2018
Other
Restricted
Ship Kinematics Estimation (SKE) module - Vessel kinematics estimation through SAR/Optical Imagery Processing
Reggiannini M, Bedini L
The main goal of the work described in this report concerns the estimation of the kinematics variables related to the motion of a navigating vessel. One way to perform such operations is to process maps captured by Synthetic Aperture Radar (SAR) and optical sensors installed on board of satellite constellations orbiting around earth-centred trajectories. The primary goal of this processing is to identify and analyze the wake traces left by navigating vessels on the water surface. Wakes can be typically observed in high resolution SAR and optical maps. A proper processing of these surface patterns allows to estimate the orientation of the vessel motion ({\it route}) and the corresponding velocity module. The resulting estimates can be exploited in the implementation of maritime surveillance and vessel traffic monitoring purposes. This document describes the design and the implementation of the software procedures dedicated to the aforementioned purposes, together combined in the software tool named Ship Kinematics Estimation module.
Reggiannini M, Bedini L
The main goal of the work described in this report concerns the estimation of the kinematics variables related to the motion of a navigating vessel. One way to perform such operations is to process maps captured by Synthetic Aperture Radar (SAR) and optical sensors installed on board of satellite constellations orbiting around earth-centred trajectories. The primary goal of this processing is to identify and analyze the wake traces left by navigating vessels on the water surface. Wakes can be typically observed in high resolution SAR and optical maps. A proper processing of these surface patterns allows to estimate the orientation of the vessel motion ({\it route}) and the corresponding velocity module. The resulting estimates can be exploited in the implementation of maritime surveillance and vessel traffic monitoring purposes. This document describes the design and the implementation of the software procedures dedicated to the aforementioned purposes, together combined in the software tool named Ship Kinematics Estimation module.
2016
Other
Restricted
A cooperative approach for pattern recognition in underwater scene understanding by multi-sensor data integration
Reggiannini M
Marine environments cover more than two thirds of the whole earth surface and represent an outstanding scenario for researchers and scientists. Concerned people are involved in specific topics such as marine biology, oil and gas extraction, environment pollution monitoring and cultural heritage safeguard and preservation. This peculiar environment represents a hostile framework for what concerns human or scientific operations, in particular archaeological surveys or intervention missions. Oceans' waters impose strict constraints to any kind of underwater activity, included survey, mapping, rescueing and manipulation of sunken objects. Nevertheless the world seas have become quite a concern to cultural institutions since the number of wrecks lying all over the globe seabeds has been estimated by UNESCO to be around 3 millions. This huge patrimony is currently threatened by criminal activities which have tools available to discover underwater sites and illegally remove their content. Joint efforts between cultural institutions and scientific communities have been fostered by the European Community to promote survey missions of the marine seabeds and safeguard actions aiming at the preservation of the archaeological sunken heritage. To face the complicated issues concerning any kind of human activity in the peculiar marine framework, technical operators and useful support in the devices typically used in the oceanography field. Surveys can be performed by unmanned robots and this enables efficient data capture campaigns to be carried out and allows the thorough and detailed observation of extremely remote locations, including those too deep to be easily accessed by human operators. Many typologies of robots have been devised for exploitation by oceanographers. They are usually classified as Remotely Operated Vehicles (ROV), semi-autonomous platforms requiring human operators to be maneuvered, and Autonomous Underwater Vehicles (AUV) that can be programmed to perform survey missions in a completely autonomous mode. The experimental missions carried out within this PhD activity have been performed by exploiting AUVs designed and developed in the framework of the 7th European Framework Programme project "ARchaeological RObot Systems for the World's Seas". For the project purposes, the robots have been equipped with a set of payload sensors, properly selected bearing in mind the specific mission requirements. Optical and, most notably, acoustic sensors are the natural choice to survey the sea environment. Acoustic sensors are particularly appealing because of the remarkable efficiency of acoustic propagation in the water medium. Actually acoustic waves propagate over long distances in the water and may warrant significant coverages (hundreds of meters or more) without suffering from strong energy loss. Among the Sound Navigation and Ranging (SONAR) devices, we mention the Side Scan Sonar (SSS) and the Multibeam Echosounder (MBES). The former generates maps of the seafloor, providing the operator with a large-scale but coarse-resolution visual representation of the environment. The latter returns bathymetry information of the seafloor as well. Depending on the sensor typology the spatial resolution properties may vary from meter to centimeter values. This thesis addresses the development and implementation of methods and procedures aimed at providing a robot platform with an autonomous capability to understand the marine environment without human supervision. Each sensor onboard generates a data stream and through proper processing returns a piece of information concerning the environment as seen from the specific viewpoint of the considered sensor. The fusion of the multiple pieces of information not only facilitates the acquisition of an overall picture of the environment but also allows to achieve increased reliability about the recognition of the objects in the scene and about its interpretation.
Reggiannini M
Marine environments cover more than two thirds of the whole earth surface and represent an outstanding scenario for researchers and scientists. Concerned people are involved in specific topics such as marine biology, oil and gas extraction, environment pollution monitoring and cultural heritage safeguard and preservation. This peculiar environment represents a hostile framework for what concerns human or scientific operations, in particular archaeological surveys or intervention missions. Oceans' waters impose strict constraints to any kind of underwater activity, included survey, mapping, rescueing and manipulation of sunken objects. Nevertheless the world seas have become quite a concern to cultural institutions since the number of wrecks lying all over the globe seabeds has been estimated by UNESCO to be around 3 millions. This huge patrimony is currently threatened by criminal activities which have tools available to discover underwater sites and illegally remove their content. Joint efforts between cultural institutions and scientific communities have been fostered by the European Community to promote survey missions of the marine seabeds and safeguard actions aiming at the preservation of the archaeological sunken heritage. To face the complicated issues concerning any kind of human activity in the peculiar marine framework, technical operators and useful support in the devices typically used in the oceanography field. Surveys can be performed by unmanned robots and this enables efficient data capture campaigns to be carried out and allows the thorough and detailed observation of extremely remote locations, including those too deep to be easily accessed by human operators. Many typologies of robots have been devised for exploitation by oceanographers. They are usually classified as Remotely Operated Vehicles (ROV), semi-autonomous platforms requiring human operators to be maneuvered, and Autonomous Underwater Vehicles (AUV) that can be programmed to perform survey missions in a completely autonomous mode. The experimental missions carried out within this PhD activity have been performed by exploiting AUVs designed and developed in the framework of the 7th European Framework Programme project "ARchaeological RObot Systems for the World's Seas". For the project purposes, the robots have been equipped with a set of payload sensors, properly selected bearing in mind the specific mission requirements. Optical and, most notably, acoustic sensors are the natural choice to survey the sea environment. Acoustic sensors are particularly appealing because of the remarkable efficiency of acoustic propagation in the water medium. Actually acoustic waves propagate over long distances in the water and may warrant significant coverages (hundreds of meters or more) without suffering from strong energy loss. Among the Sound Navigation and Ranging (SONAR) devices, we mention the Side Scan Sonar (SSS) and the Multibeam Echosounder (MBES). The former generates maps of the seafloor, providing the operator with a large-scale but coarse-resolution visual representation of the environment. The latter returns bathymetry information of the seafloor as well. Depending on the sensor typology the spatial resolution properties may vary from meter to centimeter values. This thesis addresses the development and implementation of methods and procedures aimed at providing a robot platform with an autonomous capability to understand the marine environment without human supervision. Each sensor onboard generates a data stream and through proper processing returns a piece of information concerning the environment as seen from the specific viewpoint of the considered sensor. The fusion of the multiple pieces of information not only facilitates the acquisition of an overall picture of the environment but also allows to achieve increased reliability about the recognition of the objects in the scene and about its interpretation.
2016
Conference article
Open Access
Understanding underwater archaeological scenarios by optical and acoustic sensing tools
Reggiannini M
Underwater seafloors represent a huge archive of manmade artefacts, a cultural heritage whose abandon process started since man has been able to travel by the waters. In order to put this heritage under safeguard and preservation archaeologists require and request for technological support provided by the scientific community. Automated procedures tailored for the purposes of manmade object recognition in the underwater scenario represent the main topic discussed in this work. In particular the authors propose a set of procedures that enables to extract meaningful insights about the inspected environment and that can be exploited to assign a label of interest, in terms of cultural significance, to the surveyed areas. Furthermore the authors introduce a sketch of a framework according to which the identification of interesting areas on the seafloor may be implemented in terms of a Bayes decision system.DOI: 10.1109/iwcim.2016.7801187
Metrics:
Reggiannini M
Underwater seafloors represent a huge archive of manmade artefacts, a cultural heritage whose abandon process started since man has been able to travel by the waters. In order to put this heritage under safeguard and preservation archaeologists require and request for technological support provided by the scientific community. Automated procedures tailored for the purposes of manmade object recognition in the underwater scenario represent the main topic discussed in this work. In particular the authors propose a set of procedures that enables to extract meaningful insights about the inspected environment and that can be exploited to assign a label of interest, in terms of cultural significance, to the surveyed areas. Furthermore the authors introduce a sketch of a framework according to which the identification of interesting areas on the seafloor may be implemented in terms of a Bayes decision system.DOI: 10.1109/iwcim.2016.7801187
Metrics:
See at:
CNR IRIS 
| ieeexplore.ieee.org | ISTI Repository | doi.org 
| CNR IRIS | CNR IRIS
2017
Other
Restricted
OSIRIS - Satellite SAR imagery processing for vessel kinematics estimation
Reggiannini M
Navigating vessels detection, identification and kinematics parameters estimation are relevant tasks concerning maritime surveillance and monitoring. One way to perform such operations is to process maps captured by Synthetic Aperture Radar (SAR) sensors installed on board of satellite constellations orbiting around earth-centered trajectories. Navigating vessels leave traces of their motion in the form of wake patterns on the water surface. Wakes are visible in high resolution SAR maps and bear information related to the kinematic variables of the vessel motion. A proper processing of the wake system allows to estimate the orientation of the vessel motion and the velocity module. This information can be exploited in the implementation of decision procedures dedicated to the control of maritime traffic. This document describes the design and implementation of software procedures with the purpose of estimating the motion parameters of a navigating vessel, through the processing of the wake pattern generated by the vessel itself.
Reggiannini M
Navigating vessels detection, identification and kinematics parameters estimation are relevant tasks concerning maritime surveillance and monitoring. One way to perform such operations is to process maps captured by Synthetic Aperture Radar (SAR) sensors installed on board of satellite constellations orbiting around earth-centered trajectories. Navigating vessels leave traces of their motion in the form of wake patterns on the water surface. Wakes are visible in high resolution SAR maps and bear information related to the kinematic variables of the vessel motion. A proper processing of the wake system allows to estimate the orientation of the vessel motion and the velocity module. This information can be exploited in the implementation of decision procedures dedicated to the control of maritime traffic. This document describes the design and implementation of software procedures with the purpose of estimating the motion parameters of a navigating vessel, through the processing of the wake pattern generated by the vessel itself.
2018
Journal article
Open Access
Synthetic aperture radar processing for vessel kinematics estimation
Reggiannini M, Bedini L
Navigating vessels leave traces of their motion in the form of wake patterns on the water surface. Wakes are visible in high resolution Synthetic Aperture Radar maps and bear information related to the kinematic variables of the vessel motion. A proper processing of the wake pattern allows to estimate the vessel heading and velocity. This information can be exploited in decision procedures concerning maritime surveillance and ship traffic monitoring. This document describes the design and implementation of software procedures with the purpose of estimating the motion parameters of a navigating vessel, through processing the wake pattern generated by the vessel itself.Source: PROCEEDINGS (MDPI), vol. 2 (issue 2)
DOI: 10.3390/proceedings2020091
DOI: 10.5281/zenodo.1159154
DOI: 10.5281/zenodo.1159153
Metrics:
Reggiannini M, Bedini L
Navigating vessels leave traces of their motion in the form of wake patterns on the water surface. Wakes are visible in high resolution Synthetic Aperture Radar maps and bear information related to the kinematic variables of the vessel motion. A proper processing of the wake pattern allows to estimate the vessel heading and velocity. This information can be exploited in decision procedures concerning maritime surveillance and ship traffic monitoring. This document describes the design and implementation of software procedures with the purpose of estimating the motion parameters of a navigating vessel, through processing the wake pattern generated by the vessel itself.Source: PROCEEDINGS (MDPI), vol. 2 (issue 2)
DOI: 10.3390/proceedings2020091
DOI: 10.5281/zenodo.1159154
DOI: 10.5281/zenodo.1159153
Metrics:
See at:
doi.org | ZENODO | ZENODO | CNR IRIS | ISTI Repository | www.mdpi.com | www.mdpi.com | CNR IRIS
2019
Journal article
Open Access
Multi-sensor satellite data processing for marine traffic understanding
Reggiannini M, Bedini L
The work described in this document concerns the estimation of the kinematics of a navigating vessel. This task can be accomplished through the exploitation of satellite-borne systems for Earth observation. Indeed, Synthetic Aperture Radar (SAR) and optical sensors installed aboard satellites (European Space Agency Sentinel, ImageSat International Earth Remote Observation System, Italian Space Agency Constellation of Small Satellites for Mediterranean basin Observation) return multi-resolution maps providing information about the marine surface. A moving ship represented through satellite imaging results in a bright oblong object, with a peculiar wake pattern generated by the ship’s passage throughout the water. By employing specifically tailored computer vision methods, these vessel features can be identified and individually analyzed for what concerns geometrical and radiometric properties, backscatterers spatial distribution and the spectral content of the wake components. This paper proposes a method for the automatic detection of the vessel’s motion-related features and their exploitation to provide an estimation of the vessel velocity vector. In particular, the ship’s related wake pattern is considered as a crucial target of interest for the purposes mentioned. The corresponding wake detection module has been implemented adopting a novel approach, i.e., by introducing a specifically tailored gradient estimator in the early processing stages. This results in the enhancement of the turbulent wake detection performance. The resulting overall procedure may also be included in marine surveillance systems in charge of detecting illegal maritime traffic, combating unauthorized fishing, irregular migration and related smuggling activities.Source: ELECTRONICS, vol. 8 (issue 2)
DOI: 10.3390/electronics8020152
Metrics:
Reggiannini M, Bedini L
The work described in this document concerns the estimation of the kinematics of a navigating vessel. This task can be accomplished through the exploitation of satellite-borne systems for Earth observation. Indeed, Synthetic Aperture Radar (SAR) and optical sensors installed aboard satellites (European Space Agency Sentinel, ImageSat International Earth Remote Observation System, Italian Space Agency Constellation of Small Satellites for Mediterranean basin Observation) return multi-resolution maps providing information about the marine surface. A moving ship represented through satellite imaging results in a bright oblong object, with a peculiar wake pattern generated by the ship’s passage throughout the water. By employing specifically tailored computer vision methods, these vessel features can be identified and individually analyzed for what concerns geometrical and radiometric properties, backscatterers spatial distribution and the spectral content of the wake components. This paper proposes a method for the automatic detection of the vessel’s motion-related features and their exploitation to provide an estimation of the vessel velocity vector. In particular, the ship’s related wake pattern is considered as a crucial target of interest for the purposes mentioned. The corresponding wake detection module has been implemented adopting a novel approach, i.e., by introducing a specifically tailored gradient estimator in the early processing stages. This results in the enhancement of the turbulent wake detection performance. The resulting overall procedure may also be included in marine surveillance systems in charge of detecting illegal maritime traffic, combating unauthorized fishing, irregular migration and related smuggling activities.Source: ELECTRONICS, vol. 8 (issue 2)
DOI: 10.3390/electronics8020152
Metrics:
See at:
Electronics | CNR IRIS | ISTI Repository | Electronics | Electronics | CNR IRIS
2019
Conference article
Open Access
SEARCH & INSPECTION ARCHAEOLOGICAL UNDERWATER CAMPAIGNS IN THE FRAMEWORK OF THE EUROPEAN ARROWS PROJECT
Allotta B, Costanzi R, Mugnai F, Reggiannini M, Ridolfi A, Scaradozzi D
