Real-time Surveillance System Research Articles

Implementation and evaluation of an automated surveillance system to detect hospital outbreak

The timely identification of a cluster is a critical requirement for infection prevention and control (IPC) departments because these events may represent transmission of pathogens within the health care setting. Given the issues with manual review of hospital infections, a surveillance system to detect clusters in health care settings must use automated data capture, validated statistical methods, and include all significant pathogens, antimicrobial susceptibility patterns, patient care locations, and health care teams. We describe the use of SaTScan statistical software to identify clusters, WHONET software to manage microbiology laboratory data, and electronic health record data to create a comprehensive outbreak detection system in our hospital. We also evaluated the system using the Centers for Disease Control and Prevention's guidelines. During an 8-month surveillance time period, 168 clusters were detected, 45 of which met criteria for investigation, and 6 were considered transmission events. The system was felt to be flexible, timely, accepted by the department and hospital, useful, and sensitive, but it required significant resources and has a low positive predictive value. WHONET-SaTScan is a useful addition to a robust IPC program. Although the resources required were significant, this prospective, real-time cluster detection surveillance system represents an improvement over historical methods. We detected several episodes of transmission which would have eluded us previously, and allowed us to focus infection prevention efforts and improve patient safety.

Using MALDI-TOF MS typing method to decipher outbreak: the case of Staphylococcus saprophyticus causing urinary tract infections (UTIs) in Marseille, France.

Staphylococcus saprophyticus is one of the leading causes of urinary tract infections (UTI). In December 2014, our surveillance system identified an abnormal increase in S. saprophyticus causing UTIs in four university hospitals in Marseille, indicating a suspected community S. saprophyticus UTI outbreak. This was detected by our surveillance system BALYSES (Bacterial real-time Laboratory-based Surveillance System). S. saprophyticus/ Escherichia coli UTI ratio increased three-fold from 0.0084 in 2002 to 0.025 in December 2015 in Marseille with an abnormal peak in December 2014, and with an annual estimated ratio trend of 5.10-6 (p-value<10-3). Matrix-Assisted Laser Desorption Ionisation-Time of Flight Mass Spectrometry (MALDI-TOF MS) spectral analysis of strains was used to analyse strains cluster expansion, comparing strains from Marseille to those from Nice during the same period. MALDI-TOF MS spectral analysis revealed a geographical restricted clonal expansion of the strains clusters in Marseille as compared to Nice. Our finding suggests (i) a geographically restricted expansion of a specific S. saprophyticus strain clusters circulating in Marseille, and (ii) MALDI-TOF MS can be used as a cost-effective tool to investigate an outbreak.

Space-time analysis of pneumonia hospitalisations in the Netherlands.

Community acquired pneumonia is a major global public health problem. In the Netherlands there are 40,000–50,000 hospital admissions for pneumonia per year. In the large majority of these hospital admissions the etiologic agent is not determined and a real-time surveillance system is lacking. Localised and temporal increases in hospital admissions for pneumonia are therefore only detected retrospectively and the etiologic agents remain unknown. Here, we perform spatio-temporal analyses of pneumonia hospital admission data in the Netherlands. To this end, we scanned for spatial clusters on yearly and seasonal basis, and applied wavelet cluster analysis on the time series of five main regions. The pneumonia hospital admissions show strong clustering in space and time superimposed on a regular yearly cycle with high incidence in winter and low incidence in summer. Cluster analysis reveals a heterogeneous pattern, with most significant clusters occurring in the western, highly urbanised, and in the eastern, intensively farmed, part of the Netherlands. Quantitatively, the relative risk (RR) of the significant clusters for the age-standardised incidence varies from a minimum of 1.2 to a maximum of 2.2. We discuss possible underlying causes for the patterns observed, such as variations in air pollution.

Efficient Human Motion Detection with Adaptive Background for Vision-Based Security System

Motion detection is very important in video surveillance system especially for video compression, human detection and behaviour analysis. Various approaches have been used for detecting motion in a continuous video stream but for real-time video surveillance system, we need a motion detection that can provide accurate detection even in non-static background regardless of surroundings (outdoor or indoor), object speed and size, robust to camera noisy pixels or sudden change in light intensity. This is very important to ensure that the security of a monitored parameter or area is not compromised. In this paper, we propose a method for human motion detection which employs adaptive background subtraction, camera noise reduction and white pixel counts threshold for real-time video streams.

