Chia-Tong Tang

Bio: Chia-Tong Tang is an academic researcher from Tamkang University. The author has contributed to research in topics: Video tracking & Hypervideo. The author has an hindex of 2, co-authored 3 publications receiving 13 citations.

Real-time multiple tracking using a combined technique

Abstract: This paper considers a real-time multi-object tracking algorithm for rigid and non-rigid objects. The major components of the tracking object system are extraction of the background image, adaptation of the background image, and identification of the extracted object. In each component, we improved existing methods without increasing the complexity of computation. The system was tested on our fish tank experiment that solves dynamic occlusions problems.

An object-based hypervideo authoring system

Abstract: Hypervideo is a new way for viewing films, just like hypertext on the WWW. In the literature, many standards and technologies have been developed for hypertext. However, present video processing methods cannot provide a proper solution for hyperlinks in video. We propose an object-based hypervideo authoring system. Video objects can be described by semantic annotation and multistory movies can be produced. The system offers a manual object-based interface for the film producer to select meaningful video objects and annotate them. It also has a video construction function to facilitate the audience's viewing of the annotation of interesting objects in a scene or selection of a particular viewing path. It is very useful to show the annotation of a particular object that the film producer wants to highlight in educational videos or commercials. A hypervideo player is also developed to play the video file made by the authoring system.

Hyper-Interactive video browsing by a remote controller and hand gestures

Abstract: Interactive video browsing tools are designed for e-learning applications on future interactive TVs. The integrated system includes an authoring tool that produces multi-paths videos and a playback tool that uses video tracking technology and a remote controller. The playback tool enables multi-modal interaction between the user and a multi-story video clip. Three types of hyper-interactive controls are incorporated, which include a reference link of a video object to show supplementary information on the Web, a hyper link to enable hyper-video jumps, and a choice link for online answers to pre-designed questions. The underlying video is coded using the standard MPEG technology, with navigation information hidden in the user-defined data of MPEG. Thus, the default sequence of a hypervideo can also be presented using an ordinary video player.

Towards an easy to use authoring tool for interactive non-linear video

Abstract: With growing bandwidths in the Internet and seemingly unlimited storage capacities on web servers, media became more and more important in the daily use of the World Wide Web. While about ten years ago only text and images with small file sizes (and as a result small resolutions) could be used, it is possible to watch high quality multimedia presentations nowadays. But those rarely exist because of tedious to learn authoring tools. A specialization to one main medium, in our case video, allows creating efficient authoring tools using well known paradigms. This work introduces an authoring tool called SIVA Producer. An iterative process for improving the usability of the authoring tool is described. Furthermore, a distinction of the terms "interactive video", "annotated video", "non-linear video" and "hypervideo" is given.

Authoring, viewing, and generating hypervideo: An overview of Hyper-Hitchcock

Abstract: Hyper-Hitchcock consists of three components for creating and viewing a form of interactive video called detail-on-demand video: a hypervideo editor, a hypervideo player, and algorithms for automatically generating hypervideo summaries. Detail-on-demand video is a form of hypervideo that supports one hyperlink at a time for navigating between video sequences. The Hyper-Hitchcock editor enables authoring of detail-on-demand video without programming and uses video processing to aid in the authoring process. The Hyper-Hitchcock player uses labels and keyframes to support navigation through and back hyperlinks. Hyper-Hitchcock includes techniques for automatically generating hypervideo summaries of one or more videos that take the form of multiple linear summaries of different lengths with links from the shorter to the longer summaries. User studies on authoring and viewing provided insight into the various roles of links in hypervideo and found that player interface design greatly affects people's understanding of hypervideo structure and the video they access.

Hypervideos and Interactive Multimedia Presentations

Abstract: Hypervideos and interactive multimedia presentations allow the creation of fully interactive and enriched video. It is possible to organize video scenes in a nonlinear way. Additional information can be added to the video ranging from short descriptions to images and more videos. Hypervideos are video-based but also provide navigation between video scenes and additional multimedia elements. Interactive multimedia presentations consist of different media with a temporal and spatial synchronization that can be navigated via hyperlinks. Their creation and description requires description formats, multimedia models, and standards—as well as players. Specialized authoring tools with advanced editing functions allow authors to manage all media files, link and arrange them to an overall presentation, and keep an overview during the whole process. They considerably simplify the creation process compared to writing and editing description documents in simple text editors. Data formats need features that describe interactivity and nonlinear navigation while maintaining temporal and spatial synchronization. Players should be easy to use with extended feature sets keeping elements synchronized. In this article, we analyzed more than 400 papers for relevant work in this field. From the findings we discovered a set of trends and unsolved problems, and propose directions for future research.

A tank fish recognition and tracking system using computer vision techniques

Abstract: Aquarium usually provides the visitors with pictures and some description of the fishes in the exhibition tank. In this paper, an intelligent fish recognition system using computer vision is proposed to help aquarium to educate people about the fishes in the tank. The designed system provides a convenient and friendly interface to help the users to retrieve the related fish information they are interested. The system includes three sub-systems: (1) fish object detection system (2) fish object tracking system (3) fish object recognition system. Two types of fish indexing system (offline and real time) have been designed and implemented.

Real-time surveillance video display with salience

Abstract: In this paper, we aim at providing a means for efficient display of surveillance video. In video surveillance, usually, there are certain regions of interest (ROIs), such as entrance or exit, and moving objects or persons, which should be paid more attention. By tracking and locally zooming the ROI, the proposed method adds salience on it to help surveillant to locate such important region effectively. Here, salience means highlighting special region locally. Given an input video signal, the ROI is detected first. The original video frame is mapped as a texture on a deformed mesh to produce the zoom effect. The position and shape of the ROI determine the mesh deformation. By experiment, we show that the proposed method is effective and efficient.