Weakly-supervised vehicle detection and classification by convolutional neural network

Changyu Jiang; Bailing Zhang

doi:10.1109/CISP-BMEI.2016.7852775

Weakly-supervised vehicle detection and classification by convolutional neural network

Changyu Jiang, Bailing Zhang

School of Advanced Technology

Xi'an Jiaotong-Liverpool University

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

10 Citations (Scopus)

Abstract

Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object bounding boxes, which is expensive and often subjective. In this paper, we propose a vehicle detection and recognition system by applying weakly-supervised convolutional neural network (CNN), with training relying only on image-level labels. Experiments were conducted on a datasets acquired from field-captured traffic surveillance cameras, with vehicle classification performance mAP 98.79% and accuracy 98.28%, and vehicle detection performance mAP 85.26%.

Original language	English
Title of host publication	Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	570-575
Number of pages	6
ISBN (Electronic)	9781509037100
DOIs	https://doi.org/10.1109/CISP-BMEI.2016.7852775
Publication status	Published - 13 Feb 2017
Event	9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 - Datong, China Duration: 15 Oct 2016 → 17 Oct 2016

Publication series

Name	Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

Conference

Conference	9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016
Country/Territory	China
City	Datong
Period	15/10/16 → 17/10/16

Keywords

convolutional neural networks
vehicle detection and recognition
weakly supervised lesrning

Access to Document

10.1109/CISP-BMEI.2016.7852775

Cite this

Jiang, C., & Zhang, B. (2017). Weakly-supervised vehicle detection and classification by convolutional neural network. In Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 (pp. 570-575). Article 7852775 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISP-BMEI.2016.7852775

Jiang, Changyu ; Zhang, Bailing. / Weakly-supervised vehicle detection and classification by convolutional neural network. Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 570-575 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016).

@inproceedings{bf997a7b0cee4d338647dcc32e3c8428,

title = "Weakly-supervised vehicle detection and classification by convolutional neural network",

abstract = "Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object bounding boxes, which is expensive and often subjective. In this paper, we propose a vehicle detection and recognition system by applying weakly-supervised convolutional neural network (CNN), with training relying only on image-level labels. Experiments were conducted on a datasets acquired from field-captured traffic surveillance cameras, with vehicle classification performance mAP 98.79% and accuracy 98.28%, and vehicle detection performance mAP 85.26%.",

keywords = "convolutional neural networks, vehicle detection and recognition, weakly supervised lesrning",

author = "Changyu Jiang and Bailing Zhang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016 ; Conference date: 15-10-2016 Through 17-10-2016",

year = "2017",

month = feb,

day = "13",

doi = "10.1109/CISP-BMEI.2016.7852775",

language = "English",

series = "Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016",

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

pages = "570--575",

booktitle = "Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016",

}

Jiang, C & Zhang, B 2017, Weakly-supervised vehicle detection and classification by convolutional neural network. in Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016., 7852775, Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016, Institute of Electrical and Electronics Engineers Inc., pp. 570-575, 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016, Datong, China, 15/10/16. https://doi.org/10.1109/CISP-BMEI.2016.7852775

Weakly-supervised vehicle detection and classification by convolutional neural network. / Jiang, Changyu; Zhang, Bailing.
Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 570-575 7852775 (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016).

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

TY - GEN

T1 - Weakly-supervised vehicle detection and classification by convolutional neural network

AU - Jiang, Changyu

AU - Zhang, Bailing

PY - 2017/2/13

Y1 - 2017/2/13

N2 - Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object bounding boxes, which is expensive and often subjective. In this paper, we propose a vehicle detection and recognition system by applying weakly-supervised convolutional neural network (CNN), with training relying only on image-level labels. Experiments were conducted on a datasets acquired from field-captured traffic surveillance cameras, with vehicle classification performance mAP 98.79% and accuracy 98.28%, and vehicle detection performance mAP 85.26%.

AB - Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object bounding boxes, which is expensive and often subjective. In this paper, we propose a vehicle detection and recognition system by applying weakly-supervised convolutional neural network (CNN), with training relying only on image-level labels. Experiments were conducted on a datasets acquired from field-captured traffic surveillance cameras, with vehicle classification performance mAP 98.79% and accuracy 98.28%, and vehicle detection performance mAP 85.26%.

KW - convolutional neural networks

KW - vehicle detection and recognition

KW - weakly supervised lesrning

UR - http://www.scopus.com/inward/record.url?scp=85016041969&partnerID=8YFLogxK

U2 - 10.1109/CISP-BMEI.2016.7852775

DO - 10.1109/CISP-BMEI.2016.7852775

M3 - Conference Proceeding

AN - SCOPUS:85016041969

T3 - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

SP - 570

EP - 575

BT - Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016

Y2 - 15 October 2016 through 17 October 2016

ER -

Jiang C, Zhang B. Weakly-supervised vehicle detection and classification by convolutional neural network. In Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 570-575. 7852775. (Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016). doi: 10.1109/CISP-BMEI.2016.7852775

Weakly-supervised vehicle detection and classification by convolutional neural network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this