scholarly journals FLEXIBLE 3D OBJECT RECOGNITION FRAMEWORK USING 2D VIEWS VIA A SIMILARITY-BASED ASPECT-GRAPH APPROACH

2008 ◽  
Vol 22 (06) ◽  
pp. 1141-1169
Author(s):  
JWU-SHENG HU ◽  
TZUNG-MIN SU
Keyword(s):  
Object Recognition ◽  
Scene Recognition ◽  
3D Object Recognition ◽  
3D Object ◽  
3D Objects ◽  
The Core ◽  
Database Construction ◽  
Color Features ◽  
Flexible Framework ◽  
Posture Recognition

This work presents a flexible framework for recognizing 3D objects from 2D views. Similarity-based aspect-graph, which contains a set of aspects and prototypes for these aspects, is employed to represent the database of 3D objects. An incremental database construction method that maximizes the similarity of views in the same aspect and minimizes the similarity of prototypes is proposed as the core of the framework to build and update the aspect-graph using 2D views randomly sampled from a viewing sphere. The proposed framework is evaluated on various object recognition problems, including 3D object recognition, human posture recognition and scene recognition. Shape and color features are employed in different applications with the proposed framework and the top three matching rates show the efficiency of the proposed method.

scholarly journals MAKING OBJECT LEARNING AND RECOGNITION AN ACTIVE PROCESS

2008 ◽  
Vol 05 (02) ◽  
pp. 267-286 ◽  
Author(s):  
ALEŠ UDE ◽  
DAMIR OMRČEN ◽  
GORDON CHENG
Keyword(s):  
Object Recognition ◽  
Prior Knowledge ◽  
Experimental Results ◽  
3D Object Recognition ◽  
Object Representations ◽  
Active Process ◽  
Bottom Up ◽  
3D Object ◽  
3D Objects ◽  
Object Learning

The exploration and learning of new objects is an essential capability of a cognitive robot. In this paper we focus on making use of the robot's manipulation abilities to learn complete object representations suitable for 3D object recognition. Taking control of the object allows the robot to focus on relevant parts of the images, thus bypassing potential pitfalls of purely bottom-up attention and segmentation. The main contribution of the paper consists in integrated visuomotor processes that allow the robot to learn object representations by manipulation without having any prior knowledge about the objects. Our experimental results show that the acquired data is of sufficient quality to train a classifier that can recognize 3D objects independently of the viewpoint.

3D Object Recognition by Integration of Associative and Symbolic Techniques

Visual Form ◽  
1992 ◽  
pp. 259-266
Author(s):  
Gianluca Foresti ◽  
Vittorio Murino ◽  
Carlo S. Regazzoni ◽  
Rodolfo Zunino
Keyword(s):  
Object Recognition ◽  
3D Object Recognition ◽  
3D Object

scholarly journals 3D Object Recognition with Keypoint Based Algorithms

2019 ◽  
Vol 6 (1) ◽  
pp. 139-142
Author(s):  
Muhammed Enes ATİK ◽  
Abdullah Harun İNCEKARA ◽  
Batuhan SARITÜRK ◽  
Ozan ÖZTÜRK ◽  
Zaide DURAN ◽  
...  
Keyword(s):  
Object Recognition ◽  
3D Object Recognition ◽  
3D Object
Sign in / Sign up

Export Citation Format

Share Document