Abstract
A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.
| Original language | English |
|---|---|
| Title of host publication | Digest of Technical Papers - IEEE International Conference on Consumer Electronics |
| Pages | 229-230 |
| Number of pages | 2 |
| DOIs | |
| Publication status | Published - 2012 Mar 29 |
| Event | 2012 IEEE International Conference on Consumer Electronics, ICCE 2012 - Las Vegas, NV, United States Duration: 2012 Jan 13 → 2012 Jan 16 |
Other
| Other | 2012 IEEE International Conference on Consumer Electronics, ICCE 2012 |
|---|---|
| Country | United States |
| City | Las Vegas, NV |
| Period | 12/1/13 → 12/1/16 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Industrial and Manufacturing Engineering
Cite this
An effective pedestrian detection method for driver assistance system. / Byun, Keun Yung; Kim, Bo Sang; Kim, Hyo Kak; Shin, Jeong Eun; Ko, Sung-Jea.
Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2012. p. 229-230 6161841.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - An effective pedestrian detection method for driver assistance system
AU - Byun, Keun Yung
AU - Kim, Bo Sang
AU - Kim, Hyo Kak
AU - Shin, Jeong Eun
AU - Ko, Sung-Jea
PY - 2012/3/29
Y1 - 2012/3/29
N2 - A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.
AB - A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.
UR - http://www.scopus.com/inward/record.url?scp=84863385535&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863385535&partnerID=8YFLogxK
U2 - 10.1109/ICCE.2012.6161841
DO - 10.1109/ICCE.2012.6161841
M3 - Conference contribution
SN - 9781457702310
SP - 229
EP - 230
BT - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
ER -