Foreground segmentation in depth imagery using depth and spatial dynamic models for video surveillance applications

Low-cost systems that can obtain a high-quality foreground segmentation almostindependently of the existing illumination conditions for indoor environments are verydesirable, especially for security and surveillance applications. In this paper, a novelforeground segmentation algorithm that uses only a Kinect depth sensor is proposedto satisfy the aforementioned system characteristics. This is achieved by combininga mixture of Gaussians-based background subtraction algorithm with a new Bayesiannetwork that robustly predicts the foreground/background regions between consecutivetime steps. The Bayesian network explicitly exploits the intrinsic characteristics ofthe depth data by means of two dynamic models that estimate the spatial and depthevolution of the foreground/background regions. The most remarkable contribution is thedepth-based dynamic model that predicts the changes in the foreground depth distributionbetween consecutive time steps. This is a key difference with regard to visible imagery,where the color/gray distribution of the foreground is typically assumed to be constant.Experiments carried out on two different depth-based databases demonstrate that theproposed combination of algorithms is able to obtain a more accurate segmentation of theforeground/background than other state-of-the art approaches.

Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

An artificial neural network stratifies the risks of reintervention and mortality after endovascular aneurysm repair:a retrospective observational study

Background Lifelong surveillance after endovascular repair (EVAR) of abdominal aortic aneurysms (AAA) is considered mandatory to detect potentially life-threatening endograft complications. A minority of patients require reintervention but cannot be predictively identified by existing methods. This study aimed to improve the prediction of endograft complications and mortality, through the application of machine-learning techniques. Methods Patients undergoing EVAR at 2 centres were studied from 2004-2010. Pre-operative aneurysm morphology was quantified and endograft complications were recorded up to 5 years following surgery. An artificial neural networks (ANN) approach was used to predict whether patients would be at low- or high-risk of endograft complications (aortic/limb) or mortality. Centre 1 data were used for training and centre 2 data for validation. ANN performance was assessed by Kaplan-Meier analysis to compare the incidence of aortic complications, limb complications, and mortality; in patients predicted to be low-risk, versus those predicted to be high-risk. Results 761 patients aged 75 +/- 7 years underwent EVAR. Mean follow-up was 36+/- 20 months. An ANN was created from morphological features including angulation/length/areas/diameters/ volume/tortuosity of the aneurysm neck/sac/iliac segments. ANN models predicted endograft complications and mortality with excellent discrimination between a low-risk and high-risk group. In external validation, the 5-year rates of freedom from aortic complications, limb complications and mortality were 95.9% vs 67.9%; 99.3% vs 92.0%; and 87.9% vs 79.3% respectively (p0.001) Conclusion This study presents ANN models that stratify the 5-year risk of endograft complications or mortality using routinely available pre-operative data.

Design strategies for an artificial neural network based algorithm for automatic incident detection on major arterial streets

Traffic incidents are non-recurring events that can cause a temporary reduction in roadway capacity. They have been recognized as a major contributor to traffic congestion on our nation’s highway systems. To alleviate their impacts on capacity, automatic incident detection (AID) has been applied as an incident management strategy to reduce the total incident duration. AID relies on an algorithm to identify the occurrence of incidents by analyzing real-time traffic data collected from surveillance detectors. Significant research has been performed to develop AID algorithms for incident detection on freeways; however, similar research on major arterial streets remains largely at the initial stage of development and testing. This dissertation research aims to identify design strategies for the deployment of an Artificial Neural Network (ANN) based AID algorithm for major arterial streets. A section of the US-1 corridor in Miami-Dade County, Florida was coded in the CORSIM microscopic simulation model to generate data for both model calibration and validation. To better capture the relationship between the traffic data and the corresponding incident status, Discrete Wavelet Transform (DWT) and data normalization were applied to the simulated data. Multiple ANN models were then developed for different detector configurations, historical data usage, and the selection of traffic flow parameters. To assess the performance of different design alternatives, the model outputs were compared based on both detection rate (DR) and false alarm rate (FAR). The results show that the best models were able to achieve a high DR of between 90% and 95%, a mean time to detect (MTTD) of 55-85 seconds, and a FAR below 4%. The results also show that a detector configuration including only the mid-block and upstream detectors performs almost as well as one that also includes a downstream detector. In addition, DWT was found to be able to improve model performance, and the use of historical data from previous time cycles improved the detection rate. Speed was found to have the most significant impact on the detection rate, while volume was found to contribute the least. The results from this research provide useful insights on the design of AID for arterial street applications.

