Mechanical direct seeding is one of the most important steps during rapeseed cultivation. Sowing quality can also be evaluated for precise practices, such as gap filling and thinning. It is often required to accurately estimate the coverage of rapeseed seedlings under field conditions. However, existing estimation remains a great challenge due to the small target size, dense distribution, complex soil backgrounds, and high visual similarity between rapeseed seedlings and weeds at early growth stages. This study aims to propose an improved semantic segmentation model, named RCL UNet (RCL U-shaped Network), using the classical U-Net architecture. A dataset was constructed during mechanical direct seeding. High-resolution RGB images were acquired by a DJI Mavic 3 Pro UAV. Rapeseed fields were also taken from Anhui Province, China. A total of 3 140 image tiles were obtained after image cropping, screening, and pixel-level annotation, including 2 960 training tiles (after data augmentation), 120 validation tiles, and 60 test tiles. Three improvements were introduced into the U-Net baseline: 1) The original encoder was replaced with a ResNet50 PPM S structure. A 50-layer deep residual network was integrated with a pyramid pooling module to extract multi-scale contextual features for high sensitivity to small targets. 2) A convolutional block attention module (CBAM) was embedded into the skip connections to adaptively recalibrate feature responses using channel and spatial attention, effectively suppressing background noise for the fine boundary features of seedlings. 3) The Dice loss function was adopted instead of cross-entropy loss to alleviate the severe class imbalance in small target segmentation, particularly for pixel-wise coverage of seedling regions. Ablation experiments confirmed that all three modules contributed positively to segmentation performance. The results showed that the RCL UNet achieved a mean intersection over union (mIoU) of 89.88%, a mean Pixel Accuracy (mPA) of 94.98%, a mean precision (mP) of 93.96%, and a mean recall (mR) of 93.92% on the test set, indicating absolute improvements of 16.75, 15.33, 8.21, and 14.69 percentage points over the original UNet, respectively. Furthermore, RCL UNet outperformed both PSPNet and DeepLabv3+, with mIoU gains of 10.78 and 3.33 percentage points, respectively. Visual assessments were also conducted under varying planting densities (300 000-600 000 plants/hm²) and imaging distances (0.8 and 2.5 m). Segmentation masks were obtained with high boundary precision, fewer omissions and adhesions, especially in distant view and high-density scenes. The improved model was deployed on a laptop equipped with an RTX 4060 GPU via a PyQt5 interface, with an average inference time of 49 ms per image. Field validation was conducted at an independent site under two sowing patterns: mechanical drill sowing and aerial broadcasting. 100 sampling units of 1 m × 1 m were selected for each pattern. coverage estimation showed that under mechanical drill sowing, the root mean square error (RMSE) between predictions and ground truth data was 0.42% with a coefficient of determination (R²) of 0.98; The RMSE and (R²) were 0.50% and 0.94, respectively, under aerial broadcasting. The RMSE values were below 0.5% under sowing patterns, whereas the (R²) values remained above 0.94. The high accuracy of pixel-wise segmentation was achieved for robust generalization under complex and variable field environments. Reliable technical support can help evaluate the sowing performance of mechanical direct seeding. Nevertheless, the current model has only been validated at the four-leaf stage. It is also required to cover the full growth cycle with canopy overlap. Moreover, the higher prediction accuracy can be expected for the irregular sowing patterns under aerial broadcasting, compared with mechanical drill sowing. The dataset can also be extended into multiple growth stages and source imagery for the edge deployment of lightweight architectures. These findings can provide a strong reference to further enhance model generalization and operational efficiency.

Aiming at the problem that mechanized strip sowing of wheat in rice stubble fields can be constrained to the coupling effect of clay-heavy soil and straw return to the field. The seed guide device can be blocked to cause the breakage. In this study, a double-row wide strip seed introduction device was designed to combine with the spherical collision seed part, in order to evenly divide the falling population left and right during introduction. The broadband introduction of the diverted population was also carried out with the help of beveled bottom plate slope. The mechanical model of wheat seeding and introduction was established using particle kinematics. A systematic investigation was implemented to clarify the influencing mechanism of the spherical collision seed part diameter and beveled bottom plate slope on the uniformity of seed introduction. EDEM software was then used to optimize the key structural parameters of the wheat seed introduction device. Among them, the spherical collision seed part diameter and beveled bottom plate slope were taken as the test factors. The evaluation indexes were taken as the coefficient of variation of each row seeding quantity consistency and coefficient of variation of transverse uniformity in row. The test data was obtained to combine the univariate and quadratic orthogonal rotation. Design-Expert software was also selected to perform the regression analysis on experimental data. The regression equation was established between the test factors and indicators. The results show that the spherical collision seed part diameter posed a significant coefficient of variation of each row seeding quantity consistency, whereas, the beveled bottom plate slope was some impact on the coefficient of variation of transverse uniformity in row. The optimal structural parameters were achieved in the seed guiding device spherical collision seed part diameter of 40mm, and the beveled bottom plate slope of 10°. The beveled bottom plate guide device was evaluated under optimal structural parameters. Three types (flat plate,curved bottom plate,wavy plate) of seed guide devices were selected to compare under the three sowing amounts. The simulation results show that the coefficient of variation of each row seeding quantity consistency and coefficient of variation of transverse uniformity in row were ranked in the descending order: flat plate,curved bottom plate,wavy plate,beveled bottom plate. The optimal coefficient of variation of each row seeding quantity consistency was 2.92% of the beveled bottom plate-type seed guiding device. The coefficient of variation of transverse uniformity was 14.19% in the row. The bench and field tests were combined to further verify the smallest coefficient of variation of each row seeding quantity consistency and coefficient of variation of transverse uniformity in row of the beveled bottom plate seed guiding device. Specifically, the mean coefficient of variation of each row seeding quantity consistency was 2.31%, whereas, the mean coefficient of variation of transverse uniformity in row was 14.21%. The field experimental results showed that coefficient of variation of each row seeding quantity consistency decreased by at least 2.73 percentage points, and the coefficient of variation of transverse uniformity in row decreased by at least 10.61 percentage points, compared with the other three types of seed guide devices. The error was not more than 5% between the actual and the simulation. Therefore, it was reliable for the optimized structural parameters of the split-citation combined wide strip guide device using the discrete element method. At the same time, the national technical specifications were fully met for the quality evaluation of seeders and the agronomic requirements for field seeding. The findings can provide a strong reference for the optimal design of wheat wide strip seed introduction device under a rice stubble clay loam environment.

Rapeseed is one of the most important oil crops in China. Winter rapeseed can account for more than 85% of the total cultivation acreage. However, frost damage has pose a serious threat to both the yield and quality of rapeseed, due to the low temperatures at the seedling stage. It is often required for the cold-resistant varieties using screening. Variety evaluation can be expected to accurately quantify the degree of frost damage. But conventional manual assessment cannot fully meet the large-scale production in recent years, such as the long cycles, low efficiency, and strong subjectivity. An intelligent evaluation framework is greatly hindered to construct after assessment. In this study, an improved model called YOLOv7-DH was proposed to grade the frost damage in the scenario of the rapeseed seedlings. According to the complex agronomic conditions, YOLOv7-DH was incorporated three measures: Firstly, DCNv2 was adopted to replace the standard convolution in the feature extraction backbone. With the help of learnable offset parameters, the receptive field was dynamically adjusted to better capture the irregular features that caused by frost, such as the leaf curling and heterogeneous necrosis, thereby improving the fidelity of the feature extraction. Secondly, the Focal-EIoU loss function was introduced to optimize the bounding box regression. A focal mechanism was utilized to balance the various class. At the same time, the width and height differences between the predicted and the real box were reduced for the convergence speed and the positioning accuracy. Particularly, the adjacent damage levels (such as level 1 and level 2) were distinguished. Thirdly, the lightweight CARAFE upsampling operator was used to replace the conventional interpolation in the neck and head modules. The content-aware feature reconstruction was realized after adaptive kernel adjustment. Subtle features were retained, such as the initial edge discoloration. The receptive field was expanded to effectively overcome the spatial information degradation in conventional upsampling. Empirical results show that the YOLOv7-DH performed excellently in the frost damage classification. On the test set, the precision rate reached 95.4%, the recall rate was 94.5%, and the mean average precision (mAP) was 95.2%. Three indicators increased by 9.1, 9.3, and 9.4 percentage points, respectively, compared with the baseline YOLOv7. Ablation experiments confirmed the effectiveness of each improvement: DