12 result(s)
Page Size: 10, 20, 50
Export: bibtex, xml, json, csv
Order by:

CNR Author operator: and / or
Typology operator: and / or
Language operator: and / or
Date operator: and / or
Rights operator: and / or
2020 Journal article Open Access OPEN

A State of the Art Technology in Large Scale Underwater Monitoring
Pavoni G., Corsini M., Cignoni P.
In recent decades, benthic populations have been subjected to recurrent episodes of mass mortality. These events have been blamed in part on declining water quality and elevated water temperatures (see Figure 1) correlated to global climate change. Ecosystems are enhanced by the presence of species with three-dimensional growth. The study of the growth, resilience, and recovery capability of those species provides valuable information on the conservation status of entire habitats. We discuss here a state-of-the art solution to speed up the monitoring of benthic population through the automatic or assisted analysis of underwater visual data.Source: ERCIM news 2020 (2020): 17–18.

See at: ercim-news.ercim.eu Open Access | ISTI Repository Open Access | CNR ExploRA Open Access


2020 Journal article Open Access OPEN

On improving the training of models for the semantic segmentation of benthic communities from orthographic imagery
Pavoni G., Corsini M., Callieri M., Fiameni G., Edwards C., Cignoni P.
The semantic segmentation of underwater imagery is an important step in the ecological analysis of coral habitats. To date, scientists produce fine-scale area annotations manually, an exceptionally time-consuming task that could be efficiently automatized by modern CNNs. This paper extends our previous work presented at the 3DUW'19 conference, outlining the workflow for the automated annotation of imagery from the first step of dataset preparation, to the last step of prediction reassembly. In particular, we propose an ecologically inspired strategy for an efficient dataset partition, an over-sampling methodology targeted on ortho-imagery, and a score fusion strategy. We also investigate the use of different loss functions in the optimization of a Deeplab V3+ model, to mitigate the class-imbalance problem and improve prediction accuracy on coral instance boundaries. The experimental results demonstrate the effectiveness of the ecologically inspired split in improving model performance, and quantify the advantages and limitations of the proposed over-sampling strategy. The extensive comparison of the loss functions gives numerous insights on the segmentation task; the Focal Tversky, typically used in the context of medical imaging (but not in remote sensing), results in the most convenient choice. By improving the accuracy of automated ortho image processing, the results presented here promise to meet the fundamental challenge of increasing the spatial and temporal scale of coral reef research, allowing researchers greater predictive ability to better manage coral reef resilience in the context of a changing environment.Source: Remote sensing (Basel) 12 (2020). doi:10.3390/RS12183106
DOI: 10.3390/rs12183106

See at: Remote Sensing Open Access | Remote Sensing Open Access | ISTI Repository Open Access | CNR ExploRA Open Access | Remote Sensing Open Access | Remote Sensing Open Access


2020 Conference article Open Access OPEN

Another Brick in the Wall: Improving the Assisted Semantic Segmentation of Masonry Walls
Pavoni G., Giuliani F., De Falco A., Corsini M., Ponchio F., Callieri M., Cignoni P.
In Architectural Heritage, the masonry's interpretation is an essential instrument for analyzing the construction phases, the assessment of structural properties, and the monitoring of its state of conservation. This work is generally carried out by specialists that, based on visual observation and their knowledge, manually annotate ortho-images of the masonry generated by photogrammetric surveys. This results in vectorial thematic maps segmented according to their construction technique (isolating areas of homogeneous materials/structure/texture) or state of conservation, including degradation areas and damaged parts. This time-consuming manual work, often done with tools that have not been designed for this purpose, represents a bottleneck in the documentation and management workflow and is a severely limiting factor in monitoring large-scale monuments (e.g.city walls). This paper explores the potential of AI-based solutions to improve the efficiency of masonry annotation in Architectural Heritage. This experimentation aims at providing interactive tools that support and empower the current workflow, benefiting from specialists' expertise.Source: 18th Eurographics Workshop on Graphics and Cultural Heritage, pp. 43–51, Online event, 18-19/11/2020
DOI: 10.2312/gch.20201291

