se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

07/27/2020
by   Bowen Wen, et al.
0

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome and difficult to collect for 6D poses, which complicates machine learning solutions, and (iii) incremental error drift often accumulates in long term tracking to necessitate re-initialization of the object's pose. This work proposes a data-driven optimization approach for long-term, 6D pose tracking. It aims to identify the optimal relative pose given the current RGB-D observation and a synthetic image conditioned on the previous best estimate and the object's model. The key contribution in this context is a novel neural network architecture, which appropriately disentangles the feature encoding to help reduce domain shift, and an effective 3D orientation representation via Lie Algebra. Consequently, even when the network is trained only with synthetic data can work effectively over real images. Comprehensive experiments over benchmarks - existing ones as well as a new dataset with significant occlusions related to object manipulation - show that the proposed approach achieves consistently robust estimates and outperforms alternatives, even though they have been trained with real images. The approach is also the most computationally efficient among the alternatives and achieves a tracking frequency of 90.9Hz.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

research
05/29/2021

Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

Tracking the 6D pose of objects in video sequences is important for robo...
research
08/01/2021

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

Tracking the 6D pose of objects in video sequences is important for robo...
research
01/09/2023

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

Visual object tracking is a key component to many egocentric vision prob...
research
07/27/2021

VIPose: Real-time Visual-Inertial 6D Object Pose Tracking

Estimating the 6D pose of objects is beneficial for robotics tasks such ...
research
05/22/2019

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

Tracking 6D poses of objects from videos provides rich information to a ...
research
10/11/2018

Online Visual Robot Tracking and Identification using Deep LSTM Networks

Collaborative robots working on a common task are necessary for many app...
research
06/20/2023

Prepare the Chair for the Bear! Robot Imagination of Sitting Affordance to Reorient Previously Unseen Chairs

In this letter, a paradigm for the classification and manipulation of pr...

Please sign up or login with your details

Forgot password? Click here to reset