Cross-camera complementary vehicle matching via feature expandsion for video forensics

Chao Yung Hsu; Chih Yang Lin; Li Wei Kang; Hong Yuan Mark Liao

doi:10.1109/ISCE.2013.6570190

Cross-camera complementary vehicle matching via feature expandsion for video forensics

Chao Yung Hsu, Chih Yang Lin^*, Li Wei Kang, Hong Yuan Mark Liao

^*Corresponding author for this work

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

Abstract

In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is first extracted based on ASIFT (affine and scale-invariant feature transform) for each detected vehicle in a camera network. Then, the ASIFT feature is expanded via a special vehicle database. As a result, cross-camera vehicle matching with the help of complementary part can be greatly improved. Experimental results demonstrate the effectiveness of the proposed algorithm and the feasibility to video forensics applications.

Original language	English
Title of host publication	2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013
Pages	211-212
Number of pages	2
DOIs	https://doi.org/10.1109/ISCE.2013.6570190
Publication status	Published - 2013
Externally published	Yes
Event	2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013 - Hsinchu, Taiwan Duration: 2013 Jun 3 → 2013 Jun 6

Publication series

Name	Proceedings of the International Symposium on Consumer Electronics, ISCE

Other

Other	2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013
Country/Territory	Taiwan
City	Hsinchu
Period	2013/06/03 → 2013/06/06

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/ISCE.2013.6570190

Cite this

Hsu, C. Y., Lin, C. Y., Kang, L. W., & Liao, H. Y. M. (2013). Cross-camera complementary vehicle matching via feature expandsion for video forensics. In 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013 (pp. 211-212). Article 6570190 (Proceedings of the International Symposium on Consumer Electronics, ISCE). https://doi.org/10.1109/ISCE.2013.6570190

Cross-camera complementary vehicle matching via feature expandsion for video forensics. / Hsu, Chao Yung; Lin, Chih Yang; Kang, Li Wei et al.
2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013. 2013. p. 211-212 6570190 (Proceedings of the International Symposium on Consumer Electronics, ISCE).

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

Hsu, CY, Lin, CY, Kang, LW & Liao, HYM 2013, Cross-camera complementary vehicle matching via feature expandsion for video forensics. in 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013., 6570190, Proceedings of the International Symposium on Consumer Electronics, ISCE, pp. 211-212, 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013, Hsinchu, Taiwan, 2013/06/03. https://doi.org/10.1109/ISCE.2013.6570190

@inproceedings{a704030278714c87924563db9b75427f,

title = "Cross-camera complementary vehicle matching via feature expandsion for video forensics",

abstract = "In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is first extracted based on ASIFT (affine and scale-invariant feature transform) for each detected vehicle in a camera network. Then, the ASIFT feature is expanded via a special vehicle database. As a result, cross-camera vehicle matching with the help of complementary part can be greatly improved. Experimental results demonstrate the effectiveness of the proposed algorithm and the feasibility to video forensics applications.",

author = "Hsu, {Chao Yung} and Lin, {Chih Yang} and Kang, {Li Wei} and Liao, {Hong Yuan Mark}",

year = "2013",

doi = "10.1109/ISCE.2013.6570190",

language = "English",

isbn = "9781467361996",

series = "Proceedings of the International Symposium on Consumer Electronics, ISCE",

pages = "211--212",

booktitle = "2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013",

note = "2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013 ; Conference date: 03-06-2013 Through 06-06-2013",

}

TY - GEN

T1 - Cross-camera complementary vehicle matching via feature expandsion for video forensics

AU - Hsu, Chao Yung

AU - Lin, Chih Yang

AU - Kang, Li Wei

AU - Liao, Hong Yuan Mark

PY - 2013

Y1 - 2013

N2 - In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is first extracted based on ASIFT (affine and scale-invariant feature transform) for each detected vehicle in a camera network. Then, the ASIFT feature is expanded via a special vehicle database. As a result, cross-camera vehicle matching with the help of complementary part can be greatly improved. Experimental results demonstrate the effectiveness of the proposed algorithm and the feasibility to video forensics applications.

AB - In this paper, we will investigate a more challenging vehicle matching problem. The problem is formulated as invariant image feature matching among opposite viewpoints of cameras, i.e. complementary object matching. For example, a front vehicle object may be given as a query to retrieve a rear vehicle object of the same vehicle. To solve the complementary object matching, invariant image feature is first extracted based on ASIFT (affine and scale-invariant feature transform) for each detected vehicle in a camera network. Then, the ASIFT feature is expanded via a special vehicle database. As a result, cross-camera vehicle matching with the help of complementary part can be greatly improved. Experimental results demonstrate the effectiveness of the proposed algorithm and the feasibility to video forensics applications.

UR - http://www.scopus.com/inward/record.url?scp=84883541072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883541072&partnerID=8YFLogxK

U2 - 10.1109/ISCE.2013.6570190

DO - 10.1109/ISCE.2013.6570190

M3 - Conference contribution

AN - SCOPUS:84883541072

SN - 9781467361996

T3 - Proceedings of the International Symposium on Consumer Electronics, ISCE

SP - 211

EP - 212

BT - 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013

T2 - 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013

Y2 - 3 June 2013 through 6 June 2013

ER -

Cross-camera complementary vehicle matching via feature expandsion for video forensics

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this