See at: ISTI Repository Open Access | CNR ExploRA Open Access


2020 Journal article Restricted

Challenges in the deep learning-based semantic segmentation of benthic communities from Ortho-images
Pavoni G., Corsini M., Pedersen N., Petrovic V., Cignoni P.
Since the early days of the low-cost camera development, the collection of visual data has become a common practice in the underwater monitoring field. Nevertheless, video and image sequences are a trustworthy source of knowledge that remains partially untapped. Human-based image analysis is a time-consuming task that creates a bottleneck between data collection and extrapolation. Nowadays, the annotation of biologically meaningful information from imagery can be efficiently automated or accelerated by convolutional neural networks (CNN). Presenting our case studies, we offer an overview of the potentialities and difficulties of accurate automatic recognition and segmentation of benthic species. This paper focuses on the application of deep learning techniques to multi-view stereo reconstruction by-products (registered images, point clouds, ortho-projections), considering the proliferation of these techniques among the marine science community. Of particular importance is the need to semantically segment imagery in order to generate demographic data vital to understand and explore the changes happening within marine communities.Source: Applied geomatics (Print) (2020). doi:10.1007/s12518-020-00331-6
DOI: 10.1007/s12518-020-00331-6

See at: Applied Geomatics Restricted | Applied Geomatics Restricted | Applied Geomatics Restricted | Applied Geomatics Restricted | CNR ExploRA Restricted


2019 Conference article Open Access OPEN

Visual acquisition system for georeferenced monitoring and reconstruction of the sea bottom using audio for data synchronisation
Costanzi R., Gasparri A., Pacienza F., Pollini L., Caiti A., Manzari V., Terracciano D., Stifani M., Pavoni G., Callieri M., Barbieri C., Colonna F., Gaino F., Moretto P., Pepe C. E., Romanelli A.
This work describes a Smart Dive Scooter (SDS) to be used as a support tool for monitoring application of different marine species. Professional divers of Environmental Protection Agencies are periodically involved in monitoring activities. Ligurian Regional Agency for the Environmental Protection (ARPAL) and the University of Pisa (UNIPI) are collaborating towards the integration of classical methodologies with ICT tools to support the work of divers in terms of safety, cost effectiveness and time effectiveness. The SDS is the first step in this direction. It is a classical Dive Scooter, used for rapid movements underwater, that is integrated with sensors for environment monitoring (a set of cameras) and for data georeferencing (acoustic localisation system). The SDS will be used by ARPAL divers to quickly acquire images of the bottom of a target area. Processing of optical and positioning data will allow to build a virtual model on which perform all the analysis and measurement activities. This approach results in limiting the time underwater for operators increasing the area mapper per each dive. The paper focuses on the technique used for the synchronization of optical data among the various cameras and of them with the acoustic position measurements. This goal is obtained exploiting the audio tracks acquired by the cameras avoiding the necessity of bulky and energy expensive dedicated computers. Results of the validation based on experimental data collected at sea are reported.Source: OCEANS 2019, Marseille, 17-20/6/2019
DOI: 10.1109/oceanse.2019.8867123

See at: ISTI Repository Open Access | academic.microsoft.com Restricted | ieeexplore.ieee.org Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2019 Journal article Open Access OPEN

Semantic segmentation of Benthic communities from ortho-mosaic maps
Pavoni G., Corsini M., Callieri M., Palma M., Scopigno R.
Visual sampling techniques represent a valuable resource for a rapid, non-invasive data acquisition for underwater monitoring purposes. Long-term monitoring projects usually requires the collection of large quantities of data, and the visual analysis of a human expert operator remains, in this context, a very time consuming task. It has been estimated that only the 1-2% of the acquired images are later analyzed by scientists (Beijbom et al., 2012). Strategies for the automatic recognition of benthic communities are required to effectively exploit all the information contained in visual data. Supervised learning methods, the most promising classification techniques in this field, are commonly affected by two recurring issues: the wide diversity of marine organism, and the small amount of labeled data. In this work, we discuss the advantages offered by the use of annotated high resolution ortho-mosaics of seabed to classify and segment the investigated specimens, and we suggest several strategies to obtain a considerable per-pixel classification performance although the use of a reduced training dataset composed by a single ortho-mosaic. The proposed methodology can be applied to a large number of different species, making the procedure of marine organism identification an highly adaptable task.Source: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Annals) 42 (2019): 151–158. doi:10.5194/isprs-archives-XLII-2-W10-151-2019
DOI: 10.5194/isprs-archives-xlii-2-w10-151-2019
Project(s): GreenBubbles via OpenAIRE

See at: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | ISTI Repository Open Access | CNR ExploRA Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | www.int-arch-photogramm-remote-sens-spatial-inf-sci.net Open Access


2019 Conference article Open Access OPEN

A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures
Pavoni G., Corsini M., Palma M., Scopigno R.
The automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.Source: Eurographics 2019, pp. 57–60, Genova, 6/5/2019-10/5/2019
DOI: 10.2312/egs.20191014

