Vehicle trajectory prediction using a catadioptric omnidirectional camera

Vigneshram Krishnamoorthy; Saksham Agarwal; K.S. Venkatesh

doi:10.1109/ICACCI.2016.7732480

Vehicle trajectory prediction using a catadioptric omnidirectional camera

Vigneshram Krishnamoorthy, Saksham Agarwal, K.S. Venkatesh

Research output: Contribution to conference › Paper › peer-review

Abstract

A practical method is presented to predict the future spatial-temporal trajectories of multiple vehicles at road intersections in real time using a catadioptric omnidirectional camera equipped with an Equiangular mirror. Tracking is done using CamShift algorithm running alongside a Kalman Filter to handle occlusions. Domain transformation of the tracked objects location and velocity from image space to real world is done using a geometrical model. A computationally effective model for trajectory prediction has been presented along with the experimental results obtained using it. Applications such as collision prediction and vehicle tracking or any other event of interest using a dual-camera system are also discussed briefly.

Original language	English (US)
Pages	2761-2764
DOIs	https://doi.org/10.1109/ICACCI.2016.7732480
State	Published - Nov 3 2016
Externally published	Yes
Event	2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Jaipur Duration: Sep 21 2016 → Sep 24 2016

Conference

Conference	2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI)
Period	9/21/16 → 9/24/16

Keywords

Trajectory prediction
Omnidirectional camera
Kalman and CAMShift tracking

Online availability

10.1109/ICACCI.2016.7732480

Library availability

Discover UIUC Full Text

Cite this

@conference{5781d22a8bbf49d7b23d958382eab6b2,

title = "Vehicle trajectory prediction using a catadioptric omnidirectional camera",

abstract = "A practical method is presented to predict the future spatial-temporal trajectories of multiple vehicles at road intersections in real time using a catadioptric omnidirectional camera equipped with an Equiangular mirror. Tracking is done using CamShift algorithm running alongside a Kalman Filter to handle occlusions. Domain transformation of the tracked objects location and velocity from image space to real world is done using a geometrical model. A computationally effective model for trajectory prediction has been presented along with the experimental results obtained using it. Applications such as collision prediction and vehicle tracking or any other event of interest using a dual-camera system are also discussed briefly.",

keywords = "Trajectory prediction, Omnidirectional camera, Kalman and CAMShift tracking",

author = "Vigneshram Krishnamoorthy and Saksham Agarwal and K.S. Venkatesh",

year = "2016",

month = nov,

day = "3",

doi = "10.1109/ICACCI.2016.7732480",

language = "English (US)",

pages = "2761--2764",

note = "2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI) ; Conference date: 21-09-2016 Through 24-09-2016",

}

TY - CONF

T1 - Vehicle trajectory prediction using a catadioptric omnidirectional camera

AU - Krishnamoorthy, Vigneshram

AU - Agarwal, Saksham

AU - Venkatesh, K.S.

PY - 2016/11/3

Y1 - 2016/11/3

N2 - A practical method is presented to predict the future spatial-temporal trajectories of multiple vehicles at road intersections in real time using a catadioptric omnidirectional camera equipped with an Equiangular mirror. Tracking is done using CamShift algorithm running alongside a Kalman Filter to handle occlusions. Domain transformation of the tracked objects location and velocity from image space to real world is done using a geometrical model. A computationally effective model for trajectory prediction has been presented along with the experimental results obtained using it. Applications such as collision prediction and vehicle tracking or any other event of interest using a dual-camera system are also discussed briefly.

AB - A practical method is presented to predict the future spatial-temporal trajectories of multiple vehicles at road intersections in real time using a catadioptric omnidirectional camera equipped with an Equiangular mirror. Tracking is done using CamShift algorithm running alongside a Kalman Filter to handle occlusions. Domain transformation of the tracked objects location and velocity from image space to real world is done using a geometrical model. A computationally effective model for trajectory prediction has been presented along with the experimental results obtained using it. Applications such as collision prediction and vehicle tracking or any other event of interest using a dual-camera system are also discussed briefly.

KW - Trajectory prediction

KW - Omnidirectional camera

KW - Kalman and CAMShift tracking

U2 - 10.1109/ICACCI.2016.7732480

DO - 10.1109/ICACCI.2016.7732480

M3 - Paper

SP - 2761

EP - 2764

T2 - 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

Y2 - 21 September 2016 through 24 September 2016

ER -

Vehicle trajectory prediction using a catadioptric omnidirectional camera

Abstract

Conference

Keywords

Online availability

Library availability

Fingerprint

Cite this