Invited commentary

The search for the optimal arterial replacement has continued for decades. The avenues of focus have been on material, technique, and medical adjuncts. Simultaneously, the role of interventions to salvage failing grafts has been dominated by duplex ultrasound surveillance. Duplex surveillance has been driven by the idea that demonstrable changes in hemodynamics corresponding with impending graft failure can be detected and treated before graft thrombosis. Surveillance has suffered from the determination of the best intervals, and the role of surveillance of prosthetic grafts has not been as well-demonstrated as for vein grafts. Enter the authors of the current manuscript. In this paper, the authors have taken another tack to optimize graft performance—a self-monitoring graft. Grafts previously lost in the interval between scheduled surveillance may now be saved with real-time continuous in vivo monitoring. This, the authors hope, can improve outcomes with prosthetic grafts until the holy grail of a perfect arterial substitute is attained. This paper offers a proof-of-concept study demonstrating a self-monitoring prosthetic bypass graft. The authors have developed a piezo-electric sensor that can be implanted surrounding a polytetrafluoroethylene graft. This sensor can then remotely deliver information regarding flow dynamics in the graft in real time via Blue Tooth technology. This is accomplished using proprietary parameters based on the acoustic energy present in the system. The current manuscript demonstrates early in vitro testing as well as in vivo results in an ovine carotid-carotid bypass model with follow-up to 30 days. The sensor covers 2 cm of the 20-cm graft and was able to detect upstream and downstream stenoses in vitro. The in vivo testing demonstrated that the data can be easily collected on a daily basis through living tissue. However, the in vivo testing did not provide any information on detection of stenoses (likely owing to the short time frame). This technology is exciting and has been ushered forward by the miniaturization that has been possible over the past two decades as well as the development of the Internet and wireless devices. This opens entirely new doors of investigation. Whether this new technology can be adapted to vein grafts as well as prosthetics; and whether any of this can actually lead to improved overall graft patency and clinical outcomes awaits further studies, which will likely be years in coming. As technology has improved so many other aspects of our daily lives, this report will undoubtedly usher in further avenues of study merging technology with graft materials development in an exciting way. Initial in vitro and in vivo evaluation of a self-monitoring prosthetic bypass graftJournal of Vascular SurgeryVol. 65Issue 6PreviewProsthetic grafts used for lower extremity revascularization and dialysis access fail because of hyperplastic stenosis and thrombosis. Graft surveillance is advocated to monitor function; however, graft failure can occur between episodic examinations. An innovative sensor with wireless, microchip technology allows automated surveillance with assessment of graft function using a “cloud”-based algorithm. We performed proof-of-concept experiments with in vitro and in vivo models to assess the feasibility such a real-time graft surveillance system. Full-Text PDF Open Archive

Real-time surveillance and response system for Ebola and other emerging infections

