Video Foreground Extraction Using Multi-View Receptive Field and Encoder-Decoder DCNN for Traffic and Surveillance Applications.
Akilan ThangarajahQ. M. Jonathan WuWandong ZhangPublished in: IEEE Trans. Veh. Technol. (2019)
Keyphrases
- multi view
- receptive fields
- dynamic scenes
- video surveillance
- space time
- distributed video coding
- biologically inspired
- free viewpoint
- video codec
- background subtraction
- low complexity
- natural images
- d objects
- foreground objects
- error control
- video data
- image representation
- three dimensional
- semi supervised
- moving objects
- video frames
- stereoscopic video
- view synthesis
- video sequences
- video coding
- key frames
- bit rate
- spatio temporal
- video compression
- error concealment
- object recognition
- rate distortion
- object detection
- motion estimation