Multi-objective RGB-D fusion network for non-destructive strawberry trait assessment.

Abstract

Growing consumer demand for high-quality strawberries has highlighted the need for accurate, efficient, and non-destructive methods to assess key postharvest quality traits, such as weight, size uniformity, and quantity. This study proposes a multi-objective learning algorithm that leverages RGB-D multimodal information to estimate these quality metrics. The algorithm develops a fusion expert network architecture that maximizes the use of multimodal features while preserving the distinct details of each modality. Additionally, a novel Heritable Loss function is implemented to reduce redundancy and enhance model performance. Experimental results show that the coefficient of determination (R²) values ​​for weight, size uniformity and number are 0.94, 0.90 and 0.95 respectively. Ablation studies demonstrate the advantage of the architecture in multimodal, multi-task prediction accuracy. Compared to single-modality models, non-fusion branch networks, and attention-enhanced fusion models, our approach achieves enhanced performance across multi-task learning scenarios, providing more precise data for trait assessment and precision strawberry applications.

Plant phenotyping relevance

RGB-D画像を用いてイチゴ果実の重量・サイズ均一性・個数を推定する融合ネットワークの開発と性能評価が研究の中心であり、植物器官の形質取得手法に該当する。

Code and data availability

The paper's RGB-D strawberry dataset (3740 samples), trained model, and code are not publicly deposited. The data availability statement only offers supplementary material and directs inquiries to the corresponding author, so no public, paper-specific qualifying asset exists. The Intel RealSense URL is the sensor's own

No evidence-backed public reproduction asset is currently recorded.