ObjectiveWe will describe a real-time mobile surveillance and casemanagement system designed to organize data collected bymultiple officers about cases and their contacts. We will discuss thissurveillance system and its application for Ebola and other infectiousdiseases in the Democratic Republic of the Congo (DRC) and othersimilar settings. We will review the technology, results, challenges,lessons-learned, and applicability to other contexts.IntroductionImproving surveillance and response is a critical component ofthe Global Health Security Agenda. While it is impossible to predictwhere the next Ebola outbreak will occur, it is very likely that anotheroutbreak will occur in the DRC. Of the 20 known outbreaks, 7 haveoccurred in the DRC, one as recently as 2014. To rapidly detectand respond to an Ebola outbreak, we sought to develop a real-timesurveillance and response system for use in DRC and similar settings.RTI International developed Coconut Surveillance mobile software,which is currently used for real-time malaria surveillance andresponse in Zanzibar, Africa, where malaria elimination efforts areunderway. We took this system and adapted it for Ebola as a possibletool for surveillance and response to Ebola and other (re)emergingdiseases. Plans include pilot testing functionality at clinical sites inDRC, where surveillance infrastructure is limited at the local level.Coconut Surveillance is a mobile disease surveillance and rapidresponse system currently used for malaria elimination activities.It receives suspected positive case alerts from the field via mobilephones and uses mobile software to guide surveillance officersthrough a follow-up process. Coconut Surveillance runs on Androidmobile devices that are used to coordinate work in the field as well asprovide decision support during data collection and case management.In addition to standard case information, the GPS coordinates ofthe case’s household are captured as well as malaria status of allhousehold members. Data are collected and accessed off-line, and aresynchronized with a shared database when Internet connectivity isavailable. This tool has been used successfully in Zanzibar for morethan three years and has been recognized as one of the most advancedapplications of its kind.MethodsWe adapted the Coconut Surveillance system for Ebolasurveillance and response, and expanded the system for use with othercommunicable diseases. With a near real-time outbreak detectionsystem for Ebola, we may reduce the response time and contain anoutbreak faster. Using a cloud-based data repository, the modifiedCoconut System, known as Coconut Plus, also has the added value ofcase and case-contacts specific information sharing in real-time withthe national, provincial, and district level public health authorities,who would have convenient and secure access to case and contactinformation via the Internet. The software modifications to theCoconut System have been informed by testing and stakeholderfeedback.ResultsWe have developed Coconut Plus around the Coconut softwarearchitecture, which allows the team to quickly develop specificworkflows and applications, such as contact tracing, on top of a solidand well-supported base. Additionally, the adaptation was structuredto accommodate the build-out of multiple diseases, and is uniquelyhelpful for diseases that require tracking many contacts. We weregranted access in DRC to test interoperability with DHIS 2, the mostwidely used health information system software in Ebola effectedcountries. Coconut Plus is now using the DHIS 2 organizationalhierarchy definition, which means that organizational hierarchy(including information on administrative units and health carefacilities) can be exported directly from DHIS 2 to Coconut Plus.Stakeholder feedback on the usability and feasibility of the adaptedsystem has been enthusiastic, and stressed the need for additionalresources to make a pilot successful, including mobile phones andimproved mobility of surveillance staff in the field. The followingscreencast provides an overview of the application: https://www.youtube.com/watch?v=jjLT3pLLW-UConclusionsCoconut Surveillance Plus solves an absence of a real-time mobiledecision support disease surveillance and response system that can beused for Ebola and other infectious diseases in countries with limitedsurveillance infrastructure. More broadly, this system could also beused for many communicable diseases that require contact tracing andan urgent outbreak response in environments that require rapid scaleup of a distributed surveillance, rapid response, and case managementsystem.

Trajectory-based vehicle tracking at low frame rates

In smart cities, an intelligent traffic surveillance system plays a crucial role in reducing traffic jams and air pollution, thus improving the quality of life. An intelligent traffic surveillance should be able to detect and track multiple vehicles in real-time using only limited resources. Conventional tracking methods usually run at a high video-sampling rate, assuming that the same vehicles in successive frames are similar and move only slightly. However, in cost effective embedded surveillance systems (e.g., a distributed wireless network of smart cameras), video frame rates are typically low because of limited system resources. Therefore, conventional tracking methods perform poorly in embedded surveillance systems because of discontinuity of the moving vehicles in the captured recordings. In this study, we present a fast and light algorithm that is suitable for an embedded real-time visual surveillance system to detect effectively and track multiple moving vehicles whose appearance and/or position changes abruptly at a low frame rate. For effective tracking at low frame rates, we propose a new matching criterion based on greedy data association using appearance and position similarities between detections and trackers. To manage abrupt appearance changes, manifold learning is used to calculate appearance similarity. To manage abrupt changes in motion, the next probable centroid area of the tracker is predicted using trajectory information. The position similarity is then calculated based on the predicted next position and progress direction of the tracker. The proposed method demonstrates efficient tracking performance during rapid feature changes and is tested on an embedded platform (ARM with DSP-based system).

A Real-Time Implementation of Moving Object Action Recognition System Based on Motion Analysis

This paper proposes a PixelStreams-based FPGA implementation of a real-time system that can detect and recognize human activity using Handel-C. In the first part of our work, we propose a GUI programmed using Visual C++ to facilitate the implementation for novice users. Using this GUI, the user can program/erase the FPGA or change the parameters of different algorithms and filters. The second part of this work details the hardware implementation of a real-time video surveillance system on an FPGA, including all the stages, i.e., capture, processing, and display, using DK IDE. The targeted circuit is an XC2V1000 FPGA embedded on Agility’s RC200E board. The PixelStreams-based implementation was successfully realized and validated for real-time motion detection and recognition.

