Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception.
Federico Paredes-VallésKirk Y. W. ScheperGuido C. H. E. de CroonPublished in: CoRR (2018)
Keyphrases
- optical flow estimation
- global motion
- optical flow
- unsupervised learning
- spiking neural networks
- image sequences
- coarse to fine
- camera motion
- flow field
- motor control
- biologically inspired
- consecutive frames
- motion field
- semi supervised
- supervised learning
- motion estimation
- motion model
- least squares
- computer vision
- machine learning
- moving objects
- rigid motion
- dimensionality reduction
- motion parameters
- object recognition
- multi frame
- motion trajectories
- vector field
- feature selection
- motion segmentation
- multiscale
- scale space
- motion compensation
- image processing
- kalman filter
- multiresolution
- model selection