Generalized Sparse Convolutional Neural Networks for Semantic Segmentation of Point Clouds Derived from Tri-Stereo Satellite Imagery.
Stefan BachhofnerAna-Maria LoghinJohannes OtepkaNorbert PfeiferMichael HornacekAndrea SiposovaNiklas SchmidingerKurt HornikNikolaus SchillerOlaf KählerRonald HochreiterPublished in: Remote. Sens. (2020)
Keyphrases
- point cloud
- satellite imagery
- semantic segmentation
- convolutional neural networks
- remote sensing
- change detection
- surface reconstruction
- satellite images
- structure from motion
- superpixels
- point sets
- conditional random fields
- object categories
- high dimensional
- stereo images
- stereo pair
- three dimensional
- computer vision
- data sets
- stereo vision
- object classes
- urban areas
- active learning
- multiscale
- depth map
- sparse representation
- image processing