An implementation of an affine BRISK for mobile heterogeneous parallel processors

Chulhee Lee, Chae Eun Rhee, Hyuk Jae Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As the computing power of a mobile processor increases, a number of computer vision applications are widely used by a mobile device. Feature extraction is one of the crucial tasks in a computer vision area and it is used for object recognition, panorama image generation and so on. The affine SIFT (ASIFT) feature is robust to scale, rotation and viewpoint changes but its high computational complexity makes it challenging for ASIFT to be used in applications by a mobile device. To reduce the complexity of ASIFT while maintaining affine invariance, this paper proposes an affine BRISK which replaces SIFT by BRISK of which complexity is much less than SIFT. By fully exploiting the parallelism of affine transformation for viewpoint invariance, this paper achieves the speed up by parallel execution of feature extraction and affine transformation running on the mobile CPU and GPU, respectively. The proposed affine BRISK feature is robust to a viewpoint change with a comparable accuracy. The processing time is 290.64ms on a Galaxy LTE-A mobile.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Consumer Electronics, ICCE 2016
EditorsFrancisco J. Bellido, Daniel Diaz-Sanchez, Nicholas C. H. Vun, Carsten Dolar, Wing-Kuen Ling
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages435-436
Number of pages2
ISBN (Electronic)9781467383646
DOIs
Publication statusPublished - 2016 Mar 10
EventIEEE International Conference on Consumer Electronics, ICCE 2016 - Las Vegas, United States
Duration: 2016 Jan 72016 Jan 11

Publication series

Name2016 IEEE International Conference on Consumer Electronics, ICCE 2016

Other

OtherIEEE International Conference on Consumer Electronics, ICCE 2016
CountryUnited States
CityLas Vegas
Period16/1/716/1/11

Fingerprint

Invariance
Mobile devices
Computer vision
Feature extraction
Galaxies
Object recognition
Program processors
Computational complexity
Processing
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Lee, C., Rhee, C. E., & Lee, H. J. (2016). An implementation of an affine BRISK for mobile heterogeneous parallel processors. In F. J. Bellido, D. Diaz-Sanchez, N. C. H. Vun, C. Dolar, & W-K. Ling (Eds.), 2016 IEEE International Conference on Consumer Electronics, ICCE 2016 (pp. 435-436). [7430680] (2016 IEEE International Conference on Consumer Electronics, ICCE 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE.2016.7430680
Lee, Chulhee ; Rhee, Chae Eun ; Lee, Hyuk Jae. / An implementation of an affine BRISK for mobile heterogeneous parallel processors. 2016 IEEE International Conference on Consumer Electronics, ICCE 2016. editor / Francisco J. Bellido ; Daniel Diaz-Sanchez ; Nicholas C. H. Vun ; Carsten Dolar ; Wing-Kuen Ling. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 435-436 (2016 IEEE International Conference on Consumer Electronics, ICCE 2016).
@inproceedings{ba75dd2567c647aea16155728c25a151,
title = "An implementation of an affine BRISK for mobile heterogeneous parallel processors",
abstract = "As the computing power of a mobile processor increases, a number of computer vision applications are widely used by a mobile device. Feature extraction is one of the crucial tasks in a computer vision area and it is used for object recognition, panorama image generation and so on. The affine SIFT (ASIFT) feature is robust to scale, rotation and viewpoint changes but its high computational complexity makes it challenging for ASIFT to be used in applications by a mobile device. To reduce the complexity of ASIFT while maintaining affine invariance, this paper proposes an affine BRISK which replaces SIFT by BRISK of which complexity is much less than SIFT. By fully exploiting the parallelism of affine transformation for viewpoint invariance, this paper achieves the speed up by parallel execution of feature extraction and affine transformation running on the mobile CPU and GPU, respectively. The proposed affine BRISK feature is robust to a viewpoint change with a comparable accuracy. The processing time is 290.64ms on a Galaxy LTE-A mobile.",
author = "Chulhee Lee and Rhee, {Chae Eun} and Lee, {Hyuk Jae}",
year = "2016",
month = "3",
day = "10",
doi = "10.1109/ICCE.2016.7430680",
language = "English",
series = "2016 IEEE International Conference on Consumer Electronics, ICCE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "435--436",
editor = "Bellido, {Francisco J.} and Daniel Diaz-Sanchez and Vun, {Nicholas C. H.} and Carsten Dolar and Wing-Kuen Ling",
booktitle = "2016 IEEE International Conference on Consumer Electronics, ICCE 2016",
address = "United States",

