Abstract

In this paper, we propose a real-time system using vehicle back-up camera to alert for potential back-up collisions. We developed a highly efficient algorithm, combining segmenting pedestrians and vehicles from moving background using local optical flow value, and a scale adaptive method using Deformable Part Model to detect objects at different distances. To test out algorithm, we created our own vehicle back-up dataset that contains rich scenes recorded from a back-up camera on moving/stationary vehicles with unique and challenging scenarios such as frequent occlusion with cluttered and moving background, and we made this dataset available to public for other researchers. Experiments on the dataset shows that our algorithm achieves high accuracy in near real-time, and it is about 10 times faster than the comparable state-of-the-art algorithm.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
PublisherIEEE Computer Society
Pages2275-2279
Number of pages5
Volume2015-December
ISBN (Print)9781479983391
DOIs
StatePublished - Dec 9 2015
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: Sep 27 2015Sep 30 2015

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period9/27/159/30/15

Fingerprint

Alarm systems
Cameras
Optical flows
Real time systems
Experiments

Keywords

  • Computer Vision
  • Deformable Part Model
  • Latent SVM
  • Optical Flow
  • Vehicle Safety

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Cao, J., Wang, Y., & Li, B. (2015). Real-time vehicle back-up warning system with a single camera. In Proceedings - International Conference on Image Processing, ICIP (Vol. 2015-December, pp. 2275-2279). [7351207] IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351207

Real-time vehicle back-up warning system with a single camera. / Cao, Jun; Wang, Yilin; Li, Baoxin.

Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. p. 2275-2279 7351207.

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

Cao, J, Wang, Y & Li, B 2015, Real-time vehicle back-up warning system with a single camera. in Proceedings - International Conference on Image Processing, ICIP. vol. 2015-December, 7351207, IEEE Computer Society, pp. 2275-2279, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 9/27/15. https://doi.org/10.1109/ICIP.2015.7351207
Cao J, Wang Y, Li B. Real-time vehicle back-up warning system with a single camera. In Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December. IEEE Computer Society. 2015. p. 2275-2279. 7351207 https://doi.org/10.1109/ICIP.2015.7351207
Cao, Jun ; Wang, Yilin ; Li, Baoxin. / Real-time vehicle back-up warning system with a single camera. Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. pp. 2275-2279
@inproceedings{2a7b8ed81391445388b67fe53eb9430e,
title = "Real-time vehicle back-up warning system with a single camera",
abstract = "In this paper, we propose a real-time system using vehicle back-up camera to alert for potential back-up collisions. We developed a highly efficient algorithm, combining segmenting pedestrians and vehicles from moving background using local optical flow value, and a scale adaptive method using Deformable Part Model to detect objects at different distances. To test out algorithm, we created our own vehicle back-up dataset that contains rich scenes recorded from a back-up camera on moving/stationary vehicles with unique and challenging scenarios such as frequent occlusion with cluttered and moving background, and we made this dataset available to public for other researchers. Experiments on the dataset shows that our algorithm achieves high accuracy in near real-time, and it is about 10 times faster than the comparable state-of-the-art algorithm.",
keywords = "Computer Vision, Deformable Part Model, Latent SVM, Optical Flow, Vehicle Safety",
author = "Jun Cao and Yilin Wang and Baoxin Li",
year = "2015",
month = "12",
day = "9",
doi = "10.1109/ICIP.2015.7351207",
language = "English (US)",
isbn = "9781479983391",
volume = "2015-December",
pages = "2275--2279",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Real-time vehicle back-up warning system with a single camera

AU - Cao, Jun

AU - Wang, Yilin

AU - Li, Baoxin

PY - 2015/12/9

Y1 - 2015/12/9

N2 - In this paper, we propose a real-time system using vehicle back-up camera to alert for potential back-up collisions. We developed a highly efficient algorithm, combining segmenting pedestrians and vehicles from moving background using local optical flow value, and a scale adaptive method using Deformable Part Model to detect objects at different distances. To test out algorithm, we created our own vehicle back-up dataset that contains rich scenes recorded from a back-up camera on moving/stationary vehicles with unique and challenging scenarios such as frequent occlusion with cluttered and moving background, and we made this dataset available to public for other researchers. Experiments on the dataset shows that our algorithm achieves high accuracy in near real-time, and it is about 10 times faster than the comparable state-of-the-art algorithm.

AB - In this paper, we propose a real-time system using vehicle back-up camera to alert for potential back-up collisions. We developed a highly efficient algorithm, combining segmenting pedestrians and vehicles from moving background using local optical flow value, and a scale adaptive method using Deformable Part Model to detect objects at different distances. To test out algorithm, we created our own vehicle back-up dataset that contains rich scenes recorded from a back-up camera on moving/stationary vehicles with unique and challenging scenarios such as frequent occlusion with cluttered and moving background, and we made this dataset available to public for other researchers. Experiments on the dataset shows that our algorithm achieves high accuracy in near real-time, and it is about 10 times faster than the comparable state-of-the-art algorithm.

KW - Computer Vision

KW - Deformable Part Model

KW - Latent SVM

KW - Optical Flow

KW - Vehicle Safety

UR - http://www.scopus.com/inward/record.url?scp=84956676882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956676882&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351207

DO - 10.1109/ICIP.2015.7351207

M3 - Conference contribution

SN - 9781479983391

VL - 2015-December

SP - 2275

EP - 2279

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE Computer Society

ER -