Automated Surveillance System Research Articles

Shadow elimination and vehicles classification approaches in traffic video surveillance context

Video surveillance on highway is a hot topic and a great challenge in Intelligent Transportation Systems. In such applications requiring objects extraction, cast shadows induce shape distortions and object fusions interfering performance of high level algorithms. Shadow elimination allows to improve the performances of video object extraction, classification and tracking. In other hand, it is very important to recognize the type of a detected object in order to track reliably and estimate traffic parameters correctly. This paper presents two approaches to enhance automatic traffic surveillance systems. The first deals with the elimination of shadows and the second concerns the classification of vehicles, based on robust vision and image processing. For moving shadow elimination, a contrast model is proposed to describe and remove dynamic shadows based on the idea that a shadow transformation is a change in contrast. For vehicles classification, Hu moments are calculated in a manner to reduce the perspective effects and used to describe vehicles in knowledge base. Experimental results on the various challenging video sequences show that the proposed approach outperforms classification methods of related works (with a classification accuracy of 96.96%), and that the shadow elimination approach performs better than compared works (with detection rate of 95–99% and discrimination rate of 85.7–89%).

High Frequency Manipulation at Futures Expiry: The Case of Cash Settled Indian Single Stock Futures

Futures markets are known to be vulnerable to manipulation, and despite the presence of a variety of mechanisms to prevent such manipulation, instances of market manipulation have been found in some of the largest and most liquid futures markets worldwide. In 2013, the Securities and Exchange Board of India identified a case of alleged manipulation (in September 2012) of the settlement price of cash settled single stock futures based on high frequency circular trading. As is well known, it is easy for any well-endowed manipulator to manipulate the price; the real challenge for the manipulator is to make the manipulation profitable. The use of high frequency circular trading of the form alleged in the SEBI order makes many forms of manipulation profitable, and makes futures market manipulation a much bigger problem than previously thought. As argued by Pirrong (2004), it is more practical to detect and punish manipulation than to try and prevent it. We develop an econometric technique that uses high frequency data and which can be integrated with the automated surveillance system to identify suspected cases of high frequency manipulation at futures expiry. We then use these techniques to identify a few suspected cases of manipulation. Needless to say, human judgement needs to be applied to decide which, if any, of these cases need to be taken up for investigation (and, after that, possible prosecution). This judgement is beyond the scope of our paper, and we refrain from making any judgement on whether any of the identified cases constitutes actual market manipulation.

Sparse frontal face image synthesis from an arbitrary profile image

Frontal face image synthesis from an arbitrary profile image plays an important role in automatic video surveillance systems, and remains a challenge in computer vision. The strategies of partition are popular and promising for synthesizing frontal face images. However, conventional rectangular partition criterions fail to align corresponding patches in profile images and frontal face images. Given an arbitrary profile image, to synthesize a corresponding frontal face image which is smooth in texture and similar in appearance, we introduce a triangulation-based partition criterion and do synthesis based on sparse representation. The triangulation-based partition ensures the corresponding triangular patches are strictly aligned. And sparse representation adaptively finds the most similar patches for synthesis while abandons unlike patches. Furthermore, a confederate learning strategy is proposed to reduce the blocking artifacts caused by triangulation-based partition. Experimental results conducted on the Oriental Face database demonstrate the effectiveness of the proposed frontal face image synthesis method and advantages over previous works.

지능형 감시를 위한 객체추출 및 추적시스템 설계 및 구현

The agents for security surveillance are not enough for monitoring CCTV system, so the intelligent automatic surveillance system is needed. In this paper, object detection, tracking and abnormal event detection system is implemented for intelligent CCTV system. Each modules are tested on the real CCTV environment and promoted for commercialization. Abnormal event detection module and loitering detection and sudden running detection function and it`s detection time is under 1 second which is satisfied level.

