| Paper Details: | Downloads: 366 |
| Serial Number: | P1150537101
|
| Title: | Improvement of 3-D Reconstruction by Deformal Stereo Matching using a Set of Linear Spatial Filters
|
| Authors: | Sherif El-Etriby and Ayoub. Al-Hamadi and Bernd. Michaelis
|
| Abstract: | This paper presents a stereo matching algorithm to calculate the three-dimensional (3-D) reconstruction. In view of the fact that, stereo images are obtained from the different perspective position, so that each image can have the effect of projective distortion region (foreshortening effects, occlusion region). These effects cause problems because most stereo method compares similarly-size regions (using the same size windows in both images). An alternative approach is presented, which based on the output of linear spatial filters turned to a range of orientations and scales to make the correspondence analysis more reliable and robust. The responses of these filters at a given point constitute a vector called the filter response vector is correlated instead of correlating area in the two images. In addition, an automatic procedure is used to evaluate and optimize the filters set by using the steering theorem and the singular value decomposition (SVD). The projective distortion region are detected to improve the quality of the disparity by adaptive the size of filter kernel, and a 3-D information is recovered. The real stereo images and the reference (true) disparity map are used to benchmark the performance.
|
| Keywords: | Stereovision, Structured light, linear spatial filters, correspondence analysis, Steering theorem.
|
| Journal/Conference: | ICGST Conference on Graphics, Vision and Image Processing, GVIP-05
|
| Volume: |
|
| Issue: |
|
| Submission Date: | 9/1/2005 12:00:00 AM
|
| Review Date: | 10/1/2005 12:00:00 AM
|
| Publishing Date: | 12/19/2005 12:00:00 AM
|
| Article Downloads: | 366
|
| Download: |
|