Abstract
A gradation stereo matching algorithm based on edge feature points was proposed. Its basic idea is: firstly edge feature points of image pair were extracted; then, gradient invariability and singular eigenvalue invariability were analyzed, two-grade stereo matching method was build, foundation matrix was solved further, and three-grade stereo matching algorithm was finished by foundation matrix guidance. The result indicates that the algorithm can improve matching precision, from 58.3% to 73.2%, it is simple and utility, and it is important for object recognition, tracking, and three-dimensional reconstruction.
Publisher
Trans Tech Publications, Ltd.
Reference8 articles.
1. Luke Domanski, Pascal Vallotton, Dadong Wang. Two and Three-Dimensional Image Deconvolution on Graphics Hardware[C]. 18th World IMACS / MODSIM Congress, Cairns, Australia 13-17 July, (2009).
2. Natan T. Shaked, Barak Katz, Joseph Rosen. Review of three-dimensional holographic imaging by multiple- viewpoint- projection based methods[J]. Applied Optics, 2009, 48(34): H120-H136.
3. Tao Hu, May Huang. A new stereo matching algorithm for binocular vision[C]. Proceedings of the 2009 International Conference on Hybrid Information Technology, Daejeon, Korea, 2009, 42-44.
4. Huttenlocher D, Klanderman G, Rucklidge W. Comparing images using the hausdorff distance [J]. Pattern Analysis and Machine Intelligence, 1993, 15: 850-863.
5. M. Tanase, R. C. Veltkamp, Herman Haverkort. Multiple Polyline to Polygon Matching[C]. International Society for Augmentative & Alternative Communication, 2005: 1-21.