Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction.
Daniel GehrigMichelle RüeggMathias GehrigJavier Hidalgo-CarrióDavide ScaramuzzaPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- prediction accuracy
- depth cues
- neural network ensemble
- event detection
- social networks
- prediction model
- network structure
- feed forward
- pose estimation
- depth ordering
- image sequences
- depth perception
- recurrent neural networks
- multimedia
- audio visual
- stereo camera
- frame rate
- model based tracking
- spiking neural networks
- motion trajectories
- ego motion
- neural network
- video frames
- multi modal
- optical flow
- moving objects
- reference frame
- prediction error
- depth information
- causal interactions