1,720,965 research outputs found
Adaptive SAR Image Processing Techniques to Support Flood Monitoring from Earth Observation Data
No full textThis chapter addresses the exploitation of Earth Observation (EO) data in the operational chains for flood monitoring and post-event damage assessment,
focusing specifically on the task of post-flood mapping. In this context, this work provides a general review of our research into image processing techniques with an emphasis on adaptive methods applied to synthetic aperture radar (SAR) images. These procedures involve no restrictions on SAR acquisition parameters (frequency band, polarization, spatial resolution, and observation angle). Depending on the data availability, different maps can be produced. When multi-temporal images are available, two different products can be generated: fast-ready flood maps; and detailed flood maps;. The former is a color composite image that enhances the visualization of changes that have occurred after an event. The latter is a more detailed map obtained after a segmentation process. In contrast, when only an image acquired on a single date is available, a water body map can be generated. All these maps are intended as support for institutional interventions. Since only methods of segmentation and numerical data fusion are applied, such results are not final classification products. They are symbolic and not semantic maps, generated using fast and simple procedures that can be used as input for a classification purpose or employed by the user in other application tasks. The experiments described here were performed on real SAR images related to different datasets. The images were acquired from COSMO-SkyMed (CSK) and RADARSAT satellites
An Optimal and Automatic Graph Cut Method for Biomedical Images Using Compactness Measure
No full textThis work aims to achieve an automatic and optimal graph cut phase based on a segmentation method presented in a previous paper. A graph-based segmentation algorithm, starting from a seed point belonging to the region of interest (ROI), is able to find the Minimum Path Spanning Tree (MPST) by using a new cost function and an optimal aggregation criterion. In order to extract the ROI, a graph-cut of the obtained tree is absolutely necessary.
By definition, the main drawback of the graph-based segmentation methods is the loss of spatial and contextual information. To overcome this problem, a new method based on compactness measure is here proposed The present approach is applied to the biomedical field, considering Magnetic Resonance Imaging (MRI) volumes of the hand and neurological districts
A fuzzy graph-based segmentation for marine and maritime applications in SAR images
No full textIn the context of sea monitoring, an important processing step is image segmentation. In this paper, the authors propose a new segmentation method that combines fuzzy and graphbased theories. The algorithm, starting from a single source element belonging to the region of interest, proceeds with a
propagation mechanism that aims at finding a Minimum Path Spanning Tree (MPST). The process is automatic, unsupervised, adaptive to the image
content and independent from the order of analysis. A TerraSAR-X image and Cosmo-SkyMed images are used for the experiments. The considered applications are oil spill detection, sea surface analysis, and ship detection
IDRE: AI Generated Dataset for Enhancing Empathetic Chatbot Interactions in Italian language
No full textThis paper introduces IDRE (Italian Dataset for Rephrasing with Empathy), a novel automatically generated Italian linguistic dataset. IDRE comprises typical chatbot user utterances in the healthcare domain, corresponding chatbot responses, and empathetically enhanced chatbot responses. The dataset was generated using the Llama2 language model and evaluated by human raters based on predefined metrics. The IDRE dataset offers a comprehensive and realistic collection of Italian chatbot-user interactions suitable for training and refining chatbot models in the healthcare domain. This facilitates the development of chatbots capable of natural and productive conversations with healthcare users. Notably, the dataset incorporates empathetically enhanced chatbot responses, enabling researchers to investigate the effects of empathetic language on fostering more positive and engaging human-machine interactions within healthcare settings. The methodology employed for the construction of the IDRE dataset can be extended to generate phrases in additional languages and domains, thereby expanding its applicability and utility. The IDRE dataset is publicly available for research purposes
A New Graph-Based Method for Automatic Segmentation
No full textIn this paper, a new graph-based segmentation method is proposed. Various Regions of Interest (ROIs) can be extracted from digital images/volumes without requiring any processing parameters. Only one point belonging to the region of interest must be given. The method, starting from a single source element, proceeds with a specific propagation mechanism based on the graph theory, to find a Minimum Path
Spanning Tree (MPST). As compared with other existing segmentation methods, a new cost function is here proposed. It allows the process to be adaptive to both a local and global context, to be optimal and independent from the order of analysis, requiring a single iteration step. The final decision step is based on a threshold value that is automatically selected. Performance evaluation is presented by applying the method in the biomedical field, considering the extraction of wrist bones from real Magnetic Resonance Imaging (MRI) volumes
Azimuth ambiguity spatial correlation composite (ASCC): A novel method for ghost enhancement in SAR images
No full textIn the context of sea and ocean monitoring from (single polarization) SAR images, an innovative approach in the handling of azimuth ambiguities is here described. The purpose of this paper is to provide a theoretical explanation of the method briefly presented at IGARSS 2013 [1], and suggest applications in coastal and maritime traffic monitoring. The work is developed in the context of the project funded by the Italian Space Agency1 . COSMO-SkyMed images related to Ligurian Sea (Italy) represents the data set for experimentation
Automatic MPST-cut for segmentation of carpal bones from MR volumes
No full textIn the context of rheumatic diseases, several studies suggest that Magnetic Resonance Imaging (MRI) allows the detection of the three main signs of Rheumatoid Arthritis (RA) at higher sensitivities than available through conventional radiology. The rapid, accurate segmentation of bones is an essential preliminary step for quantitative diagnosis, erosion evaluation, and multi-temporal data fusion. In the present paper, a new, semi-automatic, 3D graph-based segmentation method to extract carpal bone data is proposed. The method is unsupervised, does not employ any a priori model or knowledge, and is adaptive to the individual variability of the acquired data. After selecting one source point inside the Region of Interest (ROI), a segmentation process is initiated, which consists of two automatic stages: a cost-labeling phase and a graph-cutting phase. The algorithm finds optimal paths based on a new cost function by creating a Minimum Path Spanning Tree (MPST). To extract. the region, a cut of the obtained tree is necessary. A new criterion of the MPST-cut based on compactness shape factor was conceived and developed.The proposed approach is applied to a large database of 96 Ti-weighted MR bone volumes. Performance quality is evaluated by comparing the results with gold-standard bone volumes manually defined by rheumatologists through the computation of metrics extracted from the confusion matrix. Furthermore, comparisons with the existing literature are carried out. The results show that this method is efficient and provides satisfactory performance for bone segmentation on low-field MR volumes
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Quantification of ultrasound imaging in the staging of hepatic fibrosis
No full textThe need for a staging of hepatic fibrosis has become particularly urgent in the last few years in order to start new therapeutic treatments. The objective of this study is to identify ultrasound descriptors and achieve a staging of hepatic fibrosis with non-invasive, rapid and inexpensive methods, both as an alternative and a support to the ultrasound elastography examination
- …
