1,896 research outputs found
First Results of Ship Wake Detection by Deep Learning Techniques in Multispectral Spaceborne Images
No full textMaritime trade and trasport occupy a pivotal position in the current era of globalization. Thus, monitoring ships at sea represents the starting point of this paper in which a novel approach to detect ships by wake has been proposed, based on Instance Segmentation deep learning architecture Mask R-CNN. In order to train and test this network, 766 wake chips cropped from 50 multispectral images acquired from Sentinel-2 satellites were observed. In particular, B2 (blue), B3 (green), B4 (red) and B8 (Infrared) bands were considered since they are all characterized by same resolution. The results proved that Mask R-CNN is capable to detect the vast majority of ship wakes with high confidence percentage in different configurations, i.e. slanted wakes, multiple wake scenarios or wakes in dark areas not related to their features
Inverse analysis procedure to determine flow stress and friction data for finite element modeling of machining
No full textThis paper describes an inverse procedure to determine the constitutive constants and the friction conditions in the machining processes using Finite Elements (FE) simulations. In general, the FE modeling of machining processes is an effective tool to analyze the materials machinability under different cutting conditions. However, the use of reliable rheological and friction models represents the basis of a correct numerical investigation. The presented inverse procedure was based on the numerical results obtained using a commercial FE code and was developed considering a specific optimization problem, in which the objective functions that have to be minimized is the experimental/numerical error. This problem was performed by a routine developed in a commercial optimization software. In order to verify the goodness and the robustness of the methodology, it was applied on a Super Duplex Stainless Steel (SDSS) and on an Austenitic Stainless Steel (AUSS) orthogonal machining processes. This work, then, was focused on the identification of the Johnson-Cook (JC) coefficients (A,B,C, n and m) and on the calibration of a Coulomb friction model, in the specific cases of the SAF2507 SDSS and of an AISI 316 Based AUSS Alloy (AISI 316 ASBA). The identification phases were performed considering forces and temperatures experimental data, collected in two specific experimental tasks in which different orthogonal cutting tests were carried out under different cutting parameters conditions
AUTOMATIC SHIP WAKE DETECTION FROM SENTINEL-2 IMAGES BY DEEP LEARNING
No full textA critical role in monitoring and understanding human activities at sea is held by the detection of moving vessels, a challenging task that can be accomplished, in specific conditions, by inspecting their long wakes left in the sea. To solve the ship wake detection problem, the traditional methodology based its research on domain transformation from lines to points, such as Radon or the Hough transform. Assuming wakes as linear features, such as class of algorithms is not capable of capturing irregular or curved wakes and shows poor generalization. Nevertheless, the current digital era is dominated by Deep Learning (DL) techniques thanks to their capability of abstract feature extraction. Representation learning has proven to tackle the increasing speed and breadth of”Big Data”, outperforming humans on a variety of challenging tasks. Convolutional Neural Networks (CNNs) can glean relevant patterns from remotely sensed images and represents the core of the paper which intends to realize an automatic wake recognition system from spaceborne optical images. Several state-of-the-art DL-based approaches are benchmarked with model baselines including both object detection and instance segmentation architectures, including one- and multi-stage methods. The usage of ResNet backbones as the main feature extractor is motivated by their effectiveness on many computer vision datasets. Feature Pyramid Network (FPN), used as a neck of the backbone, grants for multi-size detection. To perform supervised learning, a novel dataset is built and proposed in this paper. The Multi-Spectral Ship Wake Dataset (MSSWD) is represented by multi-spectral chips extracted from the European Sentinel-2 mission, selected for its publicly available data policy. Chips are extracted from Level-2A ortho-images. MSSWD is composed of 1059 ship wakes gathered from 50 multi-spectral granules. Data variety was curated by selecting wakes in multiple dimensions and orientations while data veracity is assured by the corresponding AIS (Automatic Identification System) information. The multi-band side of the MSSWD has been analyzed by covering 4 bands, i.e. B2 (blue), B3 (green), B4 (red), and B8 (infrared) bands, all characterized by the same spatial resolution. The analysis of the results proves that this class of algorithms is capable of detecting the vast majority of the wakes with high confidence scores, very low probability of false alarms, and fast processing speed. In particular, Cascade Mask R-CNN, Mask R-CNN, and RetinaNet have shown the best results in terms of Average Precision (AP), being able to correctly detect the of the test dataset wakes, reporting only 3 false alarms consisting of aircraft wakes. Moreover, all bands produced the same results in terms of detection performance. However, the multi-band feature of the MSSWD could still be of use to detect the false alarms, on the basis of the temporal offset in the acquisition time of each band
Spatial Abilities at High Altitude Exploring the Role of Cultural Strategies and Hypoxia
No full textBondi, Danilo, Vittore Verratti, Raffaella Nori, Laura Piccardi, Giulia Prete, Tiziana Pietrangelo, and Luca Tommasi. Spatial abilities at high altitude Exploring the role of cultural strategies and hypoxia. High Alt Med Biol. 22 157-165, 2021. Background Over the past couple of decades, the number of people of different cultures traveling to places of high altitude (HA) increased. At HA, a decline in cognitive abilities has been described, including spatial skills. However, it is still unknown whether people accustomed to hypobaric hypoxia are less susceptible to cognitive decline. Method We aimed to determine if three ethnic groups would show any difference in the performance of spatial abilities. Italian trekkers (46.20 ± 15.83 years), Nepalese porters (30.33 ± 8.55 years), and lowlander and highlander Sherpas (30.33 ± 8.55 and 37.00 ± 16.51 years) were tested with a building photograph recognition, a map orienting, and a mental rotation task during a Himalayan expedition. Accuracy and response times were collected at low altitude (LA) and HA. Results Nepalese performed the worst (photograph task p = 0.015, η2p = 0.36; map task p = 0.016, η2p = 0.36), but the difference was mitigated after correcting for length of schooling. Participants took more time to respond at LA than in HA condition (photograph task 24.0 ± 15.3 seconds vs. 12.7 ± 6.3 seconds, p = 0.008, η2p = 0.57; map task 12.5 ± 1.8 seconds vs. 7.8 ± 0.6 seconds, p = 0.038, η2p = 0.40). In the map task, participants performed with greater accuracy at LA (5.1 ± 0.4 vs. 4.4 ± 0.4 number of correct responses, p = 0.006, η2p = 0.59). Conclusions Altitude hypoxia elicited impairments in cognitive spatial tasks. This may be due to the inability to acquire new unfamiliar patterns, and to the difficulty in managing a high cognitive workload. The ethnic differences were ascribed to schooling, even we consider the different system of reference usually exploited in each culture (egocentric dependent, or allocentric independent from the personal viewpoint), and that Westerners are more likely to focus on specific details of the scene. Further studies should investigate the diverse strategies to complete spatial tasks
The Italian populations of Viola pumila Chaix. Their ecological and genetic characterization for an integrated conservation strategy.
