Skip to main content
SpringerLink
Log in

Real-time 3D human objects rendering based on multiple camera details

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

Abstract

3D model construction techniques using RGB-D information have been gaining a great attention of the researchers around the world in recent decades. The RGB-D sensor, Microsoft Kinect is widely used in many research fields, such as in computer vision, computer graphics, and human computer interaction, due to its capacity of providing color and depth information. This paper presents our research finding on calibrating information from several Kinects in order to construct a 3D model of a human object and to render texture captured from RGB camera. We used multiple Kinect sensors, which are interconnected in a network. High bit rate streams captured at each Kinect are first sent to a centralized PC for the processing. This even can be extended to a remote PC in the Internet. Main contributions of this work include calibration of the multiple Kinects, properly aligning point clouds generated from multiple Kinects, and generation of the 3D shape of the human objects. Experimental results demonstrate that the proposed method provides a better 3D model of the human object being captured.

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
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. https://msdn.microsoft.com/en-us/library/jj131033.aspx

References

  1. Alexander O, Rogers M, Lambeth W, Chiang M, Debevec P (2009) Creating a photoreal digital actor: the digital Emily project. Sixth Eur Conf on Vis Media Prod (CVMP)

  2. Besl PJ, McKay ND (1992) A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell 14:239–256

    Article  Google Scholar 

  3. Cappelletto E, Zanuttigh P, Cortelazzo GM (2014) 3D scanning of cultural heritage with consumer depth cameras. Multimedia Tools Appl, 1–24. doi: 10.1007/s11042-014-2065-4

  4. Curless B, Levoy M (1996) A volumetric method for building complex models from range images. Proc 23rd Annual Conf on Comput Graphics and Interact Techniques pp. 303–312

  5. Curless B, Levoy M (1996) A volumetric method for building complex models from range images. Proc ACM SIGGRAPH pp. 303–312

  6. Dayrit FL, Nakashima Y, Sato T, Yokoya N (2015) Increasing pose comprehension through augmented reality reenactment. Multimed Tools Appl, 1–22. doi: 10.1007/s11042-015-3116-1

  7. Essmaeel K, Gallo L, Damiani E, De Pietro G, Dipanda A (2014) Comparative evaluation of methods for filtering Kinect depth data. Multimed Tools Appl 74:7331–7354

    Article  Google Scholar 

  8. Furukawa Y, Ponce J (2007) Accurate, dense, and robust multi-view stereopsis. Proc IEEE Conf Comput Vis and Pattern Recognit pp. 1362–1376

  9. Gallup D, Frahm JM, Mordohai P, Yang Q, Pollefeys M (2007) Real-time plane sweeping stereo with multiple sweeping directions. Proc IEEE Conf Comput Vis and Pattern Recognit pp. 1–8

  10. Geng N, Ma F, Yang H, Li B, Zhang Z (2015) Neighboring constraint-based pairwise point cloud registration algorithm. Multimed Tools Appl 1–18. doi: 10.1007/s11042-015-2941-6

  11. Goesele M, Curless B, Seitz S (2006) Multi-view stereo revisited. Proc IEEE Conf Comput Vis and Pattern Recognit pp. 2402–2409

  12. Harris M, Sengupta S, Owens JD (2007) Parallel prefix sum (scan) with CUDA. In: Nguyen H (ed) GPU gems, 3rd edn. Addison Wesley, pp. 851–876

  13. Hernandez C, Schmitt F (2004) Silhouette and stereo fusion for 3D object modeling. Comp Vision Image Underst 96:367–392

    Article  Google Scholar 

  14. Huhle B, Schairer T, Jenke P, Straßer W (2008) Robust non-local denoising of colored depth data. Proc IEEE Comput Vis Pattern Recogn Workshops (CVPRW’08) pp. 1–7

  15. Kutulakos K (2000) Approximate N-view stereo. Proc Eur Conf on Comput Vis pp. 67–83

  16. Kutulakos KN, Seitz SM (2000) A theory of shape by space carving. Int J Comput Vis 38:199–218

    Article  MATH  Google Scholar 

  17. Li X, Wang P, Zha F, Li M, Guo W, Sun L (2015) Improving convergence of ICP for registering RGB-D images using hierarchical index. J Comput Inf Syst 11:27–35

    Google Scholar 

  18. Newcombe RA, Izadi S, Hilliges O, Molyneaux D, Kim D, Davison AJ, Kohli P, Shotton J, Hodges S, Fitzgibbon A (2011) KinectFusion: real-time dense surface mapping and tracking. Proc 2011 10th IEEE Int Symp on Mixed and Augment Real pp. 127–136

  19. Reisner-Kollmann I, Maierhofer S (2011) Consolidation of multiple depth maps. Proc IEEE Int Conf Comput Vis Workshops (ICCV Workshops) pp. 1120–1126

  20. Rusinkiewicz S, Levoy M (2001) Efficient variants of the ICP algorithm. Proc IEEE 3rd Int Conf on 3D Digital Imaging and Modeling pp. 145–152

  21. Seitz SM, Dyer CR (1999) Photorealistic scene reconstruction by voxel coloring. Int J Comput Vis 35:151–173

    Article  Google Scholar 

  22. Song W, Yun S, Jung SW, Won CS (2015) Rotated top-bottom dual-Kinect for improved field of view. Multimed Tools Appl 1–25. doi: 10.1007/s11042-015-2772-5

  23. Tong J, Zhou J, Liu L, Pan Z, Yan H (2012) Scanning 3D full human bodies using Kinects. IEEE Trans Vis Comput Graph 18:643–650

    Article  Google Scholar 

  24. Xia L, Chen CC, Aggarwal JK (2011) Human detection using depth information by Kinect. IEEE Comput Soc Conf on Comput Vis and Pattern Recognit Workshops (CVPRW) pp. 15–22

  25. Xu H, Barbic J (2014) Signed distance fields for polygon soup meshes. Proc 2014 Graph Interface Conf pp. 35–41

  26. Zabulis X, Daniilidis K (2004) Multi-camera reconstruction based on surface normal estimation and best viewpoint selection. Int Symp 3D Data Process Vis and Transm pp. 733–740

  27. Zhang L, Curless B, Seitz SM (2002) Rapid shape acquisition using color structured light and multi-pass dynamic programming. Proc IEEE 1st Int Symp 3D Data Process Vis and Transm pp. 24–36

Download references

Author information

Authors and Affiliations

  1. MINE Lab, Department of Computer Science and Information Engineering, National Central University (NCU), No. 300, Jhongda Rd., Jhongli City, Taoyuan County, 32001, Taiwan, Republic of China

    W. G. C. W. Kumara, Timothy K. Shih, Wei-Chun Chang & Enkhtogtokh Togootogtokh

  2. Department of Computer Science and Information Engineering, Tamkang University, Taiwan, Republic of China

    Shwu-Huey Yen & Hui-Huang Hsu

Authors
  1. W. G. C. W. Kumara
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shwu-Huey Yen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui-Huang Hsu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Timothy K. Shih
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wei-Chun Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Enkhtogtokh Togootogtokh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Timothy K. Shih.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumara, W.G.C.W., Yen, SH., Hsu, HH. et al. Real-time 3D human objects rendering based on multiple camera details. Multimed Tools Appl 76, 11687–11713 (2017). https://doi.org/10.1007/s11042-016-3327-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-016-3327-0

Keywords

Search

Navigation