Data-Driven Machine Learning Approach for Human Action Recognition Using Skeleton and Optical Flow.
Yen-Ting LeeThitinun PengyingSule Yildirim YayilganOgerta ElezajPublished in: INTAP (2020)
Keyphrases
- data driven
- optical flow
- machine learning
- computer vision
- machine learning methods
- motion model
- machine learning algorithms
- computational intelligence
- motion field
- information extraction
- pattern recognition
- motion estimation
- motion segmentation
- dense optical flow
- image sequences
- optical flow estimation
- computer science
- least squares
- medial axis
- shape representation
- feature selection
- shape analysis
- optical flow computation
- flow field
- learning algorithm
- machine learning approaches
- feature tracking
- moving camera
- motion parameters
- knowledge acquisition
- support vector machine
- decision trees
- inductive learning
- inductive logic programming
- endpoints
- motion analysis
- vector field
- human body
- velocity field
- natural language processing
- qualitative and quantitative evaluation
- binocular disparity