基于L2, 1范数稀疏特征选择和超法向量的深度图像序列行为识别 (Activity Recognition from Depth Image Sequences Based on L2, 1-norm Sparse Feature Selection and Super Normal Vector).
Xiangfa SongYanfeng ZhangFengbin ZhengPublished in: 计算机科学 (2017)
Keyphrases
- activity recognition
- normal vectors
- image sequences
- feature selection
- depth map
- human activities
- action recognition
- ego motion
- planar surfaces
- hyperplane
- point cloud
- high dimensional
- text categorization
- motion analysis
- video sequences
- three dimensional
- feature set
- computer vision
- feature extraction
- support vector
- sparse representation
- depth information
- motion estimation
- discrete space
- optical flow
- structure from motion
- dimensionality reduction
- feature space
- support vector machine
- machine learning
- moving objects
- d scene
- motion model
- transfer learning
- camera motion
- data sets
- image classification