Chapter

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Volume 7042 of the series Lecture Notes in Computer Science pp 223-231

A Measure for Accuracy Disparity Maps Evaluation

  • Ivan CabezasAffiliated withLancaster UniversityEscuela de Ingeniería de Sistemas y Computación, Universidad del Valle, Ciudadela Universitaria Melendez
  • , Victor PadillaAffiliated withLancaster UniversityEscuela de Ingeniería de Sistemas y Computación, Universidad del Valle, Ciudadela Universitaria Melendez
  • , Maria TrujilloAffiliated withLancaster UniversityEscuela de Ingeniería de Sistemas y Computación, Universidad del Valle, Ciudadela Universitaria Melendez

* Final gross prices may vary according to local VAT.

Get Access

Abstract

The quantitative evaluation of disparity maps is based on error measures. Among the existing measures, the percentage of Bad Matched Pixels (BMP) is widely adopted. Nevertheless, the BMP does not consider the magnitude of the errors and the inherent error of stereo systems, in regard to the inverse relation between depth and disparity. Consequently, different disparity maps, with quite similar percentages of BMP, may produce 3D reconstructions of largely different qualities. In this paper, a ground-truth based measure of errors in estimated disparity maps is presented. It offers advantages over the BMP, since it takes into account the magnitude of the errors and the inverse relation between depth and disparity. Experimental validations of the proposed measure are conducted by using two state-of-the-art quantitative evaluation methodologies. Obtained results show that the proposed measure is more suited than BMP to evaluate the depth accuracy of the estimated disparity map.

Keywords

Computer vision corresponding points disparity maps quantitative evaluation error measures