Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety

Hirokatsu Kataoka, Kimimasa Tamura, Yoshimitsu Aoki, Yasuhiro Matsui, Kenji Iwata, Yutaka Satoh

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

1 Citation (Scopus)

Abstract

The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented to perform braking controls, warn the driver, and develop improved safety systems for pedestrians. We improved the technology of detecting pedestrians using highly accurate images obtained with a monocular camera. We were able to predict pedestrian activity by monitoring the images, and developed an algorithm with which to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we used an extended co-occurrence histogram of oriented gradients (ECoHOG) that accumulated the integration of gradient intensities. In the tracking step, we applied an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on the real road.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages2472-2477
Number of pages6
DOIs
Publication statusPublished - 2013
Event39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013 - Vienna, Austria
Duration: 2013 Nov 102013 Nov 14

Other

Other39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013
CountryAustria
CityVienna
Period13/11/1013/11/14

Fingerprint

Cameras
Highway accidents
Optical flows
Braking
Security systems
Monitoring

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kataoka, H., Tamura, K., Aoki, Y., Matsui, Y., Iwata, K., & Satoh, Y. (2013). Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety. In IECON Proceedings (Industrial Electronics Conference) (pp. 2472-2477). [6699519] https://doi.org/10.1109/IECON.2013.6699519

Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety. / Kataoka, Hirokatsu; Tamura, Kimimasa; Aoki, Yoshimitsu; Matsui, Yasuhiro; Iwata, Kenji; Satoh, Yutaka.

IECON Proceedings (Industrial Electronics Conference). 2013. p. 2472-2477 6699519.

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

Kataoka, H, Tamura, K, Aoki, Y, Matsui, Y, Iwata, K & Satoh, Y 2013, Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety. in IECON Proceedings (Industrial Electronics Conference)., 6699519, pp. 2472-2477, 39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013, Vienna, Austria, 13/11/10. https://doi.org/10.1109/IECON.2013.6699519
Kataoka H, Tamura K, Aoki Y, Matsui Y, Iwata K, Satoh Y. Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety. In IECON Proceedings (Industrial Electronics Conference). 2013. p. 2472-2477. 6699519 https://doi.org/10.1109/IECON.2013.6699519
Kataoka, Hirokatsu ; Tamura, Kimimasa ; Aoki, Yoshimitsu ; Matsui, Yasuhiro ; Iwata, Kenji ; Satoh, Yutaka. / Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety. IECON Proceedings (Industrial Electronics Conference). 2013. pp. 2472-2477
@inproceedings{3cd8efcdb7084c8b9849b709baa90b8c,
title = "Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety",
abstract = "The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented to perform braking controls, warn the driver, and develop improved safety systems for pedestrians. We improved the technology of detecting pedestrians using highly accurate images obtained with a monocular camera. We were able to predict pedestrian activity by monitoring the images, and developed an algorithm with which to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we used an extended co-occurrence histogram of oriented gradients (ECoHOG) that accumulated the integration of gradient intensities. In the tracking step, we applied an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on the real road.",
author = "Hirokatsu Kataoka and Kimimasa Tamura and Yoshimitsu Aoki and Yasuhiro Matsui and Kenji Iwata and Yutaka Satoh",
year = "2013",
doi = "10.1109/IECON.2013.6699519",
language = "English",
isbn = "9781479902248",
pages = "2472--2477",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",

}

TY - GEN

T1 - Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety

AU - Kataoka, Hirokatsu

AU - Tamura, Kimimasa

AU - Aoki, Yoshimitsu

AU - Matsui, Yasuhiro

AU - Iwata, Kenji

AU - Satoh, Yutaka

PY - 2013

Y1 - 2013

N2 - The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented to perform braking controls, warn the driver, and develop improved safety systems for pedestrians. We improved the technology of detecting pedestrians using highly accurate images obtained with a monocular camera. We were able to predict pedestrian activity by monitoring the images, and developed an algorithm with which to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we used an extended co-occurrence histogram of oriented gradients (ECoHOG) that accumulated the integration of gradient intensities. In the tracking step, we applied an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on the real road.

AB - The percentage of pedestrian deaths in traffic accidents is on the rise in Japan. In recent years, there have been calls for measures to be introduced to protect vulnerable road users such as pedestrians and cyclists. In this study, a method to detect and track pedestrians using an in-vehicle camera is presented to perform braking controls, warn the driver, and develop improved safety systems for pedestrians. We improved the technology of detecting pedestrians using highly accurate images obtained with a monocular camera. We were able to predict pedestrian activity by monitoring the images, and developed an algorithm with which to recognize pedestrians and their movements more accurately. The effectiveness of the algorithm was tested using images taken on real roads. For the feature descriptor, we used an extended co-occurrence histogram of oriented gradients (ECoHOG) that accumulated the integration of gradient intensities. In the tracking step, we applied an effective motion model using optical flow and the proposed feature descriptor ECoHOG in a tracking-by-detection framework. These techniques were verified using images captured on the real road.

UR - http://www.scopus.com/inward/record.url?scp=84893565377&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893565377&partnerID=8YFLogxK

U2 - 10.1109/IECON.2013.6699519

DO - 10.1109/IECON.2013.6699519

M3 - Conference contribution

AN - SCOPUS:84893565377

SN - 9781479902248

SP - 2472

EP - 2477

BT - IECON Proceedings (Industrial Electronics Conference)

ER -