Search

In this paper, we assume that a single pedestrian is a single blob, and define the representative properties of blobs to selection between merge and split of blobs. And we collect attribute information of the blob and make decision tree by using the ID3 algorithm. Next, we experimented for dividing the decision tree by directing the status of merge and split, as a result, it is possible to generate a pedestrian trajectory of the individual.

Surveillance system to improve safety and security is a major demand for the management and control of public area. Crowd management and control system requires a situation recognition technique which can predict accidents and provide alarms to the monitoring personnel. In this paper, we propose an abnormal behavior detection technique by using trajectory extraction of moving objects in video. Abnormal behavior includes running persons. The proposed abnormal behavior detection system separates background and foreground using Gaussian mixture model. And then, foreground image is used to generate the trajectories of moving objects using a Kanade-Lucas-Tomasi algorithm of the optical flow method. In addition, noise removal step is added to improve the accuracy of the created trajectory. From the trajectory of moving objects information, such as length, pixel, coordinate and moving degree is extracted. As the result of the estimation of abnormal behavior, objects' behavior is configured and analyzed based on a priori specified scenarios, such as running persons. In the results, proposed system is able to detect the abnormal behavior in public area.

There are nowadays strong demands for intelligent surveillance systems, which can infer or understand more complex behavior. The application of crowd density estimation methods could lead to a better understanding of crowd behavior, improved design of the built environment, and increased pedestrian safety. In this paper, we propose a new crowd density estimation method, which aims at estimating not only a moving crowd, but also a stationary crowd, using images captured from surveillance cameras situated in various public locations. The crowd density of the moving people is measured, based on the moving area during a specified time period. The moving area is defined as the area where the magnitude of the accumulated optical flow exceeds a predefined threshold. In contrast, the stationary crowd density is estimated from the coarseness of textures, under the assumption that each person can be regarded as a textural unit. A multilayer neural network is designed, to classify crowd density levels into 5 classes. Finally, the proposed method is experimented with PETS 2009 and the platform of Gangnam subway station image sequences.

With the development of electronic documents, plagiarism is rapidly increasing and, given the difficulty of manual detection, need for plagiarism detection systems to help protect intellectual property has emerged. Many content-based detection systems have been developed and are actually used in some foreign countries, but they are still insufficient for documents in Korean. In particular, the high variance of Hangul makes the development of detection systems more difficult. This study proposes a Hangul document detection method based on Ferret's trigrams. Ferret only considered the frequency of trigram matches as a way to detect similarity, but in this study the system is developed further by weighting results depending on the degree of trigram match, thereby improving the accuracy of similarity detection.

It is very important to prevent crimes, accidents, and incidents, so many surveillance systems are equipped in urban transit system. But in most current surveillance systems, supervisors have to monitor many screens continuously. Therefore, intelligent systems are needed by which those tedious monitoring tasks are done. These intelligent surveillance systems have two parts: image processing, context inference module. Because there are many uncertain events in urban transit, fuzzy inference engine is needed that efficiently handle these events and solve the problems that can occur in the dangerous situation. In this paper, we present a fuzzy framework that can efficiently detect dangerous situations in urban transit and classify the contexts according to their dangerous situation.

In metropolitan area, the use of analog CCTV surveillance system has steadily increased to detect and prevent crimes, terror, big persons and cars crowded in road that CCTV surveillance systems have long been employed in metropolitan area. It is necessary to equip intelligent surveillance systems, which provide an efficient solution for the problems because the cities become bigger than now in population. Therefore, a method that can efficiently measure crowd density is needed. We present an efficient method that estimates information of crowd movement by using the optical flow and the numbers of moving objects by using the numbers of edge pixels. Finally, we will classify the crowd density using the two estimated information according to five levels of crowd density.

Today, various types of sensors such as CCTV, temperature detector, CO2 detector, are widely used to prevent fire occurrence in public places. They are integrated into an intelligent surveillance system to monitor indication of fire and to alarm various levels of warning automatically. A fuzzy system is proper to solve the problem considering an ambiguous property of fire signs from various sensors. In this paper, we proposed a fuzzy rule-based method for the recognition of fire levels. We evaluated the performance with a prototype application.

In this paper we present a robust method for background subtraction from a fixed camera in video surveillance system. The background subtraction is an important part of object tracking and many algorithms have been proposed for decades. Mixture of Gaussian for those in this paper is very famous and used widely. We present the robust method that can adapt the background model to various situations. We have to detect not only moving objects but also stopped objects, but this detecting problem have not been solved in the previous research. To solve this problem, we present an efficient adaptive Mixture of Gaussian Model in urban transit. The parameter should be adapted in various situations. We train the model and get the adaptive parameter by using the time gap between moving and stopped objects. This model can be applied to the real-time application. We demonstrate and evaluate our proposed method with urban traffic sequences.

In this paper we present the improved Fast Time Series Evaluation(IFTSE) algorithm that can fast and efficiently track the objects in bad environment conditions. Object tracking in intelligent surveillance system is an important part to identify suspicious objects' behavior. But object tracking is exhaustive and time-consuming process and we cannot also efficiently search the trajectory of detected objects due to bad conditions (e.g. bad camera capacity, dust particles in the air, lighting changes). To demonstrate the performance of the proposed IFTSE algorithm for tracking the objects, we introduce evaluation metrics. A prototype tracking system that IFTSE algorithm is employed is implemented using Visual C++. We increase true positive rate by approximately 6% and reduce false alarm rate by approximately 2% and reduce id change by approximately 30%.