Finite asymmetric generalized Gaussian mixture models learning for infrared object detection

The interest in automatic surveillance and monitoring systems has been growing over the last years due to increasing demands for security and law enforcement applications. Although, automatic surveillance systems have reached a significant level of maturity with some practical success, it still remains a challenging problem due to large variation in illumination conditions. Recognition based only on the visual spectrum remains limited in uncontrolled operating environments such as outdoor situations and low illumination conditions. In the last years, as a result of the development of low-cost infrared cameras, night vision systems have gained more and more interest, making infrared (IR) imagery as a viable alternative to visible imaging in the search for a robust and practical identification system. Recently, some researchers have proposed the fusion of data recorded by an IR sensor and a visible camera in order to produce information otherwise not obtainable by viewing the sensor outputs separately. In this article, we propose the application of finite mixtures of multidimensional asymmetric generalized Gaussian distributions for different challenging tasks involving IR images. The advantage of the considered model is that it has the required flexibility to fit different shapes of observed non-Gaussian and asymmetric data. In particular, we present a highly efficient expectation–maximization (EM) algorithm, based on minimum message length (MML) formulation, for the unsupervised learning of the proposed model’s parameters. In addition, we study its performance in two interesting applications namely pedestrian detection and multiple target tracking. Furthermore, we examine whether fusion of visual and thermal images can increase the overall performance of surveillance systems.

Exploring trace transform for robust human action recognition

Machine based human action recognition has become very popular in the last decade. Automatic unattended surveillance systems, interactive video games, machine learning and robotics are only few of the areas that involve human action recognition. This paper examines the capability of a known transform, the so-called Trace, for human action recognition and proposes two new feature extraction methods based on the specific transform. The first method extracts Trace transforms from binarized silhouettes, representing different stages of a single action period. A final history template composed from the above transforms, represents the whole sequence containing much of the valuable spatio-temporal information contained in a human action. The second, involves Trace for the construction of a set of invariant features that represent the action sequence and can cope with variations usually appeared in video capturing. The specific method takes advantage of the natural specifications of the Trace transform, to produce noise robust features that are invariant to translation, rotation, scaling and are effective, simple and fast to create. Classification experiments performed on two well known and challenging action datasets (KTH and Weizmann) using Radial Basis Function (RBF) Kernel SVM provided very competitive results indicating the potentials of the proposed techniques.

Abnormal Crowd Motion Detection with Hidden Markov Model

stations,etc. With the increasing demand of surveillance of various human activities, an efficient automated surveillance system to detect anomalies has become important. There is a survey on visual surveillance in [1], and a lot of problems have not resolved in surveillance applications nowadays as discussed in some papers [2]. Crowd feature extraction and crowd modeling are two important approaches of crowd analysis in Video surveillance. Most detection methods use motion features such as image gradient, texture information, optical flow, or spatial-temporal volume characteristics [3-4]. These features allow us to analyze dense crowds using characteristics of a crowd rather than individuals. Some works in the analysis of crowds usually assume that individuals can be tracked and identified in the crowd [5]. For example, the method proposed in [6] combines the inter-images difference based on entropy image and optical flow computed by a local method with a hierarchical coarse-to-fine optical flow estimation, and this method has a big computation load. Once motion features are extracted, another approach is to model them to represent normal motion behaviors. Abnormal crowd motion is defined as a sudden change or irregularity in a crowd motion. Suppose there exists a mathematical model describing the normal behaviors in the crowd videos, anomaly detection is done by modeling normal behaviors, and a crowd behavior is declared as anomaly if its characteristic does not comply with the learning model. Many approaches use parametric models, however, in parametric approach the data characteristics have to be approximated with a standard distribution and in many cases such approximations do not work well. In [7], Social Force model is used to detect and localize abnormal behaviors in crowd videos by Mehran et al. Their result shows the approach has a better performance than similar approach based on pure optical flow. Andrade et al. [8] combined spectral clustering, Principal Components Analysis (PCA) and Hidden Markov Model (HMM) to detect the crowd emergency scenarios, but the eigenvectors obtained by dimensionality reduction with PCA on the optical flow fields can not adequately reflect the motion, and this approach was only tested in simulated data. Our approach derives variations of motion patterns though direction distribution of the crowd motion obtained by optical flow and these variations are encoded with HMM Abnormal Crowd Motion Detection with Hidden Markov Model Dongping Zhang, Yafei Lu, Xinghao Jiang, Huailiang Peng

