Temporal video segmentation using unsupervised clustering and semantic object tracking
Journal of Electronic ImagingPublished 1 July 1998
Bilge Günsel, A. Müfit Ferman, A. Murat Tekalp
Citations115
SJR quartileQ3
SJR score0.25
SNIP0.40
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A content-based temporal video segmentation system that integrates syntactic and semantic features for auto- matic management of video data and a new unsupervised scene change detection method based on two-class clustering is introduced to eliminate the data dependency of threshold selection.
Abstract
The Journal of Electronic Imaging (JEI), copublished bimonthly with the Society for Imaging Science and Technology, publishes peer-reviewed papers that cover research and applications in all areas of electronic imaging science and technology.
Keywords
Computer Science
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Determining Optical Flow</title>
7,496 Citations1981Berthold K. P. Horn, Brian G. Schunck
An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences and is robust in that it can handle image sequences that are quantized rather coarsely in space and time.
Multimedia SystemsAutomatic partitioning of full-motion video
1,275 Citations1993HongJiang Zhang, Atreyi Kankanhalli +1 more
A twin-comparison approach has been developed to solve the problem of detecting transitions implemented by special effects, and a motion analysis algorithm is applied to determine whether an actual transition has occurred.
Digital video processing
1,151 Citations2012
Digital Video Processing, Second Edition, reflects important advances in image processing, computer vision, and video compression, including new applications such as digital cinema, ultra-high-resolution video, and 3D video.
IEEE Transactions on Circuits and Systems for Video TechnologyRapid scene analysis on compressed video
718 Citations1995Boon-Lock Yeo, Bede Liu
Experimental results show that the proposed rapid scene analysis algorithms are fast and effective in detecting abrupt scene changes, gradual transitions including fade-ins and fade-outs, flashlight scenes and in deriving intrashot variations.
IEEE Transactions on Signal ProcessingAn adaptive clustering algorithm for image segmentation
586 Citations1992Thrasyvoulos N. Pappas
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEDisplacement Estimation By Hierarchical Blockmatching
376 Citations1988Matthias Bierling
A hierarchical blockmatching algorithm for the estimation of displacement vector fields in digital television sequences is presented, which yields reliable and homogeneous displacement vector - fields, which are close to the true displacements.
ComputerIntelligent access to digital video: Informedia project
344 Citations1996Howard D. Wactlar, Takeo Kanade +2 more
Carnegie Mellon's Informedia Digital Video Library project will establish a large, on-line digital video library featuring full-content and knowledge-based search and retrieval, and focused the work on two corpuses.
Multimedia SystemsVision texture for annotation
253 Citations1995Rosalind W. Picard, Thomas P. Minka
This paper demonstrates a new application of computer vision to digital libraries — the use of texture forotation, the description of content, and is equipped with the ability to choose the one that “best explains” the regions selected by the user for annotating.
Digital video segmentation
248 Citations1994Arun Hampapur, Terry E. Weymouth +1 more
This work uses the model driven approach to digital video segmentation to classify the edit effects used in video and film production and systematically design the feature detectors for detecting edit effects in digital video.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Knowledge-guided parsing in video databases</title>
219 Citations1993Deborah Swanberg, Chiao-Fe Shu +1 more
The steps in the insertion process, and some of the tools the authors have developed to semi-automatically segment the data into domain objects which are meaningful to the user are discussed.
Video and Image Processing in Multimedia Systems
213 Citations1995Borko Furht, Stephen W. Smoliar +1 more
This chapter discusses image and Video Indexing and Retrieval techniques for Multimedia Compression, and some of the techniques used in this chapter were developed in the second part of this book.
Image processing on compressed data for large video databases
205 Citations1993Farshid Arman, Arding Hsu +1 more
A novel approach to processing encoded video sequences prior to decoding by analyzing the DCT coefficients, regions of interest may be isolated prior to decompression, increasing efficiency of any subsequent image processing steps, such as edge detection.
Proceedings - International Conference on Image ProcessingEfficient matching and clustering of video shots
203 Citations2002Minerva M. Yeung, Bede Liu
A scheme to match video shots and to cluster them by taking into account the temporal variations within individual shots is proposed, using a much reduced representation for a video shot.
Journal of Visual Communication and Image RepresentationA Survey of Technologies for Parsing and Indexing Digital Video1
176 Citations1996G. Ahanger, Thomas D. C. Little
Existing research trends in this area and requirements for future data delivery systems are discussed, including an overview of video indexing is presented followed by a discussion on current indexing techniques.
Automatic parsing of news video
159 Citations1994Hao Zhang, Yihong Gong +2 more
Approaches to locating and identifying frame structure models based on temporal and spatial structure of news video data, along with algorithms to apply these models in parsing news video, have been developed and are presented in detail in this paper.
