Proposal of low-resolution vehicle image recognition method

Yusuke Kanzawa, Takenao Ohkawa, Toshio Ito

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

4 Citations (Scopus)

Abstract

Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments and possible collision with other vehicles has attracted a lot of attention recently. Especially, many researchers have proposed the forward vehicle recognition method by a camera on vehicle. In the forward vehicle recognition, however, it is difficult to detect the features of vehicle from a distant vehicle image by conventional methods because the image is too low-resolution (LR). This paper presents a vehicle image recognition method for detecting features of a distant vehicle by frame-merging of image sequences. To detect vehicle features of a distant LR vehicle image, we use the image sequences obtained from the camera on the vehicle, and utilize super-resolution (SR) image reconstruction. In SR image reconstruction, signal processing methods are utilized to obtain a high-resolution image from observed multiple LR images. Through the experiments using real road images, we show the effectiveness of the proposed methods.

Original languageEnglish
Title of host publicationIEEE Intelligent Vehicles Symposium, Proceedings
Pages43-48
Number of pages6
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE Intelligent Vehicles Symposium, IV - Eindhoven
Duration: 2008 Jun 42008 Jun 6

Other

Other2008 IEEE Intelligent Vehicles Symposium, IV
CityEindhoven
Period08/6/408/6/6

Fingerprint

Image recognition
Image resolution
Image reconstruction
Cameras
Merging
Signal processing

ASJC Scopus subject areas

  • Computer Science Applications
  • Automotive Engineering
  • Modelling and Simulation

Cite this

Kanzawa, Y., Ohkawa, T., & Ito, T. (2008). Proposal of low-resolution vehicle image recognition method. In IEEE Intelligent Vehicles Symposium, Proceedings (pp. 43-48). [4621196] https://doi.org/10.1109/IVS.2008.4621196

Proposal of low-resolution vehicle image recognition method. / Kanzawa, Yusuke; Ohkawa, Takenao; Ito, Toshio.

IEEE Intelligent Vehicles Symposium, Proceedings. 2008. p. 43-48 4621196.

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

Kanzawa, Y, Ohkawa, T & Ito, T 2008, Proposal of low-resolution vehicle image recognition method. in IEEE Intelligent Vehicles Symposium, Proceedings., 4621196, pp. 43-48, 2008 IEEE Intelligent Vehicles Symposium, IV, Eindhoven, 08/6/4. https://doi.org/10.1109/IVS.2008.4621196
Kanzawa Y, Ohkawa T, Ito T. Proposal of low-resolution vehicle image recognition method. In IEEE Intelligent Vehicles Symposium, Proceedings. 2008. p. 43-48. 4621196 https://doi.org/10.1109/IVS.2008.4621196
Kanzawa, Yusuke ; Ohkawa, Takenao ; Ito, Toshio. / Proposal of low-resolution vehicle image recognition method. IEEE Intelligent Vehicles Symposium, Proceedings. 2008. pp. 43-48
@inproceedings{bba4f9f54e4a41a3b6405634861247f8,
title = "Proposal of low-resolution vehicle image recognition method",
abstract = "Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments and possible collision with other vehicles has attracted a lot of attention recently. Especially, many researchers have proposed the forward vehicle recognition method by a camera on vehicle. In the forward vehicle recognition, however, it is difficult to detect the features of vehicle from a distant vehicle image by conventional methods because the image is too low-resolution (LR). This paper presents a vehicle image recognition method for detecting features of a distant vehicle by frame-merging of image sequences. To detect vehicle features of a distant LR vehicle image, we use the image sequences obtained from the camera on the vehicle, and utilize super-resolution (SR) image reconstruction. In SR image reconstruction, signal processing methods are utilized to obtain a high-resolution image from observed multiple LR images. Through the experiments using real road images, we show the effectiveness of the proposed methods.",
author = "Yusuke Kanzawa and Takenao Ohkawa and Toshio Ito",
year = "2008",
doi = "10.1109/IVS.2008.4621196",
language = "English",
isbn = "9781424425693",
pages = "43--48",
booktitle = "IEEE Intelligent Vehicles Symposium, Proceedings",

}

TY - GEN

T1 - Proposal of low-resolution vehicle image recognition method

AU - Kanzawa, Yusuke

AU - Ohkawa, Takenao

AU - Ito, Toshio

PY - 2008

Y1 - 2008

N2 - Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments and possible collision with other vehicles has attracted a lot of attention recently. Especially, many researchers have proposed the forward vehicle recognition method by a camera on vehicle. In the forward vehicle recognition, however, it is difficult to detect the features of vehicle from a distant vehicle image by conventional methods because the image is too low-resolution (LR). This paper presents a vehicle image recognition method for detecting features of a distant vehicle by frame-merging of image sequences. To detect vehicle features of a distant LR vehicle image, we use the image sequences obtained from the camera on the vehicle, and utilize super-resolution (SR) image reconstruction. In SR image reconstruction, signal processing methods are utilized to obtain a high-resolution image from observed multiple LR images. Through the experiments using real road images, we show the effectiveness of the proposed methods.

AB - Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments and possible collision with other vehicles has attracted a lot of attention recently. Especially, many researchers have proposed the forward vehicle recognition method by a camera on vehicle. In the forward vehicle recognition, however, it is difficult to detect the features of vehicle from a distant vehicle image by conventional methods because the image is too low-resolution (LR). This paper presents a vehicle image recognition method for detecting features of a distant vehicle by frame-merging of image sequences. To detect vehicle features of a distant LR vehicle image, we use the image sequences obtained from the camera on the vehicle, and utilize super-resolution (SR) image reconstruction. In SR image reconstruction, signal processing methods are utilized to obtain a high-resolution image from observed multiple LR images. Through the experiments using real road images, we show the effectiveness of the proposed methods.

UR - http://www.scopus.com/inward/record.url?scp=57749173877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57749173877&partnerID=8YFLogxK

U2 - 10.1109/IVS.2008.4621196

DO - 10.1109/IVS.2008.4621196

M3 - Conference contribution

AN - SCOPUS:57749173877

SN - 9781424425693

SP - 43

EP - 48

BT - IEEE Intelligent Vehicles Symposium, Proceedings

ER -