Autonomous Underwater Vehicles (AUVs), benefiting from significant investments in the past years, are commonly used for military security and offshore Oil&Gas applications. The ARROWS project, aimed at exporting the AUV technology to the field of underwater archaeology, a low-budget research field compared to the previous ones. The paper focuses on the strategy for vehicle coordination adopted within the project, a Search and Inspection (S&I) approach borrowed from the defense field (e.g., mine countermeasure - MCM) that proved to be an efficient solution also for the main phases of an underwater archaeological mission. The other main novelty aspect is represented by MARTA (MArine Robotic Tool for Archaeology) AUV: it is a modular vehicle easily and quickly reconfigurable developed in the framework of ARROWS according to the project Archaeological Advisory Group (AAG) guidelines. Results from the final demonstration of the project, held in Estonia during Summer 2015, are proposed in the paper as an experimental proof of the validity of the proposed S&I strategy, and MARTA functioning and its adaptability to the mission requirements. Even in its first prototype version, MARTA successfully played the Inspection role within the AUV team, collaborating with a commercial Search AUV. Acoustic and optical data collected during the mission and processed to increase their intelligibility for the human operator are proposed and discussed.Source: INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES, pp. 63-70. Avila, Spain, 1-5 September 2019
DOI: 10.5194/isprs-archives-xlii-2-w15-63-2019
Project(s): ARROWS
Metrics:
Allotta B, Costanzi R, Mugnai F, Reggiannini M, Ridolfi A, Scaradozzi D
Autonomous Underwater Vehicles (AUVs), benefiting from significant investments in the past years, are commonly used for military security and offshore Oil&Gas applications. The ARROWS project, aimed at exporting the AUV technology to the field of underwater archaeology, a low-budget research field compared to the previous ones. The paper focuses on the strategy for vehicle coordination adopted within the project, a Search and Inspection (S&I) approach borrowed from the defense field (e.g., mine countermeasure - MCM) that proved to be an efficient solution also for the main phases of an underwater archaeological mission. The other main novelty aspect is represented by MARTA (MArine Robotic Tool for Archaeology) AUV: it is a modular vehicle easily and quickly reconfigurable developed in the framework of ARROWS according to the project Archaeological Advisory Group (AAG) guidelines. Results from the final demonstration of the project, held in Estonia during Summer 2015, are proposed in the paper as an experimental proof of the validity of the proposed S&I strategy, and MARTA functioning and its adaptability to the mission requirements. Even in its first prototype version, MARTA successfully played the Inspection role within the AUV team, collaborating with a commercial Search AUV. Acoustic and optical data collected during the mission and processed to increase their intelligibility for the human operator are proposed and discussed.Source: INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES, pp. 63-70. Avila, Spain, 1-5 September 2019
DOI: 10.5194/isprs-archives-xlii-2-w15-63-2019
Project(s): ARROWS
Metrics:
See at:
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | CNR IRIS | Flore (Florence Research Repository) | ISTI Repository | www.int-arch-photogramm-remote-sens-spatial-inf-sci.net | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences | CNR IRIS
2019
Conference article
Open Access
Remote Sensing for Maritime Monitoring and Vessel Characterization
Reggiannini M
The main objective of the work described here concerns the development of automatic ICT procedures in charge of processing imagery data captured by satellite-borne sensors to assess the status of a given maritime area. The mentioned assessment may refer to the detection and identification of peculiar objects, such as oil leaks or, in case of maritime traffic control, the recognition of navigating vessels. This paper specifically focuses on the development of methods for estimating the kinematics of a navigating vessel through the detection and analysis, in the 2D satellite imagery, of the corresponding wake pattern. The proposed method differentiates from those retrieved in previous literature for the introduction of a novel preprocessing stage, which allows for an enhancement in the overall performance of the wake detector. The resulting procedure represents a key functionality to be included in platforms dedicated to sea surveillance.DOI: 10.1109/oceanse.2019.8867258
Metrics:
Reggiannini M
The main objective of the work described here concerns the development of automatic ICT procedures in charge of processing imagery data captured by satellite-borne sensors to assess the status of a given maritime area. The mentioned assessment may refer to the detection and identification of peculiar objects, such as oil leaks or, in case of maritime traffic control, the recognition of navigating vessels. This paper specifically focuses on the development of methods for estimating the kinematics of a navigating vessel through the detection and analysis, in the 2D satellite imagery, of the corresponding wake pattern. The proposed method differentiates from those retrieved in previous literature for the introduction of a novel preprocessing stage, which allows for an enhancement in the overall performance of the wake detector. The resulting procedure represents a key functionality to be included in platforms dedicated to sea surveillance.DOI: 10.1109/oceanse.2019.8867258
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | doi.org | CNR IRIS
2021
Other
Restricted
Ship kinematics estimation based on doppler centroid deviation in synthetic aperture radar images
Reggiannini M
This technical report describes a method, and the related software, to estimate the kinematics of a navigating vessel by processing Synthetic Aperture Radar data. The implemented software is included within the Ship Kinematics Estimation module in the framework of OSIRIS-FO (Optical/SAR data and System Integration for Rush Identification of Ship Models - Follow On).
Reggiannini M
This technical report describes a method, and the related software, to estimate the kinematics of a navigating vessel by processing Synthetic Aperture Radar data. The implemented software is included within the Ship Kinematics Estimation module in the framework of OSIRIS-FO (Optical/SAR data and System Integration for Rush Identification of Ship Models - Follow On).
2024
Conference article
Restricted
Deep learning for SAR ship classification: focus on unbalanced datasets and inter-dataset generalization
Awais C. M., Reggiannini M.
