Image analysis as a potential tool for marker-assisted selection

다국어 초록 (Multilingual Abstract)

The recent rapid changes in climate due to global warming have increased the frequency of severe natural disasters. Such disasters easily damage the fruits with large weight and volume, inflicting a great loss on the farms. Although the central and regional governments have persuaded farm owners to obtain the Crop Yield and Revenue Insurance, the lack of objec- tive criteria of damage analysis have often prevented an actual compensation. It has also been difficult to attain an accurate statistics of the national fruit production in South Korea, as the data collection through interviews and sample analyses was based on the manpower at the city and county agricultural technology centers. This study developed a deep learning model of citrus fruit detection to be used in the yield estimation and damage analysis for the Crop Yield and Revenue Insurance. The model was based on the YOLOv5 algorithm, which allows the fruit number to be estimated using images. The model showed an outstanding detection performance at AP50 0.817. This image-based deep learning model can also be widely applied in breeding. Notably, in breeding programs focused on increasing the production, the image-based high-throughput phenotyping could readily determine the fruit production per line. In the future, models for the detection of other fruit crops, including apples, and a smartphone application for the Crop Yield and Revenue Insurance and fruit production estimation will be developed.

참고문헌 (Reference)

1 이용환 ; 김영섭, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험" 한국반도체디스플레이기술학회 19 (19): 85-92, 2020

2 Hui J, "mAP (mean Average Precision) for object detection"

3 Redmon J, "You Only Look Once: Unified, Real-Time Object Detection" 779-788, 2016

4 Ultralytics, "YOLOv5"

5 Bresilla K, "Single-shot convolution neural networks for real-time fruit detection within the tree" 10 : 611-, 2019

6 Jo YW, "Recognizing transportation vulnerable using deep neural network based on object detection" 1402-1403, 2020

7 Tao Y, "Rapid detection of fruits in orchard scene based on deep neural network" 2018

8 Kim CR, "Multi-object tracking system for disaster context-aware using deep learning" The Korean Institute of Broadcast and Media Engineers 697-700, 2020

9 Maheswari P, "Intelligent fruit yield estimation for orchards using deep learning based semantic segmentation techniques—a review" 12 : 684328-, 2021

10 Bargoti S, "Image segmentation for fruit detection and yield estimation in apple orchards" 34 : 1039-1060, 2017

11 González-Araya MC, "Handbook of operations research in agriculture and the agri-food industry" Springer 79-105, 2015

12 Peng H, "General improved SSD model for picking object recognition of multiple fruits in natural environment" 34 : 155-162, 2018

13 Araus JL, "Field high-throughput phenotyping: the new crop breeding frontier" 19 : 52-61, 2014

14 Kang H, "Fast implementation of real-time fruit detection in apple orchards using deep learning" 168 : 105108-, 2019

15 Mohammad Kamran Omari ; 이재영 ; Mohammad Akbar Faqeerzada ; Rahul Joshi ; 박은수 ; 조병관, "Digital image-based plant phenotyping: a review" 농업과학연구소 47 (47): 119-130, 2020

16 Koirala A, "Deep learning –method overview and review of use for fruit detection and yield estimation" 162 : 219-234, 2019

17 Ko SS, "Concerns about overproduction of Citrus fruits in Jeju"

18 Mochida K, "Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective" 8 : giy153-, 2018

19 Wang Q, "Automated crop yield estimation for apple orchards" 81 : 745-748, 2012

20 Jang WJ, "All about data analysis, Vol 1" ILIFO 339-341, 2021

21 Korea Rural Economic Institute, "Agricultural observation information for Citrus (Nov)"

22 Korean Statistical Information Service, "Agricultural area and crop production survey"

23 Yan B, "A real-time apple targets detection method for picking robot based on improved YOLOv5" 13 : 1619-, 2021