Our goal is to recognize human action at a distance, at resolutions where a whole person may be, say, 30 pixels tall. We introduce a novel motion descriptor based on optical flow measurements in a spatiotemporal volume for each stabilized human figure, and an associated similarity measure to be used in a nearest-neighbor framework. Making use of noisy optical flow measurements is the key challenge, which is addressed by treating optical flow not as precise pixel displacements, but rather as a spatial pattern of noisy measurements which are carefully smoothed and aggregated to form our spatiotemporal motion descriptor. To classify the action being performed by a human figure in a query sequence, we retrieve nearest neighbor(s) from a database of stored, annotated video sequences. We can also use these retrieved exemplars to transfer 2D/3D skeletons onto the figures in the query sequence, as well as two forms of data-based action synthesis "do as I do" and "do as I say". Results are demonstrated on ballet, tennis as well as football datasets.
Recognizing action at a distance
2003-01-01
893462 byte
Conference paper
Electronic Resource
English
Recognizing Action at a Distance
British Library Conference Proceedings | 2003
|Recognizing Planned, Multiperson Action
British Library Online Contents | 2001
|Recognizing Action Events from Multiple Viewpoints
British Library Conference Proceedings | 2001
|Recognizing action events from multiple viewpoints
IEEE | 2001
|Recognizing 50 human action categories of web videos
British Library Online Contents | 2013
|