Real-time image detail enhancement implementing on multi-core DSP platform

Guodong Wang; Yue Cheng; Lei Zhang; Zhengjun Zhai

doi:10.1109/ICIS.2017.7960095

Real-time image detail enhancement implementing on multi-core DSP platform

Guodong Wang, Yue Cheng, Lei Zhang, Zhengjun Zhai

School of Computer Science

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

Abstract

Image detail enhancement is of wide application in image processing fields. In order to gain a better performance for detail enhancement, the computing cost is normally very large. Thus, it's unacceptable in real-time applications, such as video enhancement. In this paper, we propose a novel parallel framework for reliable real-time image detail enhancement based on recent proposed Gradient Domain Bilateral Filter (GDBF) which is realized on a multicore DSP platform: TMS320C6678. With the implement of parallel enhancement method, not only image base layer and detail layer are rapidly separated, but also the detail layer is further enhanced. Furthermore, the implementation of the parallel framework employs fix point programming instead of float point. With a bit-shift strategy for input image data, the computing precision is well satisfied. Experimental results show that our proposed framework outperform available state-of-the-art one, the processing time for 1080p image is less than 30ms. It is a good candidate for real-time image detail enhancement based on the multi-core DSP.

Original language	English
Title of host publication	Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017
Editors	Xiaohui Cui, Shaowen Yao, Simon Xu, Guobin Zhu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	763-768
Number of pages	6
ISBN (Electronic)	9781509055074
DOIs	https://doi.org/10.1109/ICIS.2017.7960095
State	Published - 27 Jun 2017
Event	16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017 - Wuhan, China Duration: 24 May 2017 → 26 May 2017

Publication series

Name	Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017

Conference

Conference	16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017
Country/Territory	China
City	Wuhan
Period	24/05/17 → 26/05/17

Keywords

Bilateral filter
DSP
Detail enhancement
Parallel computing

Access to Document

10.1109/ICIS.2017.7960095

Cite this

Wang, G., Cheng, Y., Zhang, L., & Zhai, Z. (2017). Real-time image detail enhancement implementing on multi-core DSP platform. In X. Cui, S. Yao, S. Xu, & G. Zhu (Eds.), Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017 (pp. 763-768). Article 7960095 (Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIS.2017.7960095

Wang, Guodong ; Cheng, Yue ; Zhang, Lei et al. / Real-time image detail enhancement implementing on multi-core DSP platform. Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017. editor / Xiaohui Cui ; Shaowen Yao ; Simon Xu ; Guobin Zhu. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 763-768 (Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017).

@inproceedings{0f9a919759a04b41907c38f63c7ef947,

title = "Real-time image detail enhancement implementing on multi-core DSP platform",

abstract = "Image detail enhancement is of wide application in image processing fields. In order to gain a better performance for detail enhancement, the computing cost is normally very large. Thus, it's unacceptable in real-time applications, such as video enhancement. In this paper, we propose a novel parallel framework for reliable real-time image detail enhancement based on recent proposed Gradient Domain Bilateral Filter (GDBF) which is realized on a multicore DSP platform: TMS320C6678. With the implement of parallel enhancement method, not only image base layer and detail layer are rapidly separated, but also the detail layer is further enhanced. Furthermore, the implementation of the parallel framework employs fix point programming instead of float point. With a bit-shift strategy for input image data, the computing precision is well satisfied. Experimental results show that our proposed framework outperform available state-of-the-art one, the processing time for 1080p image is less than 30ms. It is a good candidate for real-time image detail enhancement based on the multi-core DSP.",

keywords = "Bilateral filter, DSP, Detail enhancement, Parallel computing",

author = "Guodong Wang and Yue Cheng and Lei Zhang and Zhengjun Zhai",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017 ; Conference date: 24-05-2017 Through 26-05-2017",

year = "2017",

month = jun,

day = "27",

doi = "10.1109/ICIS.2017.7960095",

language = "英语",

series = "Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017",

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

pages = "763--768",

editor = "Xiaohui Cui and Shaowen Yao and Simon Xu and Guobin Zhu",

booktitle = "Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017",

}

Wang, G, Cheng, Y, Zhang, L & Zhai, Z 2017, Real-time image detail enhancement implementing on multi-core DSP platform. in X Cui, S Yao, S Xu & G Zhu (eds), Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017., 7960095, Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017, Institute of Electrical and Electronics Engineers Inc., pp. 763-768, 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017, Wuhan, China, 24/05/17. https://doi.org/10.1109/ICIS.2017.7960095

