Skip to main navigation Skip to search Skip to main content

Fuzzy Neural Network-Based Assessment of Road Traffic Situations Using Extracted Information Obtained from Optical High-Resolution Satellite Remote Sensing Images

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study proposes a comprehensive fuzzy neural network (FNN) traffic assessment method using the optical high-resolution remote sensing image (RSI) to process a non-quantified relationship between traffic information and the assessment result. Using the classic road extraction and vehicle detection method, the number of lanes and vehicle density and velocity are obtained as the model input variables. The FNN traffic assessment model is established using the Takagi-Sugeno-Kang network structure, which is constructed using the BP network based on four types of traffic situation. Using QuickBird and WorldView2 satellite 0.5 m resolution panchromatic images, the experimental results show a reasonable traffic assessment result.

Original languageEnglish
Title of host publication2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages148-151
Number of pages4
ISBN (Electronic)9781728163741
DOIs
StatePublished - 26 Sep 2020
Event2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Online, Virtual, United States
Duration: 26 Sep 20202 Oct 2020

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
ISSN (Electronic)2153-6996

Conference

Conference2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/TerritoryUnited States
CityOnline, Virtual
Period26/09/202/10/20

Keywords

  • Traffic assessment
  • fuzzy neural network
  • remote sensing image
  • road extraction

Fingerprint

Dive into the research topics of 'Fuzzy Neural Network-Based Assessment of Road Traffic Situations Using Extracted Information Obtained from Optical High-Resolution Satellite Remote Sensing Images'. Together they form a unique fingerprint.

Cite this