Probabilistic 3D object recognition from 2D invariant view sequence based on similarity

Authors:
Rui Nian;Guangrong Ji;Wencang Zhao;Chen Feng
Affiliations:
College of Information Science and Engineering, Ocean University of China, Qingdao 266003, China;College of Information Science and Engineering, Ocean University of China, Qingdao 266003, China;College of Information Science and Engineering, Ocean University of China, Qingdao 266003, China;College of Information Science and Engineering, Ocean University of China, Qingdao 266003, China
Venue:
Neurocomputing
Year:
2007

Citing 10
Cited 0

Computing exact aspect graphs of curved objects: algebraic surfaces

International Journal of Computer Vision
The nature of statistical learning theory

The nature of statistical learning theory
Classifier and shift-invariant automatic target recognition neural networks

Neural Networks - Special issue: automatic target recognition
Probabilistic 3D Object Recognition

International Journal of Computer Vision
Shape matching using edit-distance: an implementation

SODA '01 Proceedings of the twelfth annual ACM-SIAM symposium on Discrete algorithms
Probabilistic Models of Appearance for 3-D Object Recognition

International Journal of Computer Vision
Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

International Journal of Computer Vision
An Invitation to 3-D Vision: From Images to Geometric Models

An Invitation to 3-D Vision: From Images to Geometric Models
Probabilistic Object Recognition Using Multidimensional Receptive Field Histograms

ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2

Quantified Score

Hi-index	0.03

Visualization

Abstract

In this paper, a scheme of probabilistic 3D object recognition from 2D view sequence is presented. For the tradeoff between information simplicity and sufficiency, based on similarity measure, proper invariant characteristic set is first acquired in a model view learning procedure. A discrete, nonparametric probabilistic strategy then estimates the overall functional form of posterior probability distribution P(O"n|I) in several simplifications and modifications, which captures the joint statistics of local pattern and position as well as the statistics of local pattern in the visual world at large, by counting the occurrence frequency of patterns over various objects. The decision is made on maximum a posteriori (MAP) estimation in Bayes decision rule. An evidence accumulation mechanism is finally introduced for effect improvement. Simulation experiment has demonstrated promising results, achieved omnidirectional information, and proved effective, superior and feasible in the approach proposed.