Detecting ground control points via convolutional neural network for stereo matching

  • Zhun Zhong
  • Songzhi Su
  • Donglin Cao
  • Shaozi Li
  • Zhihan Lv
Article

DOI: 10.1007/s11042-016-3932-y

Cite this article as:
Zhong, Z., Su, S., Cao, D. et al. Multimed Tools Appl (2016). doi:10.1007/s11042-016-3932-y
  • 294 Downloads

Abstract

In this paper, we present a novel approach to detect ground control points (GCPs) for stereo matching problem. First of all, we train a convolutional neural network (CNN) on a large stereo set, and compute the matching confidence of each pixel by using the trained CNN model. Secondly, we present a ground control points selection scheme according to the maximum matching confidence of each pixel. Finally, the selected GCPs are used to refine the matching costs, then we apply the new matching costs to perform optimization with semi-global matching algorithm for improving the final disparity maps. We evaluate our approach on the KITTI 2012 stereo benchmark dataset. Our experiments show that the proposed approach significantly improves the accuracy of disparity maps.

Keywords

Stereo matching CNN Ground control points Matching confidence 

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Zhun Zhong
    • 1
  • Songzhi Su
    • 1
  • Donglin Cao
    • 1
  • Shaozi Li
    • 1
  • Zhihan Lv
    • 2
  1. 1.Cognitive Science DepartmentXiamen UniversityXiamenChina
  2. 2.SIAT, Chinese Academy of ScienceShenzhenChina

Personalised recommendations