Advertisement

Measuring Apple Size Distribution from a Near Top–Down Image

  • Luke ButtersEmail author
  • Zezhong XuEmail author
  • Khoa Le TrungEmail author
  • Reinhard KletteEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11854)

Abstract

The paper presents a method for estimating size information of a bin of apples; we document the machine learning and computer vision techniques applied or developed for solving this task. The system was required to return a statistical distribution of diameter sizes based off visible fruit on the top layer of an apple bin image. A custom data–set was collected before training a Mask R-CNN object detector. Image transformations were used to recover real world dimensions. The presented research was undertaken for further integration into an app where apple growers have the ability to get fast estimations of apple size.

Notes

Acknowledgement

This research has been supported by Hectre - Orchard Management Software, New Zealand. Authors thank orchards in the Nelson region of New Zealand (Hoddys Fruit Company, Tyrella Orchards and McLean Orchard) for collaboration.

References

  1. 1.
    Analytics Vidya Guide: Building a Mask R-CNN Model for Detecting Car Damage. http://analyticsvidhya.com/blog/2018/07/building-mask-r-cnn-model-detecting-damage-cars-python/. Accessed 19 July 2019
  2. 2.
    Blinn, J.: A trip down the graphics pipeline: the homogeneous perspective transform. IEEE Comput. Graph. Appl. 13(3), 75–80 (1993)CrossRefGoogle Scholar
  3. 3.
    Butters, L., Xu, Z., Klette, R.: Using machine vision to command a 6-axis robot arm to act on a randomly placed zinc die cast product. In: Proceedings of the International Conference on Control Computer Vision, South Korea (2019, to appear)Google Scholar
  4. 4.
    Common Objects in Context. http://cocodataset.org/#home. Accessed 6 July 2019
  5. 5.
    Dhiman, A., Khan, W., Klette, R.: Pothole detection using deep learning. In: Proceedings of the t-TECH19, Christchurch (2019). http://itsnz.org/files-reports
  6. 6.
    GitHub repository: Matterport Mask R-CNN. http://github.com/matterport/Mask_RCNN. Accessed 19 July 2019
  7. 7.
    Howard, A., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
  8. 8.
    He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)Google Scholar
  9. 9.
    Klette, R.: Concise Computer Vision. Springer, London (2014).  https://doi.org/10.1007/978-1-4471-6320-6CrossRefzbMATHGoogle Scholar
  10. 10.
    Lasi, H., Fettke, P., Kemper, H., Feld, T., Hoffman, M.: Industry 4.0. Bus. Inf. Syst. Eng. 6(4), 239–242 (2014)CrossRefGoogle Scholar
  11. 11.
    OpenCV Documentation on Geometric Transformations. http://docs.opencv.org/2.4/modules/imgproc/doc/geometric_transformations.html. Accessed 14 July 2019
  12. 12.
    Py Image Search: 4 Point OpenCV getPerspective Transform Example. http://pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/. Accessed 6 July 2019
  13. 13.
    VGG Image Annotator 1.0.6. http://robots.ox.ac.uk/~vgg/software/via/via-1.0.6.html. Accessed 6 July 2019
  14. 14.
    Wikipedia 20th Century Automation. https://en.wikipedia.org/wiki/Automation/#20th_century. Accessed 18 Jun 2019
  15. 15.
    Xu, Z., Xu, S., Qian, C., Klette, R.: Accurate ellipse extraction in low-quality images. In: Proceedings of the Machine Vision Applications, pp. 1–5 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Hectre - Orchard Management SoftwareAucklandNew Zealand
  2. 2.Changzhou Institute of TechnologyChangzhouChina
  3. 3.Department of Electrical and Electronic EngineeringAuckland University of TechnologyAucklandNew Zealand

Personalised recommendations