Detection and recognition of vessel targets at sea are tasks of paramount relevance for maritime monitoring purposes. A possible approach to pursue these objectives consists in acquiring and processing Synthetic Aperture Radar (SAR) data related to a given area of interest. Classically, the detection part can be implemented by exploiting statistical properties of the signal to decide whether an image area belongs to background clutter or to a ship (e.g. Constant False Alarm Rate based algorithms). Successively, discriminant features referring to the detected object can be extracted and later fed to a classifier to decide the membership category of the considered target. Recently, thanks to the development of algorithms based on deep neural network architectures, object detection and recognition experienced an unprecedented boost in the observed performances. This work, mainly motivated by the exploration of these novel approaches to the identification of vessel targets, focuses on the analysis of five different deep learning architectures (CNN, pre-trained and non-pretrained versions of ResNet50 and VGG16) trained on two public SAR vessel datasets (OpenSARShip and Fusar). To address the data quantity limitation, a third dataset was created by merging both datasets.DOI: 10.1109/iceaa61917.2024.10701968
Project(s): National Biodiversity Future Center
Metrics:
Awais C. M., Reggiannini M.
Detection and recognition of vessel targets at sea are tasks of paramount relevance for maritime monitoring purposes. A possible approach to pursue these objectives consists in acquiring and processing Synthetic Aperture Radar (SAR) data related to a given area of interest. Classically, the detection part can be implemented by exploiting statistical properties of the signal to decide whether an image area belongs to background clutter or to a ship (e.g. Constant False Alarm Rate based algorithms). Successively, discriminant features referring to the detected object can be extracted and later fed to a classifier to decide the membership category of the considered target. Recently, thanks to the development of algorithms based on deep neural network architectures, object detection and recognition experienced an unprecedented boost in the observed performances. This work, mainly motivated by the exploration of these novel approaches to the identification of vessel targets, focuses on the analysis of five different deep learning architectures (CNN, pre-trained and non-pretrained versions of ResNet50 and VGG16) trained on two public SAR vessel datasets (OpenSARShip and Fusar). To address the data quantity limitation, a third dataset was created by merging both datasets.DOI: 10.1109/iceaa61917.2024.10701968
Project(s): National Biodiversity Future Center
Metrics:
2022
Other
Restricted
Ship kinematics estimation based on Doppler centroid deviation in synthetic aperture radar images: a validation case
Reggiannini M
This technical report describes a method, and the related software, to estimate the kinematics of a navigating vessel by processing Synthetic Aperture Radar data. This document represents the final outcome of the research activity concerning the ship kinematics estimation in OSIRIS-FO (Optical/SAR data and System Integration for Rush Identification of Ship Models - Follow On).The specific objective of the presented procedure is to estimate the along-range component of the velocity of a target, through the quantification of the deviations in the azimuth signal spectrum induced by the target motion. The report includes a brief recap about the theoretical aspects of the method and a section devoted to the description of a use case that provided the validation framework for the procedure. The software attached to the present document is the refined version of the one previously released in the technical report "Ship Kinematics Estimation based on Doppler centroid deviation in Synthetic Aperture Radar images".DOI: 10.32079/isti-tr-2022/044
Metrics:
Reggiannini M
This technical report describes a method, and the related software, to estimate the kinematics of a navigating vessel by processing Synthetic Aperture Radar data. This document represents the final outcome of the research activity concerning the ship kinematics estimation in OSIRIS-FO (Optical/SAR data and System Integration for Rush Identification of Ship Models - Follow On).The specific objective of the presented procedure is to estimate the along-range component of the velocity of a target, through the quantification of the deviations in the azimuth signal spectrum induced by the target motion. The report includes a brief recap about the theoretical aspects of the method and a section devoted to the description of a use case that provided the validation framework for the procedure. The software attached to the present document is the refined version of the one previously released in the technical report "Ship Kinematics Estimation based on Doppler centroid deviation in Synthetic Aperture Radar images".DOI: 10.32079/isti-tr-2022/044
Metrics:
2024
Other
Open Access
Imbalanced datasets through the lens of transfer-learning
Awais Ch Muhammad., Reggiannini M.
Data scarcity and class imbalance hinder deep learning for tasks like SAR ship classification. This work investigates how TRANSFER-LEARNING and DATA MERGING techniques can significantly improve the performance of deep learning models for class imbalanced datasets.Project(s): National Biodiversity Future Center
Awais Ch Muhammad., Reggiannini M.
Data scarcity and class imbalance hinder deep learning for tasks like SAR ship classification. This work investigates how TRANSFER-LEARNING and DATA MERGING techniques can significantly improve the performance of deep learning models for class imbalanced datasets.Project(s): National Biodiversity Future Center
See at:
CNR IRIS | www.nbfc.it | CNR IRIS
2024
Conference article
Open Access
Evaluating the Impact of fine-tuning on deep learning models for SAR ship classification
Awais Ch Muhammad, Reggiannini M.
Tasks like SAR ship classification suffer in deep learning due to data scarcity and class imbalance. To overcome these challenges, techniques like fine-tuning and data merging can play a vital role in the performance of a deep learning model. This study evaluates the effect of fine tuning on 5 different deep learning models.Project(s): National Biodiversity Future Center
Awais Ch Muhammad, Reggiannini M.
