Depth estimation via parallel coevolution of disparity functions for area-based stereo

P. Liatsis, J. Y. Goulermas

Research output: Contribution to journalConference articlepeer-review


A novel system for depth estimation is proposed with the use of Symbiotic Genetic Algorithms for the continuous problem of disparity surface approximation. The approach is based on the decomposition of the entire surface to very small non-overlapping patches described by low-order bivariate polynomials and the use of symbiotic optimisation to enforce smoothness at the boundaries of these patches, so that the entire surface can be approximated in a smooth piecewise fashion by functionals of local support. Such optimisation is amenable to a massive parallel implementation, since each patch is optimised by a different execution unit and each unit communicates through its cost function only with its four-connected neighbours. The method makes use of various existing crossover and mutation schemes for real-valued chromosome representations and a new problem-specific mechanism for generating and hybridising the initial populations. The proposed multi-objective cost function enforces photometric similarity and smoothness between the patch boundaries at a local scale, which in the long term give rise to a globally smooth disparity surface.

Original languageBritish English
Pages (from-to)169-180
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - 2001
EventOptomechatronic Systems - Boston, MA, United States
Duration: 5 Nov 20006 Nov 2000


  • Area-based stereo
  • Disparity functionals
  • Photometric similarity
  • Symbiotic genetic algorithms


Dive into the research topics of 'Depth estimation via parallel coevolution of disparity functions for area-based stereo'. Together they form a unique fingerprint.

Cite this