3D scene's object detection and recognition using depth layers and SIFT-based machine learning

Authors:
T. Kounalakis;G. A. Triantafyllidis
Affiliations:
Applied Informatics and Multimedia Dept., Technological Educational Institute of Crete, Heraklion, Greece;Applied Informatics and Multimedia Dept., Technological Educational Institute of Crete, Heraklion, Greece
Venue:
3D Research
Year:
2011

Citing 5
Cited 0

Computer and Robot Vision

Computer and Robot Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Occlusion and visible background and foreground areas in stereo: a Bayesian approach

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel system that is fusing efficient and state-of-the-art techniques of stereo vision and machine learning, aiming at object detection and recognition. To this goal, the system initially creates depth maps by employing the Graph-Cut technique. Then, the depth information is used for object detection by separating the objects from the whole scene. Next, the Scale-Invariant Feature Transform (SIFT) is used, providing the system with unique object's feature key-points, which are employed in training an Artificial Neural Network (ANN). The system is then able to classify and recognize the nature of these objects, creating knowledge from the real world.