|Title: Comparative Study: The Evaluation of Shadow Detection Methods|
|Author(s): Habib Ullah, Mohib Ullah, Muhammad Uzair, Fasih ur Rehman|
|Pages: 1-6||Paper ID: 100302-5757-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Shadow detection is critical for robust and reliable video surveillance systems. In the presence of shadow, the performance of the video surveillance system degrades. If objects are merged together due to shadow then tracking and counting cannot be performed accurately. Many shadow detection methods have been developed for indoor and outdoor environments with different illumination conditions. Mainly shadow detection methods can be partitioned in three categories. This work performs comparative study for three representative works of shadow detection methods each one selected from different category: the first one based on intensity information, the second one based on photometric invariants information, and the last one uses color and statistical information to detect shadow. In this paper, we discuss these shadow detection approaches and compare them critically. The comparison of three methods is performed using different performance metrics. From experiments, the method based on photometric invariants information showed superior performance comparing to other two methods. It combines color and texture features with spatial and temporal consistencies proving it excellent features for shadow detection.
|Keywords: Shadow Detection, Video Surveillance System|
|Full Text (.pdf) | 263 KB|
|Title: A Hybrid Method for Extracting Key Terms of Text Documents|
|Author(s): Ahmad Ali Al-Zubi|
|Pages: 7-11||Paper ID: 100902-3737-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Key terms are important terms in the document, which can give high-level description of contents for the reader. Extracting key terms is a basic step for many problems in natural language processing, such as document classification, clustering documents, text summarization and output the general subject of the document. This article proposed a new method for extracting key terms from text documents. As an important feature of this method, we note the fact that the result of its work is a group of key terms, with terms from each group are semantically related by one of the main subjects of the document. Our proposed method is based on a combination of the following two techniques: a measure of semantic proximity of terms, calculated based on the knowledge base of Wikipedia and an algorithm for detecting communities in networks. One of the advantages of our proposed method is no need for preliminary learning, because the method works with the knowledge base of Wikipedia. Experimental evaluation of the method showed that it extracts key terms with high accuracy and completeness.
|Keywords: Extraction Method, Key Term, Semantic Graph, Text Document.|
|Full Text (.pdf) | 146 KB|
|Title: Low Cost Telesonography Model for DDH Exam|
|Author(s): Dobrivoje Martinov, Zoran Ignjatov, Dragan Markovic|
|Pages: 12-18||Paper ID: 105602-0909-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Telemedicine holds important place and has wider use in health care practice and improvement of health organization, above all providing the opportunity for standard and innovative procedures to combine. Tremendous increase in Internet bandwidth enabled a true revolution in image transmission and enabled easy remote viewing of the static images. However, transmission of real time video streams such as in ultrasound has been underreported. Here, we tested feasibility of the low-cost teleultrasound system for developmental dysplasia of the hip (DDH) screening and diagnostic values of the transmitted images and video data in real time. Sending of data was accomplished with a software package specifically designed for teleultrasound transmission through limited Internet bandwidth. Using Remote Ultrasound (RU) software in conjunction with a hardware setup and low bandwidth Internet link, we performed sonographic DDH screening exams in real time. In addition to continuous monitoring of the exam via video stream, RU enables remotely controlled recording and selection of still images on a sending and a receiving computer. Qualitative analysis of 50 transmitted ultrasound images and all video streaming during each exam, were performed. Teleultrasound screening through the Internet connection of low transmission power with the software application, provides ultrasound image and video stream, which is the base for further clinical investigation and clinical application of this model.
|Keywords: Teleultrasound, low cost, developmental dysplasia of the hip, medical diagnosis, imaging transmission, image analysis, video reviews, medical imaging, medical treatment.|
|Full Text (.pdf) | 432 KB|
|Title: 2D Beamforming for Through-the-Wall Microwave Imaging Applications|
|Author(s): Aamna M., Ammar S., Rameez T., Shabeeb S., Naveed I. Rao, Safwat. I|
|Pages: 19-24||Paper ID: 107102-6363-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Recently, microwave imaging has received a considerable amount of interest with respect to other imag-ing techniques. A large number of studies  rely on mi-crowaves, as a powerful electromagnetic tool to retrieve physical and electrical properties of penetrable and impen-etrable objects. The capability of microwave signals to pen-etrate light opaque materials and sense distant or inacces-sible objects with reasonable spatial resolution makes them attractive for dierent industrial, civil and medical applica-tions. Our Through-the-Wall Microwave Imaging (TWMI) radar system facilitates us to detect and localize objects be-hind the wall. Measurements with mono-static radar con-guration are made with various sizes of metallic materials inside the room with wooden wall (of known thickness and dielectric constant) using 2D antenna positioning assembly and scattering data is recorded in frequency domain. The simple and fast algorithm for compensation of dierent wave velocity inside the wall is used and the measured raw data is processed with 2D SAR Beamforming algorithm in time domain to reconstruct the image of the targets behind wall. This paper provides an overview of the basic concepts, foun-dation prototype system of TWMI, SAR Beamforming algo-rithm and Comparison of Various matched lter approaches and their eects on quality of image are elaborated in detail.
