Paper Info
Title
Inferring Road Boundaries Through and Despite Traffic
Abstract
This paper is about the detection and inference of road boundaries from mono-images. Our goal is to trace out, in an image, the projection of road boundaries irrespective of whether or not the boundary is actually visible. Large scale occlusion by vehicles prohibits direct approaches - many scenes present 100% occlusion and so we must infer the boundary location using scene context. Such a problem is well suited to CNN derived approaches but the sinuous structure of a hidden narrow continuous curve running through the image presents challenges for conventional NN-architectures. We approach this as a coupled, two class detection problem-solving for occluded and non-occluded curve partitions with a continuity constraint. Our network output is in a hybrid discrete-continuous form which we interpret as measurements of segments of the true road boundary. These measurements are passed to a model selection stage which associates measurements to minimal number of a-priori unknown set of geometric primitives (cubic curves) representing road boundaries. We present a semi-supervised method which leverages a visual localisation to generate 25 thousand labelled images for training and testing - the results of which are presented in the conclusion of the paper.
Year
DOI
Venue
2018
10.1109/ITSC.2018.8569570
2018 21st International Conference on Intelligent Transportation Systems (ITSC)
Keywords
Field
DocType
road boundary,mono-images,boundary location,coupled class detection problem-solving,two class detection problem-solving,nonoccluded curve partitions,labelled images,large scale occlusion,scene context,CNN,NN-architectures
Computer vision,Inference,Model selection,Geometric primitive,Artificial intelligence,Engineering
Conference
ISSN
ISBN
Citations 
2153-0009
978-1-7281-0324-2
2
PageRank 
References 
Authors
0.45
0
3
Name
Order
Citations
PageRank
Tarlan Suleymanov131.47
Paul Amayo220.78
Paul Newman34364321.76