Communication mechanisms and middleware for distributed video surveillance

A new generation of advanced surveillance systems is being conceived as a collection of multi-sensor components such as video, audio and mobile robots interacting in a cooperating manner to enhance situation awareness capabilities to assist surveillance personnel. The prominent issues that these systems face are: the improvement of existing intelligent video surveillance systems, the inclusion of wireless networks, the use of low power sensors, the design architecture, the communication between different components, the fusion of data emerging from different type of sensors, the location of personnel (providers and consumers) and the scalability of the system. This paper focuses on the aspects pertaining to real-time distributed architecture and scalability. For example, to meet real-time requirements, these systems need to process data streams in concurrent environments, designed by taking into account scheduling and synchronisation. The paper proposes a framework for the design of visual surveillance systems based on components derived from the principles of Real Time Networks/Data Oriented Requirements Implementation Scheme (RTN/DORIS). It also proposes the implementation of these components using the well-known middleware technology Common Object Request Broker Architecture (CORBA). Results using this architecture for video surveillance are presented through an implemented prototype.

Robust abandoned object detection integrating wide area visual surveillance and social context

This paper presents a video surveillance framework that robustly and efficiently detects abandoned objects in surveillance scenes. The framework is based on a novel threat assessment algorithm which combines the concept of ownership with automatic understanding of social relations in order to infer abandonment of objects. Implementation is achieved through development of a logic-based inference engine based on Prolog. Threat detection performance is conducted by testing against a range of datasets describing realistic situations and demonstrates a reduction in the number of false alarms generated. The proposed system represents the approach employed in the EU SUBITO project (Surveillance of Unattended Baggage and the Identification and Tracking of the Owner).

The future of video analytics for surveillance and its ethical implications

The current state of the art and direction of research in computer vision aimed at automating the analysis of CCTV images is presented. This includes low level identification of objects within the field of view of cameras, following those objects over time and between cameras, and the interpretation of those objects’ appearance and movements with respect to models of behaviour (and therefore intentions inferred). The potential ethical problems (and some potential opportunities) such developments may pose if and when deployed in the real world are presented, and suggestions made as to the necessary new regulations which will be needed if such systems are not to further enhance the power of the surveillers against the surveilled.

Video surveillance : past, present, and now the future

Video surveillance is a part of our daily life, even though we may not necessarily realize it. We might be monitored on the street, on highways, at ATMs, in public transportation vehicles, inside private and public buildings, in the elevators, in front of our television screens, next to our baby?s cribs, and any spot one can set a camera.

Scene understanding for auto-calibration of surveillance cameras

In the last decade, several research results have presented formulations for the auto-calibration problem. Most of these have relied on the evaluation of vanishing points to extract the camera parameters. Normally vanishing points are evaluated using pedestrians or the Manhattan World assumption i.e. it is assumed that the scene is necessarily composed of orthogonal planar surfaces. In this work, we present a robust framework for auto-calibration, with improved results and generalisability for real-life situations. This framework is capable of handling problems such as occlusions and the presence of unexpected objects in the scene. In our tests, we compare our formulation with the state-of-the-art in auto-calibration using pedestrians and Manhattan World-based assumptions. This paper reports on the experiments conducted using publicly available datasets; the results have shown that our formulation represents an improvement over the state-of-the-art.

Syndromic approach to arboviral diagnostics for global travelers as a basis for infectious disease surveillance

Background Arboviruses have overlapping geographical distributions and can cause symptoms that coincide with more common infections. Therefore, arbovirus infections are often neglected by travel diagnostics. Here, we assessed the potential of syndrome-based approaches for diagnosis and surveillance of neglected arboviral diseases in returning travelers. Method To map the patients high at risk of missed clinical arboviral infections we compared the quantity of all arboviral diagnostic requests by physicians in the Netherlands, from 2009 through 2013, with a literature-based assessment of the travelers’ likely exposure to an arbovirus. Results 2153 patients, with travel and clinical history were evaluated. The diagnostic assay for dengue virus (DENV) was the most commonly requested (86%). Of travelers returning from Southeast Asia with symptoms compatible with chikungunya virus (CHIKV), only 55% were tested. For travelers in Europe, arbovirus diagnostics were rarely requested. Over all, diagnostics for most arboviruses were requested only on severe clinical presentation. Conclusion Travel destination and syndrome were used inconsistently for triage of diagnostics, likely resulting in vast under-diagnosis of arboviral infections of public health significance. This study shows the need for more awareness among physicians and standardization of syndromic diagnostic algorithms

