Presentation | 2006-03-28 Rear and Side Vehicle Detection based on Neural Networks Masaki AMANO, Kazuyoshi TAKADA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | With the many actions for realization of ITS society, Technology and System that prevents traffic accident beforehand receive much attention. We proposed a detecting rear vehicle system which is robust for sudden environmental changes using the Recurrent Neural Networks (RNN) to prevent collisions in the lane change and the confluence at high-speed way in advance. This time, targeting for installing our system in actual vehicle, we construct a system that detect rear and side vehicle in the image taken from rear camera. In a first step to achieve this purpose, we design a three-layered neural networks (NN) considering time information, the one not considering it, and a RNN having a feedback loop. Then, we compare and examine detection ability each neural networks have. As a result, we find a RNN has the highest detection ability among these three models. In a evaluation of each frame, the detection rate of 93 [%] is obtained for the unlearned frame, and of each vehicle, 91 [%] is obtained for the unlearned car. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Neural Networks / Vehicle Detection / ITS / rear camera |
Paper # | ITS2005-111 |
Date of Issue |
Conference Information | |
Committee | ITS |
---|---|
Conference Date | 2006/3/21(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 | Intelligent Transport Systems Technology (ITS) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Rear and Side Vehicle Detection based on Neural Networks |
Sub Title (in English) | |
Keyword(1) | Neural Networks |
Keyword(2) | Vehicle Detection |
Keyword(3) | ITS |
Keyword(4) | rear camera |
1st Author's Name | Masaki AMANO |
1st Author's Affiliation | Graduate School of Engineering, Nagoya Institute of Technology() |
2nd Author's Name | Kazuyoshi TAKADA |
2nd Author's Affiliation | HYUNDAI MOTOR JAPAN R&D CENTER Inc. |
Date | 2006-03-28 |
Paper # | ITS2005-111 |
Volume (vol) | vol.105 |
Number (no) | 688 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |