3D Reconstruction of Plant Using Close Range Photogrammetry For Leaf Type Variations

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 1

3D reconstruction of Plant Using Close Range

Photogrammetry for Leaf Type Variations


Diaz Habib Dananta, Andri Prima Nugroho*, Ardyan Widyanto Putro, M. Akbar Andi Arief, and Lilik
Sutiarso
Smart Agriculture Research Group, Dept. of Agricultural and Biosystem Engineering, Faculty of Agricultural Technology,
1

Universitas Gadjah Mada, INDONESIA

*Corresponding Author: andrew@ugm.ac.id | Instagram: @smartagri.ugm | website: smart-farming.tp.ugm.ac.id

Introduction Result & Discussion


(a) (b) (c)
3-dimensional reconstruction is not only used to measure the
height, weight, and volume of plants but also useful to visualize
plant objects in a virtually 3-dimensional form.

3 dimensional plants are very important for monitoring


systems, visual 3 dimensional obtained are used to measure Figure 3. 3 dimensional reconstruction (a)Lettuce; (b) Bok choy;
the plants without damaging the plants. (c) Cabbage.

The objective of this study is to (a) (c)


understand the application of 3D
reconstruction of plants using close-
range photogrammetry method for
leaf type variation

(b)
Materials & Methods

(a) (b)

Figure 3. Comparison of the actual volume and estimated


volume (a)Lettuce; (b) Bok choy; (c) Cabbage.
Table 1. RMSE and MAPE
Bok
Lettuce Cabbage
Figure 1. (a) camera navigator; (b) Measure estimate volume by choy
3DFZephyr. RSME (cm3) 25,39 31,52 97,02
Canon 700D camera are used to shoot with 360degree rotation and to
MAPE (%) 122,08 208,17 13,58
obtain 3-dimensional visuals using Asus TUF with AMD Ryzen™ 7 4800H. When viewed using naked eye on cabbage plants have the least difference
The 3-dimensional visuals are obtained by processing images using than the other – on the other hand, using RMSE on cabbage showed the
3DFZephyr Pro biggest error with 97,02 cm3. Meanwhile, the smallest error which showed
Furthermore, the data obtained from extracting a surface is calculated with RMSE is lettuce with 25,39 cm3 and followed bok choy 31,52 cm3. The
volume to present the estimated volume lowest MAPE is cabbage with an error of 13.58%, the biggest MAPE is bok
choy which is 208.17% and for lettuce is 122.08%.

Based on MAPE and RMSE values the accuracy of the close-range


photogrammetry method tends to be low because the original leaves that
have abstract and overlapping shapes cause some parts of the plant to be
not fully reconstructed.

Conclusion and Future Works


implements 3D reconstruction using the close-range
photogrammetry method for leaf type variation. Use DLSR
cameras for 360-degree rotational shooting using the 3DF Zephyr
Pro for 3-dimensional reconstruction. The 3-dimensional visual
results has presented the shape of the real plant

In the future 3D reconstruction be able to do robotic


harvestmen, precision spraying effciently
This research is supported by:

Figure 2. Flowchart of Developed System

International Collaborative Research on Sustainable Agricultural Development Goals – Kyushu University Japan 2021

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy