A REST service framework for video retrieval based on geographic information

Abstract

With the rapid grown of the volume of user-generated video clips, the efficient video retrieval methods has become more and more important. Regarding to the disadvantage of the existing methods for video retrieval such as content-based or content-based video retrieval, the REST framework based on the geographic information for video querying is proposed. The main idea of the framework is to utilize the location, trajectory and azimuth information acquired by sensors such as GPS receivers and 3D electronic compasses in conjunction with video contents to query videos. The raw spatial information is synthesized to point, line and polygon according to the camcorder parameters such as focal length and angle of view. We defined the point, line and polygon as frame point, video line and FOV (Field of View) polygon and used the spatial relation of these objects and the query objects (point/line/polygon). And the multi-tier framework based on the REST architecture is discussed, the prototype system for video retrieval is implemented. As the video querying experiment shown, this framework plays an important role in video retrieval application.