Cornell RGBD Dataset

by Abhishek Anand,Hema S. Koppula,Thorsten Joachims,Ashutosh SaxenaUnknown

Cornell RGBD Dataset

We consider the problem of semantic scene labeling from RGB-D data for personal robots. Given the input co-registered RGB, Depth image pair, the colored 3D pointclouds can be easily obtained. We formulate the Conditional Random Field model by incorporating relatins between visual/geometric features and labels, relations between contexts, as well as relations between hierarchical labels.

Dataset Attributes

Label SVG
TasksSegmentation
Label SVG
CategoriesRobots
Label SVG
SensorRGB-D