The Hierarchical Hidden Markov Model: Analysis and Applications
Machine Learning
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discovery and Segmentation of Activities in Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating Human Body Configurations Using Shape Context Matching
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Human Action Detection Using PNF Propagation of Temporal Constraints
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Action Recognition Using Probabilistic Parsing
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Particle Filter with Analytical Inference for Human Body Tracking
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
Object Labelling from Human Action Recognition
PERCOM '03 Proceedings of the First IEEE International Conference on Pervasive Computing and Communications
Real-time Human Motion Analysis by Image Skeletonization
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Probabilistic Motion Parameter Models for Human Activity Recognition
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Introducing Termination Probabilities to HMM
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
An Appearance-Based Representation of Action
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Recognition of two-person interactions using a hierarchical Bayesian network
IWVS '03 First ACM SIGMM international workshop on Video surveillance
Human Action Segmentation via Controlled Use of Missing Data in HMMs
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Policy recognition in the abstract hidden Markov model
Journal of Artificial Intelligence Research
Fast Detection and Modeling of Human-Body Parts from Monocular Video
AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
On parsing visual sequences with the hidden Markov model
Journal on Image and Video Processing
Fitting distal limb segments for accurate skeletonization in human action recognition
Journal of Ambient Intelligence and Smart Environments
Hi-index | 0.00 |
This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.