Comparison of belief propagation and graph-cut approaches for contextual classification of 3D lidar point cloud data.
Loïc LandrieuClément MalletMartin WeinmannPublished in: IGARSS (2017)
Keyphrases
- graph cuts
- belief propagation
- markov random field
- message passing
- energy minimization
- graphical models
- energy function
- approximate inference
- point cloud
- point cloud data
- image segmentation
- loopy belief propagation
- fixed point
- markov networks
- multi label
- stereo matching
- stereo algorithms
- disparity map
- probabilistic model
- free energy
- three dimensional
- feature space
- image processing
- pairwise
- segmentation method
- higher order
- min cut
- labeling problems
- max product
- machine learning