A Real-Time Implementation of Moving Object Action Recognition System Based on Motion Analysis

This paper proposes a PixelStreams-based FPGA implementation of a real-time system that can detect and recognize human activity using Handel-C. In the first part of our work, we propose a GUI programmed using Visual C++ to facilitate the implementation for novice users. Using this GUI, the user can program/erase the FPGA or change the parameters of different algorithms and filters. The second part of this work details the hardware implementation of a real-time video surveillance system on an FPGA, including all the stages, i.e., capture, processing, and display, using DK IDE. The targeted circuit is an XC2V1000 FPGA embedded on Agility’s RC200E board. The PixelStreams-based implementation was successfully realized and validated for real-time motion detection and recognition.

Motorcycles, Cell Phones, and Electricity Can Dramatically Change the Epidemiology of Infectious Disease in Africa.

AbstractSome observations and recent publications demonstrated, particularly in Africa, the potential influence that low-cost motorcycles, cell phones, and even widespread electrification could have on the evolution of infectious diseases, particularly zoonoses. Our reflections support the conclusion that we should focus on the real-time surveillance systems including alerting systems leading to a rapid and flexible response rather than the strongly limited modeling of infectious diseases because of the continuous evolution of microorganisms, as well as changes in the environment and human habits that are unpredictable.

Analysis of Reliability of Real Time Surveillance System

Reliability of real time surveillance system was analyzed and computed. The system tree was constructed. The relations between fault ratio and temperature of subassembly and element were also calculated. And their reliability was predicted and estimated. From the analysis, improvement methods were presented to optimize and consummate the real time surveillance system.

The analytics and applications on supporting big data framework in wireless surveillance networks

Nowadays, wireless sensor networks (WSNs) are based on techniques more and more oriented towards image, video and sound processing, hence the recent need of wireless multimedia sensor networks (WMSNs). One of the important challenges for real-time surveillance system is end-to end delay QoS for packet deliveries. Providing end-to-end QoS is difficult due to two reasons. As wireless sensor nodes may require multichip transmissions to reach the sink and some of the wireless transmissions may be not successful. Multimedia data are characterised by their large volume, and have strict requirements in terms of quality of service (QoS) such as bandwidth, delay, packet loss, delay jitter, etc. In this paper, we are interested in routing protocols based on clusters that aim to reduce congestion in order to have reliable data transmission and a reduced loss rate. This is achieved by balancing the traffic load, which results into a balanced energy consumption within the network.

Pertinence of electronic death certificates for real-time surveillance and alert, France, 2012–2014

ObjectivesIn France, the early mortality monitoring, conducted by Santé publique France, the French National Public Health agency (SpFrance) (formerly French Institute for public health surveillance-InVS), is based on the administrative data provided by the National Institute for Statistic and Economic Studies (INSEE) and consequently does not allow analyses on medical causes of death. Since 2007, the physicians can certify deaths electronically. In this electronic system (Electronic Death Registration System; EDRS), the medical causes of death, in free-text format, are directly transmitted to SpFrance. In the future, these data could be used in a real-time surveillance system by medical causes of death. The objective of this study was to evaluate the pertinence of e-death certification using the following assessment criteria: timeliness, representativeness, and completeness of sociodemographic and medical information included in the e-death certificates. Study designThis study consisted of a descriptive analysis of the information collected by e-death certificates recorded between January 1, 2012 and July 31, 2014. MethodsThe study quantified the temporal and geographical evolution of the deployment of the EDRS between 2012 and 2014. The timeliness of the system was estimated by calculating the delay between the dates of death and of data availability for analysis. Sociodemographic and death-related characteristics were described. The frequency of missing data was measured for each variable. The number of completed fields per certificate and the number of words per field and per certificate were calculated for the medical causes of death. ResultsBetween January 2012 and July 2014, 77,776 e-death certificates were collected. A slight increase in the use of the e-death certification was observed during the study period, reaching 6.1% of the total number of deaths in 2014. Good national coverage was noted. Nearly 79% of e-certificates were submitted to SpFrance on the day of the death. We observed a high completeness of the e-certificates. The rate of missing data did not exceed 2.7% for sociodemographic variables. On average, 10 words, distributed in three fields, were used to describe the medical causes of death. ConclusionsE-death certificates constitute a reactive source of information on medical causes of death. The deployment of EDRS is of major public health interest for the development of a real-time warning surveillance system of mortality by cause.