Special section on image and video processing for security

Research on personal and public information security has been of great emphasis in recent years. The ubiquitous availability of digital cameras, ranging from surveillance systems to mobile phones, makes image and video contents as predominant form of information used for the analysis in security applications. Video surveillance is the most common way to monitor and enhance the security at strategic locations. Automated surveillance systems, which replace the current manual surveillance, require efficient pattern recognition for object detection, tracking, and suspicious activity identification. Another way of enforcing security, especially at immigration and check points, is identification of people based on the physical appearance or behavioral characteristics. New imageand video-based biometrics are evolved over the years to improve the accuracy of identification for strengthening the security. When visual data is abundant, their reliability will be questioned due to the ease in counterfeiting the content. Digital image/video forensics is an emerging research field which aims at validating the authenticity of images by detecting traces of forgeries. Furthermore, secure transmission of images and video over network without tampering is achieved through cryptography and steganography. These are widely used techniques that manipulate data by encrypting or hiding information.

Integration of multispectral face recognition and multi-PTZ camera automated surveillance for security applications

Abstract Due to increasing security concerns, a complete security system should consist of two major components, a computer-based face-recognition system and a real-time automated video surveillance system. A computerbased face-recognition system can be used in gate access control for identity authentication. In recent studies, multispectral imaging and fusion of multispectral narrow-band images in the visible spectrum have been employed and proven to enhance the recognition performance over conventional broad-band images, especially when the illumination changes. Thus, we present an automated method that specifies the optimal spectral ranges under the given illumination. Experimental results verify the consistent performance of our algorithm via the observation that an identical set of spectral band images is selected under all tested conditions. Our discovery can be practically used for a new customized sensor design associated with given illuminations for an improved face recognition performance over conventional broad-band images. In addition, once a person is authorized to enter a restricted area, we still need to continuously monitor his/her activities for the sake of security. Because pantilt-zoom (PTZ) cameras are capable of covering a panoramic area and maintaining high resolution imagery for real-time behavior understanding, researches in automated surveillance systems with multiple PTZ cameras have become increasingly important. Most existing algorithms require the prior knowledge of intrinsic parameters of the PTZ camera to infer the relative positioning and orientation among multiple PTZ cameras. To overcome this limitation, we propose a novel mapping algorithm that derives the relative positioning and orientation between two PTZ cameras based on a unified polynomial model. This reduces the dependence on the knowledge of intrinsic parameters of PTZ camera and relative positions. Experimental results demonstrate that our proposed algorithm presents substantially reduced computational complexity and improved flexibility at the cost of slightly decreased pixel accuracy as compared to Chen and Wang’s method [18].

Adaptation of GUARDIAN for Syndromic Surveillance During the NATO Summit

During the NATO summit, the local health department was charged with collecting and analyzing syndromic surveillance data from emergency department (ED) visits that may indicate a man-made or naturally occurring infectious disease threat. GUARDIAN, an automated surveillance system, was programmed to conduct ED syndromic surveillance during the NATO summit. The automated GUARDIAN surveillance reports not only provided timely counts of potentially positive cases for each syndrome but also provided trend analysis with baseline measures.

Spatial Calibration of a Dual PTZ‐Fixed Camera System for Tracking Moving Objects in Video

A dual camera setup is proposed, consisting of a fixed (stationary) camera and a pan‐tilt‐zoom (PTZ) camera, employed in an automatic video surveillance system. The PTZ camera is zoomed in on a selected point in the fixed camera view and it may automatically track a moving object. For this purpose, two camera spatial calibration procedures are proposed. The PTZ camera is calibrated in relation to the fixed camera image, using interpolated look-up tables for pan and tilt values. For the calibration of the fixed camera, an extension of the Tsai algorithm is proposed, based only on measurements of distances between calibration points. This procedure reduces the time needed to obtain the calibration set and improves calibration accuracy. An algorithm for calculating PTZ values required for tracking of a moving object with the PTZ camera is also presented. The performance of the proposed algorithms is evaluated using the measured data.

