A novel video detection design based on modified adaboost algorithm and HSV model

Xiao Luo; Huatao Zhao; Harutoshi Ogai; Chen Zhu

doi:10.1109/IAEAC.2017.8054437

A novel video detection design based on modified adaboost algorithm and HSV model

Xiao Luo, Huatao Zhao, Harutoshi Ogai, Chen Zhu

大学院情報生産システム研究科

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

In modern traffic systems, accurate video detection is a key challenge for traffic management. Aiming at the problem of public bus detection, this paper proposes a video detection method to well recognize the buses. Firstly, we employ the foreground detection method to find the moving vehicles. And then a training classifier which consists of the improved Adaboost algorithm and Haar-like features is proposed to filter undesired vehicles. Secondly, we use the Canny operator to locate bus characteristics, and further detect the bus with the modified HSV model. This design is tested on the Visual Stadio and OpenCV platform in which load the urban transport data as the samples. The test results show that our detection method has better robustness than both three-frame differential method and hybrid Gaussian method, and the accuracy of detection on the window positioning is more than 93 percent.

本文言語	English
ホスト出版物のタイトル	Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	2328-2331
ページ数	4
ISBN（電子版）	9781467389778
DOI	https://doi.org/10.1109/IAEAC.2017.8054437
出版ステータス	Published - 2017 9月 29
イベント	2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017 - Chongqing, China 継続期間: 2017 3月 25 → 2017 3月 26

Other

Other	2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017
国/地域	China
City	Chongqing
Period	17/3/25 → 17/3/26

ASJC Scopus subject areas

コンピュータネットワークおよび通信
コンピュータビジョンおよびパターン認識
ハードウェアとアーキテクチャ
情報システム
電子工学および電気工学
制御と最適化
情報システムおよび情報管理

文献へのアクセス

10.1109/IAEAC.2017.8054437

他のファイルとリンク

引用スタイル

Luo, X., Zhao, H., Ogai, H., & Zhu, C. (2017). A novel video detection design based on modified adaboost algorithm and HSV model. In Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017 (pp. 2328-2331). Article 8054437 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IAEAC.2017.8054437

A novel video detection design based on modified adaboost algorithm and HSV model. / Luo, Xiao; Zhao, Huatao; Ogai, Harutoshi その他.
Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2328-2331 8054437.

研究成果: Conference contribution

Luo, X, Zhao, H, Ogai, H & Zhu, C 2017, A novel video detection design based on modified adaboost algorithm and HSV model. in Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017., 8054437, Institute of Electrical and Electronics Engineers Inc., pp. 2328-2331, 2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017, Chongqing, China, 17/3/25. https://doi.org/10.1109/IAEAC.2017.8054437

@inproceedings{145ae9ce93ed409fa2adc34d0cbf57d8,

title = "A novel video detection design based on modified adaboost algorithm and HSV model",

abstract = "In modern traffic systems, accurate video detection is a key challenge for traffic management. Aiming at the problem of public bus detection, this paper proposes a video detection method to well recognize the buses. Firstly, we employ the foreground detection method to find the moving vehicles. And then a training classifier which consists of the improved Adaboost algorithm and Haar-like features is proposed to filter undesired vehicles. Secondly, we use the Canny operator to locate bus characteristics, and further detect the bus with the modified HSV model. This design is tested on the Visual Stadio and OpenCV platform in which load the urban transport data as the samples. The test results show that our detection method has better robustness than both three-frame differential method and hybrid Gaussian method, and the accuracy of detection on the window positioning is more than 93 percent.",

keywords = "Adaboost algorithm, HSV model, Intelligent traffic, Video detection",

author = "Xiao Luo and Huatao Zhao and Harutoshi Ogai and Chen Zhu",

year = "2017",

month = sep,

day = "29",

doi = "10.1109/IAEAC.2017.8054437",

language = "English",

pages = "2328--2331",

booktitle = "Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017",

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

note = "2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017 ; Conference date: 25-03-2017 Through 26-03-2017",

}

TY - GEN

T1 - A novel video detection design based on modified adaboost algorithm and HSV model

AU - Luo, Xiao

AU - Zhao, Huatao

AU - Ogai, Harutoshi

AU - Zhu, Chen

PY - 2017/9/29

Y1 - 2017/9/29

N2 - In modern traffic systems, accurate video detection is a key challenge for traffic management. Aiming at the problem of public bus detection, this paper proposes a video detection method to well recognize the buses. Firstly, we employ the foreground detection method to find the moving vehicles. And then a training classifier which consists of the improved Adaboost algorithm and Haar-like features is proposed to filter undesired vehicles. Secondly, we use the Canny operator to locate bus characteristics, and further detect the bus with the modified HSV model. This design is tested on the Visual Stadio and OpenCV platform in which load the urban transport data as the samples. The test results show that our detection method has better robustness than both three-frame differential method and hybrid Gaussian method, and the accuracy of detection on the window positioning is more than 93 percent.

AB - In modern traffic systems, accurate video detection is a key challenge for traffic management. Aiming at the problem of public bus detection, this paper proposes a video detection method to well recognize the buses. Firstly, we employ the foreground detection method to find the moving vehicles. And then a training classifier which consists of the improved Adaboost algorithm and Haar-like features is proposed to filter undesired vehicles. Secondly, we use the Canny operator to locate bus characteristics, and further detect the bus with the modified HSV model. This design is tested on the Visual Stadio and OpenCV platform in which load the urban transport data as the samples. The test results show that our detection method has better robustness than both three-frame differential method and hybrid Gaussian method, and the accuracy of detection on the window positioning is more than 93 percent.

KW - Adaboost algorithm

KW - HSV model

KW - Intelligent traffic

KW - Video detection

UR - http://www.scopus.com/inward/record.url?scp=85034574253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034574253&partnerID=8YFLogxK

U2 - 10.1109/IAEAC.2017.8054437

DO - 10.1109/IAEAC.2017.8054437

M3 - Conference contribution

AN - SCOPUS:85034574253

SP - 2328

EP - 2331

BT - Proceedings of 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2017

Y2 - 25 March 2017 through 26 March 2017

ER -

A novel video detection design based on modified adaboost algorithm and HSV model

抄録

Other

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル