Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops

Hsu Yung Cheng; Chih Chang Yu

doi:10.1109/AVSS.2019.8909906

Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops

Hsu Yung Cheng, Chih Chang Yu

Department of Computer Science and Information Engineering

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

Abstract

A traffic flow estimation mechanism is proposed for highway surveillance systems with scenes tampered by raindrops. To detect rain-drop tampered scenes, features are extracted via salient region detection and block segmentation. Feature selection is performed to select more discriminative features. For traffic flow estimation, daytime and night time models are performed separately to adapt to the characteristics of the surveillance scenes. Finally, an effective graph-based mapping method is designed to map the vehicle count sequences to per minute traffic flow. The system is tested with a highly challenging dataset. The accuracy of the traffic flow analysis is satisfying with low mean absolute errors even when the cameras are seriously tampered by rain.

Original language	English
Title of host publication	2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728109909
DOIs	https://doi.org/10.1109/AVSS.2019.8909906
State	Published - Sep 2019
Event	16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019 - Taipei, Taiwan Duration: 18 Sep 2019 → 21 Sep 2019

Publication series

Name	2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019

Conference

Conference	16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019
Country/Territory	Taiwan
City	Taipei
Period	18/09/19 → 21/09/19

Keywords

Feature Extraction
Feature Selection
Highway Surveillance
Tampered Scene
Traffic Parameter Estimation

Access to Document

10.1109/AVSS.2019.8909906

Highly Automated Intelligent Surveillance and Traffic Management System for Integrated Heterogeneous Roads(2/2)
Cheng, H.-Y. (PI)
1/08/19 → 31/07/20
Project: Research

Cite this

Cheng, H. Y., & Yu, C. C. (2019). Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops. In 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019 Article 8909906 (2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2019.8909906

Cheng, Hsu Yung ; Yu, Chih Chang. / Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops. 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019).

@inproceedings{579db5076d324357bb7c3993df957b41,

title = "Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops",

abstract = "A traffic flow estimation mechanism is proposed for highway surveillance systems with scenes tampered by raindrops. To detect rain-drop tampered scenes, features are extracted via salient region detection and block segmentation. Feature selection is performed to select more discriminative features. For traffic flow estimation, daytime and night time models are performed separately to adapt to the characteristics of the surveillance scenes. Finally, an effective graph-based mapping method is designed to map the vehicle count sequences to per minute traffic flow. The system is tested with a highly challenging dataset. The accuracy of the traffic flow analysis is satisfying with low mean absolute errors even when the cameras are seriously tampered by rain.",

keywords = "Feature Extraction, Feature Selection, Highway Surveillance, Tampered Scene, Traffic Parameter Estimation",

author = "Cheng, {Hsu Yung} and Yu, {Chih Chang}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019 ; Conference date: 18-09-2019 Through 21-09-2019",

year = "2019",

month = sep,

doi = "10.1109/AVSS.2019.8909906",

language = "???core.languages.en_GB???",

series = "2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019",

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

booktitle = "2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019",

}

Cheng, HY & Yu, CC 2019, Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops. in 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019., 8909906, 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019, Institute of Electrical and Electronics Engineers Inc., 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019, Taipei, Taiwan, 18/09/19. https://doi.org/10.1109/AVSS.2019.8909906

Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops. / Cheng, Hsu Yung; Yu, Chih Chang.
2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8909906 (2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019).

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

TY - GEN

T1 - Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops

AU - Cheng, Hsu Yung

AU - Yu, Chih Chang

PY - 2019/9

Y1 - 2019/9

N2 - A traffic flow estimation mechanism is proposed for highway surveillance systems with scenes tampered by raindrops. To detect rain-drop tampered scenes, features are extracted via salient region detection and block segmentation. Feature selection is performed to select more discriminative features. For traffic flow estimation, daytime and night time models are performed separately to adapt to the characteristics of the surveillance scenes. Finally, an effective graph-based mapping method is designed to map the vehicle count sequences to per minute traffic flow. The system is tested with a highly challenging dataset. The accuracy of the traffic flow analysis is satisfying with low mean absolute errors even when the cameras are seriously tampered by rain.

AB - A traffic flow estimation mechanism is proposed for highway surveillance systems with scenes tampered by raindrops. To detect rain-drop tampered scenes, features are extracted via salient region detection and block segmentation. Feature selection is performed to select more discriminative features. For traffic flow estimation, daytime and night time models are performed separately to adapt to the characteristics of the surveillance scenes. Finally, an effective graph-based mapping method is designed to map the vehicle count sequences to per minute traffic flow. The system is tested with a highly challenging dataset. The accuracy of the traffic flow analysis is satisfying with low mean absolute errors even when the cameras are seriously tampered by rain.

KW - Feature Extraction

KW - Feature Selection

KW - Highway Surveillance

KW - Tampered Scene

KW - Traffic Parameter Estimation

UR - http://www.scopus.com/inward/record.url?scp=85076350323&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2019.8909906

DO - 10.1109/AVSS.2019.8909906

M3 - 會議論文篇章

AN - SCOPUS:85076350323

T3 - 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019

BT - 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019

Y2 - 18 September 2019 through 21 September 2019

ER -

Cheng HY, Yu CC. Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops. In 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8909906. (2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019). doi: 10.1109/AVSS.2019.8909906

Accurate traffic flow estimation for highway surveillance systems with scenes tampered by raindrops

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Highly Automated Intelligent Surveillance and Traffic Management System for Integrated Heterogeneous Roads(2/2)

Cite this