Effectiveness of an automated surveillance system for intensive care unit-acquired infections

This study assessed the effectiveness of a fully automated surveillance system for the detection of healthcare-associated infections (HCAIs) in intensive care units. Manual ward surveillance (MS) and electronic surveillance (ES) were performed for two intensive care units of the Vienna General Hospital. All patients admitted for a period longer than 48 h between 13 November 2006 and 7 February 2007 were evaluated according to HELICS-defined rules for HCAI. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and personnel time spent per surveillance type were calculated. Ninety-three patient admissions were observed, whereby 30 HCAI episodes were taken as a reference standard. Results with MS versus ES were: sensitivity 40% versus 87%, specificity 94% versus 99%, PPV 71% versus 96%, NPV 80% versus 95%, and time spent per surveillance type 82.5 h versus 12.5 h. In conclusion, ES was found to be more effective than MS while consuming fewer personnel resources.

Biosurveillance in Outbreak Investigations

Following the terrorist attacks of September 11 and the anthrax attacks in 2001, public health entities implemented automated surveillance systems based on disease syndromes for early detection of bioterror events and to increase timeliness of responses. Despite widespread adoption, syndromic surveillance systems' ability to provide early notification of outbreaks is unproven, and there is little documentation on their role in outbreak response. We hypothesized that biosurveillance is used in practice to augment classical outbreak investigations, and we used case studies conducted in 2007-08 to determine (1) which steps in outbreak investigations were best served by biosurveillance, and (2) which steps presented the greatest opportunities for improvement. The systems used in the case studies varied in how they functioned, and there were examples in which syndromic systems had identified outbreaks before other methods. Biosurveillance was used successfully for all steps of outbreak investigations. Key advantages of syndromic systems were sensitivity, timeliness, and flexibility and as a source of data for situational awareness. Limitations of biosurveillance were a lack of specificity, reliance on chief complaint data, and a lack of formal training for users. Linking syndromic data to triage notes and medical chart data would substantially increase the value of biosurveillance in the conduct of outbreak investigations and reduce the burden on health department staff.

Region Filter and Optical Flow based Video Surveillance System

the last few years different video-surveillance systems have been developed based on video processing and using different techniques. This surveillance system generally seeks to track people (and/or vehicles) moving through a scene, to classify the behaviors of each track, and to identify whether these behaviors can be considered normal or abnormal. All Automated surveillance systems require some mechanism to detect interested objects in the field of view of the sensor. Once objects are detected, the further processing for tracking. In my paper a method is described for tracking moving objects from a sequence of video frame. This method is implemented by using optical flow (Horn-Schunck) and Region filtering in matlab simulink. The objective of this paper is to identify and track a moving object within a video sequence for both Abrupt change video as well as Gradual change video in video surveillance.

Pedestrian Detection Based on Blob Motion Statistics

Pedestrian detection based on video analysis is a key functionality in automated surveillance systems. In this paper, we present efficient detection metrics that consider the fact that human movement presents distinctive motion patterns. Contrary to several methods that perform an intrablob analysis based on motion masks, we approach the problem without necessarily considering the periodic pixel motion inside the blob. As such, we do not analyze periodicity in the pixel luminances, but in the motion statistics of the tracked blob as a whole. For this, we propose the use of the following cues: 1) a cyclic behavior in the blob trajectory, and 2) an in-phase relationship between the change in blob size and position. In addition, we also exploit the relationship between blob size and vertical position, assuming that the camera is positioned sufficiently high. If the homography between the camera and the ground is known, the features are normalized by transforming the blob size to the real person size. For improved performance, we combine these features using the Bayes classifier. We also present a theoretical statistical analysis to evaluate the system performance in the presence of noise. We perform online experiments in a real industrial scenario and also with videos from well-known databases. The results illustrate the applicability of the proposed features.

