Object concept modeling based on the relationship among appearance, usage and functions

In this paper, a novel object concept model, which encodes the relationship among appearance, functions and usage, is proposed. The essential attribute of an object (artifact) is its function that achieves a particular purpose. Therefore, the function model is constructed through observations from a camera at first. The function is defined as changes in the work object before and after tool use. At the same time, the usage model is constructed from observations of the hand shape, grasping parts, and contact points of the tool. And then, the proposed system learns the object concept that is based on the relationship among appearance, and learnt function and usage models. The object appearance is represented by SIFT (Scale Invariant Feature Transform). Since the proposed models are based on the graphical model, it is possible for the system to stochastically infer unobservable information from observed one. For example, the system can infer usage and/or functions of the tool visually through the proposed model. Some experimental results using the system, in which the proposed model is implemented, are shown to validate the proposed model.

[1]  Diane J. Cook,et al.  Learning Fuzzy Membership Functions in a Function-Based Object Recognition System , 1993, Fuzzy Logic in Artificial Intelligence.

[2]  Robert St. Amant,et al.  Tool Use for Autonomous Agents , 2005, AAAI.

[3]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Linda B. Smith,et al.  Object Shape, Object Function, and Object Name , 1998 .

[5]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[6]  Tomoaki Nakamura,et al.  Multimodal object categorization by a robot , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Kunio Fukunaga,et al.  Toward a Cooperative Recognition of Human Behaviors and Related Objects , 2005, EJC.

[8]  Azriel Rosenfeld,et al.  Recognition by Functional Parts , 1995, Comput. Vis. Image Underst..

[9]  Takayuki Nagai,et al.  Bayesian Network Model for Object Concept , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[10]  Ehud Rivlin,et al.  Efficient Search and Verification for Function Based Classification from Real Range Images , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[11]  Dmitry B. Goldgof,et al.  Recognizing object function through reasoning about partial shape descriptions and dynamic physical properties , 1996, Proc. IEEE.

[12]  Ehud Rivlin,et al.  Efficient Search and Verification for Function Based Classification from Real Range Images , 2006, ICPR.

[13]  Diane J. Cook,et al.  Learning Membership Functions in a Function-Based Object Recognition System , 1995, J. Artif. Intell. Res..

[14]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[15]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[16]  E. Torres-Jara,et al.  Challenges for Robot Manipulation in Human Environments , 2006 .

[17]  Charles C. Kemp,et al.  Challenges for robot manipulation in human environments [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[18]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[19]  Hagai Attias,et al.  Inferring Parameters and Structure of Latent Variable Models by Variational Bayes , 1999, UAI.