Accurate segmentation of leaf diseases is crucial for crop health management and disease prevention. However, existing studies fall short in addressing issues such as blurred disease spot boundaries and complex feature distributions in disease images. Although the vision foundation model, Segment Anything Model (SAM), performs well in general segmentation tasks within natural scenes, it does not exhibit good performance in plant disease segmentation. To achieve fine-grained segmentation of leaf disease images, this study proposes an advanced model: Enhanced Multi-Scale SAM (EMSAM). EMSAM employs the Local Feature Extraction Module (LFEM) and the Global Feature Extraction Module (GFEM) to extract local and global features from images respectively. The LFEM utilizes multiple convolutional layers to capture lesion boundaries and detailed characteristics, while the GFEM fine-tunes ViT blocks using a Multi-Scale Adaptive Adapter (MAA) to obtain multi-scale global information. Both outputs of LFEM and GFEM are then effectively fused in the Feature Fusion Module (FFM), which is optimized with cross-branch and channel attention mechanisms, significantly enhancing the model’s ability to handle blurred boundaries and complex shapes. EMSAM integrates lightweight linear layers as classification heads and employs a joint loss function for both classification and segmentation tasks. Experimental results on the PlantVillage dataset demonstrate that EMSAM outperforms the second-best state-of-the-art semantic segmentation model by 2.45% in Dice Coefficient and 6.91% in IoU score, and surpasses the baseline method by 21.40% and 22.57%, respectively. Particularly, for images with moderate and severe disease levels, EMSAM achieved Dice Coefficients of 0.8354 and 0.8178, respectively, significantly outperforming other semantic segmentation algorithms. Additionally, the model achieved a classification accuracy of 87.86% across the entire dataset, highlighting EMSAM’s effectiveness and superiority in plant disease segmentation and classification tasks.

To ensure national food security amidst severe water shortages, agricultural irrigation must be reduced through scientific innovation and technological progress. Efficient monitoring is essential for achieving water-saving irrigation and ensuring the sustainable development of agriculture. UAV hyperspectral remote sensing has demonstrated significant potential in monitoring large-scale crop leaf water content (LWC). In this study, hyperspectral and LWC data were collected for potatoes (Solanum tuberosum) during the tuber formation, growth, and starch accumulation stage in both 2021 and 2022. The hyperspectral data underwent mathematical transformation by multivariate scatter correction (MSC) and standard normal transformation (SNV). Next, feature spectral bands of LWC were selected using Competitive Adaptive Reweighted Sampling (CARS) and Random Frog (RF). For comparison, both the full-band and feature band were utilized to establish the estimation models of LWC. Modeling methods included partial least squares regression (PLSR), support vector regression (SVR), and BP neural network regression (BP). Results demonstrate that MSC and SNV significantly enhance the correlation between spectral data and LWC. The efficacy of estimation models varied across different growth stages, with optimal models identified as MSC-CARS-SVR (R² = 0.81, RMSE = 0.51) for tuber formation, SNV-CARS-PLSR (R² = 0.85, RMSE = 0.42) for tuber growth, and MSC-RF-PLSR (R² = 0.81, RMSE = 0.55) for starch accumulation. The RPD values of the three optimal models all exceed 2, indicating their excellent predictive performance. Utilizing these optimal models, a spatial distribution map of LWC across the entire potato canopy was generated, offering valuable insights for precise potato irrigation.

Few-shot learning (FSL) methods have made remarkable progress in the field of plant disease recognition, especially in scenarios with limited available samples. However, current FSL approaches are usually limited to a restrictive setting where base classes and novel classes come from the same domain such as PlantVillage. Consequently, when the model is generalized to new domains (field disease datasets), its performance drops sharply. In this work, we revisit the cross-domain performance of existing FSL methods from both data and model perspectives, aiming to better achieve cross-domain generalization of disease by exploring inter-domain correlations. Specifically, we propose a broader cross-domain few-shot learning(CD-FSL) framework for crop disease identification that allows the classifier to generalize to previously unseen categories and domains. Within this framework, three representative CD-FSL models were developed by integrating the Brownian distance covariance (BCD) module and improving the general feature extractor, namely metric-based CD-FSL(CDFSL-BDC), optimization-based CD-FSL(CDFSL-MAML), and non-meta-learning-based CD-FSL (CDFSL-NML). To capture the impact of domain shift on model performance, six public datasets with inconsistent feature distributions between domains were selected as source domains. We provide a unified testbed to conduct extensive meta-training and meta-testing experiments on the proposed benchmarks to evaluate the generalization performance of CD-FSL in the disease domain. The results showed that the accuracy of the three CD-FSL models improved significantly as the inter-domain similarity increased. Compared with other state-of-the-art CD-FSL models, the CDFSL-BDC models had the best average performance under different domain gaps. Shifting from the pest domain to the crop disease domain, the CDFSL-BDC model achieved an accuracy of 63.95% and 80.13% in the 1-shot/5-shot setting, respectively. Furthermore, extensive evaluation on a multi-domain datasets demonstrated that multi-domain learning exhibits stronger domain transferability compared to single-domain learning when there is a large domain gap between the source and target domain. These comparative results suggest that optimizing the CD-FSL method from a data perspective is highly effective for solving disease identification tasks in field environments. This study holds promise for expanding the application of deep learning techniques in disease detection and provides a technical reference for cross-domain disease detection.

Diseases cause crop yield reduction and quality decline, which has a great impact on agricultural production. Plant disease recognition based on computer vision can help farmers quickly and accurately recognize diseases. However, the occurrence of diseases is random and the collection cost is very high. In many cases, the number of disease samples that can be used to train the disease classifier is small. To address this problem, we propose a few-shot disease recognition algorithm that uses supervised contrastive learning. Our algorithm is divided into two phases: supervised contrastive learning and meta-learning. In the first phase, we use a supervised contrastive learning algorithm to train an encoder with strong generalization capabilities using a large number of samples. In the second phase, we treat this encoder as an extractor of plant disease features and adopt the meta-learning training mechanism to accomplish the few-shot disease recognition tasks by training a nearest-centroid classifier based on distance metrics. The experimental results indicate that the proposed method outperforms the other nine popular few-shot learning algorithms as a comparison in the disease recognition accuracy over the public plant disease dataset PlantVillage. In few-shot potato leaf disease recognition tasks in natural scenarios, the accuracy of the model reaches the accuracy of 79.51% with only 30 training images. The experiment also revealed that, in the contrastive learning phase, the combination of different image augmentation operations has a greater impact on model. Furthermore, the introduction of label information in supervised contrastive learning enables our algorithm to still obtain high accuracy in few-shot disease recognition tasks with smaller batch size, thus allowing us to complete the training with less GPU resource compared to traditional contrastive learning.

Deep convolutional neural networks (DCNN) have shown promising performance in plant disease recognition. However, these networks cannot be deployed on resource-limited smart devices due to their vast parameters and computations. To address the issue of deployability when developing cotton disease identification applications for mobile/smart devices, we compress the disease recognition models employing the pruning algorithm. The algorithm uses the γ coefficient in the Batch Normalization layer to prune the channels to realize the compression of DCNN. To further improve the accuracy of the model, we suggest two strategies in combination with transfer learning: compression after transfer learning or transfer learning after compression. In our experiments, the source dataset is famous PlantVillage while the target dataset is the cotton disease image set which contains images collected from the Internet and taken from the fields. We select VGG16, ResNet164 and DenseNet40 as compressed models for comparison. The experimental results show that transfer learning after compression overall surpass its counterpart. When compression rate is set to 80% the accuracies of compressed version of VGG16, ResNet164 and DenseNet40 are 90.77%, 96.31% and 97.23%, respectively, and the parameters are only 0.30M, 0.43M and 0.26M, respectively. Among the compressed models, DenseNet40 has the highest accuracy and the smallest parameters. The best model (DenseNet40-80%-T) is pruned 75.70% of the parameters and cut off 65.52% of the computations, with the model size being only 2.2 MB. Compared with the version of compression after transfer learning, the accuracy of the model is improved by 0.74%. We further develop a cotton disease recognition APP on the Android platform based on the model and on the test phone, the average time to identify a single image is just 87ms.

To find an economical solution to infer the depth of the surrounding environment of unmanned agricultural vehicles (UAV), a lightweight depth estimation model called MonoDA based on a convolutional neural network is proposed. A series of sequential frames from monocular videos are used to train the model. The model is composed of two subnetworks—the depth estimation subnetwork and the pose estimation subnetwork. The former is a modified version of U-Net that reduces the number of bridges, while the latter takes EfficientNet-B0 as its backbone network to extract the features of sequential frames and predict the pose transformation relations between the frames. The self-supervised strategy is adopted during the training, which means the depth information labels of frames are not needed. Instead, the adjacent frames in the image sequence and the reprojection relation of the pose are used to train the model. Subnetworks’ outputs (depth map and pose relation) are used to reconstruct the input frame, then a self-supervised loss between the reconstructed input and the original input is calculated. Finally, the loss is employed to update the parameters of the two subnetworks through the backward pass. Several experiments are conducted to evaluate the model’s performance, and the results show that MonoDA has competitive accuracy over the KITTI raw dataset as well as our vineyard dataset. Besides, our method also possessed the advantage of non-sensitivity to color. On the computing platform of our UAV’s environment perceptual system NVIDIA JETSON TX2, the model could run at 18.92 FPS. To sum up, our approach provides an economical solution for depth estimation by using monocular cameras, which achieves a good trade-off between accuracy and speed and can be used as a novel auxiliary depth detection paradigm for UAVs.