Changes in soybean flower and pod numbers are important factors affecting soybean yields. Obtaining the number of flowers and pods, as well as fallen flowers and pods, quickly and accurately is crucial for soybean variety breeding and high-quality and high-yielding production. This is especially challenging in the natural field environment. Therefore, this study proposed a field soybean flower- and pod-detection method based on an improved network model (YOLOv8-VEW). VanillaNet is used as the backbone feature-extraction network for YOLOv8, and the EMA attention mechanism module is added to C2f, replacing the CioU function with the WIoU position loss function. The results showed that the F1, mAP, and FPS (frames per second) of the YOLOv8-VEW model were 0.95, 96.9%, and 90 FPS, respectively, which were 0.05, 2.4%, and 24 FPS better than those of the YOLOv8 model. The model was used to compare soybean flower and pod counts with manual counts, and its R² for flowers and pods was 0.98311 and 0.98926, respectively, achieving rapid detection of soybean flower pods in the field. This study can provide reliable technical support for detecting soybean flowers and pod numbers in the field and selecting high-yielding varieties.

Design of precision variable-rate spray system for unmanned aerial vehicle using automatic control method

During hybrid soybean seed production, the parents’ phenotypic consistency is assessed by breeders to ensure the purity of soybean seeds. Detection traits encompass the hypocotyl, leaf, pubescence, and flower. To achieve the detection of hybrid soybean parents’ phenotypic consistency in the field, a self-propelled image acquisition platform was used to obtain soybean plant image datasets. In this study, the Large Selective Kernel Network (LSKNet) attention mechanism module, the detection layer Small Network (SNet), dedicated to detecting small objects, and the Wise Intersection over Union v3 (WIoU v3) loss function were added into the YOLOv5s network to establish the hybrid soybean parent phenotypic consistency detection model SLW-YOLO. The SLW-YOLO achieved the following: F1 score: 92.3%; mAP: 94.8%; detection speed: 88.3 FPS; and model size: 45.1 MB. Compared to the YOLOv5s model, the SLW-YOLO model exhibited an improvement in F1 score by 6.1% and in mAP by 5.4%. There was a decrease in detection speed by 42.1 FPS, and an increase in model size by 31.4 MB. The parent phenotypic consistency detected by the SLW-YOLO model was 98.9%, consistent with manual evaluation. Therefore, this study demonstrates the potential of using deep learning technology to identify phenotypic consistency in the seed production of large-scale hybrid soybean varieties.

The extraction of navigation lines is a crucial aspect in the field autopilot system for intelligent agricultural equipment. Given that soybean seedlings are small, and straw can be found in certain Northeast China soybean fields, accurately obtaining feature points and extracting navigation lines during the soybean seedling stage poses numerous challenges. To solve the above problems, this paper proposes a method of extracting navigation lines based on the average coordinate feature points of pixel points in the bean seedling belt according to the calculation of the average coordinate. In this study, the soybean seedling was chosen as the research subject, and the Hue, Saturation, Value (HSV) colour model was employed in conjunction with the maximum interclass variance (OTSU) method for RGB image segmentation. To extract soybean seedling bands, a novel approach of framing binarised image contours by drawing external rectangles and calculating average coordinates of white pixel points as feature points was proposed. The feature points were normalised, and then the improved adaptive DBSCAN clustering method was used to cluster the feature points. The least squares method was used to fit the centre line of the crops and the navigation line, and the results showed that the average distance deviation and the average angle deviation of the proposed algorithm were 7.38 and 0.32. The fitted navigation line achieved an accuracy of 96.77%, meeting the requirements for extracting navigation lines in intelligent agricultural machinery equipment for soybean inter-row cultivation. This provides a theoretical foundation for realising automatic driving of intelligent agricultural machinery in the field.

To address the issue of improving the accuracy and efficiency of variable-rate application under large-scale field conditions, an RBFNN-SMC variable-rate application control system was designed and experimentally verified. A first-order inertial pure lag model of the spray flow rate was identified through step tests. Based on this, three controllers, namely traditional SMC, fuzzy SMC, and RBFNN-SMC, were designed for comparison. The simulation results indicated that RBFNN-SMC had the shortest adjustment time and the smallest steady-state error under conditions of model uncertainty and time delay. Its maximum overshoot was reduced by 11.2% compared to traditional SMC, and the steady-state error was controlled within ±0.51%. The control strategy was implemented on a microcontroller and integrated with a prescription-based spray system. Field trials showed that the average absolute error of the proposed system in tracking the target flow rate was 3.2%, and it achieved a weed control effect comparable to that of traditional uniform spraying. These results suggest that the RBFNN-SMC-based variable spray rate system can enhance flow rate control performance and support more precise and potentially more sustainable herbicide application, providing a reference and ideas for the research on variable-rate application flow rate control based on prescription maps.

Accurate navigation line recognition in mature soybean fields presents significant challenges due to complex backgrounds. To address this issue, we developed an enhanced YOLOv10n-based model for robust visual navigation, and the assessment was conducted in the experimental fields of the laboratory. The dataset comprised 1363 original images collected at this site and was expanded to 5452 images through data augmentation. The study utilized an innovative data annotation approach focusing on inter-ridge navigation areas to minimize background noise from mature soybean rows. The model was optimized by integrating the CSP Multi-Scale Edge Information Enhancement (CSP-MEIE) module and a lightweight detection head. This architecture significantly improves efficiency, achieving a model size of just 4.5 MB and a parameter count of 2.137 M, while delivering a rapid detection speed of 204.1 FPS. Crucially, the model expands the effective receptive field to 96.6% (t = 99%), far exceeding the 73.0% of the baseline YOLOv10n, ensuring robust feature capture without compromising accuracy (92.6% mAP50-95). For path planning, path points were extracted and predicted using a combination of Kalman filtering and adaptive segmentation. Field experiments demonstrated the system’s effectiveness, achieving an average distance error of 4.53 pixels and an average angle error of 3.57°, a processing speed of 28.17 ms per frame, and a navigation line recognition accuracy of 98.05%. These findings highlight the method’s capability to meet real-time agricultural requirements, offering a reliable visual perception and decision-making basis for autonomous navigation in complex field environments.