Supervised learning based stereo matching using neural tree

Authors:
Sanjeev Kumar;Asha Rani;Christian Micheloni;Gian Luca Foresti
Affiliations:
Department of Mathematics, IIT Roorkee, Roorkee, India;Department of Mathematics and Computer Science, University of Udine, Udine, Italy;Department of Mathematics and Computer Science, University of Udine, Udine, Italy;Department of Mathematics and Computer Science, University of Udine, Udine, Italy
Venue:
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing - Volume Part II
Year:
2011

Citing 11
Cited 0

Neural tree networks

Neural networks
Exploiting neural trees in range image understanding

Pattern Recognition Letters
MLESAC: a new robust estimator with application to estimating image geometry

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Local stereovision matching through the ADALINE neural network

Pattern Recognition Letters
Stereovision matching through support vector machines

Pattern Recognition Letters
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
Affine Invariant-Based Classification of Inliers and Outliers for Image Matching

ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a supervised learning based approach is presented to classify tentative matches as inliers or outliers obtained from a pair of stereo images. A balanced neural tree (BNT) is adopted to perform the classification task. A set of tentative matches is obtained using speedup robust feature (SURF) matching and then feature vectors are extracted for all matches to classify them either as inliers or outliers. The BNT is trained using a set of tentative matches having ground-truth information, and then it is used for classifying other sets of tentative matches obtained from the different pairs of images. Several experiments have been performed to evaluate the performance of the proposed method.