Joint Monocular 3D Car Shape Estimation and Landmark Localization via Cascaded Regression

Yanan Miao, Huan Ma, Jia Cui, Xiaoming Tao

2018

Abstract

Previous works on reconstruction of a three-dimensional (3D) point shape model commonly use a two-step framework. Precisely localizing a series of feature points in an image is performed on the first step. Then the second procedure attempts to fit the 3D data to the observations to get the real 3D shape. Such an approach has high time consumption, and easily gets stuck into local minimum. To address this problem, we propose a method to jointly estimate the global 3D geometric structure of car and localize 2D landmarks from a single viewpoint image. First, we parametrizing the 3D shape by the coefficients of the linear combination of a set of predefined shape bases. Second, we adopt a cascaded regression framework to regress the global shape encoded by the prior bases, by jointly minimizing the appearance and shape fitting differences under a weak projection camera model. The position fitting item can help cope with the description ambiguity of local appearance, and provide more information for 3D reconstruction. Experimental results on a multi-view car dataset demonstrate favourable improvements on pose estimation and shape prediction, compared with some previous methods.

Paper Citation

in Harvard Style

Miao Y., Ma H., Cui J. and Tao X. (2018). Joint Monocular 3D Car Shape Estimation and Landmark Localization via Cascaded Regression.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 222-232. DOI: 10.5220/0006715102220232

in Bibtex Style

@conference{icpram18,
author={Yanan Miao and Huan Ma and Jia Cui and Xiaoming Tao},
title={Joint Monocular 3D Car Shape Estimation and Landmark Localization via Cascaded Regression},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={222-232},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006715102220232},
isbn={978-989-758-276-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Joint Monocular 3D Car Shape Estimation and Landmark Localization via Cascaded Regression
SN - 978-989-758-276-9
AU - Miao Y.
AU - Ma H.
AU - Cui J.
AU - Tao X.
PY - 2018
SP - 222
EP - 232
DO - 10.5220/0006715102220232