Search

BackgroundThe British Association of Perinatal Medicine (BAPM) published a revised framework for perinatal management of extremely preterm infants (EPIs) in 2019. We aimed to assess UK neonatal professionals’ interpretation of elements of this framework, as well as the consistency of their estimates of outcome for EPIs.MethodsAn online survey gave participants five cases involving anticipated extremely preterm birth with different favourable and unfavourable risk factors. Respondents were asked to assign a risk category and management option using the BAPM framework and to estimate the chance of survival if the baby received active resuscitation and the chance of severe disability if they survived.ResultsRespondents were consistent in interpretation of risk categories. The majority would follow parental wishes about management. Management decisions did not always correspond with risk assessment, with less inclination to recommend palliative (comfort) care. There were wide estimates of survival or severe disability (5%–90%) with consultants providing lower estimates of severe disability than other groups.ConclusionUK neonatal professionals deferred to parental wishes in the cases presented, indicating an emphasis on shared decision making. However, they did not necessarily use the risk stratification approach for management decisions. Variation in estimates of outcome raises questions about the accuracy of informed decision making and suggests support is needed for UK clinicians to incorporate risk factors into individualised counselling. There may be value in validating existing online risk calculators for UK infants or in developing a UK specific risk model.

To describe a new inner-branched device used to treat two cases of chronic post-dissection aortic thoraco-abdominal aneurysms (PD-TAAAs) after ascending aortic surgery. A 67-year-old male who had undergone an ascending aorta and arch surgical replacement and a 70-year-old male with a previous Bentall procedure for acute type A aortic dissection were admitted at our department with a PD-TAAA diagnosis. Both patients were defined unfit for open surgery by a multidisciplinary team and a totally percutaneous endovascular repair was planned. A prophylactic cerebro-spinal fluid drainage was applied and at least one hypogastric artery was targeted for salvage in order to reduce the risk of spinal cord ischemia. A new inner branch device by Jotec® (GmbH/ Criolife; Hechingen, Germany/Kennesaw, Georgia) was implanted. A TEVAR and a standard EVAR completed the procedures and a double barrel technique was performed in order to achieve the preservation of the selected hypogastric artery. In both patients the complete technical success was achieved. The postoperative period was uneventful and the patients were discharged on the 6th and 7th postoperative day, respectively. The triple-phase angio-CT performed at 6 months showed the complete false lumen exclusion and the patency of the endografts and of the target visceral vessels. The total endovascular treatment of PD-TAAAs is a fascinating technique with encouraging results in experienced centers. Inner branched devices may expand the field of application of this new technology. More data are required to evaluate mid- and long-term results.

Among the most straining trends that farmers have to face there are: on one side, to guarantee welfare and adequate life conditions for animals and to reduce the environmental footprint, on the other side, to develop new strategies to improve farm management reducing costs. The current conditions and the expected developments of the dairy sector highlight a strong need for more efficient and sustainable farming systems. Studying heat stress, herd management and housing and animals’ productive and reproductive performances is fundamental for the economic and environmental sustainability of the dairy chain. New and effective tools to cope with these challenges have been provided by Precision Livestock Farming (PLF), which is nowadays increasingly applied and makes possible to control quali-quantitative parameters related to production, health, behaviour, and real-time locomotion per animal. The research key challenge is to turn these data into knowledge to provide real-time support in farming optimisation. This research focuses specifically on different systems to collect, process and derive useful information from data on animal welfare and productivity. A multi-disciplinary approach has been adopted to generate a decision support system for farmers.

Background and purpose Patients with a history of brain radiotherapy can experience acute stroke-like syndromes related to the delayed effects of brain radiation, including stroke-like migraine attacks after radiation therapy syndrome, peri-ictal pseudoprogression and acute late-onset encephalopathy after radiation therapy syndrome. The aim of this study was to collect evidence on the long-term outcome and treatment of these conditions, whose knowledge is undermined by their rarity and fragmented description. Methods Cases were collected, both prospectively and retrospectively, amongst six neuro-oncology departments. Inclusion criteria were as follows: (i) history of brain radiotherapy (completed at least 6 months before the acute episode); (ii) new onset of acute/subacute neurological symptoms; (iii) exclusion of all etiologies unrelated to brain irradiation. A review of current literature on stroke-like syndromes was performed to corroborate our findings. Results Thirty-two patients with acute neurological conditions attributed to the delayed effects of radiation were identified, including 26 patients with stroke-like syndromes. Patients with stroke-like syndromes commonly presented with a mosaic of symptoms, including focal deficits (77%), encephalopathy (50%), seizures (35%) and headache (35%). Seventy-three percent of them had acute consistent magnetic resonance imaging alterations. Treatment included high-dose steroids in 65% of cases. Twenty-two patients recovered completely (85%). Sixteen patients (62%) experienced relapses (median follow-up 3.5 years). A literature review identified 87 additional stroke-like cases with similar characteristics. Conclusions Stroke-like events related to brain irradiation may be associated with permanent sequelae. Steroids are often administered on empirical grounds, as they are thought to accelerate recovery. Relapses are common, highlighting the need to elaborate adequate prevention strategies.

