Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines

Minh Triet Tran, Tung Dinh-Duy, Thanh Dat Truong, Vinh Ton-That, Thanh Nhon Do, Quoc An Luong, Thanh An Nguyen, Vinh Tiep Nguyen, Minh N Do

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose our method for vehicle detection with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. Inspired by the idea for tiny object detection, we use Faster R-CNN with Resnet-101 to create different specialized vehicle detectors corresponding to different levels of details and poses. We propose a heuristic to check the fitness of a particular vehicle detector to a specific region in camera's view by the mean velocity direction and the mean object size. By this way, we can determine an adaptive set of appropriate vehicle detectors for each region in camera's view. Thus our system is expected to detect vehicles with high accuracy, both in precision and recall, even with tiny objects. We exploit the U.S. road rules for the length and distance of broken white lines on roads to propose our method for vehicle's velocity estimation using such landmarks. We determine equally-distributed scanlines, virtual parallel lines that are nearly-perpendicular to the road direction, with reference to the line connecting the corresponding ends of multiple broken white lines. From the timespan for a vehicle to cross two consecutive virtual scanlines, we can calculate the average vehicle's velocity within that road segment. We also refine the speed estimation by detecting when a vehicle stops at a traffic light, and smooth the results with a moving average filter. Experiments on the dataset of Traffic Flow Analysis from NVIDIA AI City Challenge 2018 show that our method achieves the perfect detect rate of 100%, the average velocity difference of 6.9762 mph on freeways, and 8.9144 mph on both freeways and urban roads.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages100-107
Number of pages8
ISBN (Electronic)9781538661000
DOIs
StatePublished - Dec 13 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: Jun 18 2018Jun 22 2018

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2018-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
CountryUnited States
CitySalt Lake City
Period6/18/186/22/18

Fingerprint

Detectors
Highway systems
Cameras
Telecommunication traffic
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Tran, M. T., Dinh-Duy, T., Truong, T. D., Ton-That, V., Do, T. N., Luong, Q. A., ... Do, M. N. (2018). Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (pp. 100-107). [8575374] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00021

Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. / Tran, Minh Triet; Dinh-Duy, Tung; Truong, Thanh Dat; Ton-That, Vinh; Do, Thanh Nhon; Luong, Quoc An; Nguyen, Thanh An; Nguyen, Vinh Tiep; Do, Minh N.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. p. 100-107 8575374 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tran, MT, Dinh-Duy, T, Truong, TD, Ton-That, V, Do, TN, Luong, QA, Nguyen, TA, Nguyen, VT & Do, MN 2018, Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018., 8575374, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2018-June, IEEE Computer Society, pp. 100-107, 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.2018.00021
Tran MT, Dinh-Duy T, Truong TD, Ton-That V, Do TN, Luong QA et al. Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society. 2018. p. 100-107. 8575374. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2018.00021
Tran, Minh Triet ; Dinh-Duy, Tung ; Truong, Thanh Dat ; Ton-That, Vinh ; Do, Thanh Nhon ; Luong, Quoc An ; Nguyen, Thanh An ; Nguyen, Vinh Tiep ; Do, Minh N. / Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. IEEE Computer Society, 2018. pp. 100-107 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
@inproceedings{4dac907ec0124338b204b1b1af640003,
title = "Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines",
abstract = "In this paper, we propose our method for vehicle detection with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. Inspired by the idea for tiny object detection, we use Faster R-CNN with Resnet-101 to create different specialized vehicle detectors corresponding to different levels of details and poses. We propose a heuristic to check the fitness of a particular vehicle detector to a specific region in camera's view by the mean velocity direction and the mean object size. By this way, we can determine an adaptive set of appropriate vehicle detectors for each region in camera's view. Thus our system is expected to detect vehicles with high accuracy, both in precision and recall, even with tiny objects. We exploit the U.S. road rules for the length and distance of broken white lines on roads to propose our method for vehicle's velocity estimation using such landmarks. We determine equally-distributed scanlines, virtual parallel lines that are nearly-perpendicular to the road direction, with reference to the line connecting the corresponding ends of multiple broken white lines. From the timespan for a vehicle to cross two consecutive virtual scanlines, we can calculate the average vehicle's velocity within that road segment. We also refine the speed estimation by detecting when a vehicle stops at a traffic light, and smooth the results with a moving average filter. Experiments on the dataset of Traffic Flow Analysis from NVIDIA AI City Challenge 2018 show that our method achieves the perfect detect rate of 100{\%}, the average velocity difference of 6.9762 mph on freeways, and 8.9144 mph on both freeways and urban roads.",
author = "Tran, {Minh Triet} and Tung Dinh-Duy and Truong, {Thanh Dat} and Vinh Ton-That and Do, {Thanh Nhon} and Luong, {Quoc An} and Nguyen, {Thanh An} and Nguyen, {Vinh Tiep} and Do, {Minh N}",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/CVPRW.2018.00021",
language = "English (US)",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "100--107",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",

