Title :
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
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;
Conference_Titel :
Robotics and Automation, 1999. Proceedings. 1999 IEEE International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-5180-0
DOI :
10.1109/ROBOT.1999.770466