Design Strategies for an Artificial Neural Network Based Algorithm for Automatic Incident Detection on Major Arterial Streets

Traffic incidents are non-recurring events that can cause a temporary reduction in roadway capacity. They have been recognized as a major contributor to traffic congestion on our national highway systems. To alleviate their impacts on capacity, automatic incident detection (AID) has been applied as an incident management strategy to reduce the total incident duration. AID relies on an algorithm to identify the occurrence of incidents by analyzing real-time traffic data collected from surveillance detectors. Significant research has been performed to develop AID algorithms for incident detection on freeways; however, similar research on major arterial streets remains largely at the initial stage of development and testing. This dissertation research aims to identify design strategies for the deployment of an Artificial Neural Network (ANN) based AID algorithm for major arterial streets. A section of the US-1 corridor in Miami-Dade County, Florida was coded in the CORSIM microscopic simulation model to generate data for both model calibration and validation. To better capture the relationship between the traffic data and the corresponding incident status, Discrete Wavelet Transform (DWT) and data normalization were applied to the simulated data. Multiple ANN models were then developed for different detector configurations, historical data usage, and the selection of traffic flow parameters. To assess the performance of different design alternatives, the model outputs were compared based on both detection rate (DR) and false alarm rate (FAR). The results show that the best models were able to achieve a high DR of between 90% and 95%, a mean time to detect (MTTD) of 55-85 seconds, and a FAR below 4%. The results also show that a detector configuration including only the mid-block and upstream detectors performs almost as well as one that also includes a downstream detector. In addition, DWT was found to be able to improve model performance, and the use of historical data from previous time cycles improved the detection rate. Speed was found to have the most significant impact on the detection rate, while volume was found to contribute the least. The results from this research provide useful insights on the design of AID for arterial street applications.

Contextual anomaly detection in crowded surveillance scenes

This work addresses the problem of detecting human behavioural anomalies in crowded surveillance environments. We focus in particular on the problem of detecting subtle anomalies in a behaviourally heterogeneous surveillance scene. To reach this goal we implement a novel unsupervised context-aware process. We propose and evaluate a method of utilising social context and scene context to improve behaviour analysis. We find that in a crowded scene the application of Mutual Information based social context permits the ability to prevent self-justifying groups and propagate anomalies in a social network, granting a greater anomaly detection capability. Scene context uniformly improves the detection of anomalies in both datasets. The strength of our contextual features is demonstrated by the detection of subtly abnormal behaviours, which otherwise remain indistinguishable from normal behaviour.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.

Surveillance in Cyberspace: Applying Natural and Place Manager Surveillance to System Trespassing

Research on the criminological side of system trespassing (i.e. unlawfully gaining access to a computer system) is relatively rare and has yet to examine the effect of the presence of other users on the system during the trespassing event (i.e. the time of communication between a trespasser’s system and the infiltrated system). This thesis seeks to analyze this relationship drawing on principles of Situational Crime Prevention, Routine Activities Theory, and restrictive deterrence. Data were collected from a randomized control trial of target computers deployed on the Internet network of a large U.S. university. This study examined whether the number (one or multiple) and type (administrative or non-administrative) of computer users present on a system reduced the seriousness and frequency of trespassing. Results indicated that the type of user (administrative) produced a restrictive deterrent effect and significantly reduced the frequency and duration of trespassing events.

Occupational contact urticaria: lessons from the French National Network for Occupational Disease Vigilance and Prevention (RNV3P)

International audience

Intelligence, Surveillance & Reconnaissance como Agente de Mudança

O século XXI introduziu profundas mudanças no espaço onde a atuação militar se desenvolve. Esta mutação, que agora inclui o domínio físico e cognitivo na ação militar, impõe a adoção de novos conceitos de operação e estruturas organizacionais mais ágeis, de forma a fazerem face a um ambiente altamente volátil, imprevisível e complexo. Tal contexto torna as organizações, hoje mais do que nunca, dependentes de informação (e dos sistemas que as geram), e no âmbito das organizações militares, uma capacidade em particular assume, na atualidade, uma preponderância fulcral para o sucesso destas, que se designa por Intelligence, Surveillance & Reconnaissance (ISR). Considerando a complexidade de sistemas, processos e pessoas que envolvem toda esta capacidade, torna-se relevante estudar como a Força Aérea Portuguesa (FAP) está a acomodar este conceito no interior da sua estrutura, uma vez que a sua adaptação requer uma organização da era da informação, onde o trabalho em rede assume particular destaque. A presente investigação analisa formas de estruturas organizacionais contemporâneas e cruza-as com as recomendações da Organização do Tratado do Atlântico Norte (também designada por Aliança), comparando-as posteriormente com a atualidade da FAP. No final, são efetuadas propostas tangíveis, que podem potenciar as capacidades existentes, de onde se destaca a criação de uma matriz de análise quanto à eficiência organizacional, uma nova forma de organização das capacidades residentes no que ao ISR concerne, bem como o modo de potenciar o trabalho em rede com base nos meios existentes. Abstract: The 21st century has caused profound changes in the areas where military action takes place. This mutation, which now includes the physical and cognitive domain in military action, requires the adoption of new concepts of operation and more agile organizational structures in order to cope with a highly volatile, unpredictable and complex environment. Thus, more than ever, this makes the present organizations dependent of information (and the systems that generate them), in the case of military organizations, a particular capability undertakes today a strong impact on the success of military organizations. It is known as Intelligence, Surveillance& Reconnaissance (ISR). Taking into account the complexity of systems, processes and people involving all this capability, it is relevant to study how the Portuguese Air Force (PAF) is accommodating this concept within its structure, since the adaptation requires an organization adapted to the information era, where networking is particularly prominent. This research aims to analyze contemporary forms of organizational structures and cross them with the recommendations of the North Atlantic Treaty Organization (also known as Alliance), later comparing them with today's PAF. At the end of this investigation, some tangible proposals are made which can enhance existing capabilities: we can highlight the creation of an analysis matrix for organizational efficiency, a new form of organization of the resident capabilities in the ISR concerns, as well as the way of enhancing networking, based on existing means.

