Scene Text Detection and Tracking for Wearable Text-to-Speech Translation Camera.
Hideaki GotoKunqi LiuPublished in: ICCHP (2) (2016)
Keyphrases
- text detection
- text to speech
- urban scenes
- outdoor scenes
- vanishing points
- structure from motion
- video camera
- real scenes
- multiple images
- moving camera
- video images
- d scene
- stereo camera
- scene understanding
- ground plane
- dynamic scenes
- point cloud
- vision system
- video analysis
- object recognition
- text information
- urban environments
- augmented reality
- field of view
- ego motion
- single image
- camera calibration
- image sequences
- video sequences
- focal length
- camera parameters
- gesture recognition
- connected components
- planar surfaces
- hand held
- word processing
- aerial images
- multiple objects
- camera motion
- text regions
- complex scenes
- single view
- multi view
- activity recognition
- input image
- image based rendering
- depth information
- straight line
- perspective projection
- multiple cameras
- multi camera
- video data
- computer vision
- visual data