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: IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Keyphrases
- optical flow estimation
- global motion
- optical flow
- unsupervised learning
- spiking neural networks
- image sequences
- coarse to fine
- flow field
- motion field
- consecutive frames
- biologically inspired
- camera motion
- motor control
- supervised learning
- motion model
- semi supervised
- motion estimation
- vector field
- motion parameters
- multiscale
- computer vision
- kalman filter
- least squares
- moving objects
- structure from motion
- machine learning
- multimedia
- rigid motion
- motion segmentation
- feature selection
- motion trajectories
- image segmentation
- active learning
- motion analysis
- stereo matching
- object detection