International Journal of Computer Vision
The nature of statistical learning theory
The nature of statistical learning theory
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields
Computer Vision and Image Understanding
The visual analysis of human movement: a survey
Computer Vision and Image Understanding
The Analysis of Human Motion and its Application for Visual Surveillance
VS '99 Proceedings of the Second IEEE Workshop on Visual Surveillance
Recognizing Action at a Distance
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Fusion of Static and Dynamic Body Biometrics for Gait Recognition
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Recognizing Human Actions: A Local SVM Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Actions Sketch: A Novel Action Representation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Action Recognition in Broadcast Tennis Video
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Behavior recognition via sparse spatio-temporal features
ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
Human Action Recognition Based on Spatio-temporal Features
PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
A survey on vision-based human action recognition
Image and Vision Computing
Characteristic kernels on structured domains excel in robotics and human action recognition
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part I
Novel kernel-based recognizers of human actions
EURASIP Journal on Advances in Signal Processing - Special issue on video analysis for human behavior understanding
kpose: a new representation for action recognition
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Human action recognition based on skeleton splitting
Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
Low quality images taken by surveillance cameras pose a great challenge to human action recognition algorithms. This is because they are usually noisy, of low resolution and of low frame rate. In this paper we propose an action recognition algorithm to overcome the above challenges. We use optic flow to construct motion descriptors and apply a SVM to classify them. Having powerful discriminative features, we significantly reduce the size of the feature set required. This algorithm can be applied to videos with low frame rate without scarifying efficiency or accuracy, and is robust to scale and view point changes. To evaluate our method, we used a database consisting of walking, running, jogging, hand clapping, hand waving and boxing actions. This grayscale database has images of low resolution and poor quality. This image database resembles images taken by surveillance cameras. The proposed method outperforms competing algorithms evaluated on the same database.