Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition

This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or u...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2017-04
Hauptverfasser:	Wong, Sebastien C, Stamatescu, Victor, Gatt, Adam, Kearney, David, Lee, Ivan, McDonnell, Mark D
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Computer Science - Computer Vision and Pattern Recognition Computer Science - Neural and Evolutionary Computing Image classification Neural networks Object motion Object recognition Tracking
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!