Tomato is generally cultivated by transplanting seedlings in ridges and furrows. During growth, there are various types of tomato pests and diseases, making it challenging to identify them simultaneously. To address this issue, conventional convolutional neural networks have been investigated, but they have a large number of parameters and are time-consuming. In this paper, we proposed a lightweight multi-scale tomato pest and disease classification network, called CNNA. Firstly, we constructed a dataset of tomato diseases and pests consisting of 27,193 images with 18 categories. Then, we compressed and optimized the ConvNeXt-Tiny network structure to maintain accuracy while significantly reducing the number of parameters. In addition, we proposed a multi-scale feature fusion module to improve the feature extraction ability of the model for different spot sizes and pests, and we proposed a global channel attention mechanism to enhance the sensitivity of the network model to spot and pest features. Finally, the model was trained and deployed to the Jetson TX2 NX for inference of tomato pests and diseases in video stream data. The experimental results showed that the proposed CNNA model outperformed the pre-trained lightweight models such as MobileNetV3, MobileVit, and ShuffleNetV2 in terms of accuracy and all parameters, with a recognition accuracy of 98.96%. Meanwhile, the error rate, inference time for a single image, network parameters, FLOPs, and model size were only 1%, 47.35 ms, 0.37 M, 237.61 M, and 1.47 MB, respectively.

Early blight and late blight are two of the most prevalent and severe diseases affecting potato crops. Efficient and accurate grading of their severity is crucial for effective disease management. However, existing grading methods are limited to assessing the severity of each disease independently, often resulting in low recognition accuracy and slow grading processes. To address these challenges, this study proposes a novel two-stage approach for the rapid severity grading of both early blight and late blight in potato plants. In this research, two lightweight models were developed: Coformer and SegCoformer. In the initial stage, Coformer efficiently categorizes potato leaves into three classes: those afflicted by early blight, those afflicted by late blight, and healthy leaves. In the subsequent stage, SegCoformer accurately segments leaves, lesions, and backgrounds within the images obtained from the first stage. Furthermore, it assigns severity labels to the identified leaf lesions. To validate the accuracy and processing speed of the proposed methods, we conduct experimental comparisons. The experimental results indicate that Coformer achieves a classification accuracy as high as 97.86%, while SegCoformer achieves an mIoU of 88.50% for semantic segmentation. The combined accuracy of this method reaches 84%, outperforming the Sit + Unet_V accuracy by 1%. Notably, this approach achieves heightened accuracy while maintaining a faster processing speed, completing image processing in just 258.26 ms. This research methodology effectively enhances agricultural production efficiency.

Crop seedlings are similar in appearance to weeds, making crop detection extremely difficult. To solve the problem of detecting crop seedlings in complex field environments, a seedling dataset with four crops was constructed in this study. The single leaf labeling method was proposed as an alternative to conventional labeling approaches to improve the detection accuracy for dense planting crops. Second, a seedling detection network based on YOLOv5 and a transformer mechanism was proposed, and the effects of three features (query, key and value) in the transformer mechanism on the detection accuracy were explored in detail. Finally, the seedling detection network was optimized into a lightweight network. The experimental results show that application of the single leaf labeling method could improve the mAP0.5 of the model by 1.2% and effectively solve the problem of missed detection. By adding the transformer mechanism module, the mAP0.5 was improved by 1.5%, enhancing the detection capability of the model for dense and obscured targets. In the end, this study found that query features had the least impact on the transformer mechanism, and the optimized model improved the computation speed by 23 ms·frame⁻¹ on the intelligent computing platform Jetson TX2, providing a theoretical basis and technical support for real-time seedling management.

This study proposed an automatic classification method for water stress level of spinach seedlings based on N-MobileNetXt network, solving inefficient water stress classification of spinach seedlings under complex background. Firstly, this study reconstructed the Sandglass Block in MobileNetXt model to effectively increase the model accuracy by adopting up-dimension and down-dimension, and introduced NAM and two-dimensional adaptive average pooling; secondly, this study introduced the group convolution module and a two-dimensional adaptive average pool, which can significantly compress the model parameters and enhance the model robustness separately; finally, this study innovatively proposed the NCAM to enhance the image features obviously. The experimental results showed that the classification accuracy of N-MobileNetXt model for spinach seedlings under the natural environment reached 90.35%, and the number of parameters was decreased by 66% compared with the original MobileNetXt model. While, the model size is only 3.89 MB. Comparing the N-MobileNetXt model with the deep network models proposed in the past five years, the N-MobileNetXt model was superior to other network models in terms of parameters and accuracy of identification. The N-MobileNetXt exhibited a considerable advantage in the rapid and accurate classification of spinach seedlings, and can provide theoretical basis and technical support for automatic irrigation.