MAKING OBJECT LEARNING AND RECOGNITION AN ACTIVE PROCESS

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.

Download Full-text

COMBINED MODEL-BASED 3D OBJECT RECOGNITION

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001405004368 ◽

2005 ◽

Vol 19 (07) ◽

pp. 839-852 ◽

Cited By ~ 1

Author(s):

SUNGHO KIM ◽

GIJEONG JANG ◽

WANG-HEON LEE ◽

IN SO KWEON

Keyword(s):

Object Recognition ◽

Object Identification ◽

Feature Binding ◽

Human Vision ◽

3D Object Recognition ◽

Top Down ◽

Combined Model ◽

Bottom Up ◽

3D Object ◽

Model Based

This paper presents a combined model-based 3D object recognition method motivated by the robust properties of human vision. The human visual system (HVS) is very efficient and robust in identifying and grabbing objects, in part because of its properties of visual attention, contrast mechanism, feature binding, multiresolution and part-based representation. In addition, the HVS combines bottom-up and top-down information effectively using combined model representation. We propose a method for integrating these aspects under a Monte Carlo method. In this scheme, object recognition is regarded as a parameter optimization problem. The bottom-up process initializes parameters, and the top-down process optimizes them. Experimental results show that the proposed recognition model is feasible for 3D object identification and pose estimation.

Download Full-text

Implicit Learning in 3D Object Recognition: The Importance of Temporal Context

Neural Computation ◽

10.1162/089976699300016683 ◽

1999 ◽

Vol 11 (2) ◽

pp. 347-374 ◽

Cited By ~ 33

Author(s):

Suzanna Becker

Keyword(s):

Object Recognition ◽

Neural Circuit ◽

3D Object Recognition ◽

Temporal Context ◽

Bottom Up ◽

Specific Stimulus ◽

3D Object ◽

Learning Rules ◽

Temporal Continuity ◽

Stimulus Features

A novel architecture and set of learning rules for cortical self-organization is proposed. The model is based on the idea that multiple information channels can modulate one another's plasticity. Features learned from bottom-up information sources can thus be influenced by those learned from contextual pathways, and vice versa. A maximum likelihood cost function allows this scheme to be implemented in a biologically feasible, hierarchical neural circuit. In simulations of the model, we first demonstrate the utility of temporal context in modulating plasticity. The model learns a representation that categorizes people's faces according to identity, independent of viewpoint, by taking advantage of the temporal continuity in image sequences. In a second set of simulations, we add plasticity to the contextual stream and explore variations in the architecture. In this case, the model learns a two-tiered representation, starting with a coarse view-based clustering and proceeding to a finer clustering of more specific stimulus features. This model provides a tenable account of how people may perform 3D object recognition in a hierarchical, bottom-up fashion.

Download Full-text

Prior Knowledge and Learning in 3D Object Recognition

Object Recognition, Attention, and Action ◽

10.1007/978-4-431-73019-4_8 ◽

2009 ◽

pp. 105-117

Author(s):

Markus Gschwind ◽

Hans Brettel ◽

Ingo Rentschler

Keyword(s):

Object Recognition ◽

Prior Knowledge ◽

3D Object Recognition ◽

3D Object

Download Full-text

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

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001408006685 ◽

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.

Download Full-text