"Portuguese Observatory of Taeniasis and Cysticercosis": A "One Health" example for epidemiological surveillance of one neglected disease in a European country

Cysticercosis results from the ingestion Taenia solium eggs directly by faecal-oral route or contaminated food or water. Human tapeworm carriers who have become infected after ingesting pork meat contaminated with cysticerci release these eggs. Cysticercosis occurs after tapeworm eggs are ingested by an intermediate host (pig or human) and then hatch, migrate, and lodge in the host's tissues, where they develop onto larval cysticerci. When they lodged in the central nervous system of humans, results in the disease condition called Neurocysticercosis (NCC), with a heterogeneous manifestations depending of the locations of cysts, number, size and their stage of evolution (1). Consequently the prognostic ranges from asymptomatic to situations leading to death in 2% to 9.8%. of cases (7) In swine’s there are few studies, but recent works have proved that animals, for the same reasons, also have neurological abnormalities, expressed by seizures, stereotypic walk in circles, chewing motions with foamy salivation included tonic muscle contractions followed by a sudden diminution in all muscle tone leading to collapse (2). Conventional domestic wastewater treatment processes may not be totally effective in inactivating parasites eggs from Taenia solium, allowing some contamination of soils and agricultural products (11). In Portugal there are some evidence of aggregation of human cysticercosis cases in specific regions, bases in ecological design studies (6). There are few information about human tapeworm carriers and social and economic factors associated with them. Success in knowledge and consequently in lowering transmission is limited by the complex network of biological and social factors that maintain the spread. Effective control of mostly zoonosis require One Health approach, after a real knowledge and transparency in the information provided by the institutions responsible for both animal and human health, allowing sustained interventions targeted at the transmission cycle's crucial nodes. In general, the model used to control, reflects a rural reality, where pigs are raised freely, poor sanitation conditions and incipient sanitary inspection. In cysticercosis, pigs are obligate intermediate hosts and so considered as first targets for control and used as sentinels to monitor environmental T. solium contamination (3). Usually environmental contamination with Taenia spp. eggs is a key issue in most of studies with landscape factors influencing presence of Taenia spp. antigens in both pigs and humans (5). Soil-related factors as well as socio-economic and behavioural factors are associated with the emergence of significant clustering human cysticercosis (4,5). However scarce studies has been produced in urban environmental and in developed countries with the finality to characterize the spatial pattern. There are still few data available regarding its prevalence and spatial distribution; Transmission patterns are likely to exhibit correlations as housing conditions, water supply, basic sanitation, schooling and birthplace of the individual or relatives, more than pigs rearing free, soil conditions (9). As a matter of fact, tapeworm carriers from endemic zones can auto-infect or transmit infection to other people or arrive already suffering NCC (as a result of travelling to or being a citizen from an endemic cysticercosis country) to a free cysticercosis country. Transmission is fecal-oral; this includes transmission through person-to-person contact, through autoinfection, or through contaminated food This has been happening in different continents as North America (5.4–18% been autochthonous), Europe and Australia (7). Recently, case reports of NCC have also emerged from Muslim countries. (10). Actually, different papers relate an epidemic situation in Spain and Portugal (7, 8). However the kind of study done does not authorize such conclusion. There are no evidence that infections were acquired in Portugal and there are not characterized the mode of transmission. Papers with these kind of information will be allow to have economic consequences resulted from artificial trade barriers with serious consequences for pig producers and pig meat trade. We need transparency in information’s that allow provide the basis to support the development and targeting of future effective control programmes (and prove we need that). So, to have a real picture of the disease, it is necessary integrate data from human, animal and environmental factors surrounding human and pig cases to characterize the pattern of the transmission. The design needs to be able to capture unexpected, and not common outcomes (routine data). We need to think “One Health” to get a genuine image of the situation.

