Introduction: Weeds are one of the main factors affecting crop growth, making weed control a pressing global problem. In recent years, interest in intelligent mechanical weed-control equipment has been growing. Methods: We propose a semantic segmentation network, RDS_Unet, based on corn seedling fields built upon an improved U-net network. This network accurately recognizes weeds even under complex environmental conditions, facilitating the use of mechanical weeding equipment for reducing weed density. Our research utilized field-grown maize seedlings and accompanying weeds in expansive fields. We integrated the U-net semantic segmentation network, employing ResNeXt-50 for feature extraction in the encoder stage. In the decoder phase, Layer 1 uses deformable convolution with adaptive offsets, replacing traditional convolution. Furthermore, concurrent spatial and channel squeeze and excitation is incorporated after ordinary convolutional layers in Layers 2, 3, and 4. Results: Compared with existing classical semantic segmentation models such as U-net, Pspnet, and DeeplabV3, our model demonstrated superior performance on our specially constructed seedling grass semantic segmentation dataset, CGSSD, during the maize seedling stage. The Q6mean intersection over union (MIoU), precision, and recall of this network are 82.36%, 91.36%, and 89.45%, respectively. Compared to those of the original network, the proposed network achieves improvements of 5.91, 3.50, and 5.49 percentage points in the MIoU, precision, and recall, respectively. The detection speed is 12.6 frames per second. In addition, ablation experiments further confirmed the impactful contribution of each improvement component on the overall semantic segmentation performance. Discussion: This study provides theoretical and technical support for the automated operation of intelligent mechanical weeding devices.

Rice diseases are extremely harmful to rice growth, and achieving the identification and rapid classification of rice disease spots is an essential means to promote intelligent rice production. However, due to the large variety of rice diseases and the similar appearance of some rice diseases, the existing deep learning methods are less effective at classification and detection. Aiming at such problems, this paper took the spot images of five common rice diseases as the research object and constructed a rice disease data set containing 2500 images of rice bacterial blight, sheath blight, flax leaf spot, leaf streak and rice blast, including 500 images of each disease. An improved lightweight deep learning network model was proposed to realize the accurate identification of disease types and disease spots. A rice disease image classification network was designed based on the RlpNet (rice leaf plaque net) network model, Which is the underlying network, in addition to the YOLOv3 target detection network model in order to achieve the optimization of the feature extraction link, i.e., upsampling by transposed convolution and downsampling by dilated convolution. The improved YOLOv3 model was compared with traditional convolutional neural network models, including the AlexNet, GoogLeNet, VGG-16 and ResNet-34 models, for disease recognition, and the results showed that the average recall, average precision, average F1-score and overall accuracy of the network model for rice disease classification were 91.84%, 92.14%, 91.87% and 91.84%, respectively, which were all improved compared with the traditional algorithms. The improved YOLOv3 network model was compared with FSSD, Faster-RCNN, YOLOv3 and YOLOv4 for spot detection studies, and the results showed that it could achieve a mean average precision (mAP) of 86.72%, a detection rate (DR) of 93.92%, a frames per second (FPS) rate of 63.4 and a false alarm rate (FAR) of only 5.12%. In summary, the comprehensive performance of the proposed model was better than that of the traditional YOLOv3 algorithm, so this study provides a new method for rice disease identification and disease spot detection. It also had good performance in terms of the common detection and classification of multiple rice diseases, which provides some support for the common differentiation of multiple rice diseases and has some practical application value.

Obtaining the number of plants is the key to evaluating the effect of maize mechanical sowing, and is also a reference for subsequent statistics on the number of missing seedlings. When the existing model is used for plant number detection, the recognition accuracy is low, the model parameters are large, and the single recognition area is small. This study proposes a method for detecting the number of maize seedlings based on an improved You Only Look Once version 4 (YOLOv4) lightweight neural network. First, the method uses the improved Ghostnet as the model feature extraction network, and successively introduces the attention mechanism and k-means clustering algorithm into the model, thereby improving the detection accuracy of the number of maize seedlings. Second, using depthwise separable convolutions instead of ordinary convolutions makes the network more lightweight. Finally, the multi-scale feature fusion network structure is improved to further reduce the total number of model parameters, pre-training with transfer learning to obtain the optimal model for prediction on the test set. The experimental results show that the harmonic mean, recall rate, average precision and accuracy rate of the model on all test sets are 0.95%, 94.02%, 97.03% and 96.25%, respectively, the model network parameters are 18.793 M, the model size is 71.690 MB, and frames per second (FPS) is 22.92. The research results show that the model has high recognition accuracy, fast recognition speed, and low model complexity, which can provide technical support for corn management at the seedling stage.

Introduction: Missing seedlings is a common issue in field maize planting, arising from limitations in sowing machinery and seed germination rates. This phenomenon directly impacts maize yields owing to the poor effect of unmanned aerial vehicle (UAV) remote sensing images based on seedling leakage detection in fields. Therefore, this study proposed a method for detecting missing seedling in fields based on UAV remote sensing to quickly and accurately detect missing seedling and facilitate subsequent crop management decisions.Methods: The method calculates the rated inter-seedling distance in UAV-captured images of maize fields using a combination of image processing techniques, including background segmentation, stalk center region detection, linear fitting of plant rows, and average plant distance calculation. Based on these calculations, an improved Maize-YOLOv8n model was employed to detect actual seedling emergence.Results: The experimental results demonstrate that the new model achieved superior performance on a self-constructed dataset, with a mean average precision (mAP) of 97.4%, precision (P) of 94.3%, recall (R) of 93.1%, and an F1 score of 93.7%. The model was lightweight, comprising only 1.19 million parameters and requiring 20.2 floating-point operations per second (FLOPs). The inference time was 12.8 ms, satisfying real-time detection requirements. Performance evaluations across various conditions, including different leaf stages, light intensities, and weed interference levels, further indicated the robustness of the model. In addition, a linear regression equation was developed to predict the total number of missing seedlings, with model performance evaluated using the root mean squared error (RMSE) and mean absolute error (MAE) metrics.Discussion: The results confirm the ability of the model to accurately detect maize seedling gaps. This study can evaluate the quality of seeding operations and provide accurate information on the number of missing seedlings for timely replacement work in areas with high rates of missing seedlings. This study advances precision agriculture by enhancing the efficiency and accuracy of maize planting management.

Due to the limitations of the sowing machine performance and rice seed germination rates, missing seedlings inevitably occur after rice is sown in large fields. This phenomenon has a direct impact on the rice yield. In the field environment, the existing methods for detecting missing seedlings based on unmanned aerial vehicle (UAV) remote sensing images often have unsatisfactory effects. Therefore, to enable the fast and accurate detection of missing rice seedlings and facilitate subsequent reseeding, this study proposes a UAV remote-sensing-based method for detecting missing rice seedlings in large fields. The proposed method uses an improved PCERT-DETR model to detect rice seedlings and missing seedlings in UAV remote sensing images of large fields. The experimental results show that PCERT-DETR achieves an optimal performance on the self-constructed dataset, with an mean average precision (mAP) of 81.2%, precision (P) of 82.8%, recall (R) of 78.3%, and F₁-score (F₁) of 80.5%. The model’s parameter count is only 21.4 M and its FLOPs reach 66.6 G, meeting real-time detection requirements. Compared to the baseline network models, PCERT-DETR improves the P, R, F₁, and mAP by 15.0, 1.2, 8.5, and 6.8 percentage points, respectively. Furthermore, the performance evaluation experiments were carried out through ablation experiments, comparative detection model experiments and heat map visualization analysis, indicating that the model has a strong detection performance on the test set. The results confirm that the proposed model can accurately detect the number of missing rice seedlings. This study provides accurate information on the number of missing seedlings for subsequent reseeding operations, thus contributing to the improvement of precision farming practices.

The core of saline-alkali land improvement is planting suitable plants. Planting rice in saline-alkali land can not only effectively improve saline-alkali soil, but also increase grain yield. However, traditional identification methods for saline-alkali-tolerant rice varieties require tedious and time-consuming field investigations based on growth indicators by rice breeders. In this study, the visualization method of Python data processing was used to analyze the Raman spectroscopy of japonica rice in order to study a simple and efficient identification method of saline-alkali-tolerant japonica rice varieties. Three saline-alkali-tolerant japonica varieties and three saline-alkali-sensitive japonica varieties were collected from control and saline-alkali-treated fields, respectively, and the Raman spectra of 432 samples were obtained. The data preprocessing stage used filtering-difference method to process Raman spectral data to complete interference reduction and crests extraction. In the feature selection stage, scipy.signal.find_peaks (SSFP), SelectKBest (SKB) and recursive feature elimination (RFE) were used for machine feature selection of spectral data. According to the feature dimension obtained by machine feature selection, dataset partitioning by K-fold CV, the typical linear logistic regression (LR) and typical nonlinear support vector machine (SVM) models were established for classification. Experimental results showed that the typical nonlinear SVM identification model based on both RFE machine feature selection and six-fold CV dataset partitioning had the best identification rate, which was 94%. Therefore, the SVM classification model proposed in this study could provide help in the intelligent identification of saline-alkali-tolerant japonica rice varieties.