Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition

Seung Eun Lee, Kyungwon Min, Taeweon Suh

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Pedestrian recognition is an emerging visual computing application for embedded systems. In one usage model, a vehicle mounted camera acquires image from road and a pedestrian recognition system automatically recognizes and alarms information on the road preventing traffic accidents. Achieving this in software on embedded systems requires significant compute processing for object recognition. In this paper, we identify the hotspot function of the workload on an embedded system that motivates acceleration and present the detailed design of a hardware accelerator for Histograms of Oriented Gradients descriptor extraction. We also quantify the performance and area efficiency of the hardware accelerator. Our analysis shows that hardware acceleration has the potential to improve the hotspot function. As a result, user response time can be reduced significantly.

Original languageEnglish
Pages (from-to)1043-1048
Number of pages6
JournalComputers and Electrical Engineering
Volume39
Issue number4
DOIs
Publication statusPublished - 2013 May 1

Fingerprint

Embedded systems
Highway accidents
Hardware
Particle accelerators
Object recognition
Cameras
Processing

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition. / Lee, Seung Eun; Min, Kyungwon; Suh, Taeweon.

In: Computers and Electrical Engineering, Vol. 39, No. 4, 01.05.2013, p. 1043-1048.

Research output: Contribution to journalArticle

@article{c71c0a2486b2467b89cfe72a8f36183d,
title = "Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition",
abstract = "Pedestrian recognition is an emerging visual computing application for embedded systems. In one usage model, a vehicle mounted camera acquires image from road and a pedestrian recognition system automatically recognizes and alarms information on the road preventing traffic accidents. Achieving this in software on embedded systems requires significant compute processing for object recognition. In this paper, we identify the hotspot function of the workload on an embedded system that motivates acceleration and present the detailed design of a hardware accelerator for Histograms of Oriented Gradients descriptor extraction. We also quantify the performance and area efficiency of the hardware accelerator. Our analysis shows that hardware acceleration has the potential to improve the hotspot function. As a result, user response time can be reduced significantly.",
author = "Lee, {Seung Eun} and Kyungwon Min and Taeweon Suh",
year = "2013",
month = "5",
day = "1",
doi = "10.1016/j.compeleceng.2013.04.001",
language = "English",
volume = "39",
pages = "1043--1048",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Accelerating Histograms of Oriented Gradients descriptor extraction for pedestrian recognition

AU - Lee, Seung Eun

AU - Min, Kyungwon

AU - Suh, Taeweon

PY - 2013/5/1

Y1 - 2013/5/1

N2 - Pedestrian recognition is an emerging visual computing application for embedded systems. In one usage model, a vehicle mounted camera acquires image from road and a pedestrian recognition system automatically recognizes and alarms information on the road preventing traffic accidents. Achieving this in software on embedded systems requires significant compute processing for object recognition. In this paper, we identify the hotspot function of the workload on an embedded system that motivates acceleration and present the detailed design of a hardware accelerator for Histograms of Oriented Gradients descriptor extraction. We also quantify the performance and area efficiency of the hardware accelerator. Our analysis shows that hardware acceleration has the potential to improve the hotspot function. As a result, user response time can be reduced significantly.

AB - Pedestrian recognition is an emerging visual computing application for embedded systems. In one usage model, a vehicle mounted camera acquires image from road and a pedestrian recognition system automatically recognizes and alarms information on the road preventing traffic accidents. Achieving this in software on embedded systems requires significant compute processing for object recognition. In this paper, we identify the hotspot function of the workload on an embedded system that motivates acceleration and present the detailed design of a hardware accelerator for Histograms of Oriented Gradients descriptor extraction. We also quantify the performance and area efficiency of the hardware accelerator. Our analysis shows that hardware acceleration has the potential to improve the hotspot function. As a result, user response time can be reduced significantly.

UR - http://www.scopus.com/inward/record.url?scp=84878831088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878831088&partnerID=8YFLogxK

U2 - 10.1016/j.compeleceng.2013.04.001

DO - 10.1016/j.compeleceng.2013.04.001

M3 - Article

AN - SCOPUS:84878831088

VL - 39

SP - 1043

EP - 1048

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

IS - 4

ER -