Low complexity stereo matching algorithm using adaptive sized square window

Der Wei Yang; Li Chia Chu; Chun Wei Chen; Jia Ming Gan; Jonas Wang; Ming-Der Shieh

doi:10.1109/VLSI-DAT.2014.6834897

Low complexity stereo matching algorithm using adaptive sized square window

Der Wei Yang, Li Chia Chu, Chun Wei Chen, Jia Ming Gan, Jonas Wang, Ming-Der Shieh

Department of Electrical Engineering

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

Abstract

This paper presents an efficient stereo matching algorithm for hardware implementation. A low-complexity local window size decision rule is proposed in our processing scheme. The proper window size is adopted according to the local content characteristic. The matching computation cost is almost as low as the conventional fixed window size method. An efficient hardware architecture comprises unified window size processing elements is also developed. Experimental results reveal that the proposed design can achieve better quality than the related fixed window size method with the properties of low computation cost and hardware realizable flow.

Original language	English
Title of host publication	Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014
Publisher	IEEE Computer Society
ISBN (Print)	9781479927760
DOIs	https://doi.org/10.1109/VLSI-DAT.2014.6834897
Publication status	Published - 2014 Jan 1
Event	2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014 - Hsinchu, Taiwan Duration: 2014 Apr 28 → 2014 Apr 30

Publication series

Name	Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014

Other

Other	2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014
Country	Taiwan
City	Hsinchu
Period	14-04-28 → 14-04-30

All Science Journal Classification (ASJC) codes

Control and Systems Engineering

Access to Document

10.1109/VLSI-DAT.2014.6834897

Fingerprint Dive into the research topics of 'Low complexity stereo matching algorithm using adaptive sized square window'. Together they form a unique fingerprint.

Cite this

Yang, D. W., Chu, L. C., Chen, C. W., Gan, J. M., Wang, J., & Shieh, M-D. (2014). Low complexity stereo matching algorithm using adaptive sized square window. In Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014 [6834897] (Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014). IEEE Computer Society. https://doi.org/10.1109/VLSI-DAT.2014.6834897

Yang, Der Wei ; Chu, Li Chia ; Chen, Chun Wei ; Gan, Jia Ming ; Wang, Jonas ; Shieh, Ming-Der. / Low complexity stereo matching algorithm using adaptive sized square window. Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014. IEEE Computer Society, 2014. (Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014).

@inproceedings{a5ae949c3ee544e2b4402242cfc332d2,

title = "Low complexity stereo matching algorithm using adaptive sized square window",

abstract = "This paper presents an efficient stereo matching algorithm for hardware implementation. A low-complexity local window size decision rule is proposed in our processing scheme. The proper window size is adopted according to the local content characteristic. The matching computation cost is almost as low as the conventional fixed window size method. An efficient hardware architecture comprises unified window size processing elements is also developed. Experimental results reveal that the proposed design can achieve better quality than the related fixed window size method with the properties of low computation cost and hardware realizable flow.",

author = "Yang, {Der Wei} and Chu, {Li Chia} and Chen, {Chun Wei} and Gan, {Jia Ming} and Jonas Wang and Ming-Der Shieh",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/VLSI-DAT.2014.6834897",

language = "English",

isbn = "9781479927760",

series = "Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014",

publisher = "IEEE Computer Society",

booktitle = "Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014",

address = "United States",

note = "2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014 ; Conference date: 28-04-2014 Through 30-04-2014",

}

Yang, DW, Chu, LC, Chen, CW, Gan, JM, Wang, J & Shieh, M-D 2014, Low complexity stereo matching algorithm using adaptive sized square window. in Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014., 6834897, Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014, IEEE Computer Society, 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014, Hsinchu, Taiwan, 14-04-28. https://doi.org/10.1109/VLSI-DAT.2014.6834897

Low complexity stereo matching algorithm using adaptive sized square window. / Yang, Der Wei; Chu, Li Chia; Chen, Chun Wei; Gan, Jia Ming; Wang, Jonas; Shieh, Ming-Der.

Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014. IEEE Computer Society, 2014. 6834897 (Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014).

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

TY - GEN

T1 - Low complexity stereo matching algorithm using adaptive sized square window

AU - Yang, Der Wei

AU - Chu, Li Chia

AU - Chen, Chun Wei

AU - Gan, Jia Ming

AU - Wang, Jonas

AU - Shieh, Ming-Der

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents an efficient stereo matching algorithm for hardware implementation. A low-complexity local window size decision rule is proposed in our processing scheme. The proper window size is adopted according to the local content characteristic. The matching computation cost is almost as low as the conventional fixed window size method. An efficient hardware architecture comprises unified window size processing elements is also developed. Experimental results reveal that the proposed design can achieve better quality than the related fixed window size method with the properties of low computation cost and hardware realizable flow.

AB - This paper presents an efficient stereo matching algorithm for hardware implementation. A low-complexity local window size decision rule is proposed in our processing scheme. The proper window size is adopted according to the local content characteristic. The matching computation cost is almost as low as the conventional fixed window size method. An efficient hardware architecture comprises unified window size processing elements is also developed. Experimental results reveal that the proposed design can achieve better quality than the related fixed window size method with the properties of low computation cost and hardware realizable flow.

UR - http://www.scopus.com/inward/record.url?scp=84903977502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903977502&partnerID=8YFLogxK

U2 - 10.1109/VLSI-DAT.2014.6834897

DO - 10.1109/VLSI-DAT.2014.6834897

M3 - Conference contribution

AN - SCOPUS:84903977502

SN - 9781479927760

T3 - Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014

BT - Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014

PB - IEEE Computer Society

T2 - 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014

Y2 - 28 April 2014 through 30 April 2014

ER -

Yang DW, Chu LC, Chen CW, Gan JM, Wang J, Shieh M-D. Low complexity stereo matching algorithm using adaptive sized square window. In Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014. IEEE Computer Society. 2014. 6834897. (Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2014). https://doi.org/10.1109/VLSI-DAT.2014.6834897