Indexing without invariants in 3D object recognition

We present a method of indexing 3D objects from single 2D images. The method does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. Thi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 21; H. 10; S. 1000 - 1015
Hauptverfasser: Beis, J.S., Lowe, D.G.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.10.1999
Schlagworte:
Data structures
Indexing
Invariants
Mathematical models
Nearest neighbor searches
Neural networks
Object recognition
Probability distribution
Runtime
Searching
Shape
Spatial databases
Telerobotics
Three dimensional
ISSN:0162-8828
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a method of indexing 3D objects from single 2D images. The method does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. This makes hypothesis recovery more efficient in high-dimensional spaces, which are necessary to achieve specificity in large model databases. Search efficiency is maintained in these regimes by the use of best-bin first search. Neighbors recovered from the index are used to generate probability estimates, local within the feature space, which are then used to rank hypotheses for verification. On average, the ranking process greatly reduces the number of verifications required. Our approach is general in that it can be applied to any real-valued feature vector. In addition, it is straightforward to add to our index information from real images regarding the true probability distributions of the feature groupings used for indexing.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0162-8828
DOI:10.1109/34.799907