Video search engine
CleverCS, a newsletter for clever Computer Science ideas, posted a link to this research, conducted by Oxford scientists, where they attempt to produce a video search engine capable of searching for a defined object.
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.