“Motion based Feature Point Selection Algorithms with KLT Tracker and Its Hardware Implementation”

Tsuyoshi Sasaki, Kodai Kawane, Takeshi Ikenaga

Research output: Contribution to journalArticle

Abstract

Surveillance camera systems play an important role for creating safe and secure society. Especially, real-time motion detection is a key to detect abnormal scenes. So, we picked up KLT (Kanade-Lucas-Tomasi) tracker and tried to implement a system. However, there are still many problems in accuracy and system cost. This paper proposes a score control by weighted mask and an adaptive feature point interval algorithms to increase accuracy of object detection. Moreover, to implement these algorithms onto a low cost FPGA, hardware architectures, such as weighted value generation circuit, insert position calculation circuit and feature point data update circuit, are proposed. Evaluation results shows that the proposed algorithm can detect motion vectors with high accuracy for various surveillance scenes. Moreover, hardware implementation results show that the proposed architecture attains real-time processing with around 20% FPGA resources.

Original languageEnglish
Pages (from-to)590-597
Number of pages8
JournalJournal of the Institute of Image Electronics Engineers of Japan
Volume39
Issue number5
DOIs
Publication statusPublished - 2010

Fingerprint

Hardware
Field programmable gate arrays (FPGA)
Networks (circuits)
Costs
Masks
Cameras
Processing
Object detection

Keywords

  • FPGA
  • Hardware Engine
  • KLT Tracker
  • Weighted mask

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

“Motion based Feature Point Selection Algorithms with KLT Tracker and Its Hardware Implementation”. / Sasaki, Tsuyoshi; Kawane, Kodai; Ikenaga, Takeshi.

In: Journal of the Institute of Image Electronics Engineers of Japan, Vol. 39, No. 5, 2010, p. 590-597.

Research output: Contribution to journalArticle

@article{15294f859a4741908a771e4d335652e7,
title = "“Motion based Feature Point Selection Algorithms with KLT Tracker and Its Hardware Implementation”",
abstract = "Surveillance camera systems play an important role for creating safe and secure society. Especially, real-time motion detection is a key to detect abnormal scenes. So, we picked up KLT (Kanade-Lucas-Tomasi) tracker and tried to implement a system. However, there are still many problems in accuracy and system cost. This paper proposes a score control by weighted mask and an adaptive feature point interval algorithms to increase accuracy of object detection. Moreover, to implement these algorithms onto a low cost FPGA, hardware architectures, such as weighted value generation circuit, insert position calculation circuit and feature point data update circuit, are proposed. Evaluation results shows that the proposed algorithm can detect motion vectors with high accuracy for various surveillance scenes. Moreover, hardware implementation results show that the proposed architecture attains real-time processing with around 20{\%} FPGA resources.",
keywords = "FPGA, Hardware Engine, KLT Tracker, Weighted mask",
author = "Tsuyoshi Sasaki and Kodai Kawane and Takeshi Ikenaga",
year = "2010",
doi = "10.11371/iieej.39.590",
language = "English",
volume = "39",
pages = "590--597",
journal = "Journal of the Institute of Image Electronics Engineers of Japan",
issn = "0285-9831",
publisher = "Institute of Image Electronics Engineers of Japan",
number = "5",

}

TY - JOUR

T1 - “Motion based Feature Point Selection Algorithms with KLT Tracker and Its Hardware Implementation”

AU - Sasaki, Tsuyoshi

AU - Kawane, Kodai

AU - Ikenaga, Takeshi

PY - 2010

Y1 - 2010

N2 - Surveillance camera systems play an important role for creating safe and secure society. Especially, real-time motion detection is a key to detect abnormal scenes. So, we picked up KLT (Kanade-Lucas-Tomasi) tracker and tried to implement a system. However, there are still many problems in accuracy and system cost. This paper proposes a score control by weighted mask and an adaptive feature point interval algorithms to increase accuracy of object detection. Moreover, to implement these algorithms onto a low cost FPGA, hardware architectures, such as weighted value generation circuit, insert position calculation circuit and feature point data update circuit, are proposed. Evaluation results shows that the proposed algorithm can detect motion vectors with high accuracy for various surveillance scenes. Moreover, hardware implementation results show that the proposed architecture attains real-time processing with around 20% FPGA resources.

AB - Surveillance camera systems play an important role for creating safe and secure society. Especially, real-time motion detection is a key to detect abnormal scenes. So, we picked up KLT (Kanade-Lucas-Tomasi) tracker and tried to implement a system. However, there are still many problems in accuracy and system cost. This paper proposes a score control by weighted mask and an adaptive feature point interval algorithms to increase accuracy of object detection. Moreover, to implement these algorithms onto a low cost FPGA, hardware architectures, such as weighted value generation circuit, insert position calculation circuit and feature point data update circuit, are proposed. Evaluation results shows that the proposed algorithm can detect motion vectors with high accuracy for various surveillance scenes. Moreover, hardware implementation results show that the proposed architecture attains real-time processing with around 20% FPGA resources.

KW - FPGA

KW - Hardware Engine

KW - KLT Tracker

KW - Weighted mask

UR - http://www.scopus.com/inward/record.url?scp=85024730381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024730381&partnerID=8YFLogxK

U2 - 10.11371/iieej.39.590

DO - 10.11371/iieej.39.590

M3 - Article

AN - SCOPUS:85024730381

VL - 39

SP - 590

EP - 597

JO - Journal of the Institute of Image Electronics Engineers of Japan

JF - Journal of the Institute of Image Electronics Engineers of Japan

SN - 0285-9831

IS - 5

ER -