Scene retrieval method for video database applications using temporal condition changes
Shigeo Abe, Yoshihide Tonomura, Hisashi Kasahara · 2003
An algorithm is proposed to retrieve desired scenes from video sequences in a video database. The functions expressing the user's query, which describes a temporal condition change of object images, are used as search keys for retrieval. Retrieval is performed using primitive characteristic data (PCD) extracted from video images as database management data and a condition description factor generated from the user's query. A simple experiment confirms the effectiveness of the proposed method. Object locations generate the PCD values, whereas interpreted object motions are the retrieval keys. This method is effective for video database applications such as video libraries or video editing systems in which retrieval of a desired scene, specified by the user's query, is needed.>