Grigorios Tsagkatakis

Dr. Grigorios Tsagkatakis

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 September 2019 in Sensors
Verified
Journal Article
Open access
PDF file
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
AAAnastasia Aidini
Anastasia Aidini
KFKonstantina Fotiadou
Konstantina Fotiadou
MGMichalis Giannopoulos
Michalis Giannopoulos
APAnastasia Pentari
Anastasia Pentari
PTPanagiotis Tsakalides
Panagiotis Tsakalides
Deep Learning, and Deep Neural Networks in particular, have established themselves as the new norm in signal and data processing, achieving state-of-the-art performance in image, audio, and natural language understanding. In remote sensing, a large body of research has been devoted to the application of deep learning for typical supervised learning tasks such as classification. Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms. Addressing such channels is of paramount importance, both in itself, since high-altitude imaging, environmental conditions, and imaging systems trade-offs lead to low-quality observation, as well as to facilitate subsequent analysis, such as classification and detection. In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. In addition to the detailed analysis and comparison of recently presented approaches, different research avenues which could be explored in the future are also discussed.

4 February 2019 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
Radamanthys StivaktakisRadamanthys Stivaktakis
Radamanthys Stivaktakis
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
PTPanagiotis Tsakalides
Panagiotis Tsakalides
Land cover classification is a flourishing research topic in the field of remote sensing. Conventional methodologies mainly focus either on the simplified single-label case or on the pixel-based approaches that cannot efficiently handle high-resolution images. On the other hand, the problem of multilabel land cover scene categorization remains, to this day, fairly unexplored. While deep learning and convolutional neural networks have demonstrated an astounding capacity at handling challenging machine learning tasks, such as image classification, they exhibit an underwhelming performance when trained with a limited amount of annotated examples. To overcome this issue, this paper proposes a data augmentation technique that can drastically increase the size of a smaller data set to copious amounts. Our experiments on a multilabel variation of the UC Merced Land Use data set demonstrate the potential of the proposed methodology, which outperforms the current state of the art by more than 6% in terms of the F-score metric.

1 March 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
GDGeorgios I. Drakonakis
Georgios I. Drakonakis
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
KFKonstantina Fotiadou
Konstantina Fotiadou
PTPanagiotis Tsakalides
Panagiotis Tsakalides
Regions around the world experience adverse climate-change-induced conditions that pose severe risks to the normal and sustainable operations of modern societies. Extreme weather events, such as floods, rising sea levels, and storms, stand as characteristic examples that impair the core services of the global ecosystem. Especially floods have a severe impact on human activities, hence, early and accurate delineation of the disaster is of top priority since it provides environmental, economic, and societal benefits and eases relief efforts. In this article, we introduce OmbriaNet, a deep neural network architecture, based on convolutional neural networks, that detects changes between permanent and flooded water areas by exploiting the temporal differences among flood events extracted by different sensors. To demonstrate the potential of the proposed approach, we generated OMBRIA, a bitemporal and multimodal satellite imagery dataset for image segmentation through supervised binary classification. It consists of a total number of 3.376 images, synthetic aperture radar imagery from Sentinel-1, and multispectral imagery from Sentinel-2, accompanied with ground-truth binary images produced from data derived by experts and provided from the Emergency Management Service of the European Space Agency Copernicus Program. The dataset covers 23 flood events around the globe, from 2017 to 2021. We collected, co-registrated and preprocessed the data in Google Earth Engine. To validate the performance of our method, we performed different benchmarking experiments on the OMBRIA dataset and we compared with several competitive state-of-the-art techniques. The experimental analysis demonstrated that the proposed formulation is able to produce high-quality flood maps, achieving a superior performance over the state-of-the-art. We provide OMBRIA dataset, as well as OmbriaNet code at: https://github.com/geodrak/OMBRIA .

