Advertisement

Contour Detection Method of 3D Fish Using a Local Kernel Regression Method

  • Jong Min Oh
  • Sung Rak Kim
  • Sung Won Kim
  • Nam Soo Jeong
  • Min Saeng Shin
  • Hak Kyeong Kim
  • Sang Bong KimEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 554)

Abstract

This paper proposes a fish contour detection method using a local kernel regression method. To do this task, the followings are done. Firstly, 3D depth map of a fish is obtained by using Kinect camera sensor. Secondly, edge of the fish in 3D depth map is transformed into numerous points. Thirdly, all information is removed except the edge points. However, recognition points for recognizing the fish are appropriately left because there are only points left to distinguish between background and fish. Fourthly, the points are recognized as contour of the fish by using the local kernel regression method. Finally, experiment results using Kinect camera sensor are shown to verify the validity of the proposed method compared to Canny method.

Keywords

Local kernel regression Edge point Contour of fish Kinect camera sensor 

Notes

Acknowledgments

This research was a part of the project titled “Localization of unloading automation system related to Korean type of fish pump (20150446)”, funded by the Ministry of Oceans and Fisheries, Korea.

References

  1. 1.
    Nguyen, T.H., Jeong, S.K., Kim, H.K., Kim, S.B.: A method for localizing and grasping objects in a picking robot system using kinect camera. In: Proceedings of 2016 International Symposium on Advanced Mechanical and Power Engineering (ISAMPE), pp. 178–180 (2016)Google Scholar
  2. 2.
    Papazov, C., Haddadin, S., Parusel, S., Krieger, K., Burschka, D.: Rigid 3D geometry matching for grasping of known objects in cluttered scenes. Int. J. Robot. Res. 31(4), 538–553 (2012)CrossRefGoogle Scholar
  3. 3.
    Bley, F., Schmirgel, V., Kraiss, K.F.: Mobile manipulation based on generic object knowledge. In: Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (2006)Google Scholar
  4. 4.
    Canny, J.F.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  5. 5.
    Seber, G.A.F., Wild, C.J.: Nonlinear Regression. Wiley, New York (1989)CrossRefGoogle Scholar
  6. 6.
    Han, X.F., Jin, J.S.: A review of algorithms for filtering the 3D point cloud. Sig. Process.: Image Commun. 57, 103–112 (2017)Google Scholar
  7. 7.
    Wand, M., Berner, A., Bokeloh, M., Jenke, P., Fleck, A., Hoffmann, M., Maier, B., Staneker, D., Schiling, A., Seidel, H.: Processing and interactive editing of huge point clouds from 3D scanners. Comput. Graph. Sci. Direct 32, 204–220 (2008)CrossRefGoogle Scholar
  8. 8.
    Gao, T.S.: 3D image reconstruction algorithm based on depth map information of a Kinect camera sensor, Thesis, Pukyong National University (2017)Google Scholar
  9. 9.
    Oztireli, A.C., Guennebaud, G., Gros, M.: Feature preserving point set surfaces based on Non-Linear Kernel Regression. EUROGRAPHICS 28(2)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Jong Min Oh
    • 1
  • Sung Rak Kim
    • 1
  • Sung Won Kim
    • 1
  • Nam Soo Jeong
    • 2
  • Min Saeng Shin
    • 2
  • Hak Kyeong Kim
    • 1
  • Sang Bong Kim
    • 1
    Email author
  1. 1.Department of Mechanical Design EngineeringPukyong National UniversityBusanSouth Korea
  2. 2.Department of Mechanical System EngineeringDongwon Institute of Science and TechnologyYangsanRepublic of Korea

Personalised recommendations