Label Fusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes
Deep neural network (DNN) architectures have been shown to outperform traditional pipelines for object segmentation and pose estimation using RGBD data, but the performance of these DNN pipelines is directly tied to how representative the training data is of the true data. Hence a key requirement fo...
Main Authors: | Marion, James Patrick, Florence, Peter Raymond, Manuelli, Lucas, Tedrake, Russell L |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
Online Access: | https://hdl.handle.net/1721.1/129426 |
Similar Items
-
Segmentation and semantic labelling of RGBD data with convolutional neural networks and surface fitting
by: Giampaolo Pagnutti, et al.
Published: (2017-12-01) -
RGBD-Inertial Trajectory Estimation and Mapping for Ground Robots
by: Zeyong Shan, et al.
Published: (2019-05-01) -
Deriving Ground Truth Labels for Regression Problems Using Annotator Precision
by: Benjamin Johnston, et al.
Published: (2023-08-01) -
Aggressive quadrotor flight through cluttered environments using mixed integer programming
by: Landry, Benoit, et al.
Published: (2019) -
Using scene similarity for place labelling
by: Posner, I, et al.
Published: (2008)