Search

Heart diseases are still among the main causes of death in the world population. The use of tools able to discriminate early this type of problem, even by non-specialized medical personnel on an outpatient basis, would put a decrease in health pressure on hospital centers and a better patient prognosis. This paper focuses on the problem of cardiac akinesis, a condition attributable to a very large number of pathologies, and a possible serious complication for SARS-Covid19 patients. In particular, we considered echocardiographic images of both akinetic and healthy patients. The dataset, containing echocardiograms of around 700 patients, has been supplied by Sacco hospital of Milan (Italy). We implemented a modified ResNet34 architecture and we tested the model under various combinations of parameters. The final best performing model was able to achieve a F1-score of 0.91 in the binary classification Akinetic vs. Normokinetic.

Stylistic study of artworks is a well-known problem in the Cultural Heritage field. Traditional artworks, such as statues and paintings, have been extensively studied by art experts, producing standard methodologies to analyze and recognize the style of an artist. In this context, the case of historical violins is peculiar. Even if the main stylistic features of a violin are known, only few experts are capable to attribute a violin to its maker with a high degree of certainty. This paper presents a study about the use of deep learning to discriminate a violin style. Firstly, we collected images of 17th–18th century violins held, or in temporary loan, at “Museo del Violino” of Cremona (Italy) to be used as reference dataset. Then, we tested the performances of three state-of-the-art CNNs (VGG16, ResNet50 and InceptionV3) on a binary classification (Stradivari vs. NotStradivari). The best performing model was able to achieve 77.27% accuracy and 0.72 F1 score. A promising result, keeping in mind the limited amount of data and the complexity of the task, even for human experts. Finally, we compared the regions of interest identified by the network with the regions of interest identified in a previous eye tracking study conducted on expert luthiers, to highlight similarity and differences between the two behaviors.

One of the most efficient and cost-effective tools for landslide risk mitigation is often the setup of an early warning system (EWS). Even if the latter encompass both technical-scientific and social-economic topics, the focus of this note is on the monitoring and forecasting components of a slope-scale landslide EWS. In this framework, a landslide monitoring system is required to provide reliable and continuously updated data for quantitatively catching the scenario evolution, thus allowing for correct forecasting analyses and prompt actions for risk mitigation. Landslide monitoring systems based on remote sensing techniques represent efficient and robust tools for risk mitigation, allowing for a low environmental and economic impact and high operator safety in difficult environments. Among these techniques, radar interferometry is one of the most widely adopted and reliable methods, whose advantages include very high accuracy, operation during all weather conditions, and high spatial and temporal coverage. Radar interferometry output data, due to their high accuracy and acquisition frequency (which is getting higher and higher for satellite applications too), perfectly fit in the prediction activity, enabling very often to make accurate and prompt time of failure or scenario evolution forecasts. In this note, a number of case studies are presented, describing the employed monitoring systems and the associated techniques adopted for risk mitigation. In particular, an integrated EWS for rockslide risk mitigation, a landslide EWS in a volcanic environment, a landslide failure prediction using satellite InSAR and a rockfall monitoring and associated time of failure prediction are presented. Each of the cases presented shows a peculiarity that can help in the definition of the characteristics and potential of a modern and reliable landslide EWS, while the recent and upcoming technological and scientific advancements are the premise of even more accurate and meaningful landslide EWSs.

Monitoring the state of conservation of a historical violin is a difficult task. Multiple restorations during centuries have created a very complex and stratified surface, hard to correctly interpret. Moreover, the reflectance of the varnishes and the rounded morphology of the violins can easily produce noise, that can be confused for a real alteration. To properly compare multi-temporal images of the same instrument a robust segmentation is needed. To reach this goal we adopted a genetic algorithm to evolve in this direction our previous segmentation method based on HSV histogram quantization. As test set we used images of two important violins held in “Museo del Violino” in Cremona (Italy), periodically acquired during a six-month period, and images of a sample violin altered in laboratory to reproduce a long-term evolution.

A new graphical Braille display is presented. Its use, social value and advantages are discussed. In particular is developed an approach allowing objects of cultural and historical heritage to be presented in an intuitive and accessible way to low-sighted or blind people.