No full textThe Italian populations of Viola pumila Chaix. Their ecological and genetic characterization for an integrated conservation strategy
Buldrini F.1, Dallai D.1, Conte L.2, Del Prete C.1, Ferrari C.2
1 Dep. of Biology, University of Modena and Reggio Emilia
2 Dep. of Experimental Evolutionary Biology, University of Bologna
Viola pumila Chaix is an Eurasian species linked to large alluvial grasslands. Ecology and conservation problems of its Central European populations have been studied by Hölzel (2003), Eckstein & al. (2004, 2006, 2009) and Danihelka & al. (2009). In Italy, it grows only in 4 Po valley sites, in grasslands and fresh meadows regularly mown, along ditches and cultivated fields. These populations are peripheral with respect to the European distribution of the species. They contain a very low number of individuals in each site (max. 46) and are very distant and strictly isolated from the nearest populations of Central Europe. According to IUCN (2001), this species is critically endangered in Italy (Buldrini & Dallai, in press).
Since the best conservation strategy for endangered species implies a detailed knowledge of habitat requirements as well as of its genetic diversity, an ecological characterization of the 4 sites is in progress, by Ellenberg’s Indexes modified by Pignatti & al. (2005). Moreover, the genetic diversity of the Italian populations of the species will be evaluated through ISSR markers: semi-arbitrary anchored primers designed from tandem repeat motifs of microsatellites will be used to estimate the level and the distribution of genetic diversity and to provide suggestions for effective conservation programs.
A comparison between Italian populations and Central European ones will performed in the next stage of the research.
Eckstein R.L., Danihelka J., Hölzel N., Otte A. (2004), Acta Oecol. 25: 83–91
Eckstein R.L., Hölzel N., Danihelka J. (2006), Perspect. Pl. Ecol. Evol. Syst. 8: 45-66
Eckstein R.L., Danihelka J., Otte A. (2009), Biologia 64/1: 69-80
Danihelka J., Niklfeld H., Šípošová H. (2009), Preslia 81: 151-171
Hölzel N. (2003), Folia Geobot. 38: 281-298
Pignatti S., Menegoni P., Pietrosanti S. (2005), Braun-Blanquetia 39: 1-9
Impression cytology with scanning electron microscopy: a new method in the study of conjunctival microvilli.
No full textLa scuola in Italia fra tre governi e due occupazioni (1943-1945)
No full textIl contributo analizza la complessità del biennio 1943-1945 dal punto di vista della storia della scuola e dell’educazione, ma accogliendo come prospettiva storiografica generale quella tracciata da Claudio Pavone in un noto articolo del 1985: Tre governi e due occupazioni . Tutte le entità politiche e istituzionali che ebbero ruoli di governo e furono fonte di norme – secondo dinamiche di continuità o di rottura con il passato fascista o con quello monarchico-liberale – si interessarono, infatti, anche alla scuola e all’educazione: il luogotenente e i governi del Regno; il governo della Rsi; le Giunte provvisorie e i CLN; le autorità militari alleate nelle province liberate; i comandi tedeschi nell’Italia invasa e nelle nove province direttamente governate dal Reich. Sullo sfondo mantiene anche l’importante lezione metodologica di Fulvio De Giorgi che, in continuità con quella pavoniana, la riprende e la prosegue, innestandola nella prospettiva della storia dell’educazione: le radici più profonde della Ricostruzione etico-civile del paese sono pertanto individuate nei mesi della Resistenza al fascismo e all’occupazione nazista, quando cioè si avviò una prima esperienza educativa democratica e vi fu la presa di coscienza della diseducazione politica di massa ereditata dal fascismo
MULTIMISSION/MULTIFREQUENCY SAR FOR IMPROVING THE MONITORING OF COASTAL AREAS
No full textThe paper shows the strong potentialities of multimission/multifrequency SAR data for improving the maritime situational awareness in coastal areas. Two main issues are analyzed: the detection of ships that are visible in SAR images and the identification of non-collaborative vessels, which are not visible in SAR images. In the first case, the multimission/multifrequency data guarantees: (a) smaller revisit time with respect to a single mission, enabling cross-check of the detection in several images and, thus, improving the detection rate, and (b) the availability of images covering large areas at low resolution as well as smaller swath observed with higher resolution. This is crucial in particular for the coastal areas where local phenomena can strongly affect the detection performance. In the second case, the multimission/multifrequency data enables innovative approaches exploiting the different appearance of ship and its wake at different frequencies
- …
