Classification of soybean pods using the deep learning techniques

Authors

DOI:

https://doi.org/10.13083/reveng.v30i1.15436

Keywords:

Artificial intelligence, Digital agriculture, Machine learning, Productivity estimation

Abstract

Crop productivity estimate aims at the economic definitions about crop, agricultural management, and land use, among others. However, it is common to observe the use of visual methods to estimate the productivity of the soybean crop through the classification of pods, resulting in a slow, costly method besides being susceptible to human errors. Thus, the objective of this work was to carry out the training of two deep learning methods to classify soybean pods according to the number of grains based on images obtained using a smartphone. Data collection was carried out at the Federal University of Viçosa (UFV). Data consisted of capturing images from a smartphone and training two deep learning models: Mask R-CNN and YOLOv4. To capture the images, the soybean pods were pulled from the plants and placed in a white-bottom container. This procedure occurred for each plant collected. Both models tended towards a better classification for the two- and three-grain pods, reaching a value of 90% for the F1 score metric. This fact may have occurred because of the greater amount of these two types of pods present in the chosen cultivars. Finally, the potential of using deep learning to classify soybean pods based on the number of grains was observed.

Downloads

Download data is not yet available.

References

AFONSO, M. et al. Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning. Frontiers in Plant Science, v. 11, p. 1759, 19 nov. 2020.

ALVES, G. R. et al. Estimativa da produtividade de soja com redes neurais artificiais. Acta Scientiarum - Agronomy, v. 40, n. 1, p. 1-9, 2018.

CHAN, M.; WEI, F.; MOLIN, P. Soybean Yield Estimation and Its Components?: A Linear Regression Approach. n. Ml, 2020.

DAVIS, C. C. et al. A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN. Frontiers in Plant Science, v. 11, n. July, p. 1-13, 2020.

DE CARVALHO, O. L. F. et al. Instance segmentation for large, multi-channel remote sensing imagery using mask-RCNN and a mosaicking approach. Remote Sensing, v. 13, n. 1, p. 1-24, 2021.

DUTTA, A.; ZISSERMAN, A. The VIA annotation software for images, audio, and video. MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia, p. 2276-2279, 2019.

ETIENNE, A. et al. Deep learning-based object detection system for identifying weeds using uas imagery. Remote Sensing, v. 13, n. 24, p. 1-22, 2021.

GANESH, P. et al. Deep Orange: Mask R-CNN based Orange Detection and Segmentation. IFAC-PapersOnLine, v. 52, n. 30, p. 70-75, 2019.

HE, K. et al. Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence, v. 42, n. 2, p. 386-397, 2020.

HUANG, Z. et al. DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection. Information Sciences, v. 522, p. 241-258, 2020.

LEE, J. et al. Artificial intelligence approach for tomato detection and mass estimation in precision agriculture. Sustainability (Switzerland), v. 12, n. 21, p. 1-15, 2020.

MAUAD, M.; BERTOLOZE SILVA, T. L.; ALMEIDA NETO, A. I.; ABREU, V. G. Influência da densidade de semeadura sobre características agronômicas na cultura da soja. Agrarian, [S. l.], v. 3, n. 9, p. 175-181, 2011.

MAZZIA, V., Khaliq, A., Salvetti, F., & Chiaberge, M. (2020). Real-time apple detection system using embedded systems with hardware accelerators: An edge AI application. IEEE Access, 8, 9102-9114.

MEKHALFI, M. L. et al. Detecting crop circles in google earth images with mask R-CNN and YOLOv3. Applied Sciences (Switzerland), v. 11, n. 5, p. 1-12, 2021.

MILLER, J. J. et al. Characterizing soybean vigor and productivity using multiple crop canopy sensor readings. Field Crops Research, v. 216, n. November 2017, p. 22-31, 2018.

NGUGI, L. C.; ABELWAHAB, M.; ABO-ZAHHAD, M. Tomato leaf segmentation algorithms for mobile phone applications using deep learning. Computers and Electronics in Agriculture, v. 178, n. September, p. 105788, 2020.

RAMOS, P. J. et al. Automatic fruit count on coffee branches using computer vision. Computers and Electronics in Agriculture, v. 137, p. 9-22, 2017.

REDMON, J. et al. You only look once: Unified, real-time object detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, v. 2016- Decem, p. 779-788, 2016.

TEDESCO-OLIVEIRA, D. et al. Convolutional neural networks in predicting cotton yield from images of commercial fields. Computers and Electronics in Agriculture, v. 171, n. October 2019, p. 105307, 2020.

TZUTALIN. LabelImg. Git code (2015). https://github.com/tzutalin/labelImg

UZAL, L. C. et al. Seed-per-pod estimation for plant breeding using deep learning. Computers and Electronics in Agriculture, v. 150, n. April, p. 196-204, 2018.

VALICHARLA, S. K. Weed Recognition in Agriculture?: A Mask R-CNN Approach Weed Recognition in Agriculture?: A Mask R-CNN Approach. 2021.

XU, B. et al. Automated cattle counting using Mask R-CNN in quadcopter vision system. Computers and Electronics in Agriculture, v. 171, n. October 2019, p. 105300, 2020.

YU, Y. et al. Fruit detection for strawberry harvesting robot in non-structural environment based on Mask-RCNN. Computers and Electronics in Agriculture, v. 163, n. June, p. 104846, 2019.

ZHU, S. et al. Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network. Sensors 2019, Vol. 19, Page 4065, v. 19, n. 19, p. 4065, 20 set. 2019.

Downloads

Published

2023-06-20

How to Cite

Bandeira, P. M. da C., Villar, F. M. de M., Bandeira, P. P. da C., & Dias, I. A. (2023). Classification of soybean pods using the deep learning techniques . Engineering in Agriculture, 31(Contínua), 98–105. https://doi.org/10.13083/reveng.v30i1.15436

Issue

Section

Articles