Learning deep compact channel features for object detection in traffic scenes

Yuqiang Fang; Lin Sun; Hao Fu; Tao Wu; Ruili Wang; Bin Dai

doi:10.1109/ICIP.2016.7532518

Learning deep compact channel features for object detection in traffic scenes

Yuqiang Fang, Lin Sun, Hao Fu, Tao Wu, Ruili Wang, Bin Dai

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

3 Citations (Scopus)

Abstract

In this work, we present a new multiple channel feature called Deep Compact Channel Feature (DCCF), which generates a compact, discriminative feature representation by a pre-trained deep encoder-decoder. With the combination of DCCF and boosted decision trees, a new object detector is proposed which achieved outstanding performance on standard pedestrian dataset INRIA and Caltech. Furthermore, a large scale and challenging Chinese Traffic Sign Detection benchmark is constructed. DCCF and other related methods are evaluated on this dataset. The dataset and baselines are available online.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	1052-1056
Number of pages	5
ISBN (Electronic)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7532518
Publication status	Published - 3 Aug 2016
Externally published	Yes
Event	23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: 25 Sept 2016 → 28 Sept 2016

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2016-August
ISSN (Print)	1522-4880

Conference

Conference	23rd IEEE International Conference on Image Processing, ICIP 2016
Country/Territory	United States
City	Phoenix
Period	25/09/16 → 28/09/16

Keywords

Deep neural networks
Object detection
Pedestrian detection
Traffic sign

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Signal Processing
Software

Access to Document

10.1109/ICIP.2016.7532518

Cite this

Fang, Y., Sun, L., Fu, H., Wu, T., Wang, R., & Dai, B. (2016). Learning deep compact channel features for object detection in traffic scenes. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (pp. 1052-1056). Article 7532518 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532518

@inproceedings{f6faf3e8e00743e7a070f778cd364cb2,

title = "Learning deep compact channel features for object detection in traffic scenes",

abstract = "In this work, we present a new multiple channel feature called Deep Compact Channel Feature (DCCF), which generates a compact, discriminative feature representation by a pre-trained deep encoder-decoder. With the combination of DCCF and boosted decision trees, a new object detector is proposed which achieved outstanding performance on standard pedestrian dataset INRIA and Caltech. Furthermore, a large scale and challenging Chinese Traffic Sign Detection benchmark is constructed. DCCF and other related methods are evaluated on this dataset. The dataset and baselines are available online.",

keywords = "Deep neural networks, Object detection, Pedestrian detection, Traffic sign",

author = "Yuqiang Fang and Lin Sun and Hao Fu and Tao Wu and Ruili Wang and Bin Dai",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

month = aug,

day = "3",

doi = "10.1109/ICIP.2016.7532518",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "1052--1056",

booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",

address = "United States",

}

Fang, Y, Sun, L, Fu, H, Wu, T, Wang, R & Dai, B 2016, Learning deep compact channel features for object detection in traffic scenes. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings., 7532518, Proceedings - International Conference on Image Processing, ICIP, vol. 2016-August, IEEE Computer Society, pp. 1052-1056, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 25/09/16. https://doi.org/10.1109/ICIP.2016.7532518

Learning deep compact channel features for object detection in traffic scenes. / Fang, Yuqiang; Sun, Lin; Fu, Hao et al.
2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society, 2016. p. 1052-1056 7532518 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August).

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

TY - GEN

T1 - Learning deep compact channel features for object detection in traffic scenes

AU - Fang, Yuqiang

AU - Sun, Lin

AU - Fu, Hao

AU - Wu, Tao

AU - Wang, Ruili

AU - Dai, Bin

PY - 2016/8/3

Y1 - 2016/8/3

N2 - In this work, we present a new multiple channel feature called Deep Compact Channel Feature (DCCF), which generates a compact, discriminative feature representation by a pre-trained deep encoder-decoder. With the combination of DCCF and boosted decision trees, a new object detector is proposed which achieved outstanding performance on standard pedestrian dataset INRIA and Caltech. Furthermore, a large scale and challenging Chinese Traffic Sign Detection benchmark is constructed. DCCF and other related methods are evaluated on this dataset. The dataset and baselines are available online.

AB - In this work, we present a new multiple channel feature called Deep Compact Channel Feature (DCCF), which generates a compact, discriminative feature representation by a pre-trained deep encoder-decoder. With the combination of DCCF and boosted decision trees, a new object detector is proposed which achieved outstanding performance on standard pedestrian dataset INRIA and Caltech. Furthermore, a large scale and challenging Chinese Traffic Sign Detection benchmark is constructed. DCCF and other related methods are evaluated on this dataset. The dataset and baselines are available online.

KW - Deep neural networks

KW - Object detection

KW - Pedestrian detection

KW - Traffic sign

UR - http://www.scopus.com/inward/record.url?scp=85006827137&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532518

DO - 10.1109/ICIP.2016.7532518

M3 - Conference contribution

AN - SCOPUS:85006827137

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1052

EP - 1056

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016

Y2 - 25 September 2016 through 28 September 2016

ER -

Learning deep compact channel features for object detection in traffic scenes

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this