Action Recognition Using Mined Hierarchical Compound Features

The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 33; H. 5; S. 883 - 897
Hauptverfasser: Gilbert, A, Illingworth, J, Bowden, R
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Los Alamitos, CA IEEE 01.05.2011
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Action recognition
Algorithms
Applied sciences
Artificial intelligence
Association rules
Compounds
Computer science; control theory; systems
Data mining
Data Mining - methods
Data processing. List processing. Character string processing
Databases, Factual
Exact sciences and technology
Feature extraction
Hierarchies
Humans
Image Processing, Computer-Assisted - methods
Itemsets
learning
Memory organisation. Data processing
Movement - physiology
Object recognition
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
real-time
Recognition
Searching
Software
spatiotemporal
State of the art
Three dimensional
Two dimensional
High performance
Computer vision
Action
Data analysis
High resolution
Motion estimation
Video signal
Temporal databases
learning
Pattern recognition
Data mining
Real time
Object recognition
Optimization
Action recognition
Time resolution
Discrimination
real-time
Behavioral analysis
spatiotemporal
Fires
Classification
Localization
Spatial database
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase at each level of the hierarchy. The approach is tested on four state-of-the-art data sets, the popular KTH data set to provide a comparison with other state-of-the-art approaches, the Multi-KTH data set to illustrate performance at simultaneous multiaction classification, despite no explicit localization information provided during training. Finally, the recent Hollywood and Hollywood2 data sets provide challenging complex actions taken from commercial movie sequences. For all four data sets, the proposed hierarchical approach outperforms all other methods reported thus far in the literature and can achieve real-time operation.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2010.144