Range Image Based Classification System Using Support Vector Machines

Authors:
Seyed Eghbal Ghobadi;Klaus Hartmann;Otmar Loffeld;Wolfgang Weihs
Affiliations:
Center for Sensor Systems (ZESS), University of Siegen, Paul- Bonatz-Str.9-11, D57068, Siegen, Germany;Center for Sensor Systems (ZESS), University of Siegen, Paul- Bonatz-Str.9-11, D57068, Siegen, Germany;Center for Sensor Systems (ZESS), University of Siegen, Paul- Bonatz-Str.9-11, D57068, Siegen, Germany;Center for Sensor Systems (ZESS), University of Siegen, Paul- Bonatz-Str.9-11, D57068, Siegen, Germany
Venue:
Computational Intelligence and Security
Year:
2007

Citing 6
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
A Time-Of-Flight Depth Sensor - System Description, Issues and Solutions

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 3 - Volume 03
Online Detection and Classification of Moving Objects Using Progressively Improving Detectors

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
An Occupant Classification System Eigen Shapes or Knowledge-Based Features

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Vehicle detection by means of stereo vision-based obstacles features extraction and monocular pattern analysis

IEEE Transactions on Image Processing
New results on error correcting output codes of kernel machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a classification system based on Support Vector Machines (SVM) and using 3D range images. Two kinds of camera systems are used to provide the classification system with 3D range images: Time-oF-Flight (TOF) camera and Stereo Vision System. While the former uses the modulated infrared lighting source to provide the range information in each pixel of a Photonic Mixer Device(PMD) sensor, the latter employs the disparity map from stereo images to calculate three dimensional data. The proposed detection and classification system is used to classify different 3D moving objects in a dynamic environment under varying lighting conditions. The images of each camera are first preprocessed and then two different approaches are applied to extract their features. The first approach is a Computer Generated method which uses the Principal Component Analysis (PCA) to get the most relevant projection of the data over the eigenvectors and the second approach is a Human Generated method which extracts the features based on some heuristic techniques. Two training data sets are derived from each image set based on heuristic and PCA features to train a multi class SVM classifier. The experimental results show that the proposed classifier based on range data from TOF camera is superior to that from the stereo system.