Testing of an automatic outdoor gamma ambient dose-rate surveillance system in Tokyo and its calibration using measured deposition after the Fukushima nuclear accident

An in-situ fixed point radioactivity surveillance network has been developed at the Radiation Protection Bureau, Health Canada. The network consists of a number of spectrometric NaI(Tl) detectors measuring, in real-time, ambient gamma dose-rate. The present paper describes the gamma dose-rate monitoring by one detector installed at the Canadian embassy in Tokyo during the Fukushima nuclear accident. Soil samples were collected for the measurement of fallout fission products inventories at each location where the NaI(Tl) detector was installed. The gamma-ray attenuation by the soil matrix was estimated by the information on the depth distribution of 137Cs activities. The study demonstrated that the gamma dose-rates measured by the field NaI(Tl) spectrometric method agreed well with the laboratory results estimated by the inventories of fallout fission products deposited in the soil and the vertical distribution of 137Cs in the soil.

Automated Surveillance System and Data Communication

Automated video surveillance systems plays vital role in the business areas , military system and etc . Many research areas in video surveillance system is mainly focuses on algorithms to evaluate background subtraction system and alert to the system, to repeatedly detect major actions For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. In background comparison if the difference in the values reaches the threshold value then user can get alert message. So whenever user getting SMS from server system and the background image is updated whenever the system is detecting a motion.

Multi-modal user identification and object recognition surveillance system

We propose an automatic surveillance system for user identification and object recognition based on multi-modal RGB-Depth data analysis. We model a RGBD environment learning a pixel-based background Gaussian distribution. Then, user and object candidate regions are detected and recognized using robust statistical approaches. The system robustly recognizes users and updates the system in an online way, identifying and detecting new actors in the scene. Moreover, segmented objects are described, matched, recognized, and updated online using view-point 3D descriptions, being robust to partial occlusions and local 3D viewpoint rotations. Finally, the system saves the historic of user–object assignments, being specially useful for surveillance scenarios. The system has been evaluated on a novel data set containing different indoor/outdoor scenarios, objects, and users, showing accurate recognition and better performance than standard state-of-the-art approaches.

Semi-automated CCTV surveillance: The effects of system confidence, system accuracy and task complexity on operator vigilance, reliance and workload

Recent advances in computer vision technology have lead to the development of various automatic surveillance systems, however their effectiveness is adversely affected by many factors and they are not completely reliable. This study investigated the potential of a semi-automated surveillance system to reduce CCTV operator workload in both detection and tracking activities. A further focus of interest was the degree of user reliance on the automated system. A simulated prototype was developed which mimicked an automated system that provided different levels of system confidence information. Dependent variable measures were taken for secondary task performance, reliance and subjective workload. When the automatic component of a semi-automatic CCTV surveillance system provided reliable system confidence information to operators, workload significantly decreased and spare mental capacity significantly increased. Providing feedback about system confidence and accuracy appears to be one important way of making the status of the automated component of the surveillance system more ‘visible’ to users and hence more effective to use.

Communities, boundary practices and incentives for knowledge sharing?

Abstract In recent decades, the idea of learning as embedded within communities of practice has inspired research and practice in many areas, among others in the context of workplace learning. In the present study, the collaboration between members of two different communities of practice representing different economies of meaning, technicians and foundry workers, has been studied in the context of the deployment of an automatic control and surveillance system in a process industry. The collaboration has been analyzed as a boundary practice and documented through ethnographic methods including video recordings. The results indicate that the negotiation of meaning – i. e. the site of learning in the social practice approach – between (and within) the communities is restricted and instrumental to running the system only; the workers learned very little about the system or its affordances. It is argued that, in a world of competitive business incentives for sharing knowledge, it will often be limited. Even though the concept of communities of practice is an important heuristic for understanding learning, the manner in which communities promote learning is contingent on local circumstances.