Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets
This addresses the need for efficient, real-time action detection in unsegmented video streams, representing an incremental improvement over existing sliding window and dynamic programming methods.
The paper tackles the problem of online action detection from 3D skeletal data by proposing a novel approach that identifies action sub-intervals with maximum classifier scores in linear time, enabling real-time applications with low latency.
Sliding window is one direct way to extend a successful recognition system to handle the more challenging detection problem. While action recognition decides only whether or not an action is present in a pre-segmented video sequence, action detection identifies the time interval where the action occurred in an unsegmented video stream. Sliding window approaches for action detection can however be slow as they maximize a classifier score over all possible sub-intervals. Even though new schemes utilize dynamic programming to speed up the search for the optimal sub-interval, they require offline processing on the whole video sequence. In this paper, we propose a novel approach for online action detection based on 3D skeleton sequences extracted from depth data. It identifies the sub-interval with the maximum classifier score in linear time. Furthermore, it is invariant to temporal scale variations and is suitable for real-time applications with low latency.