}

TY - GEN

T1 - Traffic flow analysis with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines

AU - Tran, Minh Triet

AU - Dinh-Duy, Tung

AU - Truong, Thanh Dat

AU - Ton-That, Vinh

AU - Do, Thanh Nhon

AU - Luong, Quoc An

AU - Nguyen, Thanh An

AU - Nguyen, Vinh Tiep

AU - Do, Minh N

PY - 2018/12/13

Y1 - 2018/12/13

N2 - In this paper, we propose our method for vehicle detection with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. Inspired by the idea for tiny object detection, we use Faster R-CNN with Resnet-101 to create different specialized vehicle detectors corresponding to different levels of details and poses. We propose a heuristic to check the fitness of a particular vehicle detector to a specific region in camera's view by the mean velocity direction and the mean object size. By this way, we can determine an adaptive set of appropriate vehicle detectors for each region in camera's view. Thus our system is expected to detect vehicles with high accuracy, both in precision and recall, even with tiny objects. We exploit the U.S. road rules for the length and distance of broken white lines on roads to propose our method for vehicle's velocity estimation using such landmarks. We determine equally-distributed scanlines, virtual parallel lines that are nearly-perpendicular to the road direction, with reference to the line connecting the corresponding ends of multiple broken white lines. From the timespan for a vehicle to cross two consecutive virtual scanlines, we can calculate the average vehicle's velocity within that road segment. We also refine the speed estimation by detecting when a vehicle stops at a traffic light, and smooth the results with a moving average filter. Experiments on the dataset of Traffic Flow Analysis from NVIDIA AI City Challenge 2018 show that our method achieves the perfect detect rate of 100%, the average velocity difference of 6.9762 mph on freeways, and 8.9144 mph on both freeways and urban roads.

AB - In this paper, we propose our method for vehicle detection with multiple adaptive vehicle detectors and velocity estimation with landmark-based scanlines. Inspired by the idea for tiny object detection, we use Faster R-CNN with Resnet-101 to create different specialized vehicle detectors corresponding to different levels of details and poses. We propose a heuristic to check the fitness of a particular vehicle detector to a specific region in camera's view by the mean velocity direction and the mean object size. By this way, we can determine an adaptive set of appropriate vehicle detectors for each region in camera's view. Thus our system is expected to detect vehicles with high accuracy, both in precision and recall, even with tiny objects. We exploit the U.S. road rules for the length and distance of broken white lines on roads to propose our method for vehicle's velocity estimation using such landmarks. We determine equally-distributed scanlines, virtual parallel lines that are nearly-perpendicular to the road direction, with reference to the line connecting the corresponding ends of multiple broken white lines. From the timespan for a vehicle to cross two consecutive virtual scanlines, we can calculate the average vehicle's velocity within that road segment. We also refine the speed estimation by detecting when a vehicle stops at a traffic light, and smooth the results with a moving average filter. Experiments on the dataset of Traffic Flow Analysis from NVIDIA AI City Challenge 2018 show that our method achieves the perfect detect rate of 100%, the average velocity difference of 6.9762 mph on freeways, and 8.9144 mph on both freeways and urban roads.

UR - http://www.scopus.com/inward/record.url?scp=85060878606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060878606&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00021

DO - 10.1109/CVPRW.2018.00021

M3 - Conference contribution

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

SP - 100

EP - 107

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

PB - IEEE Computer Society

ER -