Data surveillance for infectious diseases: models, complex networks and machine learning

In this thesis, we investigate the role of applied physics in epidemiological surveillance through the application of mathematical models, network science and machine learning. The spread of a communicable disease depends on many biological, social, and health factors. The large masses of data available make it possible, on the one hand, to monitor the evolution and spread of pathogenic organisms; on the other hand, to study the behavior of people, their opinions and habits. Presented here are three lines of research in which an attempt was made to solve real epidemiological problems through data analysis and the use of statistical and mathematical models. In Chapter 1, we applied language-inspired Deep Learning models to transform influenza protein sequences into vectors encoding their information content. We then attempted to reconstruct the antigenic properties of different viral strains using regression models and to identify the mutations responsible for vaccine escape. In Chapter 2, we constructed a compartmental model to describe the spread of a bacterium within a hospital ward. The model was informed and validated on time series of clinical measurements, and a sensitivity analysis was used to assess the impact of different control measures. Finally (Chapter 3) we reconstructed the network of retweets among COVID-19 themed Twitter users in the early months of the SARS-CoV-2 pandemic. By means of community detection algorithms and centrality measures, we characterized users’ attention shifts in the network, showing that scientific communities, initially the most retweeted, lost influence over time to national political communities. In the Conclusion, we highlighted the importance of the work done in light of the main contemporary challenges for epidemiological surveillance. In particular, we present reflections on the importance of nowcasting and forecasting, the relationship between data and scientific research, and the need to unite the different scales of epidemiological surveillance.

Structural Connectivity Of The Default Mode Network And Cognition In Alzheimer׳s Disease.

Disconnectivity between the Default Mode Network (DMN) nodes can cause clinical symptoms and cognitive deficits in Alzheimer׳s disease (AD). We aimed to examine the structural connectivity between DMN nodes, to verify the extent in which white matter disconnection affects cognitive performance. MRI data of 76 subjects (25 mild AD, 21 amnestic Mild Cognitive Impairment subjects and 30 controls) were acquired on a 3.0T scanner. ExploreDTI software (fractional Anisotropy threshold=0.25 and the angular threshold=60°) calculated axial, radial, and mean diffusivities, fractional anisotropy and streamline count. AD patients showed lower fractional anisotropy (P=0.01) and streamline count (P=0.029), and higher radial diffusivity (P=0.014) than controls in the cingulum. After correction for white matter atrophy, only fractional anisotropy and radial diffusivity remained significantly lower in AD compared to controls (P=0.003 and P=0.05). In the parahippocampal bundle, AD patients had lower mean and radial diffusivities (P=0.048 and P=0.013) compared to controls, from which only radial diffusivity survived for white matter adjustment (P=0.05). Regression models revealed that cognitive performance is also accounted for by white matter microstructural values. Structural connectivity within the DMN is important to the execution of high-complexity tasks, probably due to its relevant role in the integration of the network.

The Burden Of Eclampsia: Results From A Multicenter Study On Surveillance Of Severe Maternal Morbidity In Brazil.

Maternal mortality (MM) is a core indicator of disparities in women's rights. The study of Near Miss cases is strategic to identifying the breakdowns in obstetrical care. In absolute numbers, both MM and occurrence of eclampsia are rare events. We aim to assess the obstetric care indicators and main predictors for severe maternal outcome from eclampsia (SMO: maternal death plus maternal near miss). Secondary analysis of a multicenter, cross-sectional study, including 27 centers from all geographic regions of Brazil, from 2009 to 2010. 426 cases of eclampsia were identified and classified according to the outcomes: SMO and non-SMO. We classified facilities as coming from low- and high-income regions and calculated the WHO's obstetric health indicators. SPSS and Stata softwares were used to calculate the prevalence ratios (PR) and respective 95% confidence interval (CI) to assess maternal characteristics, clinical and obstetrical history, and access to health services as predictors for SMO, subsequently correlating them with the corresponding perinatal outcomes, also applying multiple regression analysis (adjusted for cluster effect). Prevalence of and mortality indexes for eclampsia in higher and lower income regions were 0.2%/0.8% and 8.1%/22%, respectively. Difficulties in access to health care showed that ICU admission (adjPR 3.61; 95% CI 1.77-7.35) and inadequate monitoring (adjPR 2.31; 95% CI 1.48-3.59) were associated with SMO. Morbidity and mortality associated with eclampsia were high in Brazil, especially in lower income regions. Promoting quality maternal health care and improving the availability of obstetric emergency care are essential actions to relieve the burden of eclampsia.

Can We Predict The Clinical Outcomes Of Genitourinary Trauma Patients And Offer Them An Evidence-based Support? The Case For Telemedicine Network.

32