|Keywords: Beamforming, Microwave Imaging|
|Full Text (.pdf) | 432 KB|
|Title: A Novel Framework for Real Time Object Tracking Systems|
|Author(s): Sanketh Datla, Abhinav Agarwal, Rajdeep Niyogi, Barjeev Tyagi|
|Pages: 25-30||Paper ID: 109402-6363-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Object tracking is fundamental to automated video surveillance, activity analysis and event recognition . In real-time applications only a small percentage of the system resources can be allocated for tracking, the rest being required for high-level tasks such as recognition, trajectory interpretation, and reasoning. There is a desperate need to carefully optimize the tracking algorithm to keep the computational complexity of a tracker as low as possible yet maintaining its robustness and accuracy. This paper proposes a novel framework which attempts to attain a light weight tracking system by reducing undesirable and redundant computations. The frames of the video are passed through a preprocessing stage which transmits only motion detected blocks to the tracking algorithm. Further frames containing little motion in the search area of the target object are detected in preprocessing stage itself and are blocked from further processing. Our experimental results demonstrate that the throughput of the new proposed tracking system is exceptionally higher than the traditional one.
|Keywords: Video Surveillance, Object Tracking, Appearance models, Block Cluster, Performance.|
|Full Text (.pdf) | 400 KB|
|Title: Event Triggering With Crisp Set Using Images of Surveillance Systems|
|Author(s): Vijanth S. Asirvadam, Altahir A. Altahir, Patrick Sebastian|
|Pages: 31-36||Paper ID: 1010102-6767-IJVIPNS-IJENS||Published: April, 2010|
Abstract: Observing moving objects using far field’s video surveillance is core areas of research in computer vision. Similar application also can be found in surveillance systems and traffic monitoring applications. This paper presents implementing of crisp set technique on video images in order to evaluate moving objects in far field’s surveillance systems. One main objective is to create an event trigger if the scene is active. The concept is based on extracting two powerful attributes from moving objects, namely velocity and pixel frequency distribution. Combining the two measurements mentioned using crisp set rules in order to evaluate the active section in the image plane. The experimental results proved the efficiency of the technique.
|Keywords: Surveillance System, Image Processing.|
|Full Text (.pdf) | 400 KB|
|Title: Content-Based Video Browsing by Text Region Localization and Classification|
|Author(s): Bassem Bouaziz, Walid Mahdi. Tarek Zlitni, Abdelmajid ben Hamadou|
|Pages: 37-47||Paper ID: 109101-2-2727-IJVIPNS-IJENS||Published: April, 2010|
Abstract: The amount of digital video data is increasing over the world. It highlights the need for efficient algorithms that can index, retrieve and browse this data by content. This can be achieved by identifying semantic description captured automatically from video structure. Among these descriptions, text within video is considered as rich features that enable a good way for video indexing and browsing. Unlike most video text detection and extraction methods that treat video sequences as collections of still images, we propose in this paper spatiotemporal video-text localization and identification approach which proceeds in two main steps: text region localization and text region classification. In the first step we detect the significant appearance of the new objects in a frame by a split and merge processes applied on binarized edge frame pair differences. Detected objects are, a priori, considered as text. They are then filtered according to both local contrast variation and texture criteria in order to get the effective ones. The resulted text regions are classified based on a visual grammar descriptor containing a set of semantic text class regions characterized by visual features. A visual table of content is then generated based on extracted text regions occurring within video sequence enriched by a semantic identification. The experimentation performed on a variety of video sequences shows the efficiency of our approach.
|Keywords: Visual index, video structuring, non-linear video browsing, text localization, text extraction, spatiotemporal features, region filtering.|
|Full Text (.pdf) | 891 KB|