Towards Optical Flow Ego-motion Compensation for Moving Object Segmentation

Renáta Elek, Renáta Elek, Artúr Károly, Artúr Károly, Tamás Haidegger, Tamás Haidegger, Péter Galambos, Péter Galambos

2020

Abstract

Optical flow is an established tool for motion detection in the visual scene. While optical flow algorithms usually provide accurate results, they can not make a difference between image-space displacements originated from moving objects in the space and the ego-motion of the moving viewpoint. In the case of optical flow-based moving object segmentation, camera ego-motion compensation is essential. Hereby, we show the preliminary results of a moving viewpoint optical flow ego-motion filtering method, using two dimensional optical flow, image depth information and the camera holder robot arm’s state of motion. We tested its accuracy through physical experiments, where the camera was fixed on a robot arm, and a test object was attached onto an other robot arm. The test object and the camera were moved relative to each other along given trajectories in different scenarios. We validated our method for optical flow background filtering, which showed 94.88% mean accuracy in the different test cases. Furthermore, we tested the proposed algorithm for moving object state of motion estimation, which showed high accuracy in the case of translational and rotational movements without depth variation, but lower accuracy, when the relative motion produced change in depth, or the camera and the moving object move in the same directions. The proposed method with future work including outlier filtering and optimisation could become useful in various robot navigation applications and optical flow-based computer vision problems.

Paper Citation

in Harvard Style

Elek R., Elek R., Károly A., Károly A., Haidegger T., Haidegger T., Galambos P. and Galambos P. (2020). Towards Optical Flow Ego-motion Compensation for Moving Object Segmentation.In Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS, ISBN 978-989-758-479-4, pages 114-120. DOI: 10.5220/0010136301140120

in Bibtex Style

@conference{robovis20,
author={Renáta Elek and Renáta Elek and Artúr Károly and Artúr Károly and Tamás Haidegger and Tamás Haidegger and Péter Galambos and Péter Galambos},
title={Towards Optical Flow Ego-motion Compensation for Moving Object Segmentation},
booktitle={Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,},
year={2020},
pages={114-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010136301140120},
isbn={978-989-758-479-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,
TI - Towards Optical Flow Ego-motion Compensation for Moving Object Segmentation
SN - 978-989-758-479-4
AU - Elek R.
AU - Elek R.
AU - Károly A.
AU - Károly A.
AU - Haidegger T.
AU - Haidegger T.
AU - Galambos P.
AU - Galambos P.
PY - 2020
SP - 114
EP - 120
DO - 10.5220/0010136301140120