A Data Reuse Method for Fast Search Motion Estimation

  • Hongjie Li
  • Yanhui Ding
  • Weizhi Xu
  • Hui Yu
  • Li SunEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11338)


In motion estimation, the search regions of two adjacent current blocks have overlapping data. In view of this, the paper proposes a data reuse method for fast search motion estimation. The method reuses the overlapping data between the search areas of two adjacent blocks. The overlapping data are further divided into two parts, a definite data reuse area and a possible data reuse area. With this method, the memory access time of the algorithm is reduced, and the performance of the algorithm is further improved. And the proposed reuse method can effectively reduce the loading of redundant data. A typical fast search algorithm, diamond search, is used as a case study to verify the effectiveness of the method. The method is implemented on GPU platform. The experimental results show that the data reuse method can reduce the running time by 40%–60% compared with the algorithm of no use data reuse.


Motion estimation Data reuse Diamond search CUDA 



The work is supported by Primary Research & Development Plan of Shandong Province (2017GGX10112), and the Shandong Natural Science Foundation (No. ZR2015FQ009) and NNSF of China (No. 61520106005, No. 61602285, and No. 61602284).


  1. 1.
    Jiang, C., Nooshabadi, S.: GPU accelerated motion and disparity estimations for multiview coding. In: IEEE International Conference on Image Processing, pp. 2106–2110. IEEE (2014)Google Scholar
  2. 2.
    Kim, J.-N., Byun, S.-C., Kim, Y.-H., Ahn, B.-H.: Fast full search motion estimation algorithm using early detection of impossible candidate vectors. IEEE Trans. Signal Process. 50(9), 2355–2365 (2002)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Park, D., Jang, Y., Lee, J.: A new fast three step search motion estimation algorithm in H.264. In: 2007 International Forum on Strategic Technology, pp. 541–544 (2007)Google Scholar
  4. 4.
    Gaikwad, M.M.: Implementation of four step search algorithm of motion estimation using FPGA. Int. J. Adv. Res. Comput. Sci. Electron. Eng. 1(3), 68 (2012)Google Scholar
  5. 5.
    Ali, I., Raja, G., Muzammil, M., Khan, A.K.: Adaptive modified hexagon based search motion estimation algorithm. In: IEEE Fourth International Conference on Consumer Electronics, pp. 147–148. IEEE, Berlin (2014)Google Scholar
  6. 6.
    Fan, R., Zhang, Y., Li, B.: Motion classification-based fast motion estimation for high-efficiency video coding. IEEE Trans. Multimed. 19(5), 893–907 (2017)CrossRefGoogle Scholar
  7. 7.
    Xu, W., Yin, S., Liu, L., Liu, Z., Wei, S.: High-performance motion estimation for image sensors with video compression. Sensors 15(8), 20752–20778 (2015)CrossRefGoogle Scholar
  8. 8.
    Shim, H., Kang, K., Kyung, C.-M.: Search area selective reuse algorithm in motion estimation. In: 2007 IEEE International Conference on Multimedia and Expo, pp. 1611–1614 (2007)Google Scholar
  9. 9.
    Tuan, J.-C., Chang, T.-S., Jen, C.-W.: On the data reuse and memory bandwidth analysis for full-search block-matching VLSI architecture. IEEE Trans. Circuits Syst. Video Technol. 12(1), 61–72 (2002)CrossRefGoogle Scholar
  10. 10.
    Kim, T.S., SunWoo, M.H.: Data reusable search scan methods for low power motion estimation. J. Inst. Electron. Eng. Korea 50(9), 85–91 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Hongjie Li
    • 1
  • Yanhui Ding
    • 1
  • Weizhi Xu
    • 1
  • Hui Yu
    • 2
  • Li Sun
    • 3
    Email author
  1. 1.School of Information Science and EngineeringShandong Normal UniversityJinanChina
  2. 2.School of Management Science and EngineeringShandong Normal UniversityJinanChina
  3. 3.Financial DepartmentShandong Normal UniversityJinanChina

Personalised recommendations