We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion. The temporal continuity of the video within a shot is used to track the regions in order to reject unstable regions and reduce the effects of noise in the descriptors. The analogy with text retrieval is in the implementation where matches on descriptors are pre-computed (using vector quantization), and inverted file systems and document rankings are used. The result is that retrieved is immediate, returning a ranked list of key frames/shots in the manner of Google. The method is illustrated for matching in two full length feature films.
Video Google: a text retrieval approach to object matching in videos
Proceedings Ninth IEEE International Conference on Computer Vision ; 1470-1477 vol.2
2003-01-01
2282088 byte
Conference paper
Electronic Resource
English
Video Google: A Text Retrieval Approach to Object Matching in Videos
British Library Conference Proceedings | 2003
|Annotation and Retrieval of Video Documents: Sports Videos
British Library Conference Proceedings | 2003
|A spatio-temporal pyramid matching for video retrieval
British Library Online Contents | 2013
|Video retrieval based on object discovery
British Library Online Contents | 2009
|