An Approach to the Vehicle Tracking Method using Intensity Projection of the Edge Image

Kenichi Yamada, Toshio Ito

研究成果: Article

4 引用 (Scopus)

抄録

This paper describes the preceding vehicle recognition and road-lane recognition methods for the rear-end collision avoidance system (RCAS) which we are developing. These methods are using an edge histogram method based on modelbased vision. The edge histogram method can detect line elements of the objects stably with low calculation cost. When the region of interests for the preceding vehicle and road lanes in the image are established and their projected edge histograms are observed in time series order, we can recognize the positions of the vehicle and the lane. Furthermore, we apply Kalman Filter to their motions and predict their locations for time series detection. Using this stable recognition, we derive a collision time to control the on-board brake system. We show the performance of these methods by experimental results.

元の言語English
ページ(範囲)327-332
ページ数6
ジャーナルIEEJ Transactions on Sensors and Micromachines
118
発行部数6
DOI
出版物ステータスPublished - 1998
外部発表Yes

Fingerprint

Time series
Collision avoidance
Brakes
Kalman filters
Costs

ASJC Scopus subject areas

  • Mechanical Engineering
  • Electrical and Electronic Engineering

これを引用

@article{6448d2b3da1248efab3727463525e566,
title = "An Approach to the Vehicle Tracking Method using Intensity Projection of the Edge Image",
abstract = "This paper describes the preceding vehicle recognition and road-lane recognition methods for the rear-end collision avoidance system (RCAS) which we are developing. These methods are using an edge histogram method based on modelbased vision. The edge histogram method can detect line elements of the objects stably with low calculation cost. When the region of interests for the preceding vehicle and road lanes in the image are established and their projected edge histograms are observed in time series order, we can recognize the positions of the vehicle and the lane. Furthermore, we apply Kalman Filter to their motions and predict their locations for time series detection. Using this stable recognition, we derive a collision time to control the on-board brake system. We show the performance of these methods by experimental results.",
author = "Kenichi Yamada and Toshio Ito",
year = "1998",
doi = "10.1541/ieejsmas.118.327",
language = "English",
volume = "118",
pages = "327--332",
journal = "IEEJ Transactions on Sensors and Micromachines",
issn = "1341-8939",
publisher = "The Institute of Electrical Engineers of Japan",
number = "6",

}

TY - JOUR

T1 - An Approach to the Vehicle Tracking Method using Intensity Projection of the Edge Image

AU - Yamada, Kenichi

AU - Ito, Toshio

PY - 1998

Y1 - 1998

N2 - This paper describes the preceding vehicle recognition and road-lane recognition methods for the rear-end collision avoidance system (RCAS) which we are developing. These methods are using an edge histogram method based on modelbased vision. The edge histogram method can detect line elements of the objects stably with low calculation cost. When the region of interests for the preceding vehicle and road lanes in the image are established and their projected edge histograms are observed in time series order, we can recognize the positions of the vehicle and the lane. Furthermore, we apply Kalman Filter to their motions and predict their locations for time series detection. Using this stable recognition, we derive a collision time to control the on-board brake system. We show the performance of these methods by experimental results.

AB - This paper describes the preceding vehicle recognition and road-lane recognition methods for the rear-end collision avoidance system (RCAS) which we are developing. These methods are using an edge histogram method based on modelbased vision. The edge histogram method can detect line elements of the objects stably with low calculation cost. When the region of interests for the preceding vehicle and road lanes in the image are established and their projected edge histograms are observed in time series order, we can recognize the positions of the vehicle and the lane. Furthermore, we apply Kalman Filter to their motions and predict their locations for time series detection. Using this stable recognition, we derive a collision time to control the on-board brake system. We show the performance of these methods by experimental results.

UR - http://www.scopus.com/inward/record.url?scp=2442470927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2442470927&partnerID=8YFLogxK

U2 - 10.1541/ieejsmas.118.327

DO - 10.1541/ieejsmas.118.327

M3 - Article

AN - SCOPUS:2442470927

VL - 118

SP - 327

EP - 332

JO - IEEJ Transactions on Sensors and Micromachines

JF - IEEJ Transactions on Sensors and Micromachines

SN - 1341-8939

IS - 6

ER -