DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks.
Sen WangRonald ClarkHongkai WenNiki TrigoniPublished in: CoRR (2017)
Keyphrases
- end to end
- convolutional neural networks
- visual odometry
- autonomous navigation
- long range
- position information
- ego motion
- kalman filtering
- depth images
- ad hoc networks
- simultaneous localization and mapping
- congestion control
- mobile robot
- multipath
- range data
- real time
- wifi
- camera pose
- field of view
- extended kalman filter
- image sequences