A Novel Real-Time Fall Detection System Based on Real-Time Video and Mobile Phones

In recent years, due to the growing population of the elderly, falls of elderly people have aroused wide public concern. Detecting timely falls of the elderly is significant to their safety. Numerous challenges exist in real-time fall detection systems because some features of normal human activities are greatly similar to the characteristics of falls. To address these problems, we propose a novel fall detection scheme and build a health-care system to detect falls of the elderly based on a real-time video surveillance system and a smart phone. The system contains two major modules. The first module is a feature extraction module. We adopt the Gaussian mixture model, tracking learning detecting algorithm and logpolar histogram to extract the characteristics of falls from the video surveillance system and the sensors embedded in mobile phones. The main purpose of the second module is to detect a fall-based on the features obtained in the first module. The experimental results show that every module is significant. Besides, our system is effective to separate falls from other similar actions such as bend down with an accuracy rate of more than 98% and performs better than other state-of-the-art fall detection systems.

Urban and Rural Differences of Acute Cardiovascular Disease Events: A Study from the Population-Based Real-Time Surveillance System in Zhejiang, China in 2012.

Zhejiang province, China, has implemented a population based, real-time surveillance system that tracks acute cardiovascular diseases (CVDs) events since 2001. This study aimed to describe the system and report CVD incidence, mortality and case-fatality between urban and rural areas in Zhejiang in 2012. The surveillance system employs a stratified random sampling method covering all permanent residents of 30 counties/districts in Zhejiang. Acute CVD events such as coronary heart disease (CHD) and stroke were defined, registered and reviewed based on the adapted MONICA (Monitoring Trends and Determinants in Cardiovascular Disease) definitions. Data were collected from health facilities, vital registries, supplementary surveys, and additional investigations, and were checked for data quality before input in the system. We calculated the rates and compared them by gender, age and region. In 2012, the incidence, mortality and case-fatality of total acute CVD events were 367.0 (CHD 59.1, stroke 307.9), 127.1 (CHD 43.3, stroke 83.8) per 100,000 and 34.6% (CHD 73.2%, stroke 27.2%), respectively. Compared with rural areas, urban areas reported higher incidence and mortality but lower case-fatality rates for CHD (P<0.001), while lower incidence but higher mortality and case-fatality rates for stroke (P<0.001). We found significant differences on CHD and stroke epidemics between urban and rural areas in Zhejiang. Special attentions need to be given to stroke control, especially in rural areas.

Electrical Power Budgeting Analysis for LSA-02 UAV Technology Demonstrator

This paper addresses the calculation of the LSA-02 UAV electrical power requirement as a technology demonstrator. To answer this issue, the method from ASTM F2490 Standard is used. By adopting that method, the condition of aircraft operation must be defined. Therefore, there are 2 aircraft conditions that will be investigated further. First, the LSA-02 aircraft will be fitted with EO/IR camera and support payload for conducting real-time surveillance system. The other condition is conducting the aerial photography mission to investigate the vegetation condition by equipping the aircraft with a multispectral camera. The results show that the real-time mission will need bigger electrical power requirement comparing to aerial photography mission. To support the mission without sacrificing the other electrical equipment for functioning, the onboard power generator system inside LSA-02 aircraft should be upgraded, at least with 3.5 kVA capacity.

Initial in vitro and in vivo evaluation of a self-monitoring prosthetic bypass graft

ObjectiveProsthetic grafts used for lower extremity revascularization and dialysis access fail because of hyperplastic stenosis and thrombosis. Graft surveillance is advocated to monitor function; however, graft failure can occur between episodic examinations. An innovative sensor with wireless, microchip technology allows automated surveillance with assessment of graft function using a “cloud”-based algorithm. We performed proof-of-concept experiments with in vitro and in vivo models to assess the feasibility such a real-time graft surveillance system. MethodsA self-monitoring graft system was evaluated consisting of a prosthetic conduit of expanded polytetrafluoroethylene and a sensor unit, and a microsensor, microelectronics, battery, and remote processor with a monitor. The sensor unit was integrated on the extraluminal surface of expanded polytetrafluoroethylene grafts without compromise to the lumen of the conduit. The grafts were tested in vitro in a pulsatile, recirculating flow system under physiologic flow parameters. The hemodynamic parameters were varied to assess the ability to obtain wireless signal acquisition reflecting real-time flow properties in vitro. Segments of custom tubing with reduced diameters were inserted into the model to mimic stenosis proximal and distal to the grafts. After characterization of the initial data, the self-monitoring grafts were implanted in an ovine carotid model to assess proof of concept in vivo with 30-day follow-up of signal acquisition as well as arteriographic and histologic analysis. ResultsIn vitro flow data demonstrated the device was able to determine factors related to prosthetic graft function under varied hemodynamic flow conditions. Wireless signal acquisition using Bluetooth technology (Bluetooth SIG, Inc, Kirkland, Wash) allowed remote data analysis reflecting graft flow parameters through changes in microsensor voltage and frequency. Waveform analysis was applied to construct an algorithm using proprietary software and determine a parameter for graft flow characteristics. This algorithm allowed determination of the degree of stenosis and location of stenosis location (proximal or distal) for display on a remote monitor in real time. Subsequent in vivo experiments confirmed the ability of the system to generate signal acquisition through skin and soft tissue under biologic conditions with no arteriographic stenosis and a favorable healing response at 30-day harvest. ConclusionsInitial in vitro and in vivo experiments demonstrate the ability for a self-monitoring graft system to remotely monitor hemodynamic parameters reflecting graft function using wireless data transmission. This automated system shows promise to deliver real-time data that can be analyzed by cloud-based algorithms alerting the clinician of a change in graft function or development of stenosis for further diagnostic study or intervention before graft failure.

