ECRU: An Encoder-Decoder Based Convolution Neural Network (CNN) for Road-Scene Understanding.
Robail YasrabPublished in: J. Imaging (2018)
Keyphrases
- scene understanding
- neural network
- road scenes
- distributed video coding
- video codec
- decoding process
- low complexity
- video surveillance
- object detection
- error control
- object recognition
- vision system
- cellular neural networks
- d scene
- scene recognition
- noisy channel
- rate distortion
- robot navigation
- wyner ziv
- wyner ziv video coding
- successive approximation
- video coding
- scene labeling
- motion estimation
- image processing
- transform domain
- distributed source coding
- turbo codes
- scene interpretation
- error concealment
- scene categorization
- computer vision
- indoor scenes
- error resilience
- three dimensional
- markov random field
- multi class
- optical flow
- moving objects
- computational complexity
- training data