See at: diglib.eg.org Open Access | ISTI Repository Open Access | CNR ExploRA Open Access


2018 Journal article Open Access OPEN

Quasi-orthorectified projection for the measurement of red gorgonian colonies
Pavoni G., Palma M., Callieri M., Dellepiane M., Cerrano C., Pantaleo U., Scopigno R.
This study presents a practical method to estimate dimensions of Paramuricea clavata colonies using generic photographic datasets collected across wide areas. Paramuricea clavata is a non-rigid, tree-like octocoral; this morphology greatly affects the quality of the sea fans multi-view stereo matching reconstruction, resulting in hazy and incoherent clouds, full of "false" points with random orientation. Therefore, the standard procedure to take measurements over a reconstructed textured surface in 3D space is impractical. Our method overcomes this problem by using quasi-orthorectified images, produced by projecting registered photos on the plane that best fits the point cloud of the colony. The assessments of the measures collected have been performed comparing ground truth data set and time series images of the same set of colonies. The measurement errors fall below the requirements for this type of ecological observations. Compared to previous works, the presented method does not require a detailed reconstruction of individual colonies, but relies on a global multi-view stereo reconstruction performed through a comprehensive photographic coverage of the area of interest, using a low-cost pre-calibrated camera. This approach drastically reduces the time spent working on the field, helping practitioners and scientists in improving efficiency and accuracy in their monitoring plans.Source: The international archives of the photogrammetry, remote sensing and spatial information sciences (Print) 42 (2018): 853–860. doi:10.5194/isprs-archives-XLII-2-853-2018
DOI: 10.5194/isprs-archives-xlii-2-853-2018

See at: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | ISTI Repository Open Access | CNR ExploRA Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Open Access


2018 Journal article Open Access OPEN

SfM-based method to assess gorgonian forests (Paramuricea clavata (Cnidaria, Octocorallia))
Palma M., Casado M. R., Pantaleo U., Pavoni G., Pica D., Cerrano C.
Animal forests promote marine habitats morphological complexity and functioning. The red gorgonian, Paramuricea clavata, is a key structuring species of the Mediterranean coralligenous habitat and an indicator species of climate effects on habitat functioning. P. clavata metrics such as population structure, morphology and biomass inform on the overall health of coralligenous habitats, but the estimation of these metrics is time and cost consuming, and often requires destructive sampling. As a consequence, the implementation of long-term and wide-area monitoring programmes is limited. This study proposes a novel and transferable Structure from Motion (SfM) based method for the estimation of gorgonian population structure (i.e., maximal height, density, abundance), morphometries (i.e., maximal width, fan surface) and biomass (i.e., coenenchymal Dry Weight, Ash Free DriedWeight). The method includes the estimation of a novel metric (3D canopy surface) describing the gorgonian forest as a mosaic of planes generated by fitting multiple 5 cm × 5 cm facets to a SfM generated point cloud. The performance of the method is assessed for two different cameras (GoPro Hero4 and Sony NEX7). Results showed that for highly dense populations (17 colonies/m2), the SfM-method had lower accuracies in estimating the gorgonians density for both cameras (60% to 89%) than for medium to low density populations (14 and 7 colonies/m2) (71% to 100%). Results for the validation of the method showed that the correlation between ground truth and SfM estimates for maximal height, maximal width and fan surface were between R2 = 0.63 and R2 = 0.9, and R2 = 0.99 for coenenchymal surface estimation. The methodological approach was used to estimate the biomass of the gorgonian population within the study area and across the coralligenous habitat between -25 to -40 m depth in the Portofino Marine Protected Area. For that purpose, the coenenchymal surface of sampled colonies was obtained and used for the calculations. Results showed biomass values of dry weight and ash free dry weight of 220 g and 32 g for the studied area and to 365 kg and 55 Kg for the coralligenous habitat in the Marine Protected Area. This study highlighted the feasibility of the methodology for the quantification of P. clavata metrics as well as the potential of the SfM-method to improve current predictions of the status of the coralligenous habitat in the Mediterranean sea and overall management of threatened ecosystems. © 2018 by the authors.Source: Remote sensing (Basel) 10 (2018): 1–21. doi:10.3390/rs10071154
DOI: 10.3390/rs10071154

See at: Remote Sensing Open Access | Remote Sensing Open Access | Remote Sensing Open Access | Remote Sensing Open Access | ISTI Repository Open Access | CNR ExploRA Open Access | Remote Sensing Open Access | Remote Sensing Open Access | Remote Sensing Open Access


