Development of Potato Yield Monitoring System Using Machine Vision

Purpose The study is aimed at investigating the feasibility of using machine vision for potato yield monitoring systems. Therefore, it is necessary to develop experimental-scale hardware and necessary algorithms for monitoring systems and to evaluate the system performance. Methods The experimental...

Full description

Saved in:
Bibliographic Details
Published inJournal of Biosystems Engineering, 45(4) Vol. 45; no. 4; pp. 282 - 290
Main Authors Lee, Young-Joo, Shin, Beom-Soo
Format Journal Article
LanguageEnglish
Published Singapore Springer Singapore 01.12.2020
한국농업기계학회
Subjects
Agriculture
Control
Engineering
Environmental Engineering/Biotechnology
Mechatronics
Original Article
Robotics
농학
Yield monitoring
Potato
Image processing
Machine vision
Online AccessGet full text

Cover

More Information
Summary:Purpose The study is aimed at investigating the feasibility of using machine vision for potato yield monitoring systems. Therefore, it is necessary to develop experimental-scale hardware and necessary algorithms for monitoring systems and to evaluate the system performance. Methods The experimental apparatus consisted of a digital camera with an auto-iris lens, a gimbal system, a camera trigger device on a driving wheel, RTK-GPS, and a laptop computer with MATLAB installed. In a potato farm, the images of potatoes taken out of soil and scattered on the soil surface were acquired at harvest time, and the estimated mass of the potatoes was obtained through image processing and a mass estimation algorithm. Actual masses of the potatoes were measured and recorded for each specific divided region in the field to evaluate system performance. Results The algorithm for distinguishing between potato and soil noise worked well. It required 103.4 ms to complete the image processing on a single-frame image. The integrated algorithm required 344.0 ms to output the results, such as the estimated mass with GPS location information, from an acquired image. The system performance evaluation results showed that the yield estimation error was 268.60 g and 15.33% in root mean square deviation (RMSD) and percentage error, respectively. Conclusions The monitoring system used in this study is highly significant in the sense that it is possible to make a relative comparison of variations in the field.
ISSN:1738-1266
2234-1862
DOI:10.1007/s42853-020-00069-4