Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Multiple path prediction for traffic scenes using LSTMs and mixture density models

Fernandez, Jaime B. orcid logoORCID: 0000-0001-9774-3879, Little, Suzanne orcid logoORCID: 0000-0003-3281-3471 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2020) Multiple path prediction for traffic scenes using LSTMs and mixture density models. In: 6th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS), 2-4 May 2020, Prague, Czech Republic (Virtual). ISBN 978-989-758-419-0

Abstract
This work presents an analysis of predicting multiple future paths of moving objects in traffic scenes by leveraging Long Short-Term Memory architectures (LSTMs) and Mixture Density Networks (MDNs) in a single-shot manner. Path prediction allows estimating the future positions of objects. This is useful in important applications such as security monitoring systems, Autonomous Driver Assistance Systems and assistive technologies. Normal approaches use observed positions (tracklets) of objects in video frames to predict their future paths as a sequence of position values. This can be treated as a time series. LSTMs have achieved good performance when dealing with time series. However, LSTMs have the limitation of only predicting a single path per tracklet. Path prediction is not a deterministic task and requires predicting with a level of uncertainty. Predicting multiple paths instead of a single one is therefore a more realistic manner of approaching this task. In this work, predicting a set of future paths with associated uncertainty was archived by combining LSTMs and MDNs. The evaluation was made on the KITTI and the CityFlow datasets on three type of objects, four prediction horizons and two different points of view (image coordinates and birds-eye view
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Multiple Path Prediction; Traffic Scenes; LSTMs, MDNs; Time Series
Subjects:Computer Science > Artificial intelligence
Computer Science > Machine learning
Computer Science > Visualization
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: 6th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS), Proceedings. 1. Scitepress. ISBN 978-989-758-419-0
Publisher:Scitepress
Official URL:http://dx.doi.org/10.5220/0009412204810488
Copyright Information:© 2020 The Authors CC BY-NC-ND 4.0
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:EU H2020 Project VI-DAS under grant number 690772, SFI Insight Centre for Data Analytics, grant number SFI/12/RC/2289, GPU GeForce GTX 980 used for this research was donated by the NVIDIA Corporation
ID Code:24257
Deposited On:06 May 2020 17:01 by Jaime Boanerjes Fernandez Roblero . Last Modified 23 Nov 2022 14:22
Documents

Full text available as:

[thumbnail of 2020Temp_CamR_VEHITS2020_Multiple_Path_Prediction_for_Traffic_Scenes_Using_LSTMs_and_Mixture_Density_Models.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record