Paper Info
Title
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Abstract
Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity. In this paper, we propose a pipeline for understanding vehicle behaviour from a monocular image sequence or video. A monocular sequence along with scene semantics, optical flow and object labels are used to get spatial information about the object (vehicle) of interest and other objects (semantically contiguous set of locations) in the scene. This spatial information is encoded by a Multi-Relational Graph Convolutional Network (MR-GCN), and a temporal sequence of such encodings is fed to a recurrent network to label vehicle behaviours. The proposed framework can classify a variety of vehicle behaviours to high fidelity on datasets that are diverse and include European, Chinese and Indian on-road scenes. The framework also provides for seamless transfer of models across datasets without entailing re-annotation, retraining and even fine-tuning. We show comparative performance gain over baseline Spatio-temporal classifiers and detail a variety of ablations to showcase the efficacy of the framework.
Year
DOI
Venue
2020
10.1109/IV47402.2020.9304822
2020 IEEE Intelligent Vehicles Symposium (IV)
Keywords
DocType
ISSN
on-road vehicle behaviour,temporal sequence,sensor data,monocular image sequence,scene semantics,optical flow,object labels,spatial information,recurrent network,accurate vehicle behaviour classification,MR-GCN,Indian on-road scenes,Chinese on-road scenes,European on-road scenes,baseline spatio-temporal classifiers,multirelational graph convolutional networks
Conference
1931-0587
ISBN
Citations 
PageRank 
978-1-7281-6674-2
2
0.38
References 
Authors
0
6
Name
Order
Citations
PageRank
Mylavarapu Sravan120.38
Mahtab Sandhu231.07
Priyesh Vijayan332.42
K. Madhava Krishna436481.17
Balaraman Ravindran560481.83
Anoop M. Namboodiri625526.36