Browsing by Subject "Multimedia systems."

Now showing 1 - 10 of 10

Open Access
Automatic detection of salient objects for a video database system
(2005) Sevilmiş, Tarkan
Recently, the increase in the amount of multimedia data has unleashed the development of storage techniques. Multimedia databases is one of the most popular of these techniques because of its scalability and ability to be queried by the media features. One downside of these databases is the necessity for processing of the media for feature extraction prior to storage and querying. Ever growing pile of media makes this processing harder to be completed manually. This is the case with BilVideo Video Database System, as well. Improvements on computer vision techniques for object detection and tracking have made automation of this tedious manual task possible. In this thesis, we propose a tool for the automatic detection of objects of interest and deriving spatio-temporal relations between them in video frames. The proposed framework covers the scalable architecture for video processing and the stages for cut detection, object detection and tracking. We use color histograms for cut detection. Based on detected shots, the system detects salient objects in the scene, by making use of color regions and camera focus estimation. Then, the detected objects are tracked based on their location, shape and estimated speed.
Open Access
Bandwidth-aware and energy-efficient stream multicasting protocols for wireless multimedia sensor networks
(2010) Yargıçoğlu, Burcu
In recent years, the interest in wireless sensor networks has grown and resulted in the integration of low-power wireless technologies with cameras and microphones enabling video and audio transport through a sensor network besides transporting low-rate environmental measurement-data. These sensor networks are called wireless multimedia sensor networks (WMSN) and are still constrained in terms of battery, memory and achievable data rate. Hence, delivering multimedia content in such an environment has become a new research challenge. Depending on the application, content may need to be delivered to a single destination (unicast) or multiple destinations (multicast). In this work, we consider the problem of e ciently and e ectively delivering a multimedia stream to multiple destinations, i.e. the multimedia multicasting problem, in wireless sensor networks. Existing multicasting solutions for wireless sensor networks provide energy e ciency for low-bandwidth and delay-tolerant data. The aim of this work is to provide a framework that will enable multicasting of relatively highrate and long-durational multimedia streams while trying to meet the desired quality-of-service requirements. To provide the desired bandwidth to a multicast stream, our framework tries to discover, select and use multicasting paths that go through uncongested nodes and in this way have enough bandwidth, while also considering energy e ciency in the sensor network. As part of our framework, we propose a multicasting scheme, with both a centralized and distributed version, that can form energy-e cient multicast trees with enough bandwidth. We evaluated the performance of our proposed scheme via simulations and observed that our scheme can e ectively construct such multicast trees.
Open Access
Content based video copy detection using motion vectors
(2009) Taşdemir, Kasım
In this thesis, we propose a motion vector based Video Content Based Copy Detection (VCBCD) method. Detecting the videos violating the copyright of the owner comes into question by growing broadcasting of digital video on different media. Unlike watermarking methods in VCBCD methods, the video itself is considered as a signature of the video and representative feature parameters are extracted from a given video and compared with the feature parameters of a test video. Motion vectors of image frames are one of the signatures of a given video. We first investigate how well the motion vectors describe the video. We use Mean value of Magnitudes of Motion Vectors (MMMV) and Mean value of Phases of Motion Vectors (MPMV) of macro blocks, which are the main building blocks of MPEG-type video coding methods. We show that MMMV and MPMV plots may not represent videos uniquely with little motion content because the average of motion vectors in a given frame approaches zero. To overcome this problem we calculate the MMMV and MPMV graphs in a lower frame rate than the actual frame rate of the video. In this way, the motion vectors may become larger and as a result robust signature plots are obtained. Another approach is to use the Histogram of Motion Vectors (HOMV) that includes both MMMV and MPMV information. We test and compare MMMV, MPMV and HOMV methods using test videos including copies and the original movies.
Open Access
Content-based video copy detection using multimodal analysis
(2009) Küçüktunç, Onur
Huge and increasing amount of videos broadcast through networks has raised the need of automatic video copy detection for copyright protection. Recent developments in multimedia technology introduced content-based copy detection (CBCD) as a new research field alternative to the watermarking approach for identification of video sequences. This thesis presents a multimodal framework for matching video sequences using a three-step approach: First, a high-level face detector identifies facial frames/shots in a video clip. Matching faces with extended body regions gives the flexibility to discriminate the same person (e.g., an anchor man or a political leader) in different events or scenes. In the second step, a spatiotemporal sequence matching technique is employed to match video clips/segments that are similar in terms of activity. Finally the non-facial shots are matched using low-level visual features. In addition, we utilize fuzzy logic approach for extracting color histogram to detect shot boundaries of heavily manipulated video clips. Methods for detecting noise, frame-droppings, picture-in-picture transformation windows, and extracting mask for still regions are also proposed and evaluated. The proposed method was tested on the query and reference dataset of CBCD task of TRECVID 2008. Our results were compared with the results of top-8 most successful techniques submitted to this task. Experimental results show that the proposed method performs better than most of the state-of-the-art techniques, in terms of both effectiveness and efficiency.
Open Access
Data modeling and querying for video databases
(2002) Dönderler, Mehmet Emin
With the advances in information technology, the amount of multimedia data captured, produced and stored is increasing rapidly. As a consequence, multimedia content is widely used for many applications in today’s world, and hence, a need for organizing this data and accessing it from repositories with vast amount of information has been a driving stimulus both commercially and academically. In compliance with this inevitable trend, first image and especially later video database management systems have attracted a great deal of attention since traditional database systems are not suitable to be used for multimedia data. In this thesis, a novel architecture for a video database system is proposed. The architecture is original in that it provides full support for spatio-temporal queries that contain any combination of spatial, temporal, object-appearance, external-predicate, trajectory-projection and similarity-based object-trajectory conditions by a rule-based system built on a knowledge-base, while utilizing an object-relational database to respond to semantic (keyword, event/activity and category-based) and low-level (color, shape and texture) video queries. Research results obtained from this thesis work have been realized by a prototype video database management system, which we call BilVideo. Its tools, Fact-Extractor and Video-Annotator, its Web-based visual query interface and its SQL-like textual query language are presented. Moreover, the query processor of BilVideo and our spatio-temporal query processing strategy are also discussed.
