Archivio istituzionale della ricerca dell'Università degli Studi di Palermo
IRIS è il sistema di gestione integrata dei dati della ricerca (persone, pubblicazioni, progetti, attività) adottato dall’Università di Palermo, e ha lo scopo di raccogliere, conservare, documentare, e diffondere ad accesso aperto le informazioni relative alla produzione scientifica degli autori afferenti all’Ateneo.
EnglishThis paper proposes a deep convolutional neural network (CNN) for pedestrian tracking in 360◦ videos based on the target’s motion. The tracking algorithm takes advantage of a virtual Pan-Tilt-Zoom (vPTZ) camera simulated by means of the 360◦ video. The CNN takes in input a motion image, i.e. the difference of two images taken by using the vPTZ camera at different times by the same pan, tilt and zoom parameters. The CNN predicts the vPTZ camera parameter adjustments required to keep the target at the center of the vPTZ camera view. Experiments on a publicly available dataset performed in cross-validation demonstrate that the learned motion model generalizes, and that the proposed tracking algorithm achieves state-of-the-art performance.
Lo Presti Liliana, & La Cascia Marco (2019). Deep Motion Model for Pedestrian Tracking in 360 Degrees Videos. In Image Analysis and Processing ICIAP 2019 - LNCS 11751 (pp. 36-47). Springer.
| Data di pubblicazione: | 2019 |
| Titolo: | Deep Motion Model for Pedestrian Tracking in 360 Degrees Videos |
| Autori: | |
| Citazione: | Lo Presti Liliana, & La Cascia Marco (2019). Deep Motion Model for Pedestrian Tracking in 360 Degrees Videos. In Image Analysis and Processing ICIAP 2019 - LNCS 11751 (pp. 36-47). Springer. |
| Abstract: | This paper proposes a deep convolutional neural network (CNN) for pedestrian tracking in 360◦ videos based on the target’s motion. The tracking algorithm takes advantage of a virtual Pan-Tilt-Zoom (vPTZ) camera simulated by means of the 360◦ video. The CNN takes in input a motion image, i.e. the difference of two images taken by using the vPTZ camera at different times by the same pan, tilt and zoom parameters. The CNN predicts the vPTZ camera parameter adjustments required to keep the target at the center of the vPTZ camera view. Experiments on a publicly available dataset performed in cross-validation demonstrate that the learned motion model generalizes, and that the proposed tracking algorithm achieves state-of-the-art performance. |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/978-3-030-30642-7_4 |
| Settore Scientifico Disciplinare: | Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni |
| Appare nelle tipologie: | 2.01 Capitolo o Saggio |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| DeepMotionModel.pdf | Versione Editoriale | Administrator Richiedi una copia |
http://hdl.handle.net/10447/385075
Copyright © 2021