In order to solve the problem of image boundary segmentation caused by the irregularity of paddy fields in southern China, a high-precision segmentation method based on the improved MultiResUNet model for paddy field mapping is proposed, combining the characteristics of paddy field scenes. We introduce the attention gate (AG) mechanism at the end of the encoder–decoder skip connections in the MultiResUNet model to generate the weights and highlight the response of the field ridge area, add an atrous spatial pyramid pooling (ASPP) module after the end of the encoder down-sampling, use an appropriate combination of expansion rates to improve the identification of small-scale edge details, use 1 × 1 convolution to improve the range of the sensory field after bilinear interpolation to increase the segmentation accuracy, and, thus, construct the AM-UNet paddy field ridge segmentation model. The experimental results show that the IoU, precision, and F1 value of the AM-UNet model are 88.74%, 93.45%, and 93.95%, respectively, and that inference time for a single image is 168ms, enabling accurate and real-time segmentation of field ridges in a complex paddy field environment. Thus, the AM-UNet model can provide technical support for the development of vision-based automatic navigation systems for agricultural machines.

Water-sensitive paper (WSP) has been widely used to assess the quality of pesticide sprays. However, fog droplets tend to overlap on WSP. In order to accurately measure the droplet size and grasp the droplet distribution pattern, this study proposes a method based on the optimized XGBoost classification model combined with improved concave-point matching to achieve multi-level overlapping-droplet segmentation. For different types of overlapping droplets, the corresponding improved segmentation algorithm is used to improve the segmentation accuracy. For parallel overlapping droplets, the centre-of-mass segmentation method is used; for non-parallel overlapping droplets, the minimum-distance segmentation method is used; and for strong overlapping of a single concave point, the vertical-linkage segmentation method is used. Complex overlapping droplets were gradually segmented by loop iteration until a single droplet was obtained or no further segmentation was possible, and then ellipse fitting was used to obtain the final single-droplet profile. Up to 105 WSPs were obtained in an orchard field through drone spraying experiments, and were used to validate the effectiveness of the method. The experimental results show that the classification model proposed in this paper achieves an average accuracy of 98% in identifying overlapping-droplet types, which effectively meets the needs of subsequent segmentation. The overall segmentation accuracy of the method is 91.35%, which is significantly better than the contour-solidity and watershed-based algorithm (76.19%) and the improved-concave-point-segmentation algorithm (68.82%). In conclusion, the method proposed in this paper provides an efficient and accurate new approach for pesticide spraying quality assessment.

The navigation field of agricultural machinery has entered the intelligent stage, but the navigation control performance of paddy field agricultural machinery represented by rice transplanters is not stable in complex environments. Therefore, this study proposes a method to identify navigation deviation patterns based on Deep Belief Network (DBN) and designs an adaptive preview distance control method based on a driver preview model for each deviation pattern. Among them, the deviation pattern identification method is a two-stage algorithm. First, determine whether the current navigation status is abnormal. Then, the classification was refined for different abnormal states. The adaptive control method is divided into two levels. The main regulator calculates the dynamic preview distance according to the current state variable; the sub-regulator calculates the preview distance adjustment value according to the abnormal state degree. In the performance test of the identification method, all the models show excellent stability and accuracy, and the identification speed of the algorithm meets the high frequency of the rice transplanter navigation system. In the performance test of the control algorithm, compared with the static preview distance, the adaptive preview distance control method proposed in this study can effectively suppress the disturbance deviation of the rice transplanter navigation.

