ARTFLOW: A Fast, Biologically Inspired Neural Network that Learns Optic Flow Templates for Self-Motion Estimation.
Oliver W. LaytonPublished in: Sensors (2021)
Keyphrases
- biologically inspired
- optic flow
- motion estimation
- motion field
- neural network
- image sequences
- flow field
- apparent motion
- learning rules
- optical flow
- recurrent networks
- anchor points
- motion compensation
- motion vectors
- receptive fields
- scale space
- biologically plausible
- motion analysis
- spiking neural networks
- video coding
- motion model
- multiscale
- constraint equation
- motion segmentation
- artificial neural networks
- optical flow estimation
- optic flow field
- humanoid robot
- video sequences
- network architecture
- back propagation
- feature points
- computational complexity
- pattern recognition
- denoising
- feature extraction
- vector field