Browsing by Author "Fu, Hsin C."

Now showing 1 - 3 of 3

Internet Video Based Cloud Multisensor Fusion for Remote Services
(2011)
Fu, Hsin C.
;
Pao, Hsiao T.
;
Tseng, C. L.
;
資訊工程學系
;
Department of Computer Science
This paper proposes integrated video techniques, cloud computing, and multisensor data fusion for remote services over Internet. The proposed remote service approach includes three levels of different remote diagnoses: Level (1): Video and audio interaction between customer and remote service sites; Level (2): Signal and data collection from customer to remote service sites; and Level (3): Multisensor data fusion at cloud computing server. The proposed remote services have been successfully tested and evaluated for its performance: (I) 85% of technical manpower saving, (2) 90% of service response time saving, (3) 60% of maximum time to recovery (MTTR) saving, and (4) 95% of service cost saving. In the near future, we intend to implement automated diagnosis and repairing suggestion mechanism to further improve the efficiency of technical manpower of the proposed remote diagnosis and maintenance cloud platform.
Multimodal search for effective image retrieval
(2008)
Fu, Hsin C.
;
Xu, Yeong. Y.
;
Pao, Hsiao T.
;
資訊工程學系
;
Department of Computer Science
In this paper we present a multimodal approach for effectively searching and retrieving images. The proposed multimodal image query and retrieval (MIQR) method uses two or more types of query for accessing images - textual annotation associated with images and visual appearance, such as color, texture and positional features of objects in sample images. A user places a keyword-based query first and then retrieves desired images by visual content-based query. A prototype MIQR system was implemented and is available at hitp://140.113.216.66/WebImageSearch for online demo, and public evaluation. We also conducted experiments over a categorized Corel image collection and a non-categorized WWW image collection to show the performance of the proposed MIQR method.
VIDEOFARM: Playing video and display associated information
(2009)
Fu, Hsin C.
;
Pao, Hsiao T.
;
Xu, Yeong Y.
;
資訊工程學系
;
Department of Computer Science
This paper addresses a new type of video sharing platform-VideoFarm. In addition to just playing user uploaded video clips, the VideoFarm also displays the associated information of currently playing video contents. The associated information includes the general description of the video clip, a dynamic electronic map which shows the location of the current video contents. The location associated information, such as local stores, restaurants, lodging, and near by tour attractions are provided and displayed in parallel with the playing video clip. Through the URLs of the associated information, a viewer may collect plenty of tour information, when (s)he is enjoying an interesting video clip. A prototype of VideoFarm has been implemented at http://140.113.216.55/videomap for public trial, evaluation, comments, and suggestions.