On-road vehicle detection based on effective hypothesis generation

Jisu Kim, Jeonghyun Baek, Dong Yeop Kim, Euntai Kim

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

6 Citations (Scopus)

Abstract

This paper proposes an effective hypothesis generation for detection multi-vehicle using a monocular camera fixed on the host vehicle. In hypothesis generation (HG) step, we use linear model between the distance and vehicle size by using recursive least square. It generates effective image patches and improves the detection performance. In addition, it also reduces the computation time compared with sliding-window approach. In hypothesis verification (HV) step, we use the Histogram of Oriented Gradient (HOG) feature and Support Vector Machine (SVM). In our experiment, Caltech and IR datasets are used. The experimental result shows the improvement of running time and detection performance.

Original languageEnglish
Title of host publication22nd IEEE International Symposium on Robot and Human Interactive Communication
Subtitle of host publication"Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013
Pages252-257
Number of pages6
DOIs
Publication statusPublished - 2013 Dec 11
Event22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013 - Gyeongju, Korea, Republic of
Duration: 2013 Aug 262013 Aug 29

Publication series

NameProceedings - IEEE International Workshop on Robot and Human Interactive Communication

Other

Other22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013
CountryKorea, Republic of
CityGyeongju
Period13/8/2613/8/29

Fingerprint

Support vector machines
Cameras
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Kim, J., Baek, J., Kim, D. Y., & Kim, E. (2013). On-road vehicle detection based on effective hypothesis generation. In 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013 (pp. 252-257). [6628455] (Proceedings - IEEE International Workshop on Robot and Human Interactive Communication). https://doi.org/10.1109/ROMAN.2013.6628455
Kim, Jisu ; Baek, Jeonghyun ; Kim, Dong Yeop ; Kim, Euntai. / On-road vehicle detection based on effective hypothesis generation. 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013. 2013. pp. 252-257 (Proceedings - IEEE International Workshop on Robot and Human Interactive Communication).
@inproceedings{4e3a247cb635459ba883b43fce0917e6,
title = "On-road vehicle detection based on effective hypothesis generation",
abstract = "This paper proposes an effective hypothesis generation for detection multi-vehicle using a monocular camera fixed on the host vehicle. In hypothesis generation (HG) step, we use linear model between the distance and vehicle size by using recursive least square. It generates effective image patches and improves the detection performance. In addition, it also reduces the computation time compared with sliding-window approach. In hypothesis verification (HV) step, we use the Histogram of Oriented Gradient (HOG) feature and Support Vector Machine (SVM). In our experiment, Caltech and IR datasets are used. The experimental result shows the improvement of running time and detection performance.",
author = "Jisu Kim and Jeonghyun Baek and Kim, {Dong Yeop} and Euntai Kim",
year = "2013",
month = "12",
day = "11",
doi = "10.1109/ROMAN.2013.6628455",
language = "English",
isbn = "9781479905072",
series = "Proceedings - IEEE International Workshop on Robot and Human Interactive Communication",
pages = "252--257",
booktitle = "22nd IEEE International Symposium on Robot and Human Interactive Communication",

}

Kim, J, Baek, J, Kim, DY & Kim, E 2013, On-road vehicle detection based on effective hypothesis generation. in 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013., 6628455, Proceedings - IEEE International Workshop on Robot and Human Interactive Communication, pp. 252-257, 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013, Gyeongju, Korea, Republic of, 13/8/26. https://doi.org/10.1109/ROMAN.2013.6628455

On-road vehicle detection based on effective hypothesis generation. / Kim, Jisu; Baek, Jeonghyun; Kim, Dong Yeop; Kim, Euntai.

22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013. 2013. p. 252-257 6628455 (Proceedings - IEEE International Workshop on Robot and Human Interactive Communication).

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

TY - GEN

T1 - On-road vehicle detection based on effective hypothesis generation

AU - Kim, Jisu

AU - Baek, Jeonghyun

AU - Kim, Dong Yeop

AU - Kim, Euntai

PY - 2013/12/11

Y1 - 2013/12/11

N2 - This paper proposes an effective hypothesis generation for detection multi-vehicle using a monocular camera fixed on the host vehicle. In hypothesis generation (HG) step, we use linear model between the distance and vehicle size by using recursive least square. It generates effective image patches and improves the detection performance. In addition, it also reduces the computation time compared with sliding-window approach. In hypothesis verification (HV) step, we use the Histogram of Oriented Gradient (HOG) feature and Support Vector Machine (SVM). In our experiment, Caltech and IR datasets are used. The experimental result shows the improvement of running time and detection performance.

AB - This paper proposes an effective hypothesis generation for detection multi-vehicle using a monocular camera fixed on the host vehicle. In hypothesis generation (HG) step, we use linear model between the distance and vehicle size by using recursive least square. It generates effective image patches and improves the detection performance. In addition, it also reduces the computation time compared with sliding-window approach. In hypothesis verification (HV) step, we use the Histogram of Oriented Gradient (HOG) feature and Support Vector Machine (SVM). In our experiment, Caltech and IR datasets are used. The experimental result shows the improvement of running time and detection performance.

UR - http://www.scopus.com/inward/record.url?scp=84889608310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889608310&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2013.6628455

DO - 10.1109/ROMAN.2013.6628455

M3 - Conference contribution

AN - SCOPUS:84889608310

SN - 9781479905072

T3 - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

SP - 252

EP - 257

BT - 22nd IEEE International Symposium on Robot and Human Interactive Communication

ER -

Kim J, Baek J, Kim DY, Kim E. On-road vehicle detection based on effective hypothesis generation. In 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013. 2013. p. 252-257. 6628455. (Proceedings - IEEE International Workshop on Robot and Human Interactive Communication). https://doi.org/10.1109/ROMAN.2013.6628455