Grape Berry Number Prediction – 茅・朱・Buayai研究室

Abstract

The advent of smart agriculture has revolutionized and streamlined various manual tasks in grape cultivation, one of which is berry thinning. This task necessitates experienced farmers to selectively remove a specific number of berries from the working bunch, as guided by the remaining number of berries in the bunch. In response, this paper introduces a novel real-time edge computing application that automates the process of counting the berries in a working bunch using a single 2D image. The proposed application employs YOLOv5-based object detection techniques [1] to distinguish each working bunch and the visible and slightly occluded berries contained therein. The key contribution of this paper is to accurately predict the number of berries in the whole bunches including those not visible in a 2D image by harnessing the output from object detection to devise features based solely on bounding box information. In addition, the feature set is optimized by employing a wrapper feature selection method [2], in consideration of the limitations of edge computing devices. Furthermore, the proposed approach has been successfully implemented and tested on an Android smartphone without the need for an internet connection. The overall computation time per image stands at an average of 0.333 seconds, confirming its potential for real-world application.

Research Background

Appearance of the product of table grapes directly influences the quality. (High Quality = High Selling Price)

High-quality table grape cultivation involves berry thinning tasks.

Berry Thinning Task

Figure 1: Process of berry thinning task.

Publications

P. Buayai, K. R. Saikaew, and X. Mao, “End-to-end automatic berry counting for table grape thinning,” IEEE Access, vol. 9, pp. 4829-4842, 2020, doi: https://doi.org/10.1109/ACCESS.2020.3048374.
W. Yan San, B. Prawit, N. Hiromitsu, M. Koji, K. Latifah Munirah, and M. Xiaoyang, “End-to-end lightweight berry number prediction for supporting table grape cultivation,” Computers and Electronics in Agriculture, vol. 213, p. 108203, 2023, doi: https://doi.org/10.1016/j.compag.2023.108203.

Reference

[1] G. Jocher et al., “ultralytics/yolov5: v6.0 – YOLOv5n ‘Nano’ models, Roboflow integration, TensorFlow export, OpenCV DNN support,” doi: 10.5281/zenodo.5563715.

[2] R. Kohavi and G. H. John, “Wrappers for feature subset selection,” Artificial intelligence, vol. 97, no. 1-2, pp. 273-324, 1997.

Patent