Stop line detection and distance measurement for road intersection based on deep learning neural network

Guan Ting Lin; Patrisia Sherryl Santoso; Che Tsung Lin; Chia Chi Tsai; Jiun-In Guo

doi:10.1109/APSIPA.2017.8282121

Stop line detection and distance measurement for road intersection based on deep learning neural network

Guan Ting Lin, Patrisia Sherryl Santoso, Che Tsung Lin, Chia Chi Tsai, Jiun-In Guo

電子研究所

研究成果: Conference contribution › 同行評審

4 引文斯高帕斯（Scopus）

摘要

In this paper, we introduce Boost-CNN, a robust stop-line detector that can detect objects (stop line) with competitive tradeoff between speed and accuracy. Boost-CNN consists of an AdaBoost classifier and a CNN. The former is our region proposal generator and it is further combined with the later to be a stop-line detector. In addition, an automatic hard mining method is proposed to reduce the number of false alarm. Our proposed detector achieves 91.5% in accuracy and has 100 FPS performance in test time (performed on NVIDIA DIGITS DevBox and Titan X GPU).

原文	English
主出版物標題	Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	692-695
頁數	4
ISBN（電子）	9781538615423
DOIs	https://doi.org/10.1109/APSIPA.2017.8282121
出版狀態	Published - 2 7月 2017
事件	9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia 持續時間: 12 12月 2017 → 15 12月 2017

出版系列

名字	Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
卷	2018-February

Conference

Conference	9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
國家/地區	Malaysia
城市	Kuala Lumpur
期間	12/12/17 → 15/12/17

存取文件

10.1109/APSIPA.2017.8282121

其它文件與鏈接

Link to publication in Scopus

引用此

Lin, G. T., Santoso, P. S., Lin, C. T., Tsai, C. C., & Guo, J.-I. (2017). Stop line detection and distance measurement for road intersection based on deep learning neural network. 於 Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 (頁 692-695). (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017; 卷 2018-February). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2017.8282121

Lin, Guan Ting ; Santoso, Patrisia Sherryl ; Lin, Che Tsung 等. / Stop line detection and distance measurement for road intersection based on deep learning neural network. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 頁 692-695 (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017).

@inproceedings{3960b180c07049aead7a50443b08f0b0,

title = "Stop line detection and distance measurement for road intersection based on deep learning neural network",

abstract = "In this paper, we introduce Boost-CNN, a robust stop-line detector that can detect objects (stop line) with competitive tradeoff between speed and accuracy. Boost-CNN consists of an AdaBoost classifier and a CNN. The former is our region proposal generator and it is further combined with the later to be a stop-line detector. In addition, an automatic hard mining method is proposed to reduce the number of false alarm. Our proposed detector achieves 91.5% in accuracy and has 100 FPS performance in test time (performed on NVIDIA DIGITS DevBox and Titan X GPU).",

author = "Lin, {Guan Ting} and Santoso, {Patrisia Sherryl} and Lin, {Che Tsung} and Tsai, {Chia Chi} and Jiun-In Guo",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 ; Conference date: 12-12-2017 Through 15-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/APSIPA.2017.8282121",

language = "English",

series = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",

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

pages = "692--695",

booktitle = "Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017",

address = "United States",

}

Lin, GT, Santoso, PS, Lin, CT, Tsai, CC & Guo, J-I 2017, Stop line detection and distance measurement for road intersection based on deep learning neural network. 於 Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, 卷 2018-February, Institute of Electrical and Electronics Engineers Inc., 頁 692-695, 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, 12/12/17. https://doi.org/10.1109/APSIPA.2017.8282121

Stop line detection and distance measurement for road intersection based on deep learning neural network. / Lin, Guan Ting; Santoso, Patrisia Sherryl; Lin, Che Tsung 等.
Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 692-695 (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017; 卷 2018-February).

研究成果: Conference contribution › 同行評審

TY - GEN

T1 - Stop line detection and distance measurement for road intersection based on deep learning neural network

AU - Lin, Guan Ting

AU - Santoso, Patrisia Sherryl

AU - Lin, Che Tsung

AU - Tsai, Chia Chi

AU - Guo, Jiun-In

PY - 2017/7/2

Y1 - 2017/7/2

N2 - In this paper, we introduce Boost-CNN, a robust stop-line detector that can detect objects (stop line) with competitive tradeoff between speed and accuracy. Boost-CNN consists of an AdaBoost classifier and a CNN. The former is our region proposal generator and it is further combined with the later to be a stop-line detector. In addition, an automatic hard mining method is proposed to reduce the number of false alarm. Our proposed detector achieves 91.5% in accuracy and has 100 FPS performance in test time (performed on NVIDIA DIGITS DevBox and Titan X GPU).

AB - In this paper, we introduce Boost-CNN, a robust stop-line detector that can detect objects (stop line) with competitive tradeoff between speed and accuracy. Boost-CNN consists of an AdaBoost classifier and a CNN. The former is our region proposal generator and it is further combined with the later to be a stop-line detector. In addition, an automatic hard mining method is proposed to reduce the number of false alarm. Our proposed detector achieves 91.5% in accuracy and has 100 FPS performance in test time (performed on NVIDIA DIGITS DevBox and Titan X GPU).

UR - http://www.scopus.com/inward/record.url?scp=85050562797&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2017.8282121

DO - 10.1109/APSIPA.2017.8282121

M3 - Conference contribution

AN - SCOPUS:85050562797

T3 - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

SP - 692

EP - 695

BT - Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017

Y2 - 12 December 2017 through 15 December 2017

ER -

Lin GT, Santoso PS, Lin CT, Tsai CC, Guo JI. Stop line detection and distance measurement for road intersection based on deep learning neural network. 於 Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 692-695. (Proceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017). doi: 10.1109/APSIPA.2017.8282121

Stop line detection and distance measurement for road intersection based on deep learning neural network

摘要

出版系列

Conference

存取文件

其它文件與鏈接

指紋

引用此