Improved Object Proposals with Geometrical Features for Autonomous Driving
Joint Authors
Feng, Yiliu
Cai, Wanzeng
Liu, Xiaolong
Fu, Huini
Liu, Yafei
Liu, Hengzhu
Source
Issue
Vol. 2017, Issue 2017 (31 Dec. 2017), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2017-04-26
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Telecommunications Engineering
Abstract EN
This paper aims at generating high-quality object proposals for object detection in autonomous driving.
Most existing proposal generation methods are designed for the general object detection, which may not perform well in a particular scene.
We propose several geometrical features suited for autonomous driving and integrate them into state-of-the-art general proposal generation methods.
In particular, we formulate the integration as a feature fusion problem by fusing the geometrical features with existing proposal generation methods in a Bayesian framework.
Experiments on the challenging KITTI benchmark demonstrate that our approach improves the existing methods significantly.
Combined with a convolutional neural net detector, our approach achieves state-of-the-art performance on all three KITTI object classes.
American Psychological Association (APA)
Feng, Yiliu& Cai, Wanzeng& Liu, Xiaolong& Fu, Huini& Liu, Yafei& Liu, Hengzhu. 2017. Improved Object Proposals with Geometrical Features for Autonomous Driving. Mobile Information Systems،Vol. 2017, no. 2017, pp.1-11.
https://search.emarefa.net/detail/BIM-1189005
Modern Language Association (MLA)
Feng, Yiliu…[et al.]. Improved Object Proposals with Geometrical Features for Autonomous Driving. Mobile Information Systems No. 2017 (2017), pp.1-11.
https://search.emarefa.net/detail/BIM-1189005
American Medical Association (AMA)
Feng, Yiliu& Cai, Wanzeng& Liu, Xiaolong& Fu, Huini& Liu, Yafei& Liu, Hengzhu. Improved Object Proposals with Geometrical Features for Autonomous Driving. Mobile Information Systems. 2017. Vol. 2017, no. 2017, pp.1-11.
https://search.emarefa.net/detail/BIM-1189005
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1189005