An Intelligent Recognition Algorithm on Traffic Safety States

Traffic safety states can be divided into safe and dangerous according to the attributes of video images of traffic safety states. We propose a synergic neural network recognition model based on prototype pattern by analyzing various methods on intelligent video processing. Our proposed method reali...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied Mechanics and Materials Jg. 433-435; H. Advances in Mechatronics and Control Engineering II; S. 1388 - 1391
Hauptverfasser: Wang, Wei Zhi, Liu, Bing Han
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Zurich Trans Tech Publications Ltd 15.10.2013
Schlagworte:
Accuracy
Algorithms
Classification
Dangerous
Image processing
Neural networks
Object recognition
Pattern recognition
Recognition
Traffic accidents & safety
Traffic models
Traffic safety
Video
Video data
Traffic Safety State
Automatic Recognition
Intelligent Analysis
ISBN:303785894X, 9783037858943
ISSN:1660-9336, 1662-7482, 1662-7482
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Traffic safety states can be divided into safe and dangerous according to the attributes of video images of traffic safety states. We propose a synergic neural network recognition model based on prototype pattern by analyzing various methods on intelligent video processing. Our proposed method realizes real time classification of traffic safety states with high accuracy of traffic safety states recognition. The experimental results validate that the accuracy of classification of proposed method arrives at 87.5%, increased by 16.2% compared to traditional neural network methods.
Bibliographie:Selected, peer reviewed papers from the 2013 2nd International Conference on Mechatronics and Control Engineering (ICMCE 2013), August 28-29, 2013, Guangzhou, China
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISBN:303785894X
9783037858943
ISSN:1660-9336
1662-7482
1662-7482
DOI:10.4028/www.scientific.net/AMM.433-435.1388