OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery.
Pankaj BodaniKumar ShreshthaShashikant SharmaPublished in: CoRR (2018)
Keyphrases
- semantic segmentation
- convolutional neural network
- street scenes
- face detection
- label transfer
- conditional random fields
- superpixels
- weakly supervised
- scene classification
- object categories
- object class
- multi modal
- object classes
- detection method
- image understanding
- pascal voc
- computer vision
- object detection
- neural network
- multiscale
- small number
- image processing
- learning algorithm
- face recognition
- object recognition
- long range
- image set
- graphical models
- pairwise