Contextual Combination of Appearance and Motion for Intersection Videos with Vehicles and Pedestrians.
Mohammad Shokrolah ShiraziBrendan Tran MorrisPublished in: ISVC (1) (2014)
Keyphrases
- traffic scenes
- static images
- pedestrian detection
- motion cues
- dynamic textures
- motion patterns
- video sequences
- space time
- motion features
- appearance features
- periodic motion
- image sequences
- moving vehicles
- motion model
- recognition of human actions
- spatial and temporal
- input video
- object motion
- appearance model
- motion analysis
- dynamic scenes
- motion parameters
- contextual information
- key frames
- video frames
- video data
- object detection
- motion estimation
- video objects
- layered representation
- traffic light
- motion trajectories
- pedestrian detection and tracking
- foreground objects
- moving objects
- moving camera
- optical flow
- action recognition
- camera motion
- crowded scenes
- visual motion
- motion segmentation
- human detection
- human body
- video stabilization
- video content
- video surveillance
- video analysis
- bounding box
- temporal coherence
- video scene
- traffic flow
- autonomous vehicles
- image motion