2016 Conference article Restricted

A virtual experience across the buried history
Canzoneri A., Pavoni G., Callieri M., Dellepiane M., Pingi P., De Giorgi M., Scopigno R.
The Sant'Angelo cave church is an underground medieval Benedictine complex in the south of Italy, affected by serious structural and chemical degradation. In the context of a documentation campaign promoted by the local Superintendence and supported by the IPERIONCH. it project, we carried out an accurate 3D and photographic survey, and reconstructed a detailed 3D model of the site (encoding shape and colour). While the primary purpose of this large amount of collected data was to provide a metric documentation of the site, the completeness and the high detail of the survey suggested also a possible use for dissemination and virtual presentation. Thus, we exploited the 3D digital models to design and build a virtual visit of the church, oriented to scholars, museums and tourists. This paper describes the design and implementation of this educational experience, closely related to the bibliographic sources of the artistic heritage, fully enriched with hyper-textual information, intuitive and easy to use for all users regardless of their level of familiarity with the 3D medium.Source: AVR 2016 - Augmented Reality, Virtual Reality, and Computer Graphics. Third International Conference, pp. 158–171, Lecce, Italy, 15-18 June 2016
DOI: 10.1007/978-3-319-40651-0_13

See at: academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | link.springer.com Restricted | link.springer.com Restricted | link.springer.com Restricted | CNR ExploRA Restricted | rd.springer.com Restricted


2016 Conference article Restricted

Automatic selection of video frames for path regularization and 3D reconstruction
Pavoni G., Dellepiane M., Callieri M., Scopigno R.
Video sequences can be a valuable source to document the state of objects and sites. They are easy to acquire and they usually ensure a complete coverage of the object of interest. One of their possible uses is to recover the acquisition path, or the 3D shape of the scene. This can be done by applying structure-from-motion techniques to a representative set of frames extracted from the video. This paper presents an automatic method for the extraction of a predefined number of representative frames that ensures an accurate reconstruction of the sequence path, and possibly enhances the 3D reconstruction of the scene. The automatic extraction is obtained by analyzing adjacent frames in a starting subset, and adding/removing frames so that the distance between them remains constant. This ensures the reconstruction of a regularized path and an optimized coverage of all the scene. Finally, more frames are added in the portions of the sequence when more detailed objects are framed. This ensures a better description of the sequence, and a more accurate dense reconstruction. The method is automatic, fast and independent from any assumption about the acquired object or the acquisition strategy. It was tested on a variety of different video sequences, showing that a satisfying result can be obtained regardless of the length and quality of the input.Source: GCH 2016 - Eurographics Workshop on Graphics and Cultural Heritage, Genova, Italy, 5-7 October 2016
DOI: 10.2312/gch.20161376

See at: diglib.eg.org Restricted | CNR ExploRA Restricted


2015 Conference article Restricted

Alchemy in 3D: a digitization for a journey through matter
Callieri M., Pingi P., Potenziani M., Dellepiane M., Pavoni G., Lureau A., Scopigno R.
In this work, we will present the outcomes of the 3D diagnostic investigations carried out on the painting Alchemy by Jackson Pollock. Thanks to an accurate digitization and a careful processing, we were able to generate a very precise high-resolution 3D model that proved to be useful in different stages of the diagnostic and conservation campaign. The 3D model was integrated in the conservation process, along with the other diagnostic investigations; the geometric data was also used to produce images and video sequences for dissemination purposes. The most interesting aspect of the work, however, was the idea of going beyond photo-realism and the use of the scanner-measured geometry to try to interpret and understand the traces and signs on the surface of the painting, in relation with the gestures and techniques used by Pollock while painting this masterpiece. Combining the knowledge of the curators and the metric data gathered in the digitization, we were able to discover and validate several interesting aspects of the painting, in the direction of trying to better understanding the painting process which was, in the idea of the artist, an essential part of the artwork. The 3D model of the artwork played a central role also in the temporary exhibition created for the dissemination of the conservation and the diagnostic campaign to the museum visitors. This was also done following the idea of using the geometry to explain the gestures, actions and techniques of Jackson Pollock at work. The 3D model was used to create an interactive kiosk, to have the visitors navigate the model and access explanations of relevant geometrical details and to produce a 1:1 physical reproduction to give the public the possibility to physically interact with the artwork.Source: International Congress on Digital Heritage, pp. 223–231, Granada, Spain, 28/08/2015-02/10/2015
DOI: 10.1109/digitalheritage.2015.7413875

See at: academic.microsoft.com Restricted | diglib.eg.org Restricted | ieeexplore.ieee.org Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted