Image based reconstruction using hybrid optimization of simulated annealing and genetic algorithm

ABSTRACT

This work deals with the problem of estimating depth information of 3-D surface from a pair of images. The proposed method relies on Second-order Priors on the smoothness of 3D surface which cause intractable (non-submodular) optimization problems; we solved it by using the strategy of Hybrid Optimization of Simulated Annealing and Genetic Algorithm. Experimental results demonstrate the Second-order priors are a better model of typical scenes than first-order priors and the performance of the hybrid algorithm outperforms SA and GA alone.

REFERENCES

• 1: Ilya D. Rosenberg , Philip L. Davidson , Casey M. R. Muller , Jefferson Y. Han, Real-time stereo vision using semi-global matching on programmable graphics hardware, ACM SIGGRAPH 2006 Sketches, July 30-August 03, 2006, Boston, Massachusetts [doi>10.1145/1179849.1179960]
• 2: H. Hirschmüller and D. Scharstein. 2007. Evaluation of cost functions for stereo matching. In Proc. CVPR, (Minneapolis, MN, June 2007).
• 3: Tai-Pang Wu , Kam-Lun Tang , Chi-Keung Tang , Tien-Tsin Wong, Dense Photometric Stereo: A Markov Random Field Approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.11, p.1830-1846, November 2006 [doi>10.1109/TPAMI.2006.224]
• 4: Yichen Wei , Long Quan, Asymmetrical Occlusion Handling Using Graph Cut for Multi-View Stereo, Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2, p.902-909, June 20-26, 2005 [doi>10.1109/CVPR.2005.76]
• 5: H. Ishikawa and D. Geiger.2006. Rethinking the prior model for stereo. In Proc. ECCV, (2006), 526--537.
• 6: Daniel Scharstein , Richard Szeliski, A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms, International Journal of Computer Vision, v.47 n.1-3, p.7-42, April-June 2002 [doi>10.1023/A:1014573219977]
• 7: Marshall F. Tappen , William T. Freeman, Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters, Proceedings of the Ninth IEEE International Conference on Computer Vision, p.900, October 13-16, 2003
• 8: Richard Szeliski , Ramin Zabih , Daniel Scharstein , Olga Veksler , Vladimir Kolmogorov , Aseem Agarwala , Marshall Tappen , Carsten Rother, A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.30 n.6, p.1068-1080, June 2008 [doi>10.1109/TPAMI.2007.70844]
• 9: Gang Li , Steven W. Zucker, Surface Geometric Constraints for Stereo in Belief Propagation, Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.2355-2362, June 17-22, 2006 [doi>10.1109/CVPR.2006.299]
• 10: Abhijit S. Ogale , Yiannis Aloimonos, Shape and the Stereo Correspondence Problem, International Journal of Computer Vision, v.65 n.3, p.147-162, December 2005 [doi>10.1007/s11263-005-3672-3]
• 11: Xiao, W., Han, W. 2006. Evolutionary Optimization with Markov Random Field Prior. IEEE Trans. on Evolutionary Computation, Vol. 8, No 6 (2004), 567--579.
• 12: Kim, E.Y., Park, S.H. and Kim, H.J., 2000. A genetic algorithm based segmentation of Markov random field modeled images. IEEE Signal Process. Lett. 7 11. (2000), 301--303.
• 13: Salima, O., Mohamed, B, 2003. MRF-based Images Segmentation Using Ant Colony System. Electronic Letters on Computer Vision and Image Analysis vol.2, no.6 (2003), 12--24.
• 14: Zhenyu Yang , Ke Tang , Xin Yao, Large scale evolutionary optimization using cooperative coevolution, Information Sciences: an International Journal, v.178 n.15, p.2985-2999, August, 2008 [doi>10.1016/j.ins.2008.02.017]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: 3D/stereo scene analysis

General Terms:
Algorithms, Experimentation, Performance

Keywords:
genetic algorithm, hybrid optimization, image based reconstruction (ibr), second-order priors, simulated annealing