}

Lee, C, Rhee, CE & Lee, HJ 2016, An implementation of an affine BRISK for mobile heterogeneous parallel processors. in FJ Bellido, D Diaz-Sanchez, NCH Vun, C Dolar & W-K Ling (eds), 2016 IEEE International Conference on Consumer Electronics, ICCE 2016., 7430680, 2016 IEEE International Conference on Consumer Electronics, ICCE 2016, Institute of Electrical and Electronics Engineers Inc., pp. 435-436, IEEE International Conference on Consumer Electronics, ICCE 2016, Las Vegas, United States, 16/1/7. https://doi.org/10.1109/ICCE.2016.7430680

An implementation of an affine BRISK for mobile heterogeneous parallel processors. / Lee, Chulhee; Rhee, Chae Eun; Lee, Hyuk Jae.

2016 IEEE International Conference on Consumer Electronics, ICCE 2016. ed. / Francisco J. Bellido; Daniel Diaz-Sanchez; Nicholas C. H. Vun; Carsten Dolar; Wing-Kuen Ling. Institute of Electrical and Electronics Engineers Inc., 2016. p. 435-436 7430680 (2016 IEEE International Conference on Consumer Electronics, ICCE 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An implementation of an affine BRISK for mobile heterogeneous parallel processors

AU - Lee, Chulhee

AU - Rhee, Chae Eun

AU - Lee, Hyuk Jae

PY - 2016/3/10

Y1 - 2016/3/10

N2 - As the computing power of a mobile processor increases, a number of computer vision applications are widely used by a mobile device. Feature extraction is one of the crucial tasks in a computer vision area and it is used for object recognition, panorama image generation and so on. The affine SIFT (ASIFT) feature is robust to scale, rotation and viewpoint changes but its high computational complexity makes it challenging for ASIFT to be used in applications by a mobile device. To reduce the complexity of ASIFT while maintaining affine invariance, this paper proposes an affine BRISK which replaces SIFT by BRISK of which complexity is much less than SIFT. By fully exploiting the parallelism of affine transformation for viewpoint invariance, this paper achieves the speed up by parallel execution of feature extraction and affine transformation running on the mobile CPU and GPU, respectively. The proposed affine BRISK feature is robust to a viewpoint change with a comparable accuracy. The processing time is 290.64ms on a Galaxy LTE-A mobile.

AB - As the computing power of a mobile processor increases, a number of computer vision applications are widely used by a mobile device. Feature extraction is one of the crucial tasks in a computer vision area and it is used for object recognition, panorama image generation and so on. The affine SIFT (ASIFT) feature is robust to scale, rotation and viewpoint changes but its high computational complexity makes it challenging for ASIFT to be used in applications by a mobile device. To reduce the complexity of ASIFT while maintaining affine invariance, this paper proposes an affine BRISK which replaces SIFT by BRISK of which complexity is much less than SIFT. By fully exploiting the parallelism of affine transformation for viewpoint invariance, this paper achieves the speed up by parallel execution of feature extraction and affine transformation running on the mobile CPU and GPU, respectively. The proposed affine BRISK feature is robust to a viewpoint change with a comparable accuracy. The processing time is 290.64ms on a Galaxy LTE-A mobile.

UR - http://www.scopus.com/inward/record.url?scp=84965122900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965122900&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2016.7430680

DO - 10.1109/ICCE.2016.7430680

M3 - Conference contribution

AN - SCOPUS:84965122900

T3 - 2016 IEEE International Conference on Consumer Electronics, ICCE 2016

SP - 435

EP - 436

BT - 2016 IEEE International Conference on Consumer Electronics, ICCE 2016

A2 - Bellido, Francisco J.

A2 - Diaz-Sanchez, Daniel

A2 - Vun, Nicholas C. H.

A2 - Dolar, Carsten

A2 - Ling, Wing-Kuen

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lee C, Rhee CE, Lee HJ. An implementation of an affine BRISK for mobile heterogeneous parallel processors. In Bellido FJ, Diaz-Sanchez D, Vun NCH, Dolar C, Ling W-K, editors, 2016 IEEE International Conference on Consumer Electronics, ICCE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 435-436. 7430680. (2016 IEEE International Conference on Consumer Electronics, ICCE 2016). https://doi.org/10.1109/ICCE.2016.7430680