DOI QR코드

DOI QR Code

Correction Method for Measurement Failure Pixels in Depth Picture using Surface Modeling

표면 모델링을 통한 깊이 영상 내 측정 실패 화소 보정 방법

  • 이동석 (동의대학교 컴퓨터소프트웨어공학과) ;
  • 권순각 (동의대학교 컴퓨터소프트웨어공학과)
  • Received : 2019.07.28
  • Accepted : 2019.08.16
  • Published : 2019.10.31

Abstract

In this paper, we propose a correcting method of depth pixels which are failed to measure since temporary camera error. A block is modeled to plane and sphere surfaces through measured depth pixels in the block. Depth values in the block are estimated through each modeled surface and a error for the modeled surface is calculated by comparing the original and estimated pixels, then the surface which has the least error is selected. The pixels which are failed to measure are corrected by estimating depth values through selected surface. Simulation results show that the proposed method increases the correction accuracy by an average of 20% compared with the correction method of $5{\times}5$ median method.

본 논문에서는 깊이 영상에서 깊이 카메라의 일시적인 오류로 인해 측정이 되지 않은 깊이 화소의 값을 보정하는 방법을 제안한다. 깊이 영상의 한 블록 내에서 측정이 정상적으로 된 화소의 좌표와 깊이 값을 이용하여, 해당 블록의 깊이 값과 제일 오차가 적은 평면과 곡면을 모델링한다. 그 후 각각의 모델링된 표면을 통해 추정된 깊이 값과 원래 측정된 깊이 값을 비교하여 오차를 계산한다. 그 후 오차가 제일 작게 계산된 표면을 선택한 후, 측정에 실패한 깊이 화소를 선택된 모델링 표면을 통해 깊이 값을 추정함으로써 보정한다. 모의실험 결과 제안된 방법을 통한 보정방법은 $5{\times}5$ 영역의 중간 값을 이용한 보정방법에 비해 보정 성능이 평균 20% 개선되었음을 확인하였다.

Keywords

References

  1. Fanelli, G., Dantone, M. and Van Gool, L. (2013). Real Time 3D Face Alignment with Random Forests-based Active Appearance Models, Proceeding of the IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, Apr. 22-26, Shanghai, China, pp. 1-8.
  2. Kwon, S. K., Lee, D. S. and Park, Y. H. (2016). Depth Video Coding Method for Spherical Object, Journal of the Korea Industrial Information Systems Research, 21(6), 23-29. https://doi.org/10.9723/JKSIIS.2016.21.6.023
  3. Lee, D. S. and Kwon, S. K. (2018). Intra Prediction of Depth Picture with Plane Modeling, Symmetry, 10(12), 1-16. https://doi.org/10.3390/sym10120715
  4. Lee, D. S. and Kwon, S. K. (2019). Virtual Touch Sensor using a Depth Camera, Sensor, 19(4), 1-13. 2019. https://doi.org/10.3390/s19040885
  5. Levin, A., Lischinski, D. and Weiss,Y. (2004). Colorization using Optimization, Proceedings of ACM SIGGRAPH, Aug. 8-12, Los Angeles, California, pp. 689-694.
  6. Miao, D., Fu, J., Lu, Y., Li, S. and Chen, C. W. (2012). Texture-assisted Kinect Depth Inpainting, Proceeding of the IEEE International Symposium on Circuits and Systems, May 20-23, Seoul, Korea, pp.604-607.
  7. Pomerleau, F., Magnenat, S., Colas, F., Liu, M. and Siegwart, R. (2011). Tracking A Depth Camera: Parameter Exploration for Fast ICP, Proceeding of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep. 25-30, San Francisco, California, pp. 3824-3829.
  8. Siddiqui, M. and Medioni, G. (2010). Human Pose Estimation from A Single View Point, Real-time Range Sensor, Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Jun. 13-18, San Francisco, California, pp. 1-8.
  9. Silberman, N., Hoiem, D., Kohli, P. and Fergus. R. (2012). Indoor Segmentation and Support Inference from Rgbd Images, Proceeding of the European Conference on Computer Vision, Oct. 7-13, Florence, Italy, pp. 746-760.
  10. Sturm, J., Engelhard, N., Endres, F., Burgard, W. and Cremers, D. (2012). A Benchmark for The Evaluation of RGB-D Slam Systems, Proceeding of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct. 7-12, Vilamoura, Portugal, pp. 573-580.
  11. Wilson, A. D. (2010). Using A Depth Camera as A Touch Sensor, Proceeding of the ACM International Conference on Interactive Tabletops and Surfaces, Nov. 7-10, Saarbrucken, Germany, pp. 69-72.
  12. Xue, H., Zhang, S. and Cai, D. (2017). Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient Regularization, IEEE Transactions on Image Processing, 26(9), 4311-4320. https://doi.org/10.1109/TIP.2017.2718183