Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects
Abstract
We present a real-time system capable of segmenting multiple 3D objects and tracking their pose using a single RGB camera, based on prior shape knowledge. The proposed method uses twist-coordinates for pose parametrization and a pixel-wise second-order optimization approach which lead to major improvements in terms of tracking robustness, especially in cases of fast motion and scale changes, compared to previous region-based approaches. Our implementation runs at about 50–100 Hz on a commodity laptop when tracking a single object without relying on GPGPU computations. We compare our method to the current state of the art in various experiments involving challenging motion sequences and different complex objects.
Cite
Text
Tjaden et al. "Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46493-0_26Markdown
[Tjaden et al. "Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/tjaden2016eccv-real/) doi:10.1007/978-3-319-46493-0_26BibTeX
@inproceedings{tjaden2016eccv-real,
title = {{Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects}},
author = {Tjaden, Henning and Schwanecke, Ulrich and Schömer, Elmar},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {423-438},
doi = {10.1007/978-3-319-46493-0_26},
url = {https://mlanthology.org/eccv/2016/tjaden2016eccv-real/}
}