Tasks like SAR ship classification suffer in deep learning due to data scarcity and class imbalance. To overcome these challenges, techniques like fine-tuning and data merging can play a vital role in the performance of a deep learning model. This study evaluates the effect of fine tuning on 5 different deep learning models.Project(s): National Biodiversity Future Center
See at:
CNR IRIS | www.nbfc.it | CNR IRIS
2010
Other
Restricted
Considerazioni sull'errore di stima nel metodo FD-CCA
Reggiannini M, Bedini L, Salerno E
In this report, we deal with the problem of separating spatially correlated sources in astrophysics. We present a source mixing model and a strategy to estimate the sources and the mixing parameters. We then present a detailed description of the error covariance matrices and the statistical properties of the noise in the spectral domain. Finally, we deal with the problem of evaluating the estimation error in the spectral indices and in the source cross-spectra, with emphasis on the difference we found between the estimated error values and the values obtained by numerical simulation. Some hypotheses on the causes of this difference are then formulated, and a heuristic correction strategy is proposed, based on a suitable multiplicative factor for the log-posterior of the spectral indices.
Reggiannini M, Bedini L, Salerno E
In this report, we deal with the problem of separating spatially correlated sources in astrophysics. We present a source mixing model and a strategy to estimate the sources and the mixing parameters. We then present a detailed description of the error covariance matrices and the statistical properties of the noise in the spectral domain. Finally, we deal with the problem of evaluating the estimation error in the spectral indices and in the source cross-spectra, with emphasis on the difference we found between the estimated error values and the values obtained by numerical simulation. Some hypotheses on the causes of this difference are then formulated, and a heuristic correction strategy is proposed, based on a suitable multiplicative factor for the log-posterior of the spectral indices.
2013
Contribution to book
Restricted
The Arrows project for underwater archaeology
Reggiannini M, Salvetti O, Allotta B, Colombo C, Lane D, Cocco M, Gualdesi L, Roig B D, Dede C, Baines S, Tusa S, Dresen U, Salumae T
ARROWS is the acronym for ARchaeological RObot systems for the World's Seas1. The project, started in September 2012, is funded by the EU in the framework of the FP7 call ENV-2012, challenge 6.2-6, devoted to "Development of advanced technologies and tools for mapping, diagnosing, excavating, and securing underwater and coastal archaeological sites". The ARROWS consortium comprises expertise from underwater archaeology, underwater engineering, robotics, image processing and recognition from academia and industry. 10 partners from 5 different Countries are involved. The cost of underwater archaeological investigations using a research ship with skilled human operators and/or Remotely Operated Vehicles (ROVs) is high (up to EUR50k per day) and beyond the range of many archaeological research institutions. Reducing the cost of underwater archaeological operations is an important issue to address in advancing the knowledge of our cultural heritage. The challenge faced by ARROWS is to generate and adapt existing technologies in the field of military, security and offshore oil and gas applications, in order to develop user-friendly and low cost Autonomous Underwater Vehicle (AUV) technologies for archaeological investigation in different sea environments. Two different demonstration sites will used, one in the Baltic Sea and one in the Egadi archipelago (Sicily).Project(s): ARROWS
Reggiannini M, Salvetti O, Allotta B, Colombo C, Lane D, Cocco M, Gualdesi L, Roig B D, Dede C, Baines S, Tusa S, Dresen U, Salumae T
ARROWS is the acronym for ARchaeological RObot systems for the World's Seas1. The project, started in September 2012, is funded by the EU in the framework of the FP7 call ENV-2012, challenge 6.2-6, devoted to "Development of advanced technologies and tools for mapping, diagnosing, excavating, and securing underwater and coastal archaeological sites". The ARROWS consortium comprises expertise from underwater archaeology, underwater engineering, robotics, image processing and recognition from academia and industry. 10 partners from 5 different Countries are involved. The cost of underwater archaeological investigations using a research ship with skilled human operators and/or Remotely Operated Vehicles (ROVs) is high (up to EUR50k per day) and beyond the range of many archaeological research institutions. Reducing the cost of underwater archaeological operations is an important issue to address in advancing the knowledge of our cultural heritage. The challenge faced by ARROWS is to generate and adapt existing technologies in the field of military, security and offshore oil and gas applications, in order to develop user-friendly and low cost Autonomous Underwater Vehicle (AUV) technologies for archaeological investigation in different sea environments. Two different demonstration sites will used, one in the Baltic Sea and one in the Egadi archipelago (Sicily).Project(s): ARROWS
2017
Journal article
Open Access
Processing satellite imagery to detect and identify non-collaborative vessels
Reggiannini M, Righi M
In recent years, European maritime countries have had to deal with new situations involving the traffic of illegal vessels. In order to tackle such problems, systems are required that can detect relevant anomalies such as unauthorised fishing or irregular migration and related smuggling activity. The OSIRIS project aims to contribute to a solution to these problems with the use of large scale data provided by satellite missions (Sentinel, Cosmo-SkyMed, EROS). Optical/SAR data and system Integration for Rush Identification of Ship models (OSIRIS) is a European Space Agency project launched in March 2016, with the primary purpose of developing a software platform dedicated to maritime surveillance. The platform will be in charge of: (i) collecting maritime remote sensing data provided by satellite missions such as Sentinel-1, Sentinel-2, Cosmo-SkyMed and EROS-B, and (ii) processing the acquired data in order to detect and classify seagoing vessels. A main goal within OSIRIS is to develop computational imaging procedures to process Synthetic Aperture Radar and Optical data returned by satellite sensors. We propose a system to automatically detect and recognise all the vessels within in a given area; the maritime satellite imagery will be processed to extract visual informative features of candidate vessels and to assign an identification label to each vessel.Source: ERCIM NEWS, pp. 25-26
Reggiannini M, Righi M