Primary triple negative breast cancers (TNBC) are prone to dissemination but sub-clonal relationships between tumors and resulting metastases are poorly understood. Here we use cellular barcoding of two treatment-naïve TNBC patient-derived xenografts (PDXs) to track the spatio-temporal fate of thousands of barcoded clones in primary tumors, and their metastases. Tumor resection had a major impact on reducing clonal diversity in secondary sites, indicating that most disseminated tumor cells lacked the capacity to 'seed', hence originated from 'shedders' that did not persist. The few clones that continued to grow after resection i.e. 'seeders', did not correlate in frequency with their parental clones in primary tumors. Cisplatin treatment of one BRCA1-mutated PDX model to non-palpable levels had a surprisingly minor impact on clonal diversity in the relapsed tumor yet purged 50% of distal clones. Therefore, clonal features of shedding, seeding and drug resistance are important factors to consider for the design of therapeutic strategies.

Long--term video tracking is of great importance for many applications in real-world scenarios. A key component for achieving long--term tracking is the tracker's capability of updating its internal representation of targets (the appearance model) to changing conditions. Given the rapid but fragmented development of this research area, we propose a unified conceptual framework for appearance model adaptation that enables a principled comparison of different approaches. Moreover, we introduce a novel evaluation methodology that enables simultaneous analysis of tracking accuracy and tracking success, without the need of setting application-dependent thresholds. Based on the proposed framework and this novel evaluation methodology, we conduct an extensive experimental comparison of trackers that perform appearance model adaptation. Theoretical and experimental analyses allow us to identify the most effective approaches as well as to highlight design choices that favor resilience to errors during the update process. We conclude the paper with a list of key open research challenges that have been singled out by means of our experimental comparison.

Purpose of review This review summarizes recent studies on the predictive value of molecular markers in adult gliomas, including 1p/19q codeletion, MGMT methylation, IDH mutation and markers identified using omics and next-generation sequencing studies. Recent findings The long-term results of the Radiation Therapy Oncology Group and European Organization for Research and Treatment of Cancer trials in anaplastic oligodendroglial glioma have shown that the 1p/19q codeletion predicts an overall survival benefit from early PCV (procarbazine CCNU vincristine) chemotherapy. This benefit can also be predicted using gene expression-based molecular subtypes of gliomas while the predictive value of the IDH mutation in this context requires further study. In elderly patients with glioblastoma, the analysis of MGMT methylation status in two phase III trials suggests that this alteration may guide treatment decisions; however, this finding still needs confirmation in prospective studies. Omics and next-generation sequencing studies have identified additional potential predictive markers. In particular, IDH mutations, BRAF V600E mutations and FGFR gene fusions might predict efficacy of therapies targeted against these alterations. Summary Currently, the 1p/19q codeletion is the only well established predictive marker with clinical utility. However, it is likely that other molecular markers such as MGMT methylation, IDH mutation and those identified using omics and next-generation sequencing studies will further guide treatment decisions in adult gliomas.

This paper proposes an effective algorithm for recognizing objects and accurately estimating their 6DOF pose in scenes acquired by a RGB-D sensor. The proposed method is based on a combination of different recognition pipelines, each exploiting the data in a diverse manner and generating object hypotheses that are ultimately fused together in an Hypothesis Verification stage that globally enforces geometrical consistency between model hypotheses and the scene. Such a scheme boosts the overall recognition performance as it enhances the strength of the different recognition pipelines while diminishing the impact of their specific weaknesses. The proposed method outperforms the state-of-the-art on two challenging benchmark datasets for object recognition comprising 35 object models and, respectively, 176 and 353 scenes.

Pattern matching is widely used in signal processing, computer vision, and image and video processing. Full search equivalent algorithms accelerate the pattern matching process and, in the meantime, yield exactly the same result as the full search. This paper proposes an analysis and comparison of state-of-the-art algorithms for full search equivalent pattern matching. Our intention is that the data sets and tests used in our evaluation will be a benchmark for testing future pattern matching algorithms, and that the analysis concerning state-of-the-art algorithms could inspire new fast algorithms. We also propose extensions of the evaluated algorithms and show that they outperform the original formulations.

A multi-technology platform is considered to interact and cooperate with complex heterogeneous domestic or industrial environments. This way an automatic set up of the digital representation of such spaces is possible, that we shall call smart spaces, in which identifying, localizing, monitoring and updating different real objects is carried out in real time. Natural interaction with tagged and untagged items may then be carried by different users' categories having various needs. This may be accomplished by augmenting the RFID technology with a) direction finding capabilities of a monopulse radar, to remotely discover and select items; b) gesture recognition, to enable the user to interact with the Smart Space and the devices in a natural way; c) computer vision based item recognition, to allow objects themselves to act as natural tags. Interoperability of all these technologies is made possible by a suitable software infrastructure.

In this paper, we present a statistical change detection approach aimed at being robust with respect to the main disturbance factors acting in real-world applications such as illumination changes, camera gain and exposure variations, noise. We rely on modeling the effects of disturbance factors on images as locally order-preserving transformations of pixel intensities plus additive noise. This allows us to identify within the space of all of the possible image change patterns the subspace corresponding to disturbance factors effects. Hence, scene changes can be detected by a-contrario testing the hypothesis that the measured pattern is due to disturbance factors, that is, by computing a distance between the pattern and the subspace. By assuming additive Gaussian noise, the distance can be computed within a maximum likelihood nonparametric isotonic regression framework. In particular, the projection of the pattern onto the subspace is computed by an O(N) iterative procedure known as Pool Adjacent Violators algorithm.

Alaska’s Skyboys: Cowboy Pilots and the Myth of the Last Frontier . By Katherine Johnson Ringsmuth. (Seattle: University of Washington Press, 2015. xiii + 267 pp. Illustrations, maps, notes, bibliography, index. $34.95.) As the title implies, Katherine Johnson Ringsmuth’s Alaska’s Skyboys grapples with entrenched stereotypes that equate bush pilots with cowboys and other heroes of frontier mythology. Focusing on the history of aviation in eastern Alaska—primarily the Copper River Basin/Wrangell Mountains—she challenges the notion that the history of bush pilots follows the well-worn grooves of Frederick Jackson Turner’s frontier. Instead, she argues that bush pilots were at the leading edge of modern aviation and essential to the incorporation of Alaska into global pathways. Ringsmuth provides a detailed history of flying in eastern Alaska. … dldistefano{at}alaska.edu

Novel chromosomal rearrangements involving tyrosine-kinase receptors FGFR3 and EGFR and resulting in actionable fusion proteins with strong oncogenic activity have been recently described in glioblastoma (GBM). 602 gliomas [380 grade IV (GBM), 116 grade III, 106 grade II] from the Pitie-Salpetriere brain tumor bank “Onconeurotheque” were analyzed for the presence of FGFR3-TACC3 and EGFR-SEPT14 by RT-PCR and sequencing . We identified 30 patients with fusion transcripts: 11 (8 GBM, one grade III, two grade II) with FGFR3-TACC3 and 19 (18 GBM and one grade III) with EGFR-SEPT14 fusion, including a GBM patient recurring after standard treatment. None of the 144 IDH1 mutated and 12 IDH2 mutated gliomas (including 28 GBM) had FGFR3-TACC3 or EGFR-SEPT14 fusions (P < 0.0002). EGFR-SEPT14 was associated with EGFR amplification 13/16 cases (81%) (12/14 in GBM EGFR-SEPT14+ vs 79/207 in GBM EGFR-SEPT14-, P = 0.001) and with EGFR vIII variant in 8/15 (53%), whereas none of the FGFR3-TACC3 fusions had EGFR abnormalities (0/8 in GBM FGFR3-TACC3+ vs 79/207 in GBM FGFR3-TACC3-, P = 0.027). Of particular interest, FGFR3-TACC3 positive tumors showed a very strong, diffuse and homogeneous FGFR3 expression by immunostaining, in contrast to fusion negative tumors, suggesting that FGFR3-TACC3 protein is expressed in nearly all tumor cells. In GBM patients, median overall survival was 32.80 months for FGFR3-TACC3+ patients, 25.50 months for EGFR-SEPT14+ patients compared to 17.20 for the other GBM patients (P = 0.60; NS). In conclusion we found that these gene fusions are not restricted to GBM but involve also grade II and III IDH wild-type tumors. Due to their oncogenic activity these genes fusions define a subset of patients that could benefit from specific molecular targeting at recurrence. We are now planning anti-FGFR and anti-EGFR treatment in this preselected population.

Editors' Note: In reference to “White matter hyperintensities on MRI in high-altitude U-2 pilots,” Hellmann-Regen et al. identify potentially confounding factors, in addition to hypobaria, that are seen in military pilots, including high Gz stress and radiation exposure, and suggest a “regular pilot” control group. Author McGuire responds by sharing unpublished findings on a group of altitude-chamber technicians. —Megan Alcauskas, MD, and Robert C. Griggs, MD Di Stefano et al.1 reported 5 patients who developed steroid-responsive encephalopathy 9 months to 17 years after whole-brain radiotherapy for brain tumors. MRI, CSF, EEG, and other laboratory tests excluded almost all …

In the last decades several cost aggregation methods aimed at improving the robustness of stereo correspondence within local and global algorithms have been proposed. Given the recent developments and the lack of an appropriate comparison, in this paper we survey, classify and compare experimentally on a standard data set the main cost aggregation approaches proposed in literature. The experimental evaluation addresses both accuracy and computational requirements, so as to outline the best performing methods under these two criteria.

We present a method aimed at monitoring access to interlocks and secured entrance areas, which deploys two views in order to robustly perform intrusion detection and singularization. The main contributions are represented by an original approach to perform background subtraction, which is particularly robust against sudden illumination changes, shadows and photometric distortions, and by the use of a feature extraction and classification approach which allows to reliably determine an estimation of the number of people currently occupying the monitored area. Our system is designed to operate in very small interlocks and can work in a substantially unstructured environment.

This paper presents a method that reduces the computational cost of template matching based on the zero-mean normalized cross-correlation (ZNCC) without compromising the accuracy of the results. A very effective condition is determined at a small and fixed cost that allow to rapidly detect a large number of mismatching candidates with no need to compute the ZNCC score. Then, thanks to the use of an additional set of conditions, the computation of the whole ZNCC function is typically required only for a very small number of candidates. Experimental results demonstrate the effectiveness of our approach.

This “Work In Progress” paper, reports on a novel approach to pedestrian tracking in confined areas which is based on a combined use of a stereo vision tracking system and a set of sensors available on a mobile platform. This platform is a hands-free, sensory augmented, wearable computer, designed to support visits to museums and to archaeological sites. The system is going to be demonstrated within the framework of a Cultural Heritage application at the “Musei Universitari di Palazzo Poggi” in Bologna”.

Nowadays, many visual surveillance systems exploit pan/tilt/zoom (PTZ) cameras to increase the field of view of a surveyed area. The background subtraction technique is widespread to detect moving objects with a high accuracy using one stationary camera. Extending such algorithms to work with moving cameras requires to have a background mosaic at one's disposal. Many solutions using mosaic background subtraction have been proposed, which offer real time capabilities or high quality of the detected objects. However, most of them rely on prior assumptions which limit the camera motion or the algorithm to work with a depth field of view only. In this work we propose some innovative solutions to achieve a real time mosaic background apt to work with existing background subtraction algorithms to yield excellent foreground object masks. Extensive experiments accomplished on challenging indoor and outdoor scenes permit to assess the quality of the mosaic as well as of the detected moving masks.

We present a novel approach to the change detection problem based on a coarse-to-fine strategy. The basic idea consists in assigning to an efficient preliminary coarse-level detection the task to filter out the well known possible false changes (e.g., those due to camera noise and small displacements, or to scene illumination changes). This provides the subsequent fine-level detection with reliable supermasks of the true changed areas in the scene. In this way, the fine-level detection can "focus the attention" on limited parts of the frames, thus yielding remarkable advantages in terms of computational efficiency. Here, just a coarse-level detection algorithm based on background subtraction and on the concept of structure is presented, to stress that any pixel-level algorithm can be used afterwards and benefit in terms of robustness as well as of computational efficiency.

In this paper we present a change detection algorithm for grey level sequences based on the background subtraction technique, which achieves a good trade-off between time performance and detection quality. The basic idea consists in separating the background process into a deterministic background process and a stochastic camera noise process. The assumption that statistics of the camera noise for a pixel only depends on its current grey level allows to infer a nonparametric statistical camera noise model once and for all arising from a short bootstrap sequence. Hence, 256 couples of lower and upper deterministic thresholds are extracted, to be used in the background subtraction step. While the deterministic nature of the background model as well as of the thresholds lead to an efficient algorithm, utilising 256 couples of different thresholds results in a very sensitive detection. Experimental results allow to assess both the efficiency and the effectiveness of the method we devised.

Surveillance is one of the most promising applications for wireless sensor networks, stimulated by a confluence of simultaneous advances in key disciplines: computer vision, image sensors, embedded computing, energy harvesting, and sensor networks. However, computer vision typically requires notable amounts of computing performance, a considerable memory footprint and high power consumption. Thus, wireless smart cameras pose a challenge to current hardware capabilities in terms of low-power consumption and high imaging performance. For this reason, wireless surveillance systems still require considerable amount of research in different areas such as mote architectures, video processing algorithms, power management, energy harvesting and distributed engine. In this paper, we introduce a multimodal wireless smart camera equipped with a pyroelectric infrared sensor and solar energy harvester. The aim of this work is to achieve the following goals: 1) combining local processing, low power hardware design, power management and energy harvesting to develop a low-power, low-cost, power-aware, and self-sustainable wireless video sensor node for video processing on board; 2) develop an energy efficient smart camera with high accuracy abandoned/removed object detection capability. The efficiency of our approach is demonstrated by experimental results in terms of power consumption and video processing accuracy as well as in terms of self-sustainability. Finally, simulation results show how perpetual work can be achieved in an outdoor scenario within a typical video surveillance application dealing with abandoned/removed object detection.