Real-time image detail enhancement implementing on multi-core DSP platform. / Wang, Guodong; Cheng, Yue; Zhang, Lei et al.
Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017. ed. / Xiaohui Cui; Shaowen Yao; Simon Xu; Guobin Zhu. Institute of Electrical and Electronics Engineers Inc., 2017. p. 763-768 7960095 (Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017).

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

TY - GEN

T1 - Real-time image detail enhancement implementing on multi-core DSP platform

AU - Wang, Guodong

AU - Cheng, Yue

AU - Zhang, Lei

AU - Zhai, Zhengjun

PY - 2017/6/27

Y1 - 2017/6/27

N2 - Image detail enhancement is of wide application in image processing fields. In order to gain a better performance for detail enhancement, the computing cost is normally very large. Thus, it's unacceptable in real-time applications, such as video enhancement. In this paper, we propose a novel parallel framework for reliable real-time image detail enhancement based on recent proposed Gradient Domain Bilateral Filter (GDBF) which is realized on a multicore DSP platform: TMS320C6678. With the implement of parallel enhancement method, not only image base layer and detail layer are rapidly separated, but also the detail layer is further enhanced. Furthermore, the implementation of the parallel framework employs fix point programming instead of float point. With a bit-shift strategy for input image data, the computing precision is well satisfied. Experimental results show that our proposed framework outperform available state-of-the-art one, the processing time for 1080p image is less than 30ms. It is a good candidate for real-time image detail enhancement based on the multi-core DSP.

AB - Image detail enhancement is of wide application in image processing fields. In order to gain a better performance for detail enhancement, the computing cost is normally very large. Thus, it's unacceptable in real-time applications, such as video enhancement. In this paper, we propose a novel parallel framework for reliable real-time image detail enhancement based on recent proposed Gradient Domain Bilateral Filter (GDBF) which is realized on a multicore DSP platform: TMS320C6678. With the implement of parallel enhancement method, not only image base layer and detail layer are rapidly separated, but also the detail layer is further enhanced. Furthermore, the implementation of the parallel framework employs fix point programming instead of float point. With a bit-shift strategy for input image data, the computing precision is well satisfied. Experimental results show that our proposed framework outperform available state-of-the-art one, the processing time for 1080p image is less than 30ms. It is a good candidate for real-time image detail enhancement based on the multi-core DSP.

KW - Bilateral filter

KW - DSP

KW - Detail enhancement

KW - Parallel computing

UR - http://www.scopus.com/inward/record.url?scp=85030654121&partnerID=8YFLogxK

U2 - 10.1109/ICIS.2017.7960095

DO - 10.1109/ICIS.2017.7960095

M3 - 会议稿件

AN - SCOPUS:85030654121

T3 - Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017

SP - 763

EP - 768

BT - Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017

A2 - Cui, Xiaohui

A2 - Yao, Shaowen

A2 - Xu, Simon

A2 - Zhu, Guobin

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017

Y2 - 24 May 2017 through 26 May 2017

ER -

Wang G, Cheng Y, Zhang L, Zhai Z. Real-time image detail enhancement implementing on multi-core DSP platform. In Cui X, Yao S, Xu S, Zhu G, editors, Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 763-768. 7960095. (Proceedings - 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017). doi: 10.1109/ICIS.2017.7960095

Real-time image detail enhancement implementing on multi-core DSP platform

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this