In recent years, European maritime countries have had to deal with new situations involving the traffic of illegal vessels. In order to tackle such problems, systems are required that can detect relevant anomalies such as unauthorised fishing or irregular migration and related smuggling activity. The OSIRIS project aims to contribute to a solution to these problems with the use of large scale data provided by satellite missions (Sentinel, Cosmo-SkyMed, EROS). Optical/SAR data and system Integration for Rush Identification of Ship models (OSIRIS) is a European Space Agency project launched in March 2016, with the primary purpose of developing a software platform dedicated to maritime surveillance. The platform will be in charge of: (i) collecting maritime remote sensing data provided by satellite missions such as Sentinel-1, Sentinel-2, Cosmo-SkyMed and EROS-B, and (ii) processing the acquired data in order to detect and classify seagoing vessels. A main goal within OSIRIS is to develop computational imaging procedures to process Synthetic Aperture Radar and Optical data returned by satellite sensors. We propose a system to automatically detect and recognise all the vessels within in a given area; the maritime satellite imagery will be processed to extract visual informative features of candidate vessels and to assign an identification label to each vessel.Source: ERCIM NEWS, pp. 25-26
See at:
ercim-news.ercim.eu | CNR IRIS | ISTI Repository | CNR IRIS
2016
Conference article
Open Access
Archaeology oriented optical acquisitions through MARTA AUV during ARROWS European project demonstration
Allotta B, Costanzi R, Ridolfi A, Reggiannini M, Tampucci M, Scaradozzi D
The three-years European FP7 ARROWS project (ARchaeological RObot systems for the World's Seas) concluded at the end of August 2015. A heterogeneous team of cooperating AUVs has been created in the framework of ARROWS: these are both new prototypes and well known commercial vehicles. In the paper MARTA modular AUV is described: MARTA is a new prototype specifically designed during the project. Its navigation and payload capabilities are discussed and some of the results, mainly optical acquisitions for the archaeologists, reached during the first official demo of the ARROWS European project (Sicily, Italy, May and June 2015) are reported and commented.DOI: 10.1109/oceans.2016.7761127
Project(s): ARROWS
Metrics:
Allotta B, Costanzi R, Ridolfi A, Reggiannini M, Tampucci M, Scaradozzi D
The three-years European FP7 ARROWS project (ARchaeological RObot systems for the World's Seas) concluded at the end of August 2015. A heterogeneous team of cooperating AUVs has been created in the framework of ARROWS: these are both new prototypes and well known commercial vehicles. In the paper MARTA modular AUV is described: MARTA is a new prototype specifically designed during the project. Its navigation and payload capabilities are discussed and some of the results, mainly optical acquisitions for the archaeologists, reached during the first official demo of the ARROWS European project (Sicily, Italy, May and June 2015) are reported and commented.DOI: 10.1109/oceans.2016.7761127
Project(s): ARROWS
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | doi.org | CNR IRIS | CNR IRIS
2017
Journal article
Open Access
Seafloor analysis and understanding for underwater archeology
Reggiannini M, Salvetti O
Surveying the oceans' floors represents at the same time a demanding and relevant task to operators concerned with marine biology, engineering or sunken cultural heritage preservation. Scientific researchers and concerned persons combine their effort to pursue optimized solutions aiming at the mapping of underwater areas, the detection of interesting objects and, in case of archeological survey mission, the safeguard of the detected sites. Among the typical tools exploited to perform the cited operations the Autonomous Underwater Vehicles (AUVs) represent a validated and reliable technology. These vehicles are typically equipped with properly selected sensors that collect data from the surveyed environment. This data can be employed to detect and recognize targets of interest, such as manmade artifacts located on the seabed, both in an online or offline modality. The adopted approach consists in laying emphasis on the amount of regularity contained in the data, referring to the content of geometrical shapes or textural surface patterns. These features can be used to label the environment in terms of more or less interesting areas, where more interesting refers to higher chances of detecting the sought objects (such as man-made objects) in the surveyed area. This paper describes the methods developed to fulfill the purposes of mapping and object detection in the underwater scenario and presents some of the experimental results obtained by the implementation of the discussed techniques in the underwater archeology field.Source: JOURNAL OF CULTURAL HERITAGE, vol. 24, pp. 147-156
DOI: 10.1016/j.culher.2016.10.012
Metrics:
Reggiannini M, Salvetti O
Surveying the oceans' floors represents at the same time a demanding and relevant task to operators concerned with marine biology, engineering or sunken cultural heritage preservation. Scientific researchers and concerned persons combine their effort to pursue optimized solutions aiming at the mapping of underwater areas, the detection of interesting objects and, in case of archeological survey mission, the safeguard of the detected sites. Among the typical tools exploited to perform the cited operations the Autonomous Underwater Vehicles (AUVs) represent a validated and reliable technology. These vehicles are typically equipped with properly selected sensors that collect data from the surveyed environment. This data can be employed to detect and recognize targets of interest, such as manmade artifacts located on the seabed, both in an online or offline modality. The adopted approach consists in laying emphasis on the amount of regularity contained in the data, referring to the content of geometrical shapes or textural surface patterns. These features can be used to label the environment in terms of more or less interesting areas, where more interesting refers to higher chances of detecting the sought objects (such as man-made objects) in the surveyed area. This paper describes the methods developed to fulfill the purposes of mapping and object detection in the underwater scenario and presents some of the experimental results obtained by the implementation of the discussed techniques in the underwater archeology field.Source: JOURNAL OF CULTURAL HERITAGE, vol. 24, pp. 147-156
DOI: 10.1016/j.culher.2016.10.012
Metrics:
See at:
CNR IRIS | ISTI Repository | www.sciencedirect.com | Journal of Cultural Heritage | CNR IRIS | CNR IRIS
2017
Conference article
Open Access
Supporting and promoting underwater archeology through computer vision and graphics
Reggiannini M, Tampucci M
