In this paper new error measures to evaluate image features in three-dimensional scenes are proposed and reviewed. The proposed error measures are designed to take into account feature shapes, and ground truth data can be easily estimated. As other approaches, they are not error-free and a quantitative evaluation is given according to the number of wrong matches and mismatches in order to assess their validity
Bellavia, F., Tegolo, D. (2011). New Error Measures To Evaluate Features on Three Dimensional Scenes. In G. Maino, G.L. Foresti (a cura di), Image Analysis and Processing – ICIAP 2011 (pp. 524-533). Berlino : Springer-Verlag [10.1007/978-3-642-24085-0_54].
New Error Measures To Evaluate Features on Three Dimensional Scenes
Bellavia, F;TEGOLO, Domenico
2011-01-01
Abstract
In this paper new error measures to evaluate image features in three-dimensional scenes are proposed and reviewed. The proposed error measures are designed to take into account feature shapes, and ground truth data can be easily estimated. As other approaches, they are not error-free and a quantitative evaluation is given according to the number of wrong matches and mismatches in order to assess their validity
| File | Dimensione | Formato | |
|---|---|---|---|
|
bellavia.pdf
Solo gestori archvio
Tipologia:
Versione Editoriale
Dimensione
288.97 kB
Formato
Adobe PDF
|
288.97 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
