Skip to main content
SpringerLink
Log in

A camera planning method for the 3D reconstruction of a single object based on statistical deformation model

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In order to provide sufficient information for the 3D reconstruction of a single, static and known type object, this paper proposes measure indexes to evaluate the information amount and a camera planning method to guide the search of the optimal camera positions. The planning method is based on Statistical Deformation Model (SDM) which is generated from Point Distribution Model (PDM) by the Principal Component Analysis (PCA) method. The position from which the individual factor coefficients are observed clearly and the principal shape features are identified distinctly is the best viewpoint. The observed times of landmark are used to exclude the redundancy among views. So, in an iteration process new SDM is repeatedly computed to pick out the optimal viewpoints until all the landmarks are observed sufficiently. Therefore abundant information with the minimum redundancy is provided by fewer cameras, and an experiment which layout cameras for foot reconstruction was demonstrated.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Abidi BR (1995) Automatic sensor placement. Process of SPIE Conference on Intelligent Robots and Computer Vision. pp 387–398

  2. Abidi BR, Aragam NR, Yao Y et al (2008) Survey and analysis of multi model sensor planning and integration for wide area surveillance. ACM Comput Surv 41(1):1–36

    Article  Google Scholar 

  3. Banta JE, Wong LR, Dumont C et al (2000) A next-best-view system for autonomous 3-D object reconstruction. IEEE Transl Syst Man Cybern A 30(5):589–598

    Article  Google Scholar 

  4. Blaer PS, Allen PK (2009) View planning and automated data acquisition for three-dimensional modeling of complex sites. J Field Robot 26(11–12):865–891

    Article  Google Scholar 

  5. Brett AD, Taylor CJ (2000) A method of automated landmark generation for automated 3-D PDM construction. Image Vision Comput 18(9):739–748

    Article  Google Scholar 

  6. Campbell ND, Vogiatzis G, Carloshern C (2008) Using multiple hypotheses to improve depth-maps for multi-view stereo. European Conference on Computer Vision. Marseille, France, pp 766–779

  7. Computer vision datasets EB/OL. http://vision.middlebury.edu/mview/data/, 2011-08-16.

  8. Cootes TF, Taylor CJ, Cooper D et al (1995) Active shape models—their training and application. Comput Vis Image Underst 61(7):38–59

    Article  Google Scholar 

  9. Dornaika F, Ahlberg J (2003) Face model adaptation for tracking and active appearance model. British Machine Vision Conference. Norwich, UK, pp 326–339

  10. Furukawa Y, Ponce J (2007) Accurate, dense, and robust multi-view stereopsis. IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, pp 1–8

  11. Horkaew P, Yang G-Z (2004) Construction of 3D dynamic statistical deformable models for complex topological shapes. International Conference on Medical Image Computing and Computer-Assisted Intervention. Saint-Malo, France, pp 217–224

  12. Jancosek M, Pajdla T (2009) Scalable multi-view stereo. IEEE International Workshop on 3-D Digital Imaging and Modeling. Kyoto, Japan, pp 91–97, 2009

  13. Jolliffe IT (1986) Principal component analysis. Springer Verlag, New York

    Book  Google Scholar 

  14. Kass M, Witkin A, Terzopoulos D (1987) Snakes: Active Contour Models. International Conference on Computer Vision. London, UK, pp 259–268

  15. Maver J (1999) Which slightly different view is the right one. International Conference on Computer Analysis of Images and Patterns. Ljubljana, Slovenia, pp 444–453

  16. Peters G, Leopold T (2007) Dynamic learning of action patterns for object acquisition. Int Syst Tech Appl 2(3):113–124

    Google Scholar 

  17. Peters G, Zitova B, von der Malsburg C (2002) How to measure the pose robustness of object views. Image Vision Comput 20(4):249–256

    Article  Google Scholar 

  18. Pito R (1999) A solution to the next best view problem for automated surface acquisition. IEEE Trans Pattern Anal Mach Intell 21(10):1016–1030

    Article  Google Scholar 

  19. Roy SD, Chaudhury S, Banerjee S (2004) Active recognition through next view planning: a survey. Pattern Recogn 37(3):429–446

    Article  Google Scholar 

  20. Roy SD, Chaudhury S, Banerjee S (2005) Recognizing large isolated 3-D objects through next view planning using inner camera invariants. IEEE Trans Syst Man Cybern B Cybern 35(2):282–292

    Article  Google Scholar 

  21. Sheng L (2010) Landmark design in 3D PDM for PCA of shoe last. the 3rd International Conference on Advanced Computer Theory and Engineering, vol. 1, pp 1517–1521

  22. Tarabanis KA, Allen PK, Tsai RY (1995) A survey of sensor planning in computer vision. IEEE Trans Robot Autom 11(1):86–104

    Article  Google Scholar 

  23. Tarbox G, Gottschlich S (1995) Planning for complete sensor coverage in inspection. Comput Vis Image Understand 61(1):84–111

    Article  Google Scholar 

  24. Xi P, Shu C (2009) Consistent parameterization and statistical analysis of human head scans. Vis Comput 25(9):863–871

    Article  Google Scholar 

  25. Yao Y, Chen C-H, Abidi B et al (2010) Can you see me now? Sensor positioning for automated and persistent surveillance. IEEE Transl Syst Man Cybern B Cybern 40(1):101–115

    Article  Google Scholar 

  26. Yuan X (1995) A mechanism of automatic 3D object modeling. IEEE Trans Pattern Anal Mach Intell 17(3):307–311

    Article  Google Scholar 

  27. Yuan X, Yang SX (2007) Multi-robot-based nanoassembly planning with automated path generation. IEEE-ASME Trans Mechatron 12(3):352–356

    Article  Google Scholar 

  28. Zheng G (2009) Statistical deformable model-based reconstruction of a patient-specific surface model from single standard X-ray radiograph. Comput Anal Images Patterns 57(2):672–679

    Article  Google Scholar 

Download references

Acknowledgments

This research was jointly sponsored by Zhejiang Provincial Natural Science Foundation of China (Project No. Y1100075), Shanghai Key Discipline Fund of Shanghai University (Project No. B 67) and Science Foundation of Wenzhou University, which are greatly appreciated by the authors.

Author information

Authors and Affiliations

  1. College of mechanical and electronic Engineering, Wenzhou University, Wenzhou City, Zhejiang Province, China

    Luo Sheng

  2. School of Mechatronics Engineering and Automation, Shanghai University, Shanghai City, China

    Zhenbang Gong

Authors
  1. Luo Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenbang Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Luo Sheng.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sheng, L., Gong, Z. A camera planning method for the 3D reconstruction of a single object based on statistical deformation model. Multimed Tools Appl 63, 833–850 (2013). https://doi.org/10.1007/s11042-011-0939-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-011-0939-2

Keywords

Search

Navigation