Multi-layer template correlation neural network for recognition of lane mark based on pipelined image processing structure

Author

An, Xiangjing ; Chang, Wensen ; Chen, Xiangdong

Author_Institution

Dept. of Autom. Control, Nat. Univ. of Defence Technol., Changsha, China

Volume

3

fYear

1999

fDate

1999

Firstpage

2410

Abstract

It is one of the important tasks for a vision system to locate an autonomous land vehicle (ALV) by lane mark. In the paper, a multi-layer template correlation neural network (MTCNN) based on the pipelined image processing structure is proposed for recognition of lane mark. A structure of the MTCNN and a training algorithm are presented. In addition, a method that maps the MTCNN onto the pipelined image processor is introduced. The experiment manifests that the proposed MTCNN is very efficient for the task such as recognition of lane mark based on the pipelined image processing structure

Keywords

image classification; learning (artificial intelligence); mobile robots; multilayer perceptrons; pipeline processing; robot vision; autonomous land vehicle; lane mark; multi-layer template correlation neural network; pipelined image processing structure; training algorithm; vision system; Image processing; Image recognition; Information systems; Land vehicles; Machine vision; Multi-layer neural network; Neural networks; Pattern matching; Pattern recognition; Roads;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1999. Proceedings. 1999 IEEE International Conference on

Conference_Location

Detroit, MI

ISSN

1050-4729

Print_ISBN

0-7803-5180-0

Type

conf

DOI

10.1109/ROBOT.1999.770466

Filename

770466