Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Sunghoon JUNG; Minhwan KIM

doi:10.1587/transinf.2014EDP7098

Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image

Sunghoon JUNG, Minhwan KIM

Full Text Views

0

Cite this

Summary :

This paper proposes a novel method for determining a three-dimensional (3D) bounding box to estimate pose (position and orientation) and size of a 3D object corresponding to a segmented object region in an image acquired by a single calibrated camera. The method is designed to work upon an object on the ground and to determine a bounding box aligned to the direction of the object, thereby reducing the number of degrees of freedom in localizing the bounding box to 5 from 9. Observations associated with the structural properties of back-projected object regions on the ground are suggested, which are useful for determining the object points expected to be on the ground. A suitable base is then estimated from the expected on-ground object points by applying to them an assumption of bilateral symmetry. A bounding box with this base is finally constructed by determining its height, such that back-projection of the constructed box onto the ground minimally encloses back-projection of the given object region. Through experiments with some 3D-modelled objects and real objects, we found that a bounding box aligned to the dominant direction estimated from edges with common direction looks natural, and the accuracy of the pose and size is enough for localizing actual on-ground objects in an industrial working space. The proposed method is expected to be used effectively in the fields of smart surveillance and autonomous navigation.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.11 pp.2919-2934

Publication Date: 2014/11/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDP7098

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Sunghoon JUNG
Pusan National University
Minhwan KIM
Pusan National University

Keyword

3D bounding box estimation, object localization, dominant direction of object, back-projection of image region, smart surveillance

Cite this

Copy

Sunghoon JUNG, Minhwan KIM, "Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 11, pp. 2919-2934, November 2014, doi: 10.1587/transinf.2014EDP7098.
Abstract: This paper proposes a novel method for determining a three-dimensional (3D) bounding box to estimate pose (position and orientation) and size of a 3D object corresponding to a segmented object region in an image acquired by a single calibrated camera. The method is designed to work upon an object on the ground and to determine a bounding box aligned to the direction of the object, thereby reducing the number of degrees of freedom in localizing the bounding box to 5 from 9. Observations associated with the structural properties of back-projected object regions on the ground are suggested, which are useful for determining the object points expected to be on the ground. A suitable base is then estimated from the expected on-ground object points by applying to them an assumption of bilateral symmetry. A bounding box with this base is finally constructed by determining its height, such that back-projection of the constructed box onto the ground minimally encloses back-projection of the given object region. Through experiments with some 3D-modelled objects and real objects, we found that a bounding box aligned to the dominant direction estimated from edges with common direction looks natural, and the accuracy of the pose and size is enough for localizing actual on-ground objects in an industrial working space. The proposed method is expected to be used effectively in the fields of smart surveillance and autonomous navigation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7098/_p

Copy

@ARTICLE{e97-d_11_2919,
author={Sunghoon JUNG, Minhwan KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image},
year={2014},
volume={E97-D},
number={11},
pages={2919-2934},
abstract={This paper proposes a novel method for determining a three-dimensional (3D) bounding box to estimate pose (position and orientation) and size of a 3D object corresponding to a segmented object region in an image acquired by a single calibrated camera. The method is designed to work upon an object on the ground and to determine a bounding box aligned to the direction of the object, thereby reducing the number of degrees of freedom in localizing the bounding box to 5 from 9. Observations associated with the structural properties of back-projected object regions on the ground are suggested, which are useful for determining the object points expected to be on the ground. A suitable base is then estimated from the expected on-ground object points by applying to them an assumption of bilateral symmetry. A bounding box with this base is finally constructed by determining its height, such that back-projection of the constructed box onto the ground minimally encloses back-projection of the given object region. Through experiments with some 3D-modelled objects and real objects, we found that a bounding box aligned to the dominant direction estimated from edges with common direction looks natural, and the accuracy of the pose and size is enough for localizing actual on-ground objects in an industrial working space. The proposed method is expected to be used effectively in the fields of smart surveillance and autonomous navigation.},
keywords={},
doi={10.1587/transinf.2014EDP7098},
ISSN={1745-1361},
month={November},}

Copy

TY - JOUR
TI - Estimation of a 3D Bounding Box for a Segmented Object Region in a Single Image
T2 - IEICE TRANSACTIONS on Information
SP - 2919
EP - 2934
AU - Sunghoon JUNG
AU - Minhwan KIM
PY - 2014
DO - 10.1587/transinf.2014EDP7098
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2014
AB - This paper proposes a novel method for determining a three-dimensional (3D) bounding box to estimate pose (position and orientation) and size of a 3D object corresponding to a segmented object region in an image acquired by a single calibrated camera. The method is designed to work upon an object on the ground and to determine a bounding box aligned to the direction of the object, thereby reducing the number of degrees of freedom in localizing the bounding box to 5 from 9. Observations associated with the structural properties of back-projected object regions on the ground are suggested, which are useful for determining the object points expected to be on the ground. A suitable base is then estimated from the expected on-ground object points by applying to them an assumption of bilateral symmetry. A bounding box with this base is finally constructed by determining its height, such that back-projection of the constructed box onto the ground minimally encloses back-projection of the given object region. Through experiments with some 3D-modelled objects and real objects, we found that a bounding box aligned to the dominant direction estimated from edges with common direction looks natural, and the accuracy of the pose and size is enough for localizing actual on-ground objects in an industrial working space. The proposed method is expected to be used effectively in the fields of smart surveillance and autonomous navigation.
ER -