TY - JOUR
T1 - A geometric approach for regularization of the data term in stereo-vision
AU - Ben-Ari, Rami
AU - Sochen, Nir
PY - 2008/5
Y1 - 2008/5
N2 - Every stereovision application must cope with the correspondence problem. The space of the matching variables, often consisting of spatial coordinates, intensity and disparity, is commonly referred as the data term (space). Since the data is often noisy a-priori, preference is required to result a smooth disparity (or piecewise smooth). To this end, each local method (e.g. window correlation techniques) performs a regularization of the data space. In this paper we propose a geometric framework for anisotropic regularization of the data space seeking to preserve the discontinuities in this space when filtering out the noise. On the other hand, the global methods consider a non-regularized data term with a smoothing constraint imposed directly on the disparity. This paper also proposes a new idea where the data space is regularized in a global method prior to the disparity evaluation. The idea is implemented on the state of the art variational method. Experimental results on the Middlebury real images demonstrate the advantages of the proposed approach.
AB - Every stereovision application must cope with the correspondence problem. The space of the matching variables, often consisting of spatial coordinates, intensity and disparity, is commonly referred as the data term (space). Since the data is often noisy a-priori, preference is required to result a smooth disparity (or piecewise smooth). To this end, each local method (e.g. window correlation techniques) performs a regularization of the data space. In this paper we propose a geometric framework for anisotropic regularization of the data space seeking to preserve the discontinuities in this space when filtering out the noise. On the other hand, the global methods consider a non-regularized data term with a smoothing constraint imposed directly on the disparity. This paper also proposes a new idea where the data space is regularized in a global method prior to the disparity evaluation. The idea is implemented on the state of the art variational method. Experimental results on the Middlebury real images demonstrate the advantages of the proposed approach.
KW - Anisotropic regularization
KW - Data regularization
KW - Variational stereo
KW - Window correlation
UR - http://www.scopus.com/inward/record.url?scp=43449125622&partnerID=8YFLogxK
U2 - 10.1007/s10851-008-0066-5
DO - 10.1007/s10851-008-0066-5
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:43449125622
SN - 0924-9907
VL - 31
SP - 17
EP - 33
JO - Journal of Mathematical Imaging and Vision
JF - Journal of Mathematical Imaging and Vision
IS - 1
ER -