Surveillance for adverse events after DTwP/Hib vaccination in Brazil: Sensitivity and factors associated with reporting

We estimated the sensitivity, i.e., the proportion of all cases of adverse events following immunization (AEFIs) reported to the Brazilian passive surveillance for adverse events following immunization (PSAEFI) with the diphtheria-tetanus-whole-cell pertussis-Haemophilus influenzae type b (DTwP/Hib) vaccine, as well as investigating factors associated with AEFIs reporting. During 2003-2004, 8303 AEFIs associated with DTwP-Hib were reported; hypotonic-hyporesponsive episodes (HHEs), fever and convulsions being the most common. Cure without sequel was achieved in 98.4% of the cases. The mean sensitivity of the PSAEFI was 22.3% and 31.6%, respectively, for HHE and convulsions, varying widely among states. Reporting rates correlated positively with the Human Development Index and coverage of adequate prenatal care, correlating negatively with infant mortality rates. Quality of life indicators and the degree of organization of health services are associated with greater PSAEFI sensitivity. In addition to consistently describing the principal AEFIs, PSAEFI showed the DTwP/Hib vaccine to be safe and allayed public fears related to its use. (C) 2010 Elsevier Ltd. All rights reserved.

Rotavirus Gastroenteritis in Children in 4 Regions in Brazil: A Hospital-Based Surveillance Study

Background. Rotavirus is a major cause of gastroenteritis in children. Knowledge of rotavirus genotypes is important for vaccination strategies. Methods. During 2005-2006, rotavirus surveillance studies were conducted in Sao Paulo, Salvador, Goiania, and Porto Alegre, Brazil. Stool samples were collected from children <5 years of age who had diarrhea and were screened by the Rotaclone Enzyme Immunoassay for the presence of rotavirus. Confirmed rotavirus-positive samples were characterized for P and G genotypes by reverse-transcriptase polymerase chain reaction. Results. A total of 510 stool samples were collected. Of these, 221 (43.3%) were positive for rotavirus. Overall, G9 was the predominant G type, followed by G2, and G1; P[4] and P[8] were the predominant P types. The most frequent G/P genotype combination detected was G2P[4], followed by G9P[8], G9P[4], and G1P[8]. G2P[4] was the predominant type in Goiania and Salvador; G9P[8] and G1P[8] were predominant in Sao Paulo and Porto Alegre, respectively. Conclusions. The prevalence, seasonality, and genotype distribution of rotavirus infection varied in different regions in Brazil. With immunization programs, continuous monitoring of rotavirus types is important to detect novel and emerging strains.

Hospital-based Surveillance to Evaluate the Impact of Rotavirus Vaccination in Sao Paulo, Brazil

Background: Brazil implemented routine immunization with the human rotavirus vaccine, Rotarix, in 2006 and vaccination coverage reached 81% in 2008 in Sao Paulo. Our aim was to assess the impact of immunization on the incidence of severe rotavirus acute gastroenteritis (AGE). Methods: We performed a 5-year (2004-2008) prospective surveillance at a sentinel hospital in Sao Paulo, with routine testing for rotavirus in all children less than 5 years of age hospitalized with AGE. Genotypes of positive samples were determined by reverse transcription polymerase chain reaction. Results: During the study, 655 children hospitalized with AGE were enrolled; of whom 169 (25.8%) were positive for rotavirus. In the post-vaccine period, a 59% reduction in the number of hospitalizations of rotavirus AGE and a 42.2% (95% confidence interval [CI], 18.6%-59.0%; P = 0.001) reduction in the proportion of rotavirus-positive results among children younger than 5 years were observed, with the greatest decline among infants (69.2%; 95% CI, 24.7%-87.4%; P = 0.004). Furthermore, the number of all-cause hospitalizations for AGE was reduced by 29% among children aged <5 years. The onset and peak incidences of rotavirus AGE occurred 3 months later in the 2007 and 2008 seasons compared with previous years. Genotype G2 accounted for 15%, 70%, and 100% of all cases identified, respectively, in 2006, 2007, and 2008. Conclusions: After vaccine implementation, a marked decline in rotavirus AGE hospitalizations was demonstrated among children younger than 5 years of age, with the greatest reduction in the age groups targeted for vaccination. The predominance of genotype G2P[4] highlights the need of continued postlicensure surveillance studies.