A fast bicycle detector based on a geometric model for single side-view image

Chung Ping Young; Yen Bor Lin; Kuan Yu Chen

doi:10.1109/SAI.2016.7556005

A fast bicycle detector based on a geometric model for single side-view image

Chung Ping Young, Yen Bor Lin, Kuan Yu Chen

Institute of Medical Informatics

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

Abstract

Researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers for improving the safety of transportation systems. However, bicycles are also the significant factor of the safety on road. In this paper, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form of two triangles. Through the design of geometric constrains between the triangles and ellipses, the computation is fast comparing to the feature-based classifiers. Besides, the training process is unnecessary and only single image is required for our algorithm. Preliminary experimental result is also given in this paper to show the practicability and the performance of the proposed bicycle model and bicycle detection algorithm.

Original language	English
Title of host publication	Proceedings of 2016 SAI Computing Conference, SAI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	349-353
Number of pages	5
ISBN (Electronic)	9781467384605
DOIs	https://doi.org/10.1109/SAI.2016.7556005
Publication status	Published - 2016 Aug 29
Event	2016 SAI Computing Conference, SAI 2016 - London, United Kingdom Duration: 2016 Jul 13 → 2016 Jul 15

Publication series

Name	Proceedings of 2016 SAI Computing Conference, SAI 2016

Other

Other	2016 SAI Computing Conference, SAI 2016
Country	United Kingdom
City	London
Period	16-07-13 → 16-07-15

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems
Signal Processing
Modelling and Simulation

Access to Document

10.1109/SAI.2016.7556005

Fingerprint Dive into the research topics of 'A fast bicycle detector based on a geometric model for single side-view image'. Together they form a unique fingerprint.

Cite this

@inproceedings{5cbbc51ab3194a3384f99ea27029db4b,

title = "A fast bicycle detector based on a geometric model for single side-view image",

abstract = "Researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers for improving the safety of transportation systems. However, bicycles are also the significant factor of the safety on road. In this paper, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form of two triangles. Through the design of geometric constrains between the triangles and ellipses, the computation is fast comparing to the feature-based classifiers. Besides, the training process is unnecessary and only single image is required for our algorithm. Preliminary experimental result is also given in this paper to show the practicability and the performance of the proposed bicycle model and bicycle detection algorithm.",

author = "Young, {Chung Ping} and Lin, {Yen Bor} and Chen, {Kuan Yu}",

year = "2016",

month = aug,

day = "29",

doi = "10.1109/SAI.2016.7556005",

language = "English",

series = "Proceedings of 2016 SAI Computing Conference, SAI 2016",

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

pages = "349--353",

booktitle = "Proceedings of 2016 SAI Computing Conference, SAI 2016",

address = "United States",

note = "2016 SAI Computing Conference, SAI 2016 ; Conference date: 13-07-2016 Through 15-07-2016",

}

Young, CP, Lin, YB & Chen, KY 2016, A fast bicycle detector based on a geometric model for single side-view image. in Proceedings of 2016 SAI Computing Conference, SAI 2016., 7556005, Proceedings of 2016 SAI Computing Conference, SAI 2016, Institute of Electrical and Electronics Engineers Inc., pp. 349-353, 2016 SAI Computing Conference, SAI 2016, London, United Kingdom, 16-07-13. https://doi.org/10.1109/SAI.2016.7556005

A fast bicycle detector based on a geometric model for single side-view image. / Young, Chung Ping; Lin, Yen Bor; Chen, Kuan Yu.

Proceedings of 2016 SAI Computing Conference, SAI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 349-353 7556005 (Proceedings of 2016 SAI Computing Conference, SAI 2016).

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

TY - GEN

T1 - A fast bicycle detector based on a geometric model for single side-view image

AU - Young, Chung Ping

AU - Lin, Yen Bor

AU - Chen, Kuan Yu

PY - 2016/8/29

Y1 - 2016/8/29

N2 - Researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers for improving the safety of transportation systems. However, bicycles are also the significant factor of the safety on road. In this paper, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form of two triangles. Through the design of geometric constrains between the triangles and ellipses, the computation is fast comparing to the feature-based classifiers. Besides, the training process is unnecessary and only single image is required for our algorithm. Preliminary experimental result is also given in this paper to show the practicability and the performance of the proposed bicycle model and bicycle detection algorithm.

AB - Researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers for improving the safety of transportation systems. However, bicycles are also the significant factor of the safety on road. In this paper, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form of two triangles. Through the design of geometric constrains between the triangles and ellipses, the computation is fast comparing to the feature-based classifiers. Besides, the training process is unnecessary and only single image is required for our algorithm. Preliminary experimental result is also given in this paper to show the practicability and the performance of the proposed bicycle model and bicycle detection algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84988841549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988841549&partnerID=8YFLogxK

U2 - 10.1109/SAI.2016.7556005

DO - 10.1109/SAI.2016.7556005

M3 - Conference contribution

AN - SCOPUS:84988841549

T3 - Proceedings of 2016 SAI Computing Conference, SAI 2016

SP - 349

EP - 353

BT - Proceedings of 2016 SAI Computing Conference, SAI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 SAI Computing Conference, SAI 2016

Y2 - 13 July 2016 through 15 July 2016

ER -