Optimized vision-directed deployment of UAVs for rapid traffic monitoring

The flexibility and cost efficiency of traffic monitoring using Unmanned Aerial Vehicles (UAVs) has made such a proposition an attractive topic of research. To date, the main focus was placed on the types of sensors used to capture the data, and the alternative data processing options to achieve goo...

Full description

Saved in:
Bibliographic Details
Main Authors: Kyrkou, Christos, Timotheou, Stelios, Kolios, Panayiotis, Theocharides, Theocharis, Panayiotou, Christos G.
Format: Conference Proceeding
Language:English
Subjects:
Buildings
Convolutional neural networks
Image segmentation
Monitoring
Pipelines
Roads
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The flexibility and cost efficiency of traffic monitoring using Unmanned Aerial Vehicles (UAVs) has made such a proposition an attractive topic of research. To date, the main focus was placed on the types of sensors used to capture the data, and the alternative data processing options to achieve good monitoring performance. In this work we move a step further, and explore the deployment strategies that can be realized for rapid traffic monitoring over particular regions of the transportation network by considering a monitoring scheme that captures data from a visual sensor on-board the UAV, and subsequently analyzes it through a specific vision processing pipeline to extract network state information. These innovative deployment strategies can be used in real-time to assess traffic conditions, while for longer periods, to validate the underlying mobility models that characterise traffic patterns.
ISSN:2158-4001
DOI:10.1109/ICCE.2018.8326145