Real-Time Keypoint Recognition Using Restricted Boltzmann Machine

Feature point recognition is a key component in many vision-based applications, such as vision-based robot navigation, object recognition and classification, image-based modeling, and augmented reality. Real-time performance and high recognition rates are of crucial importance to these applications....

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2014-11, Vol.25 (11), p.2119-2126
Main Authors: Yuan, Miaolong, Tang, Huajin, Li, Haizhou
Format: Article
Language:English
Subjects:
Classification
Data models
deep learning
Feature extraction
feature matching
keypoint recognition
Learning systems
Navigation
Object recognition
Real time
Real-time systems
real-time tracking
Recognition
restricted Boltzmann machine (RBM)
Robots
Tracking
Training
Training data
Vectors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Feature point recognition is a key component in many vision-based applications, such as vision-based robot navigation, object recognition and classification, image-based modeling, and augmented reality. Real-time performance and high recognition rates are of crucial importance to these applications. In this brief, we propose a novel method for real-time keypoint recognition using restricted Boltzmann machine (RBM). RBMs are generative models that can learn probability distributions of many different types of data including labeled and unlabeled data sets. Due to the inherent noise of the training data sets, we use an RBM to model statistical distributions of the training data. Furthermore, the learned RBM can be used as a competitive classifier to recognize the keypoints in real-time during the tracking stage, thus making it advantageous to be employed in applications that require real-time performance. Experiments have been conducted under a variety of conditions to demonstrate the effectiveness and generalization of the proposed approach.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2014.2303478