Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image.
Florian ChabotMohamed ChaouchJaonary RabarisoaCéline TeulièreThierry ChateauPublished in: CoRR (2017)
Keyphrases
- coarse to fine
- hierarchical segmentation
- multiscale
- hierarchical representation
- scan line
- image analysis
- image pyramid
- multiresolution
- input image
- matching scheme
- image data
- template matching
- image segmentation
- segmentation method
- image retrieval
- machine learning
- dynamic programming
- ground plane
- convolutional network
- normalized cross correlation
- energy function
- image registration
- object recognition
- similarity measure
- feature selection