A new representation of content for haptic exploration of two-dimensional pictorial art masterpieces is presented. To realize a “tactile image”, pictures must be simplified and converted to a bas-relief with distinct and logically homogeneous areas, so that each segment can convey the original content in an intelligible way. Pictures must be digitized, modified, adapted and reconstructed as 3D models that are finally processed by a 3D printer to get an object analyzable through fingertips. We assess the quality and efficiency of the proposed solution through a cooperation with the Italian Union of Blind and Visually Impaired People. The resulting representations were implemented in two different events, gathering visitors’ comments. Remarks obtained during the exhibition in Pavia in 2015 led to a version of a tactile image that is now shown in Milan, at the Pinacoteca di Brera, beside the original masterpiece. The collected comments confirm that the approach is appreciated.

Open image in new window On October 24th 2015, following a period of heavy rainfall, a landslide triggered in the Calatabiano Municipality (Sicily Island, Southern Italy) causing the rupture of a water pipeline transect of the aqueduct supplying water to the city of Messina. This event, caused critical water shortages for several days to a large part of the city inhabitants. In order to restore the city water supplies, a provisional by-pass, consisting of three 350 m long pipes passing through the landslide area, was carried out. On November 11th 2015, a landslide monitoring system was installed, based on the combined use of advanced remote sensing techniques such as Ground-Based Interferometric Synthetic Aperture Radar (GB-InSAR), Terrestrial Laser Scanning (TLS) and Infrared Thermography (IRT). The installed monitoring system allowed to: (i) analyze the landslide geomorphological and kinematic features in order to assess the landslide residual risk; (ii) support the early warning procedures needed to ensure the safety of the personnel involved in the by-pass realization and the landslide stabilization works. In this work, the preliminary results of the monitoring activities and a 3-D mapping of the landslide area are presented.

New generation multimedia may have a great impact on exhibition visit experience. This contribution focuses on the innovative use of interactive digital technologies in cultural heritage practices. “Live” displays steered by visitors support the creation of various content formats, smartly adapt the content delivered to the visitor, stimulate self-motivated learning, and lead to a memorable and effective experience. Multimodal interaction modalities have been developed for the exhibition “1525–2015. Pavia, the Battle, the Future. Nothing was the same again”, a satellite event of the Universal Exhibition in Milan (Expo 2015). The Computer Vision & Multimedia Lab of the University of Pavia, in cooperation with the Bulgarian Academy of Sciences, in the framework of the European project “Advanced Computing for Innovation”, has contributed to set up the exhibition, enriching an educational and experiential room with products and targeted applications. Visitors can observe and analyze seven ancient tapestries, illustrating different phases of the battle, through 3D reconstructions, virtual simulations, eye interaction and gesture navigation, along with transpositions of the tapestries into tactile images that enable the exploration by partially sighted and blind people. In the near future, we may assess the impact of this interactive experience. Due to the novelty of the approach, new insights can be potentially derived about the effectiveness and manageability of each specific system component. Under this scope, not only the exhibition success is important, but also the augmented learning experience in cultural heritage contexts.

In the last years, economic multichannel sensors became very widespread. The most known of these devices is certainly the Microsoft Kinect, able to provide at the same time a color image and a depth map of the scene. However Kinect focuses specifically on human-computer interaction, so the SDK supplied with the sensors allows to achieve an efficient detection of foreground people but not of generic objects. This paper presents an alternative and more general solution for the foreground segmentation and a comparison with the standard background subtraction algorithm of Kinect. The proposed algorithm is a porting of a previous one that works on a Time-of-Flight camera, based on a combination of a Otsu thresholding and a region growing. The new implementation exploits the particular characteristic of Kinect sensor to achieve a fast and precise result.

UV fluorescence photography is widely use in the study of artworks, in particular for the analysis of historical musical instruments. This technique allows seeing important details which cannot be observed with visible light, such as retouching, different paints coats or worn areas. The complexity of the interpretation of the surface of a violin is proportional to its state of preservation: more alterations correspond to a more wide range of colors. We designed an interactive tool able to help the scientist to understand the composition of the surface and in particular the distribution of the colors on the entire instrument, avoiding perception illusion. The result is achieved using a quantized histogram in HSV color space. The tests were performed on UV imagery of the Stradivari violins collection stored by “Museo del Violino” in Cremona.