Fruit Tree Image Registration Based on Improved FAST Algorithm

  • Juan Feng
  • Lihua ZengEmail author
  • Jianping Li
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 509)


In order to promote the efficiency and accuracy of image registration, this paper proposes an improved registration algorithm for fruit tree images acquired by a dual-sensor vision system. In the algorithm, feature points are extracted by FAST detectors from Gaussian scale space, and main orientation is determined and SURF descriptor is created with statistical method of neighbor intensity distribution, matching pairs are determined with a relative ratio method and a iterative purifying method in succession. Experimental results show that the proposed algorithm outperforms previous algorithms comprehensively.


Fruit tree Fast corner detection Gaussian scale space Image registration 



The authors thank the financial support from the Natural Science Foundation of Hebei Province (No. C2015204043) and the Science and Engineering Foundation of Agricultural University of Hebei Province (No. LG20140602).


  1. 1.
    Mai, C., Zheng, L., Li, M.: Rapid 3D reconstruction of fruit tree based on point cloud registration. Trans. Chin. Soc. Agric. Eng. 31(supp. 2), 137–144 (2015)Google Scholar
  2. 2.
    Fan, Y., Huang, X.: Research progress in reconstruction of three-dimensional structure of trees. Forestry Mach. Woodworking Equipment 41(2), 26–28 (2013)Google Scholar
  3. 3.
    Liu, G., Si, Y., Feng, J.: 3D reconstruction of agriculture and forestry crops. Trans. Chin. Soc. Agric. Mach. 45(6), 38–46 (2014)Google Scholar
  4. 4.
    Schulze, M.: An approach for the calibration of a combined RGB-sensor and 3D-camera device. In: Paper presented at the Proceedings of SPIE 8085, Videometricsm, Range Imaging and Applications, vol. XI (2011)Google Scholar
  5. 5.
    Ma, X., Gang, L., Feng, J., Wei, Z.: Multi-source image registration for Canopy Organ of apple trees in mature period. Trans. Chin. Soc. Agric. Mach. 45(4), 82–88 (2014)Google Scholar
  6. 6.
    Rosten, L., Drummond, T.: A machine learning approach to corner detection. IEEE Trans. Pattern Anal. Mach. Intell. 32(1), 105–119 (2010)CrossRefGoogle Scholar
  7. 7.
    Wang, M., Dai, Y.P.: Local robust feature based on FAST corner detection. Beijing Ligong Daxue Xuebao/Trans. Beijing Inst. Technol. 33(10), 1045–1050 (2013)Google Scholar
  8. 8.
    Guo, L., Li, J., Zhu, Y.: Fast image matching algorithm based on multi-scale FAST-9. Comput. Eng. 38(12), 208–210 (2012)Google Scholar
  9. 9.
    Viswanathan, D.: Features from Accelerated Segment Test (2016).
  10. 10.
    Bay, H., et al.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  11. 11.
    Nie, T., Hao, X., Fu, T., Zhao, W.: Electronic image stabilization based on improved fast feature matching. Electron. Measur. Technol. 38(11), 42–45 (2015)Google Scholar
  12. 12.
    Feng, J., Liu, G., Wang, S., Ma, X., Zhou, W.: Multi-source Images Registration for harvesting robot to recognize fruits. Trans. Chin. Soc. Agric. Mach. 44(3), 197–203 (2013)Google Scholar
  13. 13.
    Chen, J., Han, X.: Image matching algorithm combining FAST-SURF and improved k-d tree nearest neighbor search. J. Xian Univ. Technol. 32(2), 213–217, 252 (2016)Google Scholar
  14. 14.
    Li, H., Wang, K., Liu, S.: Registration method between infrared and visible images of electrical equipment based on gray-scale redundancy and SURF. Power Syst. Prot. Control. 39(11), 111–115, 123 (2011)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  1. 1.College of Information Science and TechnologyHebei Agricultural UniversityBaodingChina
  2. 2.College of Mechanical and Electrical EngineeringHebei Agricultural UniversityBaodingChina

Personalised recommendations