Soluble solids content is the most important attribute related to the quality and price of apples. The objective of this study was to detect the soluble solids content (SSC) in ‘Fuji’ apples using hyperspectral imaging combined with a deep learning algorithm. The hyperspectral images of 570 apple samples were obtained and the whole region of apple sample hyperspectral data was collected and preprocessed. In addition, a method involving multi-attention convolutional neural network (MA-CNN) is proposed, which extracts spectral and spatial features from hyperspectral images by embedding channel attention (CA) and spatial attention (SA) modules in a convolutional neural network. The CA and SA modules help the network adaptively focus on important spectral–spatial features while reducing the interference of redundant information. Additionally, the Bayesian optimization algorithm (BOA) is used for model hyperparameter optimization. A comprehensive evaluation is conducted by comparing the proposed model with CA-CNN models, SA-CNN, and the current mainstream models. Furthermore, the best prediction performances for detecting SSC in apple samples were obtained from the MA-CNN model, with an ${\mathrm{R}}_{\mathrm{p}}^2$ value of 0.9602 and an RMSEP value of 0.0612 °Brix. The results of this study indicated that the MA-CNN algorithm combined with hyperspectral imaging technology can be used as an effective method for rapid detection of apple quality parameters.

To achieve efficient vineyard grape picking, a vision-based information processing framework integrating two-stage segmentation with morphological perception is proposed. In the first stage, an improved YOLOv8s-seg model is employed for coarse segmentation, incorporating two key enhancements: first, a dynamic deformation feature aggregation module (DDFAM), which facilitates the extraction of complex structural and morphological features; and second, an efficient asymmetric decoupled head (EADHead), which improves boundary awareness while reducing parameter redundancy. Compared with mainstream segmentation models, the improved model achieves superior performance, attaining the highest mAP@0.5 of 86.75%, a lightweight structure with 10.34 M parameters, and a real-time inference speed of 10.02 ms per image. In the second stage, the fine segmentation of fruit stems is performed using an improved OTSU thresholding algorithm, which is applied to a single-channel image derived from the hue component of the HSV color space, thereby enhancing robustness under complex lighting conditions. Morphological features extracted from the preprocessed fruit stem, including centroid coordinates and a skeleton constructed via medial axis transform (MAT), are further utilized to establish the spatial relationships with a picking point and cutting axis. The visualization analysis confirms the high feasibility and adaptability of the proposed framework, providing essential technical support for the automation of grape harvesting.

In recent years, heavy metal contamination in agricultural products has become a growing concern in the field of food safety. Copper (Cu) stress in crops not only leads to significant reductions in both yield and quality but also poses potential health risks to humans. This study proposes an efficient and precise non-destructive detection method for Cu stress in oilseed rape, which is based on hyperspectral false-color image construction using principal component analysis (PCA). By comprehensively capturing the spectral representation of oilseed rape plants, both the one-dimensional (1D) spectral sequence and spatial image data were utilized for multi-class classification. The classification performance of models based on 1D spectral sequences was compared from two perspectives: first, between machine learning and deep learning methods (best accuracy: 93.49% vs. 96.69%); and second, between shallow and deep convolutional neural networks (CNNs) (best accuracy: 95.15% vs. 96.69%). For spatial image data, deep residual networks were employed to evaluate the effectiveness of visible-light and false-color images. The RegNet architecture was chosen for its flexible parameterization and proven effectiveness in extracting multi-scale features from hyperspectral false-color images. This flexibility enabled RegNetX-6.4GF to achieve optimal performance on the dataset constructed from three types of false-color images, with the model reaching a Macro-Precision, Macro-Recall, Macro-F₁, and Accuracy of 98.17%, 98.15%, 98.15%, and 98.15%, respectively. Furthermore, Grad-CAM visualizations revealed that latent physiological changes in plants under heavy metal stress guided feature learning within CNNs, and demonstrated the effectiveness of false-color image construction in extracting discriminative features. Overall, the proposed technique can be integrated into portable hyperspectral imaging devices, enabling real-time and non-destructive detection of heavy metal stress in modern agricultural practices.