Real-time visual content description system based on MPEG-7 descriptors
Multimedia Tools and Applications
Hi-index | 0.00 |
Advances in digital signal processing technology makeit possible to embed the low-level functions performed by avideo surveillance system into cameras. The result is metadatacameras, like MPEG-7 cameras, that provide descriptionsof what they see in the form of XML documents servedover a network. We use this concept to build video informationservers that are conceptually similar to MPEG-7cameras, but differ in that they interact with client applicationsand can be configured dynamically to perform differentfunctions. We demonstrate the use of these videoinformation servers in some simple surveillance applications.Dynamic configuration of the servers allows themto do more than describe video content. For example, wepresent a functioning surveillance system, built with contentdescription servers, that describes the activity in ahockey game based on the observations of several cameras.Thus, we demonstrate that content description servers providebuilding blocks with which to create networked videosurveillance systems.