Prediction of future paths of mobile objects using path library

In situational awareness, the ability to make predictions about the near future situation in the area under surveillance is often as essential as being aware of the current situation. We introduce a privacy-preserving instance-based prediction method, where a path library is collected by learning ea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Leppäkoski Helena, Adhikari Bishwo, Raivio Leevi, Ritala Risto
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	path prediction people tracking probabilistic data association instance-based learning computer vision Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/45b3bd61f2b9446097ae8349a6eab829
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:45b3bd61f2b9446097ae8349a6eab829
record_format	dspace
spelling	oai:doaj.org-article:45b3bd61f2b9446097ae8349a6eab8292021-12-05T14:10:47ZPrediction of future paths of mobile objects using path library2391-543910.1515/eng-2021-0103https://doaj.org/article/45b3bd61f2b9446097ae8349a6eab8292021-11-01T00:00:00Zhttps://doi.org/10.1515/eng-2021-0103https://doaj.org/toc/2391-5439In situational awareness, the ability to make predictions about the near future situation in the area under surveillance is often as essential as being aware of the current situation. We introduce a privacy-preserving instance-based prediction method, where a path library is collected by learning earlier paths of mobile objects in the area of surveillance. The input to the prediction is the most recent coordinates of the objects in the scene. Based on similarity to short segments of currently tracked paths, a relative weight is associated with each path in the library. Future paths are predicted by computing the weighted average of the library paths. We demonstrate the operation of a situational awareness system where privacy-preserving data are extracted from an inexpensive computer vision which consists of a camera-equipped Raspberry PI-based edge device. The system runs a deep neural network-based object detection algorithm on the camera feed and stores the coordinates, object class labels, and timestamps of the detected objects. We used probabilistic reasoning based on joint probabilistic data association, Hungarian algorithm, and Kalman filter to infer which detections from different time instances came from the same object.Leppäkoski HelenaAdhikari BishwoRaivio LeeviRitala RistoDe Gruyterarticlepath predictionpeople trackingprobabilistic data associationinstance-based learningcomputer visionEngineering (General). Civil engineering (General)TA1-2040ENOpen Engineering, Vol 11, Iss 1, Pp 1048-1058 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	path prediction people tracking probabilistic data association instance-based learning computer vision Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	path prediction people tracking probabilistic data association instance-based learning computer vision Engineering (General). Civil engineering (General) TA1-2040 Leppäkoski Helena Adhikari Bishwo Raivio Leevi Ritala Risto Prediction of future paths of mobile objects using path library
description	In situational awareness, the ability to make predictions about the near future situation in the area under surveillance is often as essential as being aware of the current situation. We introduce a privacy-preserving instance-based prediction method, where a path library is collected by learning earlier paths of mobile objects in the area of surveillance. The input to the prediction is the most recent coordinates of the objects in the scene. Based on similarity to short segments of currently tracked paths, a relative weight is associated with each path in the library. Future paths are predicted by computing the weighted average of the library paths. We demonstrate the operation of a situational awareness system where privacy-preserving data are extracted from an inexpensive computer vision which consists of a camera-equipped Raspberry PI-based edge device. The system runs a deep neural network-based object detection algorithm on the camera feed and stores the coordinates, object class labels, and timestamps of the detected objects. We used probabilistic reasoning based on joint probabilistic data association, Hungarian algorithm, and Kalman filter to infer which detections from different time instances came from the same object.
format	article
author	Leppäkoski Helena Adhikari Bishwo Raivio Leevi Ritala Risto
author_facet	Leppäkoski Helena Adhikari Bishwo Raivio Leevi Ritala Risto
author_sort	Leppäkoski Helena
title	Prediction of future paths of mobile objects using path library
title_short	Prediction of future paths of mobile objects using path library
title_full	Prediction of future paths of mobile objects using path library
title_fullStr	Prediction of future paths of mobile objects using path library
title_full_unstemmed	Prediction of future paths of mobile objects using path library
title_sort	prediction of future paths of mobile objects using path library
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/45b3bd61f2b9446097ae8349a6eab829
work_keys_str_mv	AT leppakoskihelena predictionoffuturepathsofmobileobjectsusingpathlibrary AT adhikaribishwo predictionoffuturepathsofmobileobjectsusingpathlibrary AT raivioleevi predictionoffuturepathsofmobileobjectsusingpathlibrary AT ritalaristo predictionoffuturepathsofmobileobjectsusingpathlibrary
_version_	1718371718215499776

Prediction of future paths of mobile objects using path library

Ejemplares similares