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 quantity 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.
Cheng, Zhenzhen & Cheng, Yifan & Miao, Bailing & Fang, Tingting & Gong, Shoufu. (2025). Multi-objective RGB-D fusion network for non-destructive strawberry trait assessment. Frontiers in Plant Science. 16. 10.3389/fpls.2025.1564301.
Source: Research Gate