Smart Harvesting Decision System for Date Fruit Based on Fruit Detection and Maturity Analysis Using YOLO and K-Means Segmentation

Abstract

The date palm (Phoenix dactylifera) is a large palm with exotic fruits measuring up to 30 meters in height. The date palm produces fruits rich in nutrients provides a multitude of secondary products, and generates income necessary for the survival of a large population. Losses attributed to manual harvesting encompass both quantitative and qualitative aspects, with the latter measured through attributes such as appearance, taste, texture, and nutritional or economic value. These losses, in terms of both quantity and quality, are influenced by practices across all phases of the harvesting process. On the other hand, the risks of work accidents are high because of the length of the date palms. To reduce the losses and reduce risks, it is essential to propose a decision system for robotic harvesting to help farmers overcome the constraints during the harvest. The assessment of quality and maturity levels in various agricultural products is heavily reliant on the crucial attribute of color. In this study, an intelligent harvesting decision system is proposed to estimate the level of maturity based on deep learning, K-means clustering, and color analysis. The decision system’s performance is assessed using the dataset of date fruit in the orchard and various metrics. Based on the experimental results, the proposed approach has been deemed effective and the system demonstrates a high level of accuracy. The system can detect, locate, and analyze the maturity stage to make a harvest decision.