Presentation | 2012-09-03 A preliminary study on a pedestrian detector adaptive to the driving environment using an in-vehicle camera Daichi SUZUO, Hidefumi YOSHIDA, Daisuke DEGUCHI, Ichiro IDE, Hiroshi MURASE, Takashi MACHIDA, Yoshiko KOJIMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, pedestrian detection from in-vehicle camera images is being focused. However, it is difficult to detect pedestrians accurately due to the variety of their appearances caused by various environmental factors such as time, weather, season, and location. To deal with changes of pedestrians' pose and environment, most existing methods that makes use of their appearances require the preparation of a lot of pedestrian images manually. However, it is difficult to provide training images considering all possible environmental factors. To tackle this problem, we propose a method to make a pedestrian detector adaptive to a driving environment by collecting training images from in-vehicle camera images. We focused on the variety of the appearance per location that primarily affects the accuracy of pedestrian detection, and built an environment adaptive pedestrian detector by collecting pedestrians images and non-pedestrian images in each driving location. In evaluation experiments assuming ideal adaptation to the environment, we confirmed the effectiveness of the method conpared to existing methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Pedestrian detection / Adaptive detector / HOG / SVM / ITS |
Paper # | PRMU2012-41,IBISML2012-24 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2012/8/26(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A preliminary study on a pedestrian detector adaptive to the driving environment using an in-vehicle camera |
Sub Title (in English) | |
Keyword(1) | Pedestrian detection |
Keyword(2) | Adaptive detector |
Keyword(3) | HOG |
Keyword(4) | SVM |
Keyword(5) | ITS |
1st Author's Name | Daichi SUZUO |
1st Author's Affiliation | Graduate School of Information Science Nagoya University() |
2nd Author's Name | Hidefumi YOSHIDA |
2nd Author's Affiliation | Graduate School of Information Science Nagoya University |
3rd Author's Name | Daisuke DEGUCHI |
3rd Author's Affiliation | Graduate School of Information Science Nagoya University |
4th Author's Name | Ichiro IDE |
4th Author's Affiliation | Strategy Office Information and Communications Headquarters |
5th Author's Name | Hiroshi MURASE |
5th Author's Affiliation | Graduate School of Information Science Nagoya University |
6th Author's Name | Takashi MACHIDA |
6th Author's Affiliation | Toyota Central Research and Development Laboratories Inc. |
7th Author's Name | Yoshiko KOJIMA |
7th Author's Affiliation | Graduate School of Information Science Nagoya University |
Date | 2012-09-03 |
Paper # | PRMU2012-41,IBISML2012-24 |
Volume (vol) | vol.112 |
Number (no) | 197 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |