Horticulturae

Automated cucumber harvesting requires a perception system that can detect fruit, assess ripeness and localize the peduncle for cutting under real commercial greenhouse conditions. This study proposes an RGB-D perception framework combining YOLOv8n object detection with depth-based geometric estimation. The framework was evaluated on data collected in commercial greenhouses with dense, continuously varying occlusion, variable illumination and multiple co-visible fruits at different maturity stages. Detections were assigned to five operational classes: ripe, unripe, flagged (non-marketable due to overripeness or deformity), obstructed and peduncle. The detector achieved an overall mAP50 of 0.568, but appearance-based ripeness classification proved unreliable. Confusion concentrated along two boundaries: a continuous, judgment-based occlusion criterion and an absolute length threshold that RGB appearance cannot directly resolve. Depth-based length estimation, by contrast, achieved an MAE of 0.72 cm (RMSE = 1.15 cm, MAPE = 4.04%) directly in the greenhouse. Applying the ripeness length threshold to the estimated lengths misclassified 6.4% of fruits at the RIPE/UNRIPE boundary on the dimensional validation set, indicating that length-based ripeness assignment is feasible. Diameter estimation was markedly less accurate (R² = 0.49) and is not proposed as a validated measurement for grading or yield estimation. The framework also estimated candidate 3D cutting points that remained spatially consistent across frames; cutting accuracy requires future robotic validation. These results suggest that, in complex greenhouse environments, ripeness decisions of cucumber should rely on depth-based geometric measurement, with object detection used primarily for fruit and peduncle localization. Combining visual detection with quantitative measurement therefore appears to be a promising basis for robotic cucumber harvesting.

The diagnosis of leaf diseases in medicinal and non-mainstream plants is often hindered by the scarcity of labeled samples, whereas existing deep learning methods generally rely on large-scale labeled datasets. Prototype-based few-shot methods are constrained by the limited number of support samples and fine-grained visual similarities among categories, which can result in unstable class representations. To address these limitations, LUCID, a training-free few-shot framework, is proposed for diagnosing leaf diseases in medicinal and non-mainstream plants. The framework constructs category-level visual prototypes from a small number of support images and integrates them with structured symptom knowledge to establish complementary discriminative criteria. LUCID employs a vision-dominated confidence-gated fusion mechanism that adjusts the knowledge correction weights according to the relative discriminative confidence of the visual and knowledge branches. For candidate categories that remain difficult to distinguish after the visual and knowledge scores have been fused, Top-2 difference-driven re-examination is further performed to incorporate additional discriminative information concerning key symptom differences. The prediction ranking is then revised based on the newly incorporated information, and a concise diagnostic rationale is ultimately generated. Few-shot experiments were conducted on the Azadirachta indica leaf dataset from the publicly available AI-MedLeafX dataset, and LUCID was compared with supervised vision models, vision-language models, and other methods. The experimental results showed that LUCID achieved the best performance across all few-shot settings. In the 1-shot setting, its Accuracy and Macro-F1 exceeded those of the best-performing baseline by 15.68 and 14.22 percentage points, respectively. Beyond the primary dataset, LUCID also demonstrated consistent performance advantages on the Ocimum tenuiflorum and Ziziphus jujuba datasets, validating its ability to generalize across plant species. These results indicate that LUCID can effectively integrate limited visual evidence with structured symptom knowledge without additional training, thereby providing an accurate, generalizable, and evidence-based solution for diagnosing leaf diseases in medicinal and non-mainstream plants.

Prunus davidiana Franch. is an important wild relative of cultivated peach and a source of stress-resistance germplasm. The genetic resources of this species in Gansu Province, which spans complex topography and climatic transition zones, have long lacked systematic evaluation. Here, 110 P. davidiana accessions from Gansu Province were genotyped with 20 highly polymorphic SSR markers to assess genetic diversity and population structure and to construct DNA fingerprints. The analyzed collection showed high diversity (mean number of alleles, N_a = 22.1; expected heterozygosity, H_e = 0.945; and polymorphism information content, PIC = 0.938). Bayesian clustering and complementary ordination indicated only weak, largely continuous subdivision: although the ΔK method nominally selected four clusters, the mean silhouette coefficient was low (0.0396 at K = 2), locus-bootstrap stability was moderate to low (mean adjusted Rand index = 0.407), and the first two PCoA axes accounted for only 9.88% of the variation. Mean F_st was 0.035, and analysis of molecular variance (AMOVA) attributed 92.75% of the variation to within-individual differences. For fingerprinting, no duplicate, unresolved or near-match pairs were detected among the 5995 accession pairs, and a minimal three-locus panel (DW344741F, DW345934F, BU041198R) resolved all pairs within this collection. These results provide the first systematic characterization of the genetic diversity and population structure of P. davidiana germplasm in Gansu Province and a candidate identification tool for the analyzed collection, pending validation in independent material.