Open AccessZ-Net: A Novel Way of Lane Detection
Author(s) -
Ziyuan Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1682/1/012013
Subject(s) - computer science , artificial neural network , novelty , net (polyhedron) , artificial intelligence , novelty detection , data mining , pattern recognition (psychology) , machine learning , mathematics , philosophy , geometry , theology
In this paper we proposed a new neural network Z-net for lane detection. The novelty of this network is not the network itself but the detection method. After comprehensive investigation and analysis of the application of several used networks in lane detection, we analyzed the advantages and disadvantages of various networks and modified the existing network to get the Z-net. Under the influence of rapid development of lane detection, it is necessary to propose a neural network with fast detection speed and great accuracy. We found out that Z-netsatisfies these two requirements very well.