Introduction: In the natural harvesting conditions of cherry tomatoes, the robotic vision for harvesting faces challenges such as lighting, overlapping, and occlusion among various environmental factors. To ensure accuracy and efficiency in detecting cherry tomatoes in complex environments, the study proposes a precise, realtime, and robust target detection algorithm: the CTDA model, to support robotic harvesting operations in unstructured environments.Methods: The model, based on YOLOv8, introduces a lightweight downsampling method to restructure the backbone network, incorporating adaptive weights and receptive field spatial characteristics to ensure that low-dimensional small target features are not completely lost. By using softpool to replace maxpool in SPPF, a new SPPFS is constructed, achieving efficient feature utilization and richer multi-scale feature fusion. Additionally, by incorporating a dynamic head driven by the attention mechanism, the recognition precision of cherry tomatoes in complex scenarios is enhanced through more effective feature capture across different scales.Results: CTDA demonstrates good adaptability and robustness in complex scenarios. Its detection accuracy reaches 94.3%, with recall and average precision of 91.5% and 95.3%, respectively, while achieving a mAP@0.5:0.95 of 76.5% and an FPS of 154.1 frames per second. Compared to YOLOv8, it improves mAP by 2.9% while maintaining detection speed, with a model size of 6.7M.Discussion: Experimental results validate the effectiveness of the CTDA model in cherry tomato detection under complex environments. While improving detection accuracy, the model also enhances adaptability to lighting variations, occlusion, and dense small target scenarios, and can be deployed on edge devices for rapid detection, providing strong support for automated cherry tomato picking.

The adoption of grafting machines has become an essential trend in the advancement of the vegetable nursery industry, driven by the aging population and the rapid growth of the vegetable sector. Domestic and foreign research organizations have designed various types of vegetable grafting devices for the huge nursery market. However, most of the machines developed and designed at home and abroad are now semi-automated and are thus highly susceptible to damaging the stems of the seedlings during operation. Therefore, in order to realize the complete automation of the grafting operation and improve the grafting survival rate and quality, in this paper, eggplant hole tray seedlings were grafted as the object, and the cutting mechanism, the integrated mechanism of clamping and fitting, and the wrapping mechanism were structured on the basis of the affixing method. The transition conversion from semi-automatic to fully automatic was realized. And the rationality of the design was verified via the cutting test and the clamping characteristic test, which maximized the fit rate between the cutting surface of the rootstock and the scion seedling and maximized the protection of the grafted seedling from damage in the clamping process. Finally, the device was tested using Torubam rootstock and a Nova 101 tomato scion. The results showed that the optimal cutting angles were 35° and 30° for rootstock and scion, respectively, and that the lengths of the cutting surfaces were 11.28 ± 0.18 mm and 11.43 ± 0.14 mm. The grafting efficiency of the machine was up to 700 grafts per hour, with an average grafting success rate of up to 95% and zero stem damage to the seedlings. The experiments proved that the structure design of the machine is reasonable, and it can fully improve the grafting efficiency and quality. Meanwhile, the research findings can provide a theoretical basis for the application of the latter in the field of plant grafting. The research results can effectively alleviate the dependence on manual labor in the nursery industry and further liberate the labor force.

To produce a firm and cohesive root plug to promote automated transplanting of nursery-grown seedlings, hydrolyzed soy protein-modified urea–formaldehyde (H-UF) resins were used to bind renewable substrate [mixture of coconut ( Cocos nucifera ) coir dust, coconut fiber, organic manure, perlite, vermiculite]. The resulting substrate block showed high density and nutrient concentrations in the peripheral portion and relatively low density and nutrient levels in the center. The porosity of the H-UF/substrate block was slightly lower than that of standard substrate. The electrical conductivity and pH were beneficial for germination and early seedling development. The modified resins in the substrate block existed in the form of spheres that adhered to each other and formed a porous structure from nano- to micrometer scale. In particular, the H-UF/substrate block increased the seedling height, stem diameter, root length, and leaf area of ‘Sujiao No. 5’ pepper ( Capsicum annum ) seedlings by 56.07%, 43.33%, 1.33%, and 89.63%, respectively, compared with those of seedlings grown in substrate without H-UF resin. The contents of nitrogen, phosphorus, and potassium in the shoot and root of pepper seedlings grown in H-UF/substrate blocks were enhanced by 39% to 69% compared with those of seedlings grown in standard substrate. The compressive strength of the H-UF/substrate block was 3.6-fold higher than that of substrate when 50% resin was added to the substrate. The results indicated that a combination of the substrate with the modified resin was suitable as a growth substrate for nursery production of pepper seedling plugs.

Vacuum saccharification significantly affected the flavor and color of preserved French plums. However, the correlation between color, flavor, and metabolites remains unclear. Metabolites contribute significantly to enhancing the taste and overall quality of preserved French plums. This study aimed to investigate the distinctive metabolites in samples from various stages of the processing of preserved French plums. The PCF4 exhibited the highest appearance, overall taste, and chroma. Furthermore, utilizing UPLC and ESI-Q TRAP-MS/MS, a comprehensive examination of the metabolome in the processing of preserved French plums was conducted. A total of 1776 metabolites were analyzed. Using WGCNA, we explored metabolites associated with sensory features through 10 modules. Based on this, building the correlation of modules and objective quantification metrics yielded three key modules. After screening for 151 differentiated metabolites, amino acids, and their derivatives, phenolic acids, flavonoids, organic acids, and other groups were identified as key differentiators. The response of differential metabolites to stress influenced the taste and color properties of preserved prunes. Based on these analyses, six important metabolic pathways were identified. This study identified changes in the sensory properties of sugar-stained preserved prunes and their association with metabolite composition, providing a scientific basis for future work to improve the quality of prune processing.

This study explored the protective effects of antifreeze glycopeptide and alginate on the quality of −18 °C frozen lamb meatballs across various storage periods. Methods: Measurements of volatile salt nitrogen (TVB-N), thiobarbituric acid (TBARS), water retention, water distribution, microstructure, and metabolite changes were taken in the lamb meatballs. Results: The results showed that the addition of antifreeze glycopeptides (AFGs) significantly preserved the quality characteristics of lamb meatballs. In particular, the 0.30% antifreeze glycopeptide demonstrated the strongest protective effect on water retention and metabolites during freezing. The ice crystal area within the microstructure of lamb meatballs with added antifreeze glycopeptides was markedly reduced compared to the others after 14 days of freezing (p < 0.05). Additionally, AFGs lessened the lipid oxidation reaction and prolonged the oxidation time of lamb after 28 days of freezing. Conclusion: In summary, AFGs beneficially affected the quality of frozen lamb meatballs and are a potential, safe, and efficient cryoprotectant.