Open Access
Detection and tracking of repeated sequences in videos
(2007) Can, Tolga
In this thesis, we propose a new method to search different instances of a video sequence inside a long video. The proposed method is robust to view point and illumination changes which may occur since the sequences are captured in different times with different cameras, and to the differences in the order and the number of frames in the sequences which may occur due to editing. The algorithm does not require any query to be given for searching, and finds all repeating video sequences inside a long video in a fully automatic way. First, the frames in a video are ranked according to their similarity on the distribution of salient points and colour values. Then, a tree based approach is used to seek for the repetitions of a video sequence if there is any. These repeating sequences are pruned for more accurate results in the last step. Results are provided on two full length feature movies, Run Lola Run and Groundhog Day, on commercials of TRECVID 2004 news video corpus and on dataset created for CIVR Copy Detection Showcase 2007. In these experiments, we obtain %93 precision values for CIVR2007 Copy Detection Showcase dataset and exceed %80 precision values for other sets.
Open Access
Leveraging large scale data for video retrieval
(2014) Armağan, Anıl
The large amount of video data shared on the web resulted in increased interest on retrieving videos using usual cues, since textual cues alone are not sufficient for satisfactory results. We address the problem of leveraging large scale image and video data for capturing important characteristics in videos. We focus on three different problems, namely finding common patterns in unusual videos, large scale multimedia event detection, and semantic indexing of videos. Unusual events are important as being possible indicators of undesired consequences. Discovery of unusual events in videos is generally attacked as a problem of finding usual patterns. With this challenging problem at hand, we propose a novel descriptor to encode the rapid motions in videos utilizing densely extracted trajectories. The proposed descriptor, trajectory snippet histograms, is used to distinguish unusual videos from usual videos, and further exploited to discover snapshots in which unusualness happen. Next, we attack the Multimedia Event Detection (MED) task. We approach this problem as representing the videos in the form of prototypes, that correspond to models each describing a different visual characteristic of a video shot. Finally, we approach the Semantic Indexing (SIN) problem, and collect web images to train models for each concept.
Open Access
Mean-shift analysis for image and video applications
(2005) Cüce, Halil İbrahim
In this thesis, image and video analysis algorithms are developed. Tracking moving objects in video have important applications ranging from CCTV (Closed Circuit Television Systems) to infrared cameras. In current CCTV systems, 80% of the time, it is impossible to recognize suspects from the recorded scenes. Therefore, it is very important to get a close shot of a person so that his or her face is recognizable. To take high-resolution pictures of moving objects, a pan-tiltzoom camera should automatically follow moving objects and record them. In this thesis, a mean-shift based moving object tracking algorithm is developed. In ordinary mean-shift tracking algorithm a color histogram or a probability density function (pdf) estimated from image pixels is used to represent the moving object. In our case, a joint-probability density function is used to represent the object. The joint-pdf is estimated from the object pixels and their wavelet transform coefficients. In this way, relations between neighboring pixels, edge and texture information of the moving object are also represented because wavelet coefficients are obtained after high-pass filtering. Due to this reason the new tracking algorithm is more robust than ordinary mean-shift tracking using only color information. A new content based image retrieval (CBIR) system is also developed in this thesis. The CBIR system is based on mean-shift analysis using a joint-pdf. In this system, the user selects a window in an image or an entire image and queries similar images stored in a database. The selected region is represented using a joint-pdf estimated from image pixels and their wavelet transform coefficients. The retrieval algorithm is more reliable compared to other CBIR systems using only color information or only edge or texture information because the jointpdf based approach represents both texture, edge and color information. The proposed method is also computationally efficient compared to sliding-window based retrieval systems because the joint-pdfs are compared in non-overlapping windows. Whenever there is a reasonable amount of match between the queried window and the original image window then a mean-shift analysis is started.
Open Access
Query processing for an MPEG-7 compliant video database
(2008) Çam, Hayati
Based on the recent advancements in multimedia, communication, and storage technologies, the amount of audio-visual content stored is increased dramatically. The need to organize and access the growing multimedia content led researchers to develop multimedia database management systems. However, each system has its own way of describing the multimedia content that disables interoperability among other systems. To overcome this problem and to be able to standardize the description of audio-visual content stored in those databases, MPEG-7 standard has been developed by MPEG (Moving Picture Experts Group). In this thesis, a query language and a query processor for an MPEG-7 compliant video database system is proposed. The query processor consists of three main modules: query parsing module, query execution module, and result fusion module. The query parsing module parses the XML based query and divides it into subqueries. Each sub-query is then executed with related query execution module and the final result is obtained by fusing the results of the sub-queries according to user defined weights. The prototype video database system BilVideo v2.0, which is formed as a result of this thesis work, supports spatio-temporal and low level feature queries that contain any weighted combination of keyword, temporal, spatial, trajectory, and low level visual feature (color, shape and texture) queries. Compatibility with MPEG-7, low-level visual query support, and weighted result fusion feature are the major factors that highly differentiate between BilVideo v2.0 and its predecessor, BilVideo.
Open Access
Web-based user interface for query specification in a video database system
(2001) Şaykol, Ediz