CFVL: A Coarse-to-Fine Vehicle Localizer with Omnidirectional Perception across Severe Appearance Variations.
Yicheng FangKaiwei WangRuiqi ChengKailun YangPublished in: IV (2020)
Keyphrases
- coarse to fine
- appearance variations
- illumination variations
- multiscale
- multiresolution
- appearance model
- visual tracking
- object detection
- image registration
- lighting conditions
- generative model
- dynamic programming
- illumination conditions
- active appearance models
- viewpoint
- stereo vision
- computer vision
- image sequences
- body parts
- target object
- three dimensional
- linear subspace
- feature selection