Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection
Abstract
This paper proposes a novel method to estimate the global scale of a 3D reconstructed model within a Kalman filtering-based monocular SLAM algorithm. Our Bayesian framework integrates height priors over the detected objects belonging to a set of broad predefined classes, based on recent advances in fast generic object detection. Each observation is produced on single frames, so that we do not need a data association process along video frames. This is because we associate the height priors with the image region sizes at image places where map features projections fall within the object detection regions. We present very promising results of this approach obtained on several experiments with different object classes.
Cite
Text
Sucar and Hayet. "Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.135Markdown
[Sucar and Hayet. "Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/sucar2017cvprw-probabilistic/) doi:10.1109/CVPRW.2017.135BibTeX
@inproceedings{sucar2017cvprw-probabilistic,
title = {{Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection}},
author = {Sucar, Edgar and Hayet, Jean-Bernard},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {988-996},
doi = {10.1109/CVPRW.2017.135},
url = {https://mlanthology.org/cvprw/2017/sucar2017cvprw-probabilistic/}
}