. cluster splitting and merging techniques). The cluster splitting techniques such as Iterative Self-Organising Data Technique (ISODATA), Mean Shift Clustering (MSC), Niche Genetic Algorithm (NGA) and Niche Particle Swarm Optimisation (NPSO) were applied on SAR and LISS-III data. The cluster centres obtained from these algorithms are used to group similar data points by using merging method into their respective classes. Further, the results obtained for each method are overlaid to analyse the individual land cover region that is affected by floods. © 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.Item Despeckling of SAR Images Using Shrinkage of Two-Dimensional Discrete Orthonormal S-Transform(World Scientific, 2021) Kamath, P.R.; Senapati, K.; Padikkal, P.Speckles are inherent to SAR. They hide and undermine several relevant information contained in the SAR images. In this paper, a despeckling algorithm using the shrinkage of two-dimensional discrete orthonormal S-transform (2D-DOST) coefficients in the transform domain along with shock filter is proposed. Also, an attempt has been made as a post-processing step to preserve the edges and other details while removing the speckle. The proposed strategy involves decomposing the SAR image into low and high-frequency components and processing them separately. A shock filter is used to smooth out the small variations in low-frequency components, and the high-frequency components are treated with a shrinkage of 2D-DOST coefficients. The edges, for enhancement, are detected using a ratio-based edge detection algorithm. The proposed method is tested, verified, and compared with some well-known models on C-band and X-band SAR images. A detailed experimental analysis is illustrated. © 2021 World Scientific Publishing Company.Item A weighted nuclear norm (WNN)-based retinex DIP framework for restoring aerial and satellite images corrupted by gamma distributed speckle noise(Springer, 2024) Shastry, A.; Padikkal, J.; George, S.; Bini, A.A.Restoration and enhancement are crucial preprocessing steps in the satellite domain. Mainly in active remote sensing such as Synthetic Aperture Radar (SAR), the images are more prone to speckle distortions and their reduction is not so trivial. Traditional deep learning models require large training datasets, limiting their applicability. This paper introduces a novel approach that combines the Deep Image Prior (DIP) model with a weighted nuclear norm (WNN) within a variational retinex framework to address these challenges. DIP leverages prior knowledge about noise distribution and works effectively with a single noisy image, eliminating the need for a large number of training images or ground truth. The WNN assigns non-negative weights to singular values, capturing the significance of each value and preserving crucial information during restoration. This approach offers a promising solution for satellite image restoration without relying on huge training data. The proposed method is evaluated through extensive experiments using various image quality metrics, including PSNR, SSIM, ENL, CNR, Entropy, and GCF. The comparative studies provide compelling evidence that the proposed method surpasses existing techniques in effectively restoring and enhancing speckled input images. Furthermore, statistical analysis performed using the Friedman test demonstrates the superior denoising performance of the model. Additionally, an ablation study is conducted to empirically determine the optimal regularization parameters, ensuring the optimal performance of the model. However, the theoretical selection of parameters for achieving optimal results remains an area that requires further exploration. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.Item AttentionDIP: attention-based deep image prior model to restore satellite and aerial images from gamma distributed speckle interference(Springer Science and Business Media Deutschland GmbH, 2024) Shastry, A.; George, S.; Bini, A.A.; Padikkal, J.Image restoration is an inevitable pre-processing step in most satellite imaging applications. The satellite imaging modality such as Synthetic Aperture Radar (SAR) is prone to speckle distortions due to constructive and destructive interference of the probing signals. Speckles being data correlated and multiplicative, their reduction is not so trivial. Since speckles are not purely noise interventions, a blind reduction process leads to spurious analysis at the later stages. Moreover, the image details are liable to get compromised during such a noise reduction process. An attention-based deep image prior (DIP) model with U-Net architecture has been proposed in this work to carefully address these setbacks. The attention block is used to scale the features extracted from the encoder, and they are concatenated with the features from the decoder to obtain both low- and high-level features. The attention module incorporated in the model helps to extract significant complex structures in SAR images. Further, the DIP model duly respects the noise distribution of speckles while performing the despeckling task. Various synthetic, natural, aerial, and satellite images are subjected to the testing and verification process, and the results obtained are in favor of the proposed model. The quantitative analysis carried out using various statistical metrics in this study also reveals the restoration ability of the proposed method in terms of both despeckling and structure preservation. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.Item TransSARNet: a deep learning framework for despeckling of SAR images(Institute of Physics, 2025) Kevala, V.D.; Sravya, N.; Lal, S.; Suresh, S.; Dell’Acqua, F.Synthetic Aperture Radar(SAR) images are extensively used for Earth observation because of their all-weather, day, and night imaging capabilities. However, speckle noise in SAR images significantly reduces their usability in a variety of applications. Deep learning models developed for SAR despeckling exhibit promising noise reduction capabilities. Bringing a balance between reducing graininess and preserving texture details is a challenging task. In addition, supervised training of a robust deep learning model requires noisy images that capture the SAR speckle dynamics and the corresponding speckle-free ground truth, which is generally not available. This study proposes the first hybrid CNN-Halo attention-based transformer model for SAR despeckling. CNN-based feature extraction modules provide multiscale and multidirectional and large-scale feature maps. A halo-attention transformer block is used in the skip connection. It aids in the better preservation of radiometric information in the despeckled SAR images. TransSARNet is trained in a supervised manner using a new synthetic SAR dataset, which is a combination of the Kylberg and UCMerced land-use datasets. This study also analyzed the effect of combining the Kylberg and UCMerced datasets on texture preservation in despeckled SAR images. The visual and qualitative metrics evaluated on Sentinel-1 Single Look Complex SAR data showed that the proposed TransSARNet approach outperformed the other models under consideration. TransSARNet achieves a harmonious balance between model complexity, despeckling ability, edge preservation, radiometric information preservation, and smoothing in homogeneous regions. © 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.