Abstract
Human activity recognition is still a very challenging
research area, due to the inherently complex temporal and
spatial patterns that characterize most human activities. This
paper proposes a human activity recognition framework based
on random forests, where each activity is classified requiring few
training examples (i.e. no frame-by-frame activity classification).
In a first approach, a simple mechanism that divides each action
sequence into a fixed-size window is employed, where max-min
skeleton-based features are extracted. In the second approach,
each window is delimited by a pair of automatically detected key
poses, where static and max-min dynamic features are extracted,
based on the determined activity example. Both approaches are
evaluated using the Cornell Activity Dataset [1], obtaining relevant
overall average results, considering that these approaches
are fast to train and require just a few training examples.
These characteristics suggest that the proposed framework can beuseful for real-time applications, where the activities are typicallywell distinctive and little training time is required, or to be
integrated in larger and sophisticated systems, for a first quick
impression/learning of certain activities
research area, due to the inherently complex temporal and
spatial patterns that characterize most human activities. This
paper proposes a human activity recognition framework based
on random forests, where each activity is classified requiring few
training examples (i.e. no frame-by-frame activity classification).
In a first approach, a simple mechanism that divides each action
sequence into a fixed-size window is employed, where max-min
skeleton-based features are extracted. In the second approach,
each window is delimited by a pair of automatically detected key
poses, where static and max-min dynamic features are extracted,
based on the determined activity example. Both approaches are
evaluated using the Cornell Activity Dataset [1], obtaining relevant
overall average results, considering that these approaches
are fast to train and require just a few training examples.
These characteristics suggest that the proposed framework can beuseful for real-time applications, where the activities are typicallywell distinctive and little training time is required, or to be
integrated in larger and sophisticated systems, for a first quick
impression/learning of certain activities
| Original language | English |
|---|---|
| Publication status | Published - 31 Aug 2016 |
| Event | IEEE RO-MAN'16: Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics (BAILAR) - New York, United States Duration: 26 Aug 2016 → 31 Aug 2016 |
Conference
| Conference | IEEE RO-MAN'16: Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics (BAILAR) |
|---|---|
| Country/Territory | United States |
| City | New York |
| Period | 26/08/16 → 31/08/16 |
Bibliographical note
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Keywords
- Human Daily Activity Recognition, Random Forest, Max-Min Skeleton-based Features, Key Poses, Static and Dynamic Features