1 / 41

NON-DESTRUCTIVE GROWTH MEASUREMENT OF SELECTED VEGETABLE SEEDLINGS USING MACHINE VISION

NON-DESTRUCTIVE GROWTH MEASUREMENT OF SELECTED VEGETABLE SEEDLINGS USING MACHINE VISION. Ta-Te Lin, Sheng-Fu Cheng, Tzu-Hsiu Lin, Meng-Ru Tsai Department of Agricultural Machinery Engineering, National Taiwan University, Taipei, Taiwan, ROC. INTRODUCTION.

mattox
Download Presentation

NON-DESTRUCTIVE GROWTH MEASUREMENT OF SELECTED VEGETABLE SEEDLINGS USING MACHINE VISION

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. NON-DESTRUCTIVE GROWTH MEASUREMENT OF SELECTED VEGETABLE SEEDLINGS USING MACHINE VISION Ta-Te Lin, Sheng-Fu Cheng, Tzu-Hsiu Lin, Meng-Ru Tsai Department of Agricultural Machinery Engineering, National Taiwan University, Taipei, Taiwan, ROC

  2. INTRODUCTION • Plant growth measurement and modeling • Machine vision technique • Seedling characteristics • Applications in production management

  3. OBJECTIVES • Image processing algorithm development • Growth measurements of selected vegetable seedlings • Model parameter determination and simulations

  4. SYSTEM IMPLEMENTATION

  5. SEEDLING CHARACTERISTICS • Stem length • Height • Span • Total leaf area • Top fresh weight • Top dry weight • Number of leaves

  6. IMAGE PROCESSING ALGORITHM

  7. RESULT OF NODE TRACING

  8. RESULT OF NODE TRACING

  9. Calibration of cabbage top fresh weight from seedling projection area.

  10. Calibration of cabbage top dry weight from seedling projection area.

  11. Calibration of cabbage total leaf area from seedling projection area.

  12. Calibration of amaranth top fresh weight from seedling projection area.

  13. Calibration of amaranth top dry weight from seedling projection area.

  14. Calibration of amaranth total leaf area from seedling projection area.

  15. Calibration of kale top fresh weight from seedling projection area.

  16. Calibration of kale top dry weight from seedling projection area.

  17. Calibration of kale total leaf area from seedling projection area.

  18. Comparison between manually measured top fresh weight and that determined by the automatic measurement system.

  19. Comparison between manually measured total leaf area and that determined by the automatic measurement system.

  20. Comparison between manually measured top fresh weight and that determined by the automatic measurement system.

  21. Serial images of kale seedlings at various growth stages. (images are not of the same scale)

  22. Kale seedlings images from different angles

  23. Top fresh weight of kale seedlings growing under 25/20C. Each curve indicates individual seedling.

  24. Average plant height of kale seedlings grown under five different day/night temperatures.

  25. Average plant top fresh weight of kale seedlings grown under five different day/night temperatures.

  26. Average top dry weight of kale seedlings grown under five different day/night temperatures.

  27. Average total leaf area of kale seedlings growing under five different day/night temperatures.

  28. PLANT GROWTH MODELS • LOGISTIC MODEL Y = Y0 / [ Y0 + ( 1 -  Y0 ) e-m t] t : Time Y : Plant characteristics  : Growth constant  : Reciprocal of Y when t =  Y0 : Y at time = 0

  29. PLANT GROWTH MODELS • RICHARDS MODEL Y = Y0 / { ( Y0) + [ 1 - ( Y0 )] e-m t }1/ t : Time Y : Plant characteristics  : Growth constant  : Reciprocal of Y when t =  Y0 : Y at time = 0  : For logistic model,  =1

  30. Comparison of regression curves to the experimental data. Top fresh weight of cabbage seedlings growing under various day/night temperatures was used as an example.

  31. GROWTH MODEL PARAMETERS

  32. GROWTH MODEL PARAMETERS

  33. RELATIVE GROWTH RATE, RGR • LOGISTIC MODEL • RICHARDS MODEL

  34. Predicted relative growth rate of cabbage seedling growing under 5 different day/night temperatures using the logistic model.

  35. Comparison of calculated top fresh weight of cabbage, amaranth and kale seedlings growing at 25/200C.

  36. Comparison of calculated relative growth rate (RGR) of cabbage, amaranth and kale seedlings growing at 25/200C.

  37. SEEDLING 3-D RECONSTRUCTION • ARTIFICIAL WIRE MODEL

  38. SEEDLING 3-D RECONSTRUCTION • CABBAGE SEEDLING

  39. CONCLUSIONS • A non-destructive machine vision system was successfully developed for the measurement of vegetable seedling characteristics. A new algorithm for the determination of seedling nodes was implemented. • 3-dimension reconstruction of seedling architecture can be achieved with the nodal coordinates determined with the machine vision system. • Growth responses of cabbage, kale and amaranth seedlings under various temperature conditions were measured and compared. • The dynamic growth responses of selected vegetable seedlings were analyzed with logistic and Richards growth model and the relative growth rates of the seedlings under various conditions were calculated.

  40. FUTURE DEVELOPMENT • Measurement under natural lighting • Leaf area index (LAI) determination • Extraction of information from serial images • Modification of the current growth model • Application of geometrical modeling in seedling 3D reconstruction

  41. THANK YOU 謝 謝

More Related