14 November 2018 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
KFKonstantina Fotiadou
Konstantina Fotiadou
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
PTPanagiotis Tsakalides
Panagiotis Tsakalides
High-spectral resolution imaging systems play a critical role in the identification and characterization of objects in a scene of interest. Unfortunately, multiple factors impair spectral resolution, as in the case of modern snapshot spectral imagers that associate each hyperpixel with a specific spectral band. In this paper, we introduce a novel postacquisition computational technique aiming to enhance the spectral dimensionality of imaging systems by exploiting the mathematical frameworks of sparse representations and dictionary learning. We propose a coupled dictionary learning model which considers joint feature spaces, composed of low- and high-spectral resolution hypercubes, in order to achieve spectral superresolution performance. We formulate our spectral coupled dictionary learning optimization problem within the context of the alternating direction method of multipliers, and we manage to update the involved quantities via closed-form expressions. In addition, we consider a realistic spectral subsampling scenario, taking into account the spectral response functions of different satellites. Moreover, we apply our spectral superresolution algorithm on real satellite data acquired by Landsat-8 and Sentinel-2 sensors. Finally, we have investigated the problem of hyperspectral image unmixing using the recovered high-spectral resolution data cube, and we are able to demonstrate that the proposed scheme provides significant value in hyperspectral image understanding techniques. Experimental results demonstrate the ability of the proposed approach to synthesize high-spectral-resolution 3-D hypercubes, achieving better performance compared to state-of-the-art resolution enhancement methods.

28 March 2011 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
ASAndreas Savakis
Andreas Savakis
Tracking an object without any prior information regarding its appearance is a challenging problem. Modern tracking algorithms treat tracking as a binary classification problem between the object class and the background class. The binary classifier can be learned offline, if a specific object model is available, or online, if there is no prior information about the object's appearance. In this paper, we propose the use of online distance metric learning in combination with nearest neighbor classification for object tracking. We assume that the previous appearances of the object and the background are clustered so that a nearest neighbor classifier can be used to distinguish between the new appearance of the object and the appearance of the background. In order to support the classification, we employ a distance metric learning (DML) algorithm that learns to separate the object from the background. We utilize the first few frames to build an initial model of the object and the background and subsequently update the model at every frame during the course of tracking, so that changes in the appearance of the object and the background are incorporated into the model. Furthermore, instead of using only the previous frame as the object's model, we utilize a collection of previous appearances encoded in a template library to estimate the similarity under variations in appearance. In addition to the utilization of the online DML algorithm for learning the object/background model, we propose a novel feature representation of image patches. This representation is based on the extraction of scale invariant features over a regular grid coupled with dimensionality reduction using random projections. This type of representation is both robust, capitalizing on the reproducibility of the scale invariant features, and fast, performing the tracking on a reduced dimensional space. The proposed tracking algorithm was tested under challenging conditions and achieved state-of-the art performance.

18 February 2016 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
KKKonstantinos Karalas
Konstantinos Karalas
GTGrigorios Tsagkatakis
Grigorios Tsagkatakis
MZMichael Zervakis
Michael Zervakis
PTPanagiotis Tsakalides
Panagiotis Tsakalides
Obtaining an up-to-date high-resolution description of land cover is a challenging task due to the high cost and labor-intensive process of human annotation through field studies. This work introduces a radically novel approach for achieving this goal by exploiting the proliferation of remote sensing satellite imagery, allowing for the up-to-date generation of global-scale land cover maps. We propose the application of multilabel classification, a powerful framework in machine learning, for inferring the complex relationships between the acquired satellite images and the spectral profiles of different types of surface materials. Introducing a drastically different approach compared to unsupervised spectral unmixing, we employ contemporary ground-collected data from the European Environment Agency to generate the label set and multispectral images from the MODIS sensor to generate the spectral features, under a supervised classification framework. To validate the merits of our approach, we present results using several state-of-the-art multilabel learning classifiers and evaluate their predictive performance with respect to the number of annotated training examples, as well as their capability to exploit examples from neighboring regions or different time instances. We also demonstrate the application of our method on hyperspectral data from the Hyperion sensor for the urban land cover estimation of New York City. Experimental results suggest that the proposed framework can achieve excellent prediction accuracy, even from a limited number of diverse training examples, surpassing state-of-the-art spectral unmixing methods.