Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm

Chiang Heng Chien, Chiang Ju Chien, Chen-Chien James Hsu

研究成果: 書貢獻/報告類型會議貢獻

摘要

Providing low cost and rich information, visual sensors are becoming the top choice for automatic systems. Particularly in the field of navigations or SLAM technologies, extracting and matching features are the basic aspects. This paper addresses the required computational efficiency, computational resources and power-consumption problem of image feature detection and matching algorithm by designing a hardware-software co-design architecture for the implementation on a field-programmable gate array (FPGA) and a Nios II CPU. Given images data from the Nios II, features are extracted and matched by the scale-invariant feature transform (SIFT) algorithm and a linear exhaustive search (LES) method using an Altera DE2i-150 FPGA, respectively. The matched features are subsequently transferred back from the FPGA to Nios II. To show the effectiveness of the proposed approach, two images with affine transformations are provided. An object tracking system is also developed. Experimental results show that, taking the advantages of parallel computing of an FPGA, the overall computational time and the hardware resources usage of the proposed approach are greatly reduced, compared to a full-software implementation and other existing methods.

原文英語
主出版物標題Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019
發行者Institute of Electrical and Electronics Engineers Inc.
頁面37-41
頁數5
ISBN(電子)9781728126623
DOIs
出版狀態已發佈 - 2019 二月 1
事件2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019 - Singapore, 新加坡
持續時間: 2019 二月 282019 三月 2

出版系列

名字Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019

會議

會議2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019
國家新加坡
城市Singapore
期間19/2/2819/3/2

指紋

Hardware/software Co-design
Feature Matching
Matching Algorithm
Field Programmable Gate Array
Feature Extraction
Field programmable gate arrays (FPGA)
Feature extraction
Hardware
Feature Detection
Resources
Simultaneous Localization and Mapping
Scale Invariant Feature Transform
Exhaustive Search
Object Tracking
Tracking System
Parallel processing systems
Parallel Computing
Computational efficiency
Search Methods
Computational Efficiency

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Automotive Engineering
  • Control and Optimization

引用此文

Chien, C. H., Chien, C. J., & Hsu, C-C. J. (2019). Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm. 於 Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019 (頁 37-41). [8782443] (Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICoIAS.2019.00013

Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm. / Chien, Chiang Heng; Chien, Chiang Ju; Hsu, Chen-Chien James.

Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 37-41 8782443 (Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019).

研究成果: 書貢獻/報告類型會議貢獻

Chien, CH, Chien, CJ & Hsu, C-CJ 2019, Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm. 於 Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019., 8782443, Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019, Institute of Electrical and Electronics Engineers Inc., 頁 37-41, 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019, Singapore, 新加坡, 19/2/28. https://doi.org/10.1109/ICoIAS.2019.00013
Chien CH, Chien CJ, Hsu C-CJ. Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm. 於 Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 37-41. 8782443. (Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019). https://doi.org/10.1109/ICoIAS.2019.00013
Chien, Chiang Heng ; Chien, Chiang Ju ; Hsu, Chen-Chien James. / Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm. Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 頁 37-41 (Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019).
@inproceedings{24005fd21e61486892cd8671bb241752,
title = "Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm",
abstract = "Providing low cost and rich information, visual sensors are becoming the top choice for automatic systems. Particularly in the field of navigations or SLAM technologies, extracting and matching features are the basic aspects. This paper addresses the required computational efficiency, computational resources and power-consumption problem of image feature detection and matching algorithm by designing a hardware-software co-design architecture for the implementation on a field-programmable gate array (FPGA) and a Nios II CPU. Given images data from the Nios II, features are extracted and matched by the scale-invariant feature transform (SIFT) algorithm and a linear exhaustive search (LES) method using an Altera DE2i-150 FPGA, respectively. The matched features are subsequently transferred back from the FPGA to Nios II. To show the effectiveness of the proposed approach, two images with affine transformations are provided. An object tracking system is also developed. Experimental results show that, taking the advantages of parallel computing of an FPGA, the overall computational time and the hardware resources usage of the proposed approach are greatly reduced, compared to a full-software implementation and other existing methods.",
keywords = "FPGA, LES, Nios, SIFT, feature detection and matching, hardware-software co-design, object tracking",
author = "Chien, {Chiang Heng} and Chien, {Chiang Ju} and Hsu, {Chen-Chien James}",
year = "2019",
month = "2",
day = "1",
doi = "10.1109/ICoIAS.2019.00013",
language = "English",
series = "Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "37--41",
booktitle = "Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019",

}

TY - GEN

T1 - Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm

AU - Chien, Chiang Heng

AU - Chien, Chiang Ju

AU - Hsu, Chen-Chien James

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Providing low cost and rich information, visual sensors are becoming the top choice for automatic systems. Particularly in the field of navigations or SLAM technologies, extracting and matching features are the basic aspects. This paper addresses the required computational efficiency, computational resources and power-consumption problem of image feature detection and matching algorithm by designing a hardware-software co-design architecture for the implementation on a field-programmable gate array (FPGA) and a Nios II CPU. Given images data from the Nios II, features are extracted and matched by the scale-invariant feature transform (SIFT) algorithm and a linear exhaustive search (LES) method using an Altera DE2i-150 FPGA, respectively. The matched features are subsequently transferred back from the FPGA to Nios II. To show the effectiveness of the proposed approach, two images with affine transformations are provided. An object tracking system is also developed. Experimental results show that, taking the advantages of parallel computing of an FPGA, the overall computational time and the hardware resources usage of the proposed approach are greatly reduced, compared to a full-software implementation and other existing methods.

AB - Providing low cost and rich information, visual sensors are becoming the top choice for automatic systems. Particularly in the field of navigations or SLAM technologies, extracting and matching features are the basic aspects. This paper addresses the required computational efficiency, computational resources and power-consumption problem of image feature detection and matching algorithm by designing a hardware-software co-design architecture for the implementation on a field-programmable gate array (FPGA) and a Nios II CPU. Given images data from the Nios II, features are extracted and matched by the scale-invariant feature transform (SIFT) algorithm and a linear exhaustive search (LES) method using an Altera DE2i-150 FPGA, respectively. The matched features are subsequently transferred back from the FPGA to Nios II. To show the effectiveness of the proposed approach, two images with affine transformations are provided. An object tracking system is also developed. Experimental results show that, taking the advantages of parallel computing of an FPGA, the overall computational time and the hardware resources usage of the proposed approach are greatly reduced, compared to a full-software implementation and other existing methods.

KW - FPGA

KW - LES

KW - Nios

KW - SIFT

KW - feature detection and matching

KW - hardware-software co-design

KW - object tracking

UR - http://www.scopus.com/inward/record.url?scp=85070926314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070926314&partnerID=8YFLogxK

U2 - 10.1109/ICoIAS.2019.00013

DO - 10.1109/ICoIAS.2019.00013

M3 - Conference contribution

AN - SCOPUS:85070926314

T3 - Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019

SP - 37

EP - 41

BT - Proceedings - 2019 2nd International Conference on Intelligent Autonomous Systems, ICoIAS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -