In this work we present a new algorithm for 3D object recognition. The goal is to identify the correct position and orientation of complex objects without using a CAD model, input of main current systems. The approach we follow performs feature matching. The characteristics extracted belong only by shape information to achieve a system independent to brightness, colour or texture. Designing opportune settable parameters, we allow recognition also in presence of small deformations

3D object recognition without CAD models for industrial robot manipulation

Benvegnù, Luca
2017/2018

Abstract

In this work we present a new algorithm for 3D object recognition. The goal is to identify the correct position and orientation of complex objects without using a CAD model, input of main current systems. The approach we follow performs feature matching. The characteristics extracted belong only by shape information to achieve a system independent to brightness, colour or texture. Designing opportune settable parameters, we allow recognition also in presence of small deformations
2017-10-09
3D Object recognition, point cloud, feature matching, deformable objects, bin-picking, riconoscimento di oggetti 3D, oggetti deformabili
File in questo prodotto:
File Dimensione Formato  
TesiLucaBenvegnu.pdf

accesso aperto

Dimensione 8.56 MB
Formato Adobe PDF
8.56 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/28231