The current grading of Chinese Mitten crab relies primarily on manual observation and weighing, resulting in high labor intensity, high cost, and low efficiency. These limitations no longer meet the requirements for the rapid development of crab industry. This study utilizes computer vision and deep learning to rapidly extract physiological features including gender, carapace length and width for grading. A YOLOv5- seg model was trained with 764 RGB images and manually measured physiological traits of Chinese mitten crabs. The performance of the constructed models in recognizing genders and predicting carapace length and width was evaluated. The results demonstrate an average accuracy rate of 100% for gender recognition. The average absolute percentage error was 1.5% for measuring the carapace length and width. The results of this study may facilitate the development of non-destructive high-precision crab grading systems and devices for the aquaculture industry.

The geographical tracing of high-value salmonids is essential in mitigating food fraud and ensuring authenticity. This study combined hyperspectral imaging with elemental/isotopic profiling to reflect geographical origin information of salmonids and improve the explainability of discrimination models. Pearson correlation analysis was conducted using spectra and elements/isotopes for spectral fingerprinting, followed by developing machine/deep learning models with full spectra and extracted spectral features, respectively. The key isotopes and elements were further predicted using random forest modeling. The results indicated elements and isotopes highly correlating with spectral regions around 900, 1000, and 1200 nm, reflecting important spectral profiling of geographical origins for fresh salmonid products. Further, all discrimination models achieved acceptable overall accuracies (>65 %), with SFS-ELM achieved the highest precision (88.13 %). Key elements/isotopes were satisfactorily predicted (R² > 0.70) with chemical maps for vivid visualization. This study combined HSI with elemental/isotopic analysis to provide a chemometric basis for interpreting spectral regions that are most relevant to origin discrimination, improving the comprehensive understanding of model interpretability and feature validation.

Accurate identification of the hepatopancreas is essential for prawn quality assessment and automated seafood processing. This study presents an explainable deep learning framework for the binary classification of prawn images into “with hepatopancreas” and “no hepatopancreas” categories. A custom convolutional neural network (CNN) was developed using a dataset of 252 annotated images. To improve feature extraction from the limited dataset, an image preprocessing pipeline incorporating automatic contour-based cropping, contrast enhancement, and data augmentation was employed. The proposed model achieved a test accuracy of 97.37% and a calibrated full-dataset accuracy of 97.22%. Five-fold cross-validation yielded a mean accuracy of 96.83% ± 1.94%, indicating stable performance across different data partitions. Receiver operating characteristic analysis demonstrated satisfactory discriminative ability with AUC > 0.99. Gradient-weighted Class Activation Mapping (Grad-CAM) showed that the model primarily focused on biologically relevant hepatopancreas regions, improving the interpretability of the classification results. A graphical user interface was developed to enable rapid image analysis with visual feedback. Although further validation using larger and more diverse datasets is required, the proposed framework demonstrates the potential of explainable deep learning for automated prawn quality assessment and provides a practical foundation for intelligent seafood inspection applications.

Accurate morphometric analysis of Macrobrachium rosenbergii is essential for selective breeding, growth monitoring, and precision aquaculture, yet conventional manual measurements are labor-intensive, time-consuming, and prone to operator variability. This study presents ReViTA-UNet, an automated, non-contact morphometric analysis framework based on an enhanced semantic segmentation network coupled with a geometric topology refinement algorithm to accurately extract multiple morphological traits. The proposed framework integrates complementary feature extraction to improve segmentation of elongated anatomical structures and complex body boundaries. A complete automated measurement system was subsequently developed to convert segmented images into biologically meaningful morphometric parameters. The results demonstrated that ReViTA-UNet achieved a Dice coefficient of 97.7%, a mean Intersection over Union (mIoU) of 96.7%, a precision of 98.3%, and a recall of 98.4%, outperforming eight representative semantic segmentation models. The automated measurement system achieved a mean absolute percentage error of 1.83% for body length, with strong agreement with manual measurements (R² = 0.987), while maintaining high accuracy for other major morphometric traits. These results indicate that the proposed framework provides an accurate and efficient solution for automated prawn phenotyping under controlled imaging conditions. It establishes a practical foundation for future intelligent aquaculture applications following validation under commercial farming environments.

Aquatic vegetation is critical for maintaining water quality, dissolved oxygen levels, and suitable habitats for crabs in aquaculture ponds. However, traditional manual surveys for monitoring aquatic plant growth and identifying invasive weeds are inefficient, labor-intensive, and prone to subjective errors. To address these limitations, this study proposes an integrated framework combining unmanned aerial vehicles (UAVs), remote sensing, and deep learning (DL) for pixel-level monitoring of aquatic plants in crab ponds. High-resolution UAV RGB and multispectral (MS) images were collected by a drone in Changxing County, Zhejiang Province, China. A specialized dataset was constructed, including cultivated Elodea canadensis and Hydrilla verticillata and two dominant invasive weed species (Alternanthera philoxeroides and Lemna minor). Next, an improved U2Net was designed to fuse the RGB-MS images and provide more detailed information. We also propose a SAM-based model, PondSAM, which integrates three modules: (1) a multiscale vision transformer encoder, (2) a self-generated prompt module, and (3) a multilayer aggregation decoder. The Pond-SAM results are relatively better than those of other state-of-the-art methods (e.g., SAM), achieving a Dice score of 0.865, an mIoU score of 0.858, and a recall score of 0.907. Additionally, the proposed method has been tested on the dataset with different light intensities and training ratios, and its reliability was verified. This study confirms that UAV remote sensing combined with deep learning provides a rapid, nondestructive, large-scale solution for aquatic plant monitoring and invasive weed identification in crab ponds, supporting precision aquaculture and ecological regulation.