Time-based feedback-control framework for real-time video surveillance systems with utilization control

Multi-camera surveillance systems generally are used by intelligent vision applications to analysis moving objects in the urban environments. Object tracking is an essential component of these applications. Real-time tracking of moving objects in the crowded urban scenes is a challenging problem because the number of moving objects in the scene varies and is usually unpredictable. In order to meet the real-time requirements of intelligent vision applications, it is necessary to control the surveillance workload over processing system and enforce the utilization bound on the system. The utilization control is challenging especially when the workload in the system is unpredictable. The workload for a particular camera depending on the number of targets in its view and execution rate of services that are used to detect and track the moving objects. In this paper, an adaptive real-time system based on the feedback-control framework is proposed to control the system utilization by adjusting input video frame rate that guarantees real-time performance and quality of intelligent vision applications. This approach can handle the workload uncertainties by identifying the parameters of system model online by solving an optimization problem and can simultaneously adjust the frame rate in each sampling period. In each sampling instance, the system utilization is monitored and the error is obtained by comparing it with the set point. The real-time operation of the computing system is achieved by adjusting the input video frame rate to keep the utilization at a given set point slightly below their schedulable bound. Evaluation results demonstrate proposed scheme outperforms the existing schemes especially under workload uncertainties.

Implementation of an integrated real-time process surveillance and diagnostic system for nuclear power plants

This paper presents two parts, real-time process surveillance unit and fault diagnosis unit, which are separated from each other. However, these units are connected by trigger-rules in a real-time expert system. The design structure that has been adopted is capable of inspecting errors and revising the model.Multilevel Flow Model (MFM), which is a method for functional modeling, is introduced briefly and illustrated with a reactor coolant system. Utilizing functional modeling method to represent system knowledge, this modeling method is especially useful when the domain experts are not available.Considering issues such as loop modeling and mutually exclusive events inevitably exist between the observation points, a novel modeling technology called observation points’ protection was used to build a generic fault model and preserve the statuses of observation points during reasoning within an expert system. This paper also presents minimal candidate and domains of interpretation, which are especially useful for finding the fundamental root cause when multiple faults occur.The process surveillance and diagnostic system is implemented on the platform of G2, which is an environment for developing real-time expert systems. The emulation test was conducted and it has been proven that the fault diagnosis expert system can identify the faults correctly and in a timely manner.

Normalized Metadata Generation for Human Retrieval Using Multiple Video Surveillance Cameras.

Since it is impossible for surveillance personnel to keep monitoring videos from a multiple camera-based surveillance system, an efficient technique is needed to help recognize important situations by retrieving the metadata of an object-of-interest. In a multiple camera-based surveillance system, an object detected in a camera has a different shape in another camera, which is a critical issue of wide-range, real-time surveillance systems. In order to address the problem, this paper presents an object retrieval method by extracting the normalized metadata of an object-of-interest from multiple, heterogeneous cameras. The proposed metadata generation algorithm consists of three steps: (i) generation of a three-dimensional (3D) human model; (ii) human object-based automatic scene calibration; and (iii) metadata generation. More specifically, an appropriately-generated 3D human model provides the foot-to-head direction information that is used as the input of the automatic calibration of each camera. The normalized object information is used to retrieve an object-of-interest in a wide-range, multiple-camera surveillance system in the form of metadata. Experimental results show that the 3D human model matches the ground truth, and automatic calibration-based normalization of metadata enables a successful retrieval and tracking of a human object in the multiple-camera video surveillance system.