Semantic Scene Labeling for Personal Robots
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.
3d Pointclouds Labeling
|Original Scene||Ground Truth Labels||Predicted Labels|
Hierarchical Semantic Labeling
|2d Label Mask||3d Label Mask||Semantic Hierarchy Graph|
New Scientist, ACM Technews, Newswise, Zee News, News Tonight, Azo Robotics, VoiCE, iNewsOne.
Data and code  to be released.
- . Hierarchical Semantic Labeling for Task-Relevant RGB-D Perception, Chenxia Wu, Ian Lenz, Ashutosh Saxena. In Robotics: Science and Systems (RSS), 2014. [PDF]
- . Contextually Guided Semantic Labeling and Search for 3D Point Clouds, Abhishek Anand, Hema S. Koppula, Thorsten Joachims, Ashutosh Saxena. In IJRR, 2012. [PDF]
- . Semantic Labeling of 3D Point Clouds for Indoor Scenes, Hema S. Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena. In NIPS, 2011. [PDF]
- . Labeling 3D scenes for Personal Assistant Robots, Hema Swetha Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena. In RSS workshop on RGB-D Cameras, 2011. [PDF]
- 3D-Based Reasoning with Blocks, Support, and Stability. Zhaoyin Jia, Andy Gallagher, Ashutosh Saxena, Tsuhan Chen. In Computer Vision and Pattern Recognition (CVPR), 2013. [PDF]
- Hallucinated Humans as the Hidden Context for Labeling 3D Scenes, Yun Jiang, Ashutosh Saxena. In Computer Vision and Pattern Recognition (CVPR), 2013. [PDF, project page]
|Hema Koppula||hema at cs.cornell.edu ([2,3,4]Corresponding Author)|
|Chenxia Wu||chenxiawu at cs.cornell.edu (Corresponding Author)|
|Prof. Thorsten Joachims||tj at cs.cornell.edu|
|Prof. Ashutosh Saxena||asaxena at cs.cornell.edu|