Learning to tell brake lights with convolutional features

Guangyu Zhong; Yi Hsuan Tsai; Yi Ting Chen; Xue Mei; Danil Prokhorov; Michael James; Ming Hsuan Yang

doi:10.1109/ITSC.2016.7795765

Learning to tell brake lights with convolutional features

Guangyu Zhong, Yi Hsuan Tsai, Yi Ting Chen, Xue Mei, Danil Prokhorov, Michael James, Ming Hsuan Yang

College of Computing

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

19 Citations (Scopus)

Abstract

In this paper, we present a learning-based brake light classification algorithm for intelligent driver-Assistance systems. State-of-The-Art approaches apply different image processing techniques with hand-crafted features to determine whether brake lights are on or off. In contrast, we learn a brake light classifier based on discriminative color descriptors and convolutional features fine-Tuned for traffic scenes. We show how brake light regions can be segmented and classified in one framework. Numerous experimental results show that the proposed algorithm performs well against state-of-The-Art alternatives in real-world scenes.

Original language	English
Title of host publication	2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1558-1563
Number of pages	6
ISBN (Electronic)	9781509018895
DOIs	https://doi.org/10.1109/ITSC.2016.7795765
Publication status	Published - 2016 Dec 22
Event	19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016 - Rio de Janeiro, Brazil Duration: 2016 Nov 1 → 2016 Nov 4

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Conference

Conference	19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016
Country/Territory	Brazil
City	Rio de Janeiro
Period	16/11/1 → 16/11/4

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

All Science Journal Classification (ASJC) codes

Automotive Engineering
Mechanical Engineering
Computer Science Applications

Access to Document

10.1109/ITSC.2016.7795765

Cite this

Zhong, G., Tsai, Y. H., Chen, Y. T., Mei, X., Prokhorov, D., James, M., & Yang, M. H. (2016). Learning to tell brake lights with convolutional features. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016 (pp. 1558-1563). Article 7795765 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC.2016.7795765

@inproceedings{d543d63f76e54f7e85de329169d773b7,

title = "Learning to tell brake lights with convolutional features",

abstract = "In this paper, we present a learning-based brake light classification algorithm for intelligent driver-Assistance systems. State-of-The-Art approaches apply different image processing techniques with hand-crafted features to determine whether brake lights are on or off. In contrast, we learn a brake light classifier based on discriminative color descriptors and convolutional features fine-Tuned for traffic scenes. We show how brake light regions can be segmented and classified in one framework. Numerous experimental results show that the proposed algorithm performs well against state-of-The-Art alternatives in real-world scenes.",

author = "Guangyu Zhong and Tsai, {Yi Hsuan} and Chen, {Yi Ting} and Xue Mei and Danil Prokhorov and Michael James and Yang, {Ming Hsuan}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016 ; Conference date: 01-11-2016 Through 04-11-2016",

year = "2016",

month = dec,

day = "22",

doi = "10.1109/ITSC.2016.7795765",

language = "English",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

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

pages = "1558--1563",

booktitle = "2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016",

address = "United States",

}

Zhong, G, Tsai, YH, Chen, YT, Mei, X, Prokhorov, D, James, M & Yang, MH 2016, Learning to tell brake lights with convolutional features. in 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016., 7795765, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Institute of Electrical and Electronics Engineers Inc., pp. 1558-1563, 19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016, Rio de Janeiro, Brazil, 16/11/1. https://doi.org/10.1109/ITSC.2016.7795765

Learning to tell brake lights with convolutional features. / Zhong, Guangyu; Tsai, Yi Hsuan; Chen, Yi Ting et al.
2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1558-1563 7795765 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

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

TY - GEN

T1 - Learning to tell brake lights with convolutional features

AU - Zhong, Guangyu

AU - Tsai, Yi Hsuan

AU - Chen, Yi Ting

AU - Mei, Xue

AU - Prokhorov, Danil

AU - James, Michael

AU - Yang, Ming Hsuan

PY - 2016/12/22

Y1 - 2016/12/22

N2 - In this paper, we present a learning-based brake light classification algorithm for intelligent driver-Assistance systems. State-of-The-Art approaches apply different image processing techniques with hand-crafted features to determine whether brake lights are on or off. In contrast, we learn a brake light classifier based on discriminative color descriptors and convolutional features fine-Tuned for traffic scenes. We show how brake light regions can be segmented and classified in one framework. Numerous experimental results show that the proposed algorithm performs well against state-of-The-Art alternatives in real-world scenes.

AB - In this paper, we present a learning-based brake light classification algorithm for intelligent driver-Assistance systems. State-of-The-Art approaches apply different image processing techniques with hand-crafted features to determine whether brake lights are on or off. In contrast, we learn a brake light classifier based on discriminative color descriptors and convolutional features fine-Tuned for traffic scenes. We show how brake light regions can be segmented and classified in one framework. Numerous experimental results show that the proposed algorithm performs well against state-of-The-Art alternatives in real-world scenes.

UR - http://www.scopus.com/inward/record.url?scp=85010082103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010082103&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2016.7795765

DO - 10.1109/ITSC.2016.7795765

M3 - Conference contribution

AN - SCOPUS:85010082103

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 1558

EP - 1563

BT - 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th IEEE International Conference on Intelligent Transportation Systems, ITSC 2016

Y2 - 1 November 2016 through 4 November 2016

ER -

Zhong G, Tsai YH, Chen YT, Mei X, Prokhorov D, James M et al. Learning to tell brake lights with convolutional features. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1558-1563. 7795765. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC.2016.7795765

Learning to tell brake lights with convolutional features

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this