Farmland boundaries distinguish agricultural areas from non-agricultural areas, providing limits for field operations and navigation paths of agricultural machinery. However, in hilly regions, the irregularity of paddy field boundaries complicates the extraction of boundary information, hindering the widespread use of GNSS-based navigation systems in agricultural machinery. This paper focuses on the paddy field border prior to rice planting and utilizes machine vision and GNSS fusion technology to extract navigation line coordinates. First, the BiSeNet semantic segmentation network was employed to extract paddy field ridges. Second, the camera’s 3D attitude was obtained in real time using an Attitude and Heading Reference System (AHRS). A method and device based on the hydraulic profiling system were proposed to measure the camera’s height relative to the paddy field, providing a dynamic external reference. An improved inverse perspective transformation was applied to generate a bird’s-eye view of the paddy field ridges. Finally, a homogeneous coordinate transformation method was used to extract the navigation line coordinates, with the model and algorithms deployed on the Jetson AGX Xavier platform Field tests demonstrated a real-time segmentation speed of 26.31 fps, pixel segmentation accuracy of 92.43%, and an average intersection ratio of 90.62%. The average distance error of the extracted navigation line was 0.071 m, with a standard deviation of 0.039 m. The coordinate extraction took approximately 100 ms, meeting the accuracy and real-time requirements for navigation line extraction at the rice transplanter’s speed of 0.7 m s⁻¹, providing path information for subsequent autonomous navigation.

Aiming at the path tracking oscillation problem caused by sideslip of navigation agricultural machinery in complex farmland environments, this paper takes the Yanmar YR-70D transplanter as the research object and proposes an adaptive control method based on deep belief network (DBN) sideslip identification. Based on the preview tracking model, this method dynamically adjusts the preview distance by real-time identifying the sideslip status via DBN. In this research, the Optuna framework is utilized to optimize the DBN model, and the SHAP framework is introduced to quantify the feature contribution. The results show that, considering both real-time performance and accuracy, when the combined variable of “lateral deviation + heading deviation” with a data length of 20 is adopted, the prediction accuracy of the model reaches 88.04%, among which heading deviation (HD) has the highest contribution with a SHAP value of 0.957. Comparative experiments indicate that the accuracy of DBN is comparable to that of mainstream models such as LSTM and Transformer, but its forward propagation speed (0.0487 ms) is better than other models’. Upland field experiments verify that under different test factors of vehicle speed and slope angle, the line-on time (1.83–5.60 s), line-on distance (1.46–5.07 m), and maximum overshoot (0.32–15.75 cm) of the adaptive control group are all superior to those of the fixed-parameter control group. Paddy field experiments further confirm that under the working condition of 1.0 m/s vehicle speed and 15° slope, the above three indicators of the experimental group are 0.85–3.1 s, 0.75–3.14 m and 0–7.44 cm, respectively, all of which are better than those of the control group. The proposed method demonstrated superior path tracking performance under the operating conditions of the tested rice transplanting machines, indicating its potential application in lateral slip perception adaptive navigation control. However, further verification is still needed with different types of transplanting machines, field environments, and operating conditions to assess its general applicability.

Mechanized rice transplanting is a key method for large-scale cultivation. To enable rapid, accurate seedling detection and evaluate rice transplanting quality, this paper proposes an improved YOLOv12n model, YOLOv12n-SCA. First, this study embeds SCA hybrid attention modules into the YOLOv12n backbone and neck networks, integrating the advantages of SCSA (Spatial and Channel Synergistic Attention) and CA (Coordinate Attention) modules to enhance the model’s ability to extract and locate seedling features against complex paddy field backgrounds. Second, clustering analysis and a plant-spacing discrimination rule, based on seedling detection coordinates, automatically identify areas with missed transplanted seedlings. Experimental results show that the YOLOv12n-SCA model achieved precision, recall, mAP@0.5, and mAP@0.5:0.95 of 93.6%, 90.3%, 95.3%, and 79.8%, respectively, with overall performance superior to that of the original YOLOv12n and single-attention-based improved models. In experiments on an independent dataset, the detection algorithm for rice seedlings in missed transplants achieved 82.34% accuracy and a counting error of 2.06%, indicating that it can effectively identify rice seedling locations and provide quality assessment results. These results show that YOLOv12n-SCA can support intelligent rice seedling detection, rice transplant quality evaluation, and smart field management in complex rice paddy environments.