Velocity estimation from monocular video for automotive applications using convolutional neural networks.
Koyel BanerjeeTuan Van DinhLudmila LevkovaPublished in: Intelligent Vehicles Symposium (2017)
Keyphrases
- convolutional neural networks
- optical flow
- depth from motion
- video data
- image sequences
- convolutional network
- multimedia
- video streams
- space time
- video sequences
- visual sensor
- video content
- video analysis
- computer vision
- moving objects
- ego motion
- estimation algorithm
- video frames
- angular velocity
- velocity field
- depth perception
- visual data
- dynamic scenes
- pose estimation