The essential mission of an archeologist can be synthesized in two main objectives. The first one concerns the entire system of experimental measurements and subsequent decision making procedures involved in the archaeological fieldwork process. These actions are usually based on the employment of engineering methods and technical tools that enable the implementation of site searching, mapping and documentation collecting tasks. On the other hand, once the fieldwork has been accomplished, the archaeologist main goal becomes the development of specific actions dedicated to the site preservation and prevention from illicit intrusion events and finally, to the dissemination of the gathered knowledge to increase people awareness about cultural heritage. The mentioned issues constitute the primary concerns for every institution involved in the safeguard and promotion of cultural heritage. This is true for on land and for underwater archeology as well. This paper focuses on issues related to the underwater archeology scenario, a circumstance that deserves an in-depth discussion since the intrinsic threats for human safety as well as the complex working conditions pose challenging issues to the archaeological mission. Nevertheless the huge patrimony of wrecks and man made artifacts lying all over the globe sea floors must be preserved in that it represents a collective community asset.Project(s): ARROWS
Reggiannini M, Tampucci M
The essential mission of an archeologist can be synthesized in two main objectives. The first one concerns the entire system of experimental measurements and subsequent decision making procedures involved in the archaeological fieldwork process. These actions are usually based on the employment of engineering methods and technical tools that enable the implementation of site searching, mapping and documentation collecting tasks. On the other hand, once the fieldwork has been accomplished, the archaeologist main goal becomes the development of specific actions dedicated to the site preservation and prevention from illicit intrusion events and finally, to the dissemination of the gathered knowledge to increase people awareness about cultural heritage. The mentioned issues constitute the primary concerns for every institution involved in the safeguard and promotion of cultural heritage. This is true for on land and for underwater archeology as well. This paper focuses on issues related to the underwater archeology scenario, a circumstance that deserves an in-depth discussion since the intrinsic threats for human safety as well as the complex working conditions pose challenging issues to the archaeological mission. Nevertheless the huge patrimony of wrecks and man made artifacts lying all over the globe sea floors must be preserved in that it represents a collective community asset.Project(s): ARROWS
See at:
CNR IRIS | ISTI Repository | CNR IRIS | CNR IRIS
2019
Book
Open Access
Special Issue "Ocean Big Data Application - Engineering"
Pieri G, Reggiannini M
Ocean observation represents a crucial task for human communities. Above sea level, this entails the implementation of maritime surveillance platforms, typically addressing security and safety issues (vessel traffic monitoring, search and rescue) as well as environmental sustainability aspects (fishery, pollution). On the other hand, the submerged ocean environment poses equally hard challenges for what concerns oil and gas exploitation or biology and cultural heritage safeguard. Performing the mentioned activities operationally requires the collection of a huge amount of multi-source and multi-sensor data, typically including optical images, videos, sonograms, radar/synthetic aperture radar maps, hydrocarbon concentration measurements, and so on. Publications in this Special Issue will aim at composing a comprehensive overview of the several aspects that emerge in the implementation of ocean observation platforms through big data processing. With these issues in mind, among the various subjects the authors are invited to discuss theoretical issues in big data processing for ocean observation, as well as methods for big data processing through high performance computing (such as cloud computing infrastructures, big data fusion, etc.), not excluding application case studies exploiting big data issues. To this purpose, authors are invited to submit contributions that take into considerations the following topics: Ocean data representation, analysis and learning; Deep learning applied to big data for ocean observation; Techniques for data processing applied to ocean observation and cultural heritage safeguard; Target detection, classification and identification in ocean data; Vessel traffic monitoring; Marine pollution monitoring along with sea environment monitoring issues. Dr. Gabriele Pieri Dr. Marco Reggiannini Guest EditorsSource: JOURNAL OF MARINE SCIENCE AND ENGINEERING
Pieri G, Reggiannini M
Ocean observation represents a crucial task for human communities. Above sea level, this entails the implementation of maritime surveillance platforms, typically addressing security and safety issues (vessel traffic monitoring, search and rescue) as well as environmental sustainability aspects (fishery, pollution). On the other hand, the submerged ocean environment poses equally hard challenges for what concerns oil and gas exploitation or biology and cultural heritage safeguard. Performing the mentioned activities operationally requires the collection of a huge amount of multi-source and multi-sensor data, typically including optical images, videos, sonograms, radar/synthetic aperture radar maps, hydrocarbon concentration measurements, and so on. Publications in this Special Issue will aim at composing a comprehensive overview of the several aspects that emerge in the implementation of ocean observation platforms through big data processing. With these issues in mind, among the various subjects the authors are invited to discuss theoretical issues in big data processing for ocean observation, as well as methods for big data processing through high performance computing (such as cloud computing infrastructures, big data fusion, etc.), not excluding application case studies exploiting big data issues. To this purpose, authors are invited to submit contributions that take into considerations the following topics: Ocean data representation, analysis and learning; Deep learning applied to big data for ocean observation; Techniques for data processing applied to ocean observation and cultural heritage safeguard; Target detection, classification and identification in ocean data; Vessel traffic monitoring; Marine pollution monitoring along with sea environment monitoring issues. Dr. Gabriele Pieri Dr. Marco Reggiannini Guest EditorsSource: JOURNAL OF MARINE SCIENCE AND ENGINEERING
See at:
CNR IRIS | ISTI Repository | www.mdpi.com | CNR IRIS