Multi-modal vibration control of the cantilevered laminated composite plates using collocated piezoceramic sensors/actuators is analyzed theoretically and verified experimentally for various fiber orientations. Impact on the stiffness and the damping properties by varying the stacking sequence of [04/02/902j, for the laminated composite plate is studied. The finite element method is used for the dynamic analysis of the plates with and without the piezoceramics. Natural frequencies and modal damping of the first bending and the first torsional modes are predicted theoretically by taking into account damping and stiffness of the adhesive layer and the piezoceramics in the modeling. Active modal damping of the first bending and the first torsional modes are measured experimentally. It is demonstrated that the active control is more effective for the structure with higher stiffness when the feedback gain is large, whereas it follows trends of the passive control by tailoring when the gain is small.

At present, a lot of information that is provided online is actually being plagiarized or illegally copied. Specifically, it is very tricky to identify some plagiarism from tremendous amount of information because the original sentences can be simply restructured or replaced with similar words, which would make them look different from original sentences. This means that managing and protecting the knowledge start to be regarded as important, though it is important to create the knowledge through the investment and efforts. This dissertation tries to suggest new method and theory that would be instrumental in effectively detecting any infringement on and plagiarism of intellectual property of others. Dynamic Incremental Comparison Method, a method which was developed by this research to detect plagiarism of document, focuses on realizing a system that can detect plagiarized documents and parts efficiently, accurately and immediately by creating positive and various detectors.

Vast amount of information is generated and shared in this active digital information society. Due to easy access to information in our digital society, there are many cases of illegal counterfeiting and usage of personal information. Producing information with investment and effort is important indeed, but managing and protecting information is becoming a furthermore important issue. This is to promote a new detecting theory and solution for cases of intellectual property violations and plagiarizing digital contents. The document duplication method developed by this research is DICOM (dynamic incremental comparison method) is highly active. It targets on producing various detectors to embody a system to expeditiously and effectively detect duplicated documents and parts.

Documents saved in digital libraries have high value as public documents or for commercial use. So, appropriate client authentication and copyright protection systems should be prepared. That is because more and more information is being digitized, as information processing equipment are rapidly progressing, the necessity of security on various kinds of facilities, digital libraries and communications is becoming an important issue. In this study, DLFAS (digital library fingerprint authentication system) is designed and actualized, based on online RTFRM (real-time fingerprint recognition mechanism), centering on fingerprint authentication technology that is decided to be more stable, convenient and credible than password authentication in client identification and authentication using physical characteristics of human. DLFAS that is suggested in this study provides high-quality service effectively in a more stable and convenient environment to authorized clients by solving the weak points and inconvenience of passwords and suggests the model of DLDCPS (digital library digital content protection system) that can prevent unauthorized illegal clients from accessing protected content.

This paper describes a pipeline by which facial expression of the face is recognized and then 3-D facial animation is synthesized in the remote place based upon timing information of the facial. The system first detects a facial area within the given image and then classifies its facial expression into 7 emotional weightings. Such weighting information, transmitted to the PDA via a mobile network, is used for non-photorealistic facial expression animation. A cartoon-like shading is used to render a 3-D avatar that conveys a familiar and yet unique facial character, even without employing extensive polygons. It turns out that facial expression animation using emotional curves is more effective in expressing the timing of an expression comparing to the linear interpolation method. The emotional avatar embedded on a mobile platform has some potential in conveying emotion between peoples in Internet.

A model for the long-term software technology plan that we applied for Korean National Information Infrastructure as reviewed in this paper. Analysis and assumption on technology trends for twenty-year time frame are attempted, and application service requirements for public, economic and socio-cultural domains are identified. Based on the service requirements and technological environments of the future information society, we have categorized core sets of software technology, and have structured those technology sets into a technology tree. In the actual plan of SOFTECH 2015, each component of the technology tree was broken down into technical specifications to be utilized as inputs for the national plan of software R&D. We recognize that software technology life-cycle is becoming shorter, and many say that the life-cycle is less than one year. However, under many uncertainties, long-term plans are still required in, many instances.

With the advent of information technology, it is only a matter of time that more and more of digital transactions will be made via the Internet. This increased popularity of the digital transactions has required more efficient protection schemes such as digital rights management system (DRM). DRM protects digital contents, returns profits generated from the contents use to the digital rights providers (DRPs). And it also helps DRPs' gold rush into a new market. This paper introduces a model that contains DRM, and verification methods using applied one-way functional analysis and fingerprinting which is characterized by its immutability and individuality. This model is designed to distinguish clients from unauthorized users, so that only valid users can have access to the digital contents. To sort out unauthorized users, fingerprints recognition mechanism (FRM) is adopted, rather than conventional passwords. The advantages of using FRM surpass the advantages of using passwords. We hope FRMs reliable feature will allow a better digital environment for contents design, distribution and implementation.

This paper compares two clustering methods: SOM, and a graph-based clustering technique , for text-independent speaker verification. The focus of comparison is given to the distribution characteristics of representative frames for each cluster, to the use of processing time of clustering and MLP learning, and to verification performance. Simulation results show that the graph-based technique produces better verification performance than SOM. Other statistics are collected to explain significant difference in MLP learning time with each clustering method. This experiment suggests that there is a best match between a classifier and a clustering method for a given application.

This work addresses the data balancing problem of the existing neural network based speaker verification methods, and proposes new method using modular neural network. In this method, each expert network is trained with the balanced number of genuine speaker data and imposter speaker data. In our experiments, we obtained high performance results for the unknown imposter speakers. High performance and the modular nature of the proposed method enables building a large scalable speaker verification system.

Multi-modal vibration control of laminated composite plates using collocated piezoelectric sensor/actuator is analyzed theoretically and verified experimentally for various fiber orientations. The modal damping (2(zetz) (omega) ) is chosen as a performance index rather than the damping ratio ((zetz) ) for the vibration suppression in the structure. The active modal dampings of the first bending and the first torsional modes are measured experimentally and are in good agreement with those of finite element analysis.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.