This paper proposes a sliding window approach, whose length and time shift are dynamically adaptable in order to improve model confidence, speed and segmentation accuracy in human action sequences. Activity recognition is the process of inferring an action class from a set of observations acquired by sensors. We address the temporal segmentation problem of body part trajectories in Cartesian Space in which features are generated using Discrete Fast Fourier Transform (DFFT) and Power Spectrum (PS). We pose this as an entropy minimization problem. Using entropy from the classifier output as a feedback parameter, we continuously adjust the two key parameters in a sliding window approach, to maximize the model confidence at every step. The proposed classifier is a Dynamic Bayesian Network (DBN) model where classes are estimated using Bayesian inference. We compare our approach with our previously developed fixed window method. Experiments show that our method accurately recognizes and segments activities, with improved model confidence and faster convergence times, exhibiting anticipatory capabilities. Our work demonstrates that entropy feedback mitigates variability problems, and our method is applicable in research areas where action segmentation and classification is used. A working demo source code is provided online for academical dissemination purposes, by requesting the authors.
Trajectory-based human action segmentation
2015-02-01
doi:10.1016/j.patcog.2014.08.015
Article (Journal)
Electronic Resource
English
DDC: | 629 |
A feature extraction based trajectory segmentation approach based on multiple movement parameters
BASE | 2020
|Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models
British Library Online Contents | 2011
|British Library Online Contents | 2017
|Trajectory Generation Based Vehicle Action Tracking for Intersection Driving Safe
British Library Conference Proceedings | 2011
|