Pattern RecognitionRetrieval of similar pictures on pictorial databases
126 Citations1991Chia‐Chan Chang, Shyh‐Yuan Lee
A method of retrieving iconic pictures in a pictorial database based upon the spatial relationship among the objects in the picture is suggested and the pictures satisfying that query can be easily determined.
Optical EngineeringGeneral approach to block-matching motion estimation
106 Citations1993V. Seferidis
It is shown that the proposed method outperforms the conventional full search method by improving the overall SNR of the prediction error by at least 1 dB and reducing the bit rate by 10%.
ACM SIGMOD RecordMetadata in video databases
93 Citations1994Ramesh Jain, Arun Hampapur
A data model for video databases is presented based on a study of the applications of video, the nature of video retrieval requests, and the features of video that is used in the architectural framework of a video database.
Graphical Models and Image ProcessingAutomatic Image Annotation Using Adaptive Color Classification
91 Citations1996Eli Saber, A. Murat Tekalp +2 more
A system which automatically annotates images with a set of prespecified keywords, based on supervised color classification of pixels intoprespecified classes using simple pixelwise operations is described.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEVideo browsing using brightness data
78 Citations1991Kiyotaka Otsuji, Yoshinobu Tonomura +1 more
A video browsing tool (VBTool) is proposed that creates a compressed video containing all important scenes that utilizes two factors related to pixel brightness to allow the automatic generation of the compressed video.
Educational Theatre JournalThe Technique of Television Production
75 Citations1962Colby Lewis, Gerald Millerson
Computer Graphics and Image ProcessingFormation of an object concept by analysis of systematic time variations in the optically perceptible environment
69 Citations1978Hans-Hellmut Nagel
An algorithm to isolate a representation for a moving object of unknown form and size from a sequence of TV frames based on the assumption that a group of connected regions being jointly displaced in a systematic way from frame to frame without changing their relative positions is described.
Computer Vision and Image UnderstandingA Bayesian Approach to Model Matching with Geometric Hashing
62 Citations1995Isidore Rigoutsos, Robert A. Hummel
This paper shows how intuitive notions can be translated into a well-founded Bayesian approach to object recognition and give precise formulas for the optimal weight functions that should be used in hash space, and demonstrates the validity of the approach by performing similarity-invariant object recognition.
Graphical Models and Image ProcessingTracking Motion and Intensity Variations Using Hierarchical 2-D Mesh Modeling for Synthetic Object Transfiguration
59 Citations1996Candemir Toklu, A. Tanju Erdem +2 more
The proposed method is capable of tracking image regions corresponding to scene objects with nonplanar and/or mildly deforming surfaces, accounting for intensity variations, and is shown to be effective with real image sequences.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Extracting multidimensional signal features for content-based visual query</title>
50 Citations1995Shih‐Fu Chang, John R. Smith
This paper focuses on automatic extraction of low-level visual features such as texture, color, and shape and proposes a quad-tree based data structure to bind various signal features and Integrated feature maps are proposed to improve the overall effectiveness of the feature-based image query system.
Signal Processing Image CommunicationDevelopment of Columbia's video on demand testbed
39 Citations1996Shih‐Fu Chang, Alexandros Eleftheriadis +1 more
The current research focus covers video transmission with heterogeneous quality-of-service (QoS) provision, video storage architecture design, content-based video indexing and browsing, multi-resolution video coding, efficient manipulation of compressed video, and advanced user interfaces.
Affine models for image matching and motion detection
27 Citations1991Chiou‐Shann Fuh, Petros Maragos
It is experimentally demonstrated that the affine matching model performs better than other standard approaches for detecting the displacement field in spatiotemporal image sequences.
IRE Transactions on Communications SystemsImage Activity Characteristics in Broadcast Television
17 Citations1976D.C. Coll, G. Choma
The results of a series of measurements of the dynamics of typical broadcast television programs are presented and it is demonstrated that image activity is separable into two distinct classes, one caused by image and camera movement, and the other by scene switches.
Object-based video indexing for virtual-studio productions
16 Citations2002Bilge Günsel, A. Murat Tekalp +1 more
An object-based approach for temporal video partitioning and content-based indexing, where the basic indexing unit is "lifespan of a video object", rather than a "camera shot" or "story unit", is introduced.
Deep Blue (University of Michigan)Designing video data management systems
15 Citations1995Arun Hampapur
The segmentation and indexing algorithms are incorporated into a prototype system which operates on video from commercial cable television, and results of experiments with half hour of video data are presented.
Proceedings - International Conference on Image Processing2-D mesh tracking for synthetic transfiguration
11 Citations2002Candemir Toklu, A. Tanju Erdem +2 more
A 2-D mesh tracking method that estimates, on a local basis, the motion and intensity variations of a region of interest of interest and is shown to be effective in real-life situations.