Geometry-aware traffic flow analysis by detection and tracking

Honghui Shi; Zhonghao Wang; Yang Zhang; Xinchao Wang; Thomas Huang

doi:10.1109/CVPRW.2018.00023

Geometry-aware traffic flow analysis by detection and tracking

Honghui Shi, Zhonghao Wang, Yang Zhang, Xinchao Wang, Thomas Huang

Coordinated Science Lab

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

Abstract

In the second Nvidia AI City Challenge hosted in 2018, the traffic flow analysis challenge proposes an interest task that requires participants to predict the speed of vehicles on road from various traffic camera videos. We propose a simple yet effective method combing both learning based detection and geometric calibration based estimation. We use a learning based method to detect and track vehicles, and use a geometry based camera calibration method to calculate the speed of those vehicles. We achieve a perfect detection rate of target vehicles and a root mean square error (RMSE) of 6.6674 in predicting the vehicle speed, which rank us the third place in the competition.

Original language	English (US)
Title of host publication	Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Publisher	IEEE Computer Society
Pages	116-120
Number of pages	5
ISBN (Electronic)	9781538661000
DOIs	https://doi.org/10.1109/CVPRW.2018.00023
State	Published - Dec 13 2018
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States Duration: Jun 18 2018 → Jun 22 2018

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2018-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Other

Other	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Country/Territory	United States
City	Salt Lake City
Period	6/18/18 → 6/22/18

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Online availability

10.1109/CVPRW.2018.00023

Library availability

Discover UIUC Full Text

Cite this

Shi, H., Wang, Z., Zhang, Y., Wang, X., & Huang, T. (2018). Geometry-aware traffic flow analysis by detection and tracking. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 116-120). Article 8575394 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00023

Geometry-aware traffic flow analysis by detection and tracking. / Shi, Honghui; Wang, Zhonghao; Zhang, Yang et al.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 116-120 8575394 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

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

Shi, H, Wang, Z, Zhang, Y, Wang, X & Huang, T 2018, Geometry-aware traffic flow analysis by detection and tracking. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575394, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 116-120, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 6/18/18. https://doi.org/10.1109/CVPRW.2018.00023

Shi H, Wang Z, Zhang Y, Wang X, Huang T. Geometry-aware traffic flow analysis by detection and tracking. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society. 2018. p. 116-120. 8575394. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2018.00023

@inproceedings{f068199a77e3417a951b451b0bd17d8e,

title = "Geometry-aware traffic flow analysis by detection and tracking",

abstract = "In the second Nvidia AI City Challenge hosted in 2018, the traffic flow analysis challenge proposes an interest task that requires participants to predict the speed of vehicles on road from various traffic camera videos. We propose a simple yet effective method combing both learning based detection and geometric calibration based estimation. We use a learning based method to detect and track vehicles, and use a geometry based camera calibration method to calculate the speed of those vehicles. We achieve a perfect detection rate of target vehicles and a root mean square error (RMSE) of 6.6674 in predicting the vehicle speed, which rank us the third place in the competition.",

author = "Honghui Shi and Zhonghao Wang and Yang Zhang and Xinchao Wang and Thomas Huang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

month = dec,

day = "13",

doi = "10.1109/CVPRW.2018.00023",

language = "English (US)",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "116--120",

booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",

}

TY - GEN

T1 - Geometry-aware traffic flow analysis by detection and tracking

AU - Shi, Honghui

AU - Wang, Zhonghao

AU - Zhang, Yang

AU - Wang, Xinchao

AU - Huang, Thomas

PY - 2018/12/13

Y1 - 2018/12/13

N2 - In the second Nvidia AI City Challenge hosted in 2018, the traffic flow analysis challenge proposes an interest task that requires participants to predict the speed of vehicles on road from various traffic camera videos. We propose a simple yet effective method combing both learning based detection and geometric calibration based estimation. We use a learning based method to detect and track vehicles, and use a geometry based camera calibration method to calculate the speed of those vehicles. We achieve a perfect detection rate of target vehicles and a root mean square error (RMSE) of 6.6674 in predicting the vehicle speed, which rank us the third place in the competition.

AB - In the second Nvidia AI City Challenge hosted in 2018, the traffic flow analysis challenge proposes an interest task that requires participants to predict the speed of vehicles on road from various traffic camera videos. We propose a simple yet effective method combing both learning based detection and geometric calibration based estimation. We use a learning based method to detect and track vehicles, and use a geometry based camera calibration method to calculate the speed of those vehicles. We achieve a perfect detection rate of target vehicles and a root mean square error (RMSE) of 6.6674 in predicting the vehicle speed, which rank us the third place in the competition.

UR - http://www.scopus.com/inward/record.url?scp=85060883108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060883108&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00023

DO - 10.1109/CVPRW.2018.00023

M3 - Conference contribution

AN - SCOPUS:85060883108

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 116

EP - 120

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

Geometry-aware traffic flow analysis by detection and tracking

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this