Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Colored Point Clouds
This addresses the challenge of automated fruit monitoring for agricultural production, though it appears incremental as it builds on existing 3D segmentation and re-identification techniques.
The paper tackles the problem of monitoring fruits over time in orchards by proposing a method for 3D instance segmentation and re-identification using colored point clouds, achieving improved performance over existing methods on datasets of strawberries and apples.
Accurate and consistent fruit monitoring over time is a key step toward automated agricultural production systems. However, this task is inherently difficult due to variations in fruit size, shape, occlusion, orientation, and the dynamic nature of orchards where fruits may appear or disappear between observations. In this article, we propose a novel method for fruit instance segmentation and re-identification on 3D terrestrial point clouds collected over time. Our approach directly operates on dense colored point clouds, capturing fine-grained 3D spatial detail. We segment individual fruits using a learning-based instance segmentation method applied directly to the point cloud. For each segmented fruit, we extract a compact and discriminative descriptor using a 3D sparse convolutional neural network. To track fruits across different times, we introduce an attention-based matching network that associates fruits with their counterparts from previous sessions. Matching is performed using a probabilistic assignment scheme, selecting the most likely associations across time. We evaluate our approach on real-world datasets of strawberries and apples, demonstrating that it outperforms existing methods in both instance segmentation and temporal re-identification, enabling robust and precise fruit monitoring across complex and dynamic orchard environments.