The development of smart electricity grids represents one of the most important topics in the European energy strategy. Enel Distribuzione designed a high performance, reliable and secure smart grid that will be carried out in the south of Italy and tested under real operating conditions within the Isernia Project, which aims at implementing innovative solutions to optimally regulate the bi-directional energy flow on the Medium Voltage distribution networks while integrating Distributed Energy Resources. In this context, consumers will be involved in “Enel Info+”, a large scale trial of the “Enel smart info” device, that sets out to increase understanding and control of their own usage of energy as a first step towards “Active Demand”: providing electricity consumers with information on their consumption and the ability to actively manage it in line with the network conditions, such that modifications in consumer demand become a viable option for addressing challenges of electricity systems like the increase of efficiency and reliability, infrastructure planning and investments deferral. Most of the times, end users are not really aware of the actual power consumption of their home appliances and how effective it would be to change the way they make use of electricity for their domestic activities towards sustainable lifestyle. Integrating energy monitoring technologies and easy to use interfaces in the consumers' houses can lead to economic benefits helping them to improve their knowledge and control over their energy use. Enel smart info has been designed to provide end users with the certified information on electricity consumptions managed by the electronic smart meter, addressing more efficient behaviors while enabling further integration of smart home appliances and the participation to demand response programs. It can be plugged in every domestic socket to start data collection from the smart meter through powerline. End devices (e.g. display or pc) can be connected using two dedicated USB plugs in order to enable consumers to view how much electricity is currently being used and to process the preceding load curves. Moreover, the use of a wireless (e.g. ZigBee) USB dongle makes communication with domestic appliances easier. A monitoring kit including Enel smart info, a dedicated display and two software applications (to monitor, collect and analyze consumption data by pc and Smartphone) will be supplied to a representative sample of families of Low Voltage end users participating to the trial “Enel Info+”, whose consumes will be observed for the whole duration of the project and compared with the previous ones. Besides, a “control group” of consumers who will not receive the kit will be selected and monitored, to verify that to the use of Enel smart info is actually responsible for any change in the load curves. In-depth qualitative interviews and quantitative surveys will be carried out among an appropriate representative sample of families participating to the trial and among the control group likewise. The collected data will be used to analyze the actual awareness, understanding and attitude towards energy and its use, while estimating the effect of the proposed monitoring technologies.. (4 pages)

Objectives: Renal dysfunction is a common complication in human immunodeficiency virus (HIV)-infected patients and can be attributed to direct viral damage, comorbidities or drug toxicity. The aim of this study was to assess cross-sectional correlates of renal damage in a contemporary European cohort of patients. Methods: We performed a case-control study from our cohort of 750 HIV-infected adults over a period of 5 months. We assessed renal damage by either proteinuria (≥+ on urine dipstick), reduced creatinine clearance (< 60 ml/min) or reduced estimated glomerular filtration rate (eGFR) of < 60 ml/ min/1.73 m 2 . The characteristics of cases and controls were compared in analysis and in multivariate logistic regression models with stepwise selection. Results: Approximately 50% of the screened 106 patients had a qualifying abnormality. Altogether, we identified 55 cases with 110 age- and gender-matched controls. Mean eGFR was 90.7 (4.8) for cases vs. 106.1 (2.3) ml/min/1.73 m 2 for controls (p = 0.001). Cases had a longer duration of HIV infection, more complex regimen, longer exposure to antiretroviral therapy and a more frequent diagnosis of acquired immune-deficiency syndrome (AIDS) and hepatitis C virus (HCV) infection. In the logistic multivariate model, renal damage remained significantly associated with longer known duration of HIV infection (OR 2.88, 95% CI: 1.28-6.46, p = 0.0 1), AIDS defining condition (OR 1.09 95% CI: 1.03 -1.16, p=0.002) female gender (OR 2.01, 95% CI: 0.96 - 4.18, p = 0.06), and HCV infection (OR 2.12, 95% CI: 0.99 - 4.52, p = 0.05). Conclusions: Duration, antiretroviral regimen and coincidental HCV impacted the frequency of renal abnormalities in our patients.

In parallel to the increasing amount of information on the molecular biology of gliomas, novel markers of clinical interest have become available. Loss of heterozygosity (LOH) studies were the first to provide such markers. LOH on 1p and 19q, in particular, appeared as associated with chemosensitivity in oligodendrogliomas and mixed gliomas; because of this, their investigation became increasingly popular in clinical trials on gliomas. Even more relevant in the clinical practice is the assessment of the methylation of regulatory regions of the methyl-guanine methyl-transferase (MGMT) gene. Seminal studies by Esteller et al. established that MGMT methylation is present in about 40% of glioblastomas (GBM); these are the patients with increased survival, and subsequent studies by Hegi et al. proposed that this is due to increased chemosensitivity, particularly to temozolomide. Thus, MGMT methylation is presently a major criterion for stratification of patients with malignant gliomas enrolled in clinical trials. Also of relevance in gliomas are three other markers: EGFR, p53, and PTEN. Amplification and/or deletion of EGFR are present in GBM originating de novo and may be therapeutic targets, p53 mutations, in contrast, are present in secondary GBM, and PTEN mutations are present in both types of GBM and may help to pinpoint a patient subgroup responding to erlotinib. In this chapter, we try to re-assess the role of all these markers, based on the most recent literature. We also focus on more recent markers and on their relationships to that fraction of glioma cells that express stem cell genes like CD133. This fraction of tumor cells, defined as cancer stem cells, may have a key role in cancer perpetuation; their assessment, therefore, can be very important for prognosis and therapy. Clearly; what we will have is a snapshot of a highly dynamic landscape. The ongoing effort to sequence the genome of several hundred GBM will undoubtedly make this area of research ripe for significant changes in the clinical handling of this devastating disease.

