Contact: Brent Griffin (griffb at umich dot edu)
Video Object Segmentation-based Visual Servo Control and Object Depth Estimation on a Mobile Robot Platform
Brent Griffin, Victoria Florence, and Jason J. Corso
Please cite our paper if you find it useful for your research.
@inproceedings{GrFlCo19,
author = {Griffin, Brent and Florence, Victoria and Corso, Jason J.},
title = {Video Object Segmentation-based Visual Servo Control and Object Depth Estimation on a Mobile Robot Platform},
journal = {CoRR},
volume = {abs/1903.08336},
year = {2019}
}
Video Demonstration: https://youtu.be/hlog5FV9RLs
HSR Segmenting Objects at Various Heights. HSR's grasp camera faces downward (left) and only collects RGB data for objects in the scene (top right). However, using active perception and video object segmentation (bottom right), HSR can locate and grasp a variety of objects in real time.
Depth Estimation of Sugar Box. Data are collected and processed in real time during the initial approach to the sugar box in the video demonstration.
Source code for our video object segmentation-based framework is located in the /robot_exp folder.
Source code for annotating data and training OSVOS for segmentation is located in the /OSVOS_train folder.
This code is available for non-commercial research purposes only.
