Abstract
Accurate mass estimation of table-top grown strawberries under field conditions remains challenging due to frequent occlusions and pose variations. This study proposes a vision-based pipeline integrating RGB-D sensing and deep learning to enable non-destructive, real-time and online mass estimation. The method employed YOLOv8-Seg for instance segmentation, Cycle-consistent generative adversarial network (CycleGAN) for occluded region completion, and tilt-angle correction to refine frontal projection area calculations. A polynomial regression model then mapped the geometric features to mass. Experiments demonstrated mean mass estimation errors of 8.11% for isolated strawberries and 10.47% for occluded cases. CycleGAN outperformed large mask inpainting (LaMa) model in occlusion recovery, achieving superior pixel area ratios (PAR) (mean: 0.978 vs. 1.112) and higher intersection over union (IoU) scores (92.3% vs. 47.7% in the [0.9-1] range). This approach addresses critical limitations of traditional methods, offering a robust solution for automated harvesting and yield monitoring with complex occlusion patterns.
Abstract (translated)
在田间条件下，准确估算桌面栽培的草莓的质量仍然具有挑战性，主要是由于频繁遮挡和姿态变化。本研究提出了一种基于视觉的流水线方法，该方法结合了RGB-D传感技术和深度学习技术，以实现非破坏性的、实时在线质量估计。 所采用的方法包括使用YOLOv8-Seg进行实例分割，使用循环一致生成对抗网络（CycleGAN）完成遮挡区域，并通过调整倾斜角度来修正正面投影面积计算。然后，多项式回归模型将几何特征映射到质量上。 实验表明，在孤立草莓的情况下，平均质量估计误差为8.11%，在有遮挡的情况下的误差为10.47%。CycleGAN在遮挡恢复方面优于大型掩码插补（LaMa）模型，实现了更优的像素面积比（PAR）（均值：0.978 vs 1.112）和更高的交并比（IoU）分数（范围[0.9-1]内的CycleGAN为92.3%，而LaMa为47.7%）。这种方法解决了传统方法的关键限制，为自动化收获和产量监测提供了复杂遮挡模式下的稳健解决方案。
URL
https://arxiv.org/abs/2507.23487
