ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Improved Stereo Matching With Boosting Method

Journal: International Journal of Scientific & Technology Research (Vol.4, No. 6)

Publication Date:

Authors : ; ;

Page : 177-181

Keywords : Index Terms Stereo matching; occlusion handling; initial processing; classification; completion stage; median filtering; performance evaluation;

Source : Downloadexternal Find it from : Google Scholarexternal


Abstract This paper presents an approach based on classification for improving the accuracy of stereo matching methods. We propose this method for occlusion handling. This work employs classification of pixels for finding the erroneous disparity values. Due to the wide applications of disparity map in 3D television medical imaging etc the accuracy of disparity map has high significance. An initial disparity map is obtained using local or global stereo matching methods from the input stereo image pair. The various features for classification are computed from the input stereo image pair and the obtained disparity map. Then the computed feature vector is used for classification of pixels by using GentleBoost as the classification method. The erroneous disparity values in the disparity map found by classification are corrected through a completion stage or filling stage. A performance evaluation of stereo matching using AdaBoostM1 RUSBoost Neural networks and GentleBoost is performed.

Last modified: 2015-11-13 18:30:49