Car tracking in rear view based on bicycle specific motions in vertical vibration and angular variation via prediction and likelihood models with particle filter for rear confirmation support

Norikazu Ikoma, Yohei Mikami, Takeshi Ikenaga

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

2 Citations (Scopus)

Abstract

Aiming at rear confirmation support of a bicycle, our objective is to track of a car in rear view captured by a camera settled under the saddle. Where specific motions of bicycle such as angular variation and vertical vibration are necessary to cope with. We propose a novel state space model coping with the two specific motions and utilize particle filter for state estimation. For angular variation, an elaborated system noise with variable mean having larger pulling force for larger angle. For likelihood model to cope with vertical vibration, we propose an elaborated likelihood evaluation having more sensitive feature for horizontal while less sensitive for vertical motion. Experimental result with real scene videos achieves 74.24 percent precision of the tracking.

Original languageEnglish
Title of host publicationWorld Automation Congress Proceedings
PublisherIEEE Computer Society
Pages279-284
Number of pages6
ISBN (Print)9781889335490
DOIs
Publication statusPublished - 2014 Oct 24
Event2014 World Automation Congress, WAC 2014 - Waikoloa
Duration: 2014 Aug 32014 Aug 7

Other

Other2014 World Automation Congress, WAC 2014
CityWaikoloa
Period14/8/314/8/7

Fingerprint

Bicycles
Railroad cars
Railroad tracks
State estimation
Cameras

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Car tracking in rear view based on bicycle specific motions in vertical vibration and angular variation via prediction and likelihood models with particle filter for rear confirmation support. / Ikoma, Norikazu; Mikami, Yohei; Ikenaga, Takeshi.

World Automation Congress Proceedings. IEEE Computer Society, 2014. p. 279-284 6935890.

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

Ikoma, N, Mikami, Y & Ikenaga, T 2014, Car tracking in rear view based on bicycle specific motions in vertical vibration and angular variation via prediction and likelihood models with particle filter for rear confirmation support. in World Automation Congress Proceedings., 6935890, IEEE Computer Society, pp. 279-284, 2014 World Automation Congress, WAC 2014, Waikoloa, 14/8/3. https://doi.org/10.1109/WAC.2014.6935890
@inproceedings{aa62af0737b9463bba78073529128787,
title = "Car tracking in rear view based on bicycle specific motions in vertical vibration and angular variation via prediction and likelihood models with particle filter for rear confirmation support",
abstract = "Aiming at rear confirmation support of a bicycle, our objective is to track of a car in rear view captured by a camera settled under the saddle. Where specific motions of bicycle such as angular variation and vertical vibration are necessary to cope with. We propose a novel state space model coping with the two specific motions and utilize particle filter for state estimation. For angular variation, an elaborated system noise with variable mean having larger pulling force for larger angle. For likelihood model to cope with vertical vibration, we propose an elaborated likelihood evaluation having more sensitive feature for horizontal while less sensitive for vertical motion. Experimental result with real scene videos achieves 74.24 percent precision of the tracking.",
author = "Norikazu Ikoma and Yohei Mikami and Takeshi Ikenaga",
year = "2014",
month = "10",
day = "24",
doi = "10.1109/WAC.2014.6935890",
language = "English",
isbn = "9781889335490",
pages = "279--284",
booktitle = "World Automation Congress Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Car tracking in rear view based on bicycle specific motions in vertical vibration and angular variation via prediction and likelihood models with particle filter for rear confirmation support

AU - Ikoma, Norikazu

AU - Mikami, Yohei

AU - Ikenaga, Takeshi

PY - 2014/10/24

Y1 - 2014/10/24

N2 - Aiming at rear confirmation support of a bicycle, our objective is to track of a car in rear view captured by a camera settled under the saddle. Where specific motions of bicycle such as angular variation and vertical vibration are necessary to cope with. We propose a novel state space model coping with the two specific motions and utilize particle filter for state estimation. For angular variation, an elaborated system noise with variable mean having larger pulling force for larger angle. For likelihood model to cope with vertical vibration, we propose an elaborated likelihood evaluation having more sensitive feature for horizontal while less sensitive for vertical motion. Experimental result with real scene videos achieves 74.24 percent precision of the tracking.

AB - Aiming at rear confirmation support of a bicycle, our objective is to track of a car in rear view captured by a camera settled under the saddle. Where specific motions of bicycle such as angular variation and vertical vibration are necessary to cope with. We propose a novel state space model coping with the two specific motions and utilize particle filter for state estimation. For angular variation, an elaborated system noise with variable mean having larger pulling force for larger angle. For likelihood model to cope with vertical vibration, we propose an elaborated likelihood evaluation having more sensitive feature for horizontal while less sensitive for vertical motion. Experimental result with real scene videos achieves 74.24 percent precision of the tracking.

UR - http://www.scopus.com/inward/record.url?scp=84908874856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908874856&partnerID=8YFLogxK

U2 - 10.1109/WAC.2014.6935890

DO - 10.1109/WAC.2014.6935890

M3 - Conference contribution

AN - SCOPUS:84908874856

SN - 9781889335490

SP - 279

EP - 284

BT - World Automation Congress Proceedings

PB - IEEE Computer Society

ER -