RGB-Based Non-Destructive Measurement of Greenhouse Tomato Fruit Traits Using High-Fidelity Segmentation

Greenhouse tomato production requires frequent, fruit-level information on maturity, quality, and yield, yet conventional assessment is often destructive, labor-intensive, or dependent on costly sensing hardware. This study presents a lightweight RGB-based framework for non-destructive measurement of greenhouse tomato fruits under foliage occlusion, uneven illumination, and fruit overlap. By improving instance segmentation while constraining computational cost, the framework generated cleaner fruit masks for downstream color analysis, quality inference, and single-fruit weight estimation. Compared with YOLO11n, the proposed model reduced GFLOPs from 10.2 to 8.2 and improved mask precision from 78.2% to 84.6% and mask F1-score from 82.8% to 85.2%, while box recall, mask recall, and IoU showed small trade-offs. Segmentation remained comparatively stable across maturity stages. RGB features from the refined masks were most useful for vitamin C and soluble solids, supporting rapid, indirect quality screening. In parallel, disk-based geometric reconstruction from fruit contours estimated single-fruit weight with MAE values of 1.69 g·fruit−1 for large-fruited tomatoes and 1.29 g·fruit−1 for cherry tomatoes. The improved masks enhanced single-fruit weight estimation, whereas biochemical quality prediction remained an indirect, trait-dependent estimation that may partly reflect maturity-related color variation rather than direct measurement. Overall, the results demonstrate that improving segmentation fidelity can strengthen downstream trait estimation without increasing sensing complexity, providing a practical RGB-based solution for automated greenhouse tomato phenotyping, while also highlighting the need for standardized imaging and cautious interpretation of biochemical trait predictions.