We present a novel approach to change detection based on a coarse-to-fine strategy. An efficient coarse-level detection is proposed that filters out most of the possible false changes, thus attaining reliable and tight coarse-grain super-masks of the truly changed areas. The subsequent fine-level detection can thus "focus the attention" just on the "interesting" parts of the frame and perform a robust selective background updating procedure by considering the complement of these masks. Besides, the analysis of a strip of pixels surrounding each coarse-grain blob allows to infer information on light changes possibly occurring in the blob's vicinity. Although any algorithm can be used as the final fine-level detection, here we show how the approach applies to a particular algorithm we devised, based on a non-parametric statistical modelling of the camera noise.

In intelligent transportation systems (ITS's) vehicle tracking is necessary to permit high-level analysis, such as vehicle counting or classification. Nowadays, the need for a precise vehicle behavior analysis is growing mainly in urban intersections. Typical urban traffic scenes contain high-cluttered areas where static and dynamic occlusions take place and objects are missed. Tracking systems relying on monocular cameras are widespread. However, often they are misled by the complicated object interactions occurring in those areas, thus yielding errors in the higher level modules. The real-time tracking system we have conceived relies on an algorithm exploiting local and global information from corner points and whole object's features that allows us to keep track of many different objects in challenging urban scenarios. We assess our results through extensive on-field testing by manually extracting the ground truth from different sequences taken by real world traffic monitoring systems.

Previous work has shown that adaptive traffic smoothing can be successfully applied to a Shared Ethernet to enable it to support Statistical real-time communication at the Field level. This paper addresses the case for fuzzy traffic smoothing to realize a tradeoff between bounded delivery times for soft real-time packets and throughput for non real-time traffic over non-microsegmented Switched Ethernet networks. The paper proposes an optimization technique, based on the use of multiobjective optimization, to tune the parameters of the fuzzy controller and discusses the implementation of the optimized fuzzy smoother in a real scenario, also giving comparative performance assessments. Copyright © 2005 IFAC

The paper proposes a novel change-detection algorithm for automated video surveillance applications. The algorithm is based on the idea of incorporating into the background model a set of simple low-level features capable of capturing effectively "structural" (i.e. robust with respect to illumination variations) information. Thanks to this approach, and unlike most conventional change-detection algorithms, the proposed algorithm is capable of handling correctly still and slow objects as well as of working properly throughout very long time spans. Moreover, the algorithm can naturally interact with the higher-level processing modules found in advanced video-based surveillance systems in order to allow for flexible and intelligent background maintenance.

This work proposes a novel technique aimed at improving the performance of exhaustive template matching based on the normalized cross correlation (NCC). An effective sufficient condition, capable of rapidly pruning those match candidates that could not provide a better cross correlation score with respect to the current best candidate, can be obtained exploiting an upper bound of the NCC function. This upper bound relies on partial evaluation of the crosscorrelation and can be computed efficiently, yielding a significant reduction of operations compared to the NCC function and allows for reducing the overall number of operations required to carry out exhaustive searches. However, the bounded partial correlation (BPC) algorithm turns out to be significantly data dependent. In this paper we propose a novel algorithm that improves the overall performance of BPC thanks to the deployment of a more selective sufficient condition which allows for rendering the algorithm significantly less data dependent. Experimental results with real images and actual CPU time are reported. © 2003 IEEE.

This paper presents a stereo algorithm that enables real time dense disparity measurements on standard personal computers. Unlike many other dense stereo algorithms, which are based on two matching phases, the proposed algorithm relies on a single matching phase and allows for rejecting unreliable matches by exploiting violations of the uniqueness constraint and analysing the behaviour of the correlation scores. The overall algorithm has been carefully optimised using very efficient calculation schemes and deploying massively the SIMD parallel processing capabilities available nowadays in state-of-the-art general purpose microprocessors. The paper describes the algorithm and the optimisation strategies, and provides experimental results obtained on stereo pairs with ground-truth as well as execution times measurements.

The paper describes an SIMD massively parallel computer conceived for robot vision, and presents an application where the system is installed on a mobile robot to support inspection and manipulation tasks. The system consists of a scalable array of up to 4 K single-bit processors controlled by a general-purpose microcomputer through a dedicated interface. The system's architecture is overviewed, addressing the available prototype as well as the functional units currently under design. The authors provide examples of image analysis goals that can be efficiently reached using spatially-organized parallel architectures such as SIMD arrays and give measurements of present performances. Using code profiles the authors also evaluate the speedup associated with the configuration being designed. >

The paper proposes a temporal filtering technique for the disparity measurements generated by area-based stereo-matching algorithms. The technique improves temporal consistency of disparity measurements by reducing the matching errors due to noise affecting the imaging system. Moreover, the technique is capable of increasing the number of correct matches by locating uncertain measurements with a criterion based on statistical assumptions that has proven to be more accurate and selective than those relying on texture operators only which are typically deployed with standard area-based stereo algorithms. © 2001 IEEE.

The VIDET project is aimed at investigating the possibility of developing a wearable robotic system for helping the mobility of visually impaired persons. The basic idea consists in the conversion of real-time depth data gathered through stereo-vision into a virtual, 'bas-relief' model perceivable by means of a haptic interface. In this paper we describe the real-time stereo system, review the basic principles of the two main haptic devices developed so far, and present new experimental results concerning extraction of depth data by the stereo system and haptic perception of the virtual model recovered from stereo-data.

Background and Study Aims: Inadequate disinfection of endoscopes and associated instrumentation can result in transmission of bacterial infections to patients. The aim of this study was to investigate the disinfection procedures carried out in the Italian centers of digestive endoscopy. Materials and Methods: An anonymous postal questionnaire on the methods of cleaning and disinfecting endoscopy equipment in Italy was sent to 781 digestive endoscopy centers; 386 units (49.4 %) replied. Results: Automatic washers were available in 47.6% of units. Nearly all the respondets (99.2 %) cleaned the instruments before disinfection, using detergent, germicidal or enzymatic cleaner, but only 69.7% carried out brushing. Most centers (89.2 %) used a glutaraldehyde-based disinfectant (51% used 2% glutaraldehyde; 26.9% used 0.4% glutaraldehyde with 1.41% phenol and 0.26% sodium phenate; 5.9% used either; 5.4% did not specify glutaraldehyde formulation). The contact time of the disinfectant was

Recent research activity on stereo matching has proved the efficacy of local approaches based on advanced cost aggregation strategies in accurately retrieving 3D information. However, accuracy is typically achieved at expense of computational efficiency, with best methods being far from meeting real-time requirements. On the other side, basic real-time local algorithms relying on a rectangular correlation window suffer from significant ambiguity along depth borders and untextured areas. This work proposes a novel local approach aimed at maximizing the speed-accuracy trade-off by means of an efficient segmentation-based cost aggregation strategy.

Whole understanding of the surroundings is paramount to autonomous systems. Recent works have shown that deep neural networks can learn geometry (depth) and motion (optical flow) from a monocular video without any explicit supervision from ground truth annotations, particularly hard to source for these two tasks. In this paper, we take an additional step toward holistic scene understanding with monocular cameras by learning depth and motion alongside with semantics, with supervision for the latter provided by a pre-trained network distilling proxy ground truth images. We address the three tasks jointly by a) a novel training protocol based on knowledge distillation and self-supervision and b) a compact network architecture which enables efficient scene understanding on both power hungry GPUs and low-power embedded platforms. We thoroughly assess the performance of our framework and show that it yields state-of-the-art results for monocular depth estimation, optical flow and motion segmentation., Comment: CVPR 2020. Code will be available at https://github.com/CVLAB-Unibo/omeganet

Depth estimation from a single image represents a very exciting challenge in computer vision. While other image-based depth sensing techniques leverage on the geometry between different viewpoints (e.g., stereo or structure from motion), the lack of these cues within a single image renders ill-posed the monocular depth estimation task. For inference, state-of-the-art encoder-decoder architectures for monocular depth estimation rely on effective feature representations learned at training time. For unsupervised training of these models, geometry has been effectively exploited by suitable images warping losses computed from views acquired by a stereo rig or a moving camera. In this paper, we make a further step forward showing that learning semantic information from images enables to improve effectively monocular depth estimation as well. In particular, by leveraging on semantically labeled images together with unsupervised signals gained by geometry through an image warping loss, we propose a deep learning approach aimed at joint semantic segmentation and depth estimation. Our overall learning framework is semi-supervised, as we deploy groundtruth data only in the semantic domain. At training time, our network learns a common feature representation for both tasks and a novel cross-task loss function is proposed. The experimental findings show how, jointly tackling depth prediction and semantic segmentation, allows to improve depth estimation accuracy. In particular, on the KITTI dataset our network outperforms state-of-the-art methods for monocular depth estimation.

We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the local frame at each point; importantly, it directly inherits the properties and invariance classes of the underlying scalar function, making it remarkably robust under strong sampling artifacts, vertex noise, as well as non-rigid deformations. Existing local descriptors can directly benefit from our repeatable frames, as we showcase in a selection of 3D vision and shape analysis applications where we demonstrate state-of-the-art performance in a variety of challenging settings.

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs. These models, however, suffer from a notable decrease in accuracy when exposed to scenarios significantly different from the training set, e.g., real vs synthetic images, etc.). We argue that it is extremely unlikely to gather enough samples to achieve effective training/tuning in any target domain, thus making this setup impractical for many applications. Instead, we propose to perform unsupervised and continuous online adaptation of a deep stereo network, which allows for preserving its accuracy in any environment. However, this strategy is extremely computationally demanding and thus prevents real-time inference. We address this issue introducing a new lightweight, yet effective, deep stereo architecture, Modularly ADaptive Network (MADNet) and developing a Modular ADaptation (MAD) algorithm, which independently trains sub-portions of the network. By deploying MADNet together with MAD we introduce the first real-time self-adaptive deep stereo system enabling competitive performance on heterogeneous datasets., Comment: Accepted at CVPR2019 as oral presentation. Code Available https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo

This paper proposes an area-based stereo algorithm suitable to real time applications. The core of the algorithm relies on the uniqueness constraint and on a matching process that rejects previous matches as soon as more reliable ones are found. The proposed approach is also compared with bidirectional matching (BM), since the latter is the basic method for detecting unreliable matches in most area-based stereo algorithms. We describe the algorithm's matching core, the additional constraints introduced to improve the reliability and the computational optimizations carried out to achieve a very fast implementation. We provide a large set of experimental results, obtained on a standard set of images with ground-truth as well as on stereo sequences, and computation time measurements. These data are used to evaluate the proposed algorithm and compare it with a well-known algorithm based on BM.

In the past few years detection of repeatable and distinctive keypoints on 3D surfaces has been the focus of intense research activity, due on the one hand to the increasing diffusion of low-cost 3D sensors, on the other to the growing importance of applications such as 3D shape retrieval and 3D object recognition. This work aims at contributing to the maturity of this field by a thorough evaluation of several recent 3D keypoint detectors. A categorization of existing methods in two classes, that allows for highlighting their common traits, is proposed, so as to abstract all algorithms to two general structures. Moreover, a comprehensive experimental evaluation is carried out in terms of repeatability, distinctiveness and computational efficiency, based on a vast data corpus characterized by nuisances such as noise, clutter, occlusions and viewpoint changes.

The literature on local invariant 3D features is growing, also fostered by the advent of cheap off-the-shelf 3D sensors. Although several recent proposals in the field include both a detector and a descriptor, some of the most successful and used descriptors do not define a companion detector. Moreover, as vouched by the related field of image features, detectors and descriptors defined within the same proposal do not necessarily yield the highest performance when used together. Hence, in this work we investigate on the effectiveness of the many possible combinations between state-of-the-art 3D detectors and descriptors, so as to identify optimal pairs as well as highlight well-matched detectors for those descriptors lacking a companion feature detection algorithm.

The paper investigates on canonical references used for local surface description and matching. We formulate a novel proposal and carry out an extensive experimental evaluation addressing two major surface matching scenarios, namely shape registration and object recognition. We provide also a methodological contribution as, unlike previous work in the field, we propose a repeatability metric that captures the actual impact of the adopted local reference frame algorithm within surface matching tasks based on local 3D descriptors. Our proposal outperforms existing algorithms by a wide margin on several datasets acquired with different devices, such as laser scanners, stereo cameras and the Kinect, and in experiments relying on randomly extracted feature as well as state-of-the art key points.

Visual search for mobile devices relies on transmitting wirelessly image descriptors to a remote server. Hence, descriptors needs to be compressed to reduce bandwidth occupancy and network latency. In this paper, we investigate on the compression ratio versus accuracy of two low complexity coding schemes, based on Arithmetic and Type coding, applied to SIFT local descriptors.

This work proposes a novel approach for the detection of free-form shapes in a 3D space. The proposed method matches 3D features through their descriptions to attain correspondences, then accumulates evidence of the presence of the object(s) being sought by verifying the consensus of correspondences within a 3D Hough space. Our approach is capable of recognizing 3D shapes under significant degree of occlusion and clutter and can deal with multiple instances of the shape to be recognized. We validate our proposal by means of a quantitative experimental comparison to the state of the art over two datasets acquired with different sensors (a laser scanner and a stereo camera) and characterized by high degrees of clutter and occlusion. In addition, we propose an extension of the approach to RGB-D (i.e., color and depth) data together with results concerning 3D object recognition from RGB-D data acquired by a Microsoft Kinect sensor.

Visual search for mobile devices relies on transmitting wirelessly a compact representation of the query image, generally in the form of feature descriptors, to a remote server. Descriptors are therefore compressed, so as to reduce bandwidth occupancy and network latency. Given the impressive pace of growth of 3D video technology, we foresee 3D visual search applications for the mobile and the robotic market to become a reality. Accordingly, our work proposes a study on compressed 3D descriptors, a fundamental building block for such prospective applications. Based on analysis of several compression approaches, we develop and assess different schemes to achieve a compact version of a state-of-the-art 3D descriptor. Through experiments on a vast dataset we demonstrate the ability to achieve compression rates as high as 98% with a negligible loss in 3D visual search performance.

We propose a novel approach for verifying model hypotheses in cluttered and heavily occluded 3D scenes. Instead of verifying one hypothesis at a time, as done by most state-of-the-art 3D object recognition methods, we determine object and pose instances according to a global optimization stage based on a cost function which encompasses geometrical cues. Peculiar to our approach is the inherent ability to detect significantly occluded objects without increasing the amount of false positives, so that the operating point of the object recognition algorithm can nicely move toward a higher recall without sacrificing precision. Our approach outperforms state-of-the-art on a challenging dataset including 35 household models obtained with the Kinect sensor, as well as on the standard 3D object recognition benchmark dataset.