On the improvement of human action recognition from depth map sequences using Space-Time Occupancy Patterns
Explore this paper's citation graph
Summary
A new visual representation for 3D action recognition from sequences of depth maps that preserves spatial and temporal contextual information between space and time cells while being flexible enough to accommodate intra-action variations and combines depth maps with skeletons to obtain view invariance.
- Type
- article
- Published
- 2014-01-01
- Cited by
- 62
- References
- 28
- OpenAlex
- https://openalex.org/W1989353817
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:30947752
Keywords
Occupancy grid mapping, Artificial intelligence, Pattern recognition (psychology), Curse of dimensionality, Representation (politics)
References
- A face and gesture recognition system based on an active stereo sensor
- Three-dimensional imaging in the studio and elsewhere
- Using occupancy grids for mobile robot perception and navigation
- Recognizing actions using depth motion maps-based histograms of oriented gradients
- Free viewpoint action recognition using motion history volumes
- Discriminative human action recognition in the learned hierarchical manifold space
- EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor
- A survey of vision-based methods for action representation, segmentation and recognition
- Hand gesture recognition using depth data
- Hierarchical spatio-temporal context modeling for action recognition
- The Visual Hull Concept for Silhouette-Based Image Understanding
- Real-time classification of dance gestures from skeleton animation
- Actions sketch: a novel action representation
- Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests
- Action and Gait Recognition From Recovered 3-D Human Joints
- Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures
- Action recognition based on a bag of 3D points
- Sparse Spatial Coding: A novel approach for efficient and accurate object recognition
- Actions as Space-Time Shapes
- Video-rate capture of dynamic face shape and appearance
Cited by
- Advanced Concepts for Intelligent Vision Systems
- Human Action Recognition Based on DMMs, HOGs and Contourlet Transform
- A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset
- Action Recognition from Depth Sequences Using Depth Motion Maps-Based Local Binary Patterns
- Skeletal Quads: Human Action Recognition Using Joint Quadruples
- Review on Vision based Human Activity Analysis
- Simplified Training for Gesture Recognition
- VALIDITY AND RELIABILITY OF THE MICROSOFT KINECT TO OBTAIN THE EXECUTION TIME OF THE TAEKWONDO'S FRONTAL KICK
- Recent trends in gesture recognition: how depth data has improved classical approaches
- High performance moves recognition and sequence segmentation based on key poses filtering
- Action recognition using completed local binary patterns and multiple-class boosting classifier
- Robust object representation by boosting-like deep learning architecture
- Improving Action Recognition Using Collaborative Representation of Local Depth Map Feature
- Motion segment decomposition of RGB-D sequences for human behavior understanding
- Efficient action recognition from compressed depth maps
- Online human moves recognition through discriminative key poses and speed-aware action graphs
- Depth-based action recognition using multiscale sub-actions depth motion maps and local auto-correlation of space-time gradients
- Combining 3D joints Moving Trend and Geometry property for human action recognition
- Efficient Human Motion Retrieval via Temporal Adjacent Bag of Words and Discriminative Neighborhood Preserving Dictionary Learning
- Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier
Related papers
- Dynamic-segmentation-based feature dimension reduction for quick audio/video searching
- Dictionary-based output-space dimensionality reduction
- Anatomization of the systems of dimension relaxation for facial recognition
- Least desirable feature elimination in a general pattern recognition problem
- An Efficient Feature Extraction and Dimensionality Reduction Scheme for Isolated Greek Handwritten Character Recognition
- Robust Dimensionality Reduction for Human Action Recognition
- Glasses detection in face images using histogram of Oriented Gradients
- Thermal infrared face image recognition based on combination of linear dimensionality reduction technology and BP neural network
- On the Discriminant Vector Method of Feature Selection