Scene-guided region proposal re-ranking method for on-road vehicle candidate generation

Zhixiong Nan; Yang Feng; Jiawei He; Ping Wei; Linhai Xu; Hongbin Sun; Nanning Zheng

doi:10.1109/IVS.2019.8814149

Scene-guided region proposal re-ranking method for on-road vehicle candidate generation

Zhixiong Nan
, Yang Feng
, Jiawei He
, Ping Wei
, Linhai Xu
, Hongbin Sun
, Nanning Zheng

College of Artificial Intelligence and Robotics

Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Vehicle candidate generation is important for vehicle detection. Existing vehicle detection studies usually employ general-purpose region proposal methods to generate vehicle candidates, which do not consider the specificity of on-road vehicles in traffic scenes. In this paper, we propose a model to re-rank the candidates that are generated by general-purpose region proposal methods. Our model considers the specificity of on-road vehicle candidate generation in traffic scenes by encoding global-local semantic context and location-size geometric compatibility. In the experiments, we test our model on three art-of-the-state region proposal methods using two public datasets. The results show the significant performance improvement is gained after applying our model.

Original language	English
Title of host publication	2019 IEEE Intelligent Vehicles Symposium, IV 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2377-2382
Number of pages	6
ISBN (Electronic)	9781728105604
DOIs	https://doi.org/10.1109/IVS.2019.8814149
State	Published - Jun 2019
Event	30th IEEE Intelligent Vehicles Symposium, IV 2019 - Paris, France Duration: 9 Jun 2019 → 12 Jun 2019

Publication series

Name	IEEE Intelligent Vehicles Symposium, Proceedings
Volume	2019-June

Conference

Conference	30th IEEE Intelligent Vehicles Symposium, IV 2019
Country/Territory	France
City	Paris
Period	9/06/19 → 12/06/19

Access to Document

10.1109/IVS.2019.8814149

Cite this

Nan, Z., Feng, Y., He, J., Wei, P., Xu, L., Sun, H., & Zheng, N. (2019). Scene-guided region proposal re-ranking method for on-road vehicle candidate generation. In 2019 IEEE Intelligent Vehicles Symposium, IV 2019 (pp. 2377-2382). Article 8814149 (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2019-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVS.2019.8814149

@inproceedings{79003272c8584af7acd5aede7875276a,

title = "Scene-guided region proposal re-ranking method for on-road vehicle candidate generation",

abstract = "Vehicle candidate generation is important for vehicle detection. Existing vehicle detection studies usually employ general-purpose region proposal methods to generate vehicle candidates, which do not consider the specificity of on-road vehicles in traffic scenes. In this paper, we propose a model to re-rank the candidates that are generated by general-purpose region proposal methods. Our model considers the specificity of on-road vehicle candidate generation in traffic scenes by encoding global-local semantic context and location-size geometric compatibility. In the experiments, we test our model on three art-of-the-state region proposal methods using two public datasets. The results show the significant performance improvement is gained after applying our model.",

author = "Zhixiong Nan and Yang Feng and Jiawei He and Ping Wei and Linhai Xu and Hongbin Sun and Nanning Zheng",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 30th IEEE Intelligent Vehicles Symposium, IV 2019 ; Conference date: 09-06-2019 Through 12-06-2019",

year = "2019",

month = jun,

doi = "10.1109/IVS.2019.8814149",

language = "英语",

series = "IEEE Intelligent Vehicles Symposium, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2377--2382",

booktitle = "2019 IEEE Intelligent Vehicles Symposium, IV 2019",

}

Nan, Z, Feng, Y, He, J, Wei, P, Xu, L, Sun, H & Zheng, N 2019, Scene-guided region proposal re-ranking method for on-road vehicle candidate generation. in 2019 IEEE Intelligent Vehicles Symposium, IV 2019., 8814149, IEEE Intelligent Vehicles Symposium, Proceedings, vol. 2019-June, Institute of Electrical and Electronics Engineers Inc., pp. 2377-2382, 30th IEEE Intelligent Vehicles Symposium, IV 2019, Paris, France, 9/06/19. https://doi.org/10.1109/IVS.2019.8814149

Scene-guided region proposal re-ranking method for on-road vehicle candidate generation. / Nan, Zhixiong; Feng, Yang; He, Jiawei et al.
2019 IEEE Intelligent Vehicles Symposium, IV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2377-2382 8814149 (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2019-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Scene-guided region proposal re-ranking method for on-road vehicle candidate generation

AU - Nan, Zhixiong

AU - Feng, Yang

AU - He, Jiawei

AU - Wei, Ping

AU - Xu, Linhai

AU - Sun, Hongbin

AU - Zheng, Nanning

PY - 2019/6

Y1 - 2019/6

N2 - Vehicle candidate generation is important for vehicle detection. Existing vehicle detection studies usually employ general-purpose region proposal methods to generate vehicle candidates, which do not consider the specificity of on-road vehicles in traffic scenes. In this paper, we propose a model to re-rank the candidates that are generated by general-purpose region proposal methods. Our model considers the specificity of on-road vehicle candidate generation in traffic scenes by encoding global-local semantic context and location-size geometric compatibility. In the experiments, we test our model on three art-of-the-state region proposal methods using two public datasets. The results show the significant performance improvement is gained after applying our model.

AB - Vehicle candidate generation is important for vehicle detection. Existing vehicle detection studies usually employ general-purpose region proposal methods to generate vehicle candidates, which do not consider the specificity of on-road vehicles in traffic scenes. In this paper, we propose a model to re-rank the candidates that are generated by general-purpose region proposal methods. Our model considers the specificity of on-road vehicle candidate generation in traffic scenes by encoding global-local semantic context and location-size geometric compatibility. In the experiments, we test our model on three art-of-the-state region proposal methods using two public datasets. The results show the significant performance improvement is gained after applying our model.

UR - https://www.scopus.com/pages/publications/85072280966

U2 - 10.1109/IVS.2019.8814149

DO - 10.1109/IVS.2019.8814149

M3 - 会议稿件

AN - SCOPUS:85072280966

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 2377

EP - 2382

BT - 2019 IEEE Intelligent Vehicles Symposium, IV 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 30th IEEE Intelligent Vehicles Symposium, IV 2019

Y2 - 9 June 2019 through 12 June 2019

ER -

Scene-guided region proposal re-ranking method for on-road vehicle candidate generation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this