Scipediacontent: Scipediacontent moved page Draft Content 407040490 to O'Connor et al 2020a

2021-02-03T20:09:21Z

Scipediacontent moved page Draft Content 407040490 to O'Connor et al 2020a

Scipediacontent: Created page with " == Abstract == This work presents an analysis of predicting multiple future paths of moving objects in traffic scenes by leveraging Long Short-Term Memory architectures (LST..."

2021-02-03T20:09:18Z

Created page with " == Abstract == This work presents an analysis of predicting multiple future paths of moving objects in traffic scenes by leveraging Long Short-Term Memory architectures (LST..."

New page

== 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

== Original document ==

The different versions of the original document can be found in:

* [http://doras.dcu.ie/24257 http://doras.dcu.ie/24257]

* [http://dx.doi.org/10.5220/0009412204810488 http://dx.doi.org/10.5220/0009412204810488]

* [https://doi.org/10.5220/0009412204810488 https://doi.org/10.5220/0009412204810488] under the license cc-by-nc-nd

* [http://doras.dcu.ie/24257 http://doras.dcu.ie/24257],
: [https://academic.microsoft.com/#/detail/3026908970 https://academic.microsoft.com/#/detail/3026908970]

← Older revision	Revision as of 20:09, 3 February 2021
(No difference)

O'Connor et al 2020a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 407040490 to O'Connor et al 2020a

Scipediacontent: Created page with " == Abstract == This work presents an analysis of predicting multiple future paths of moving objects in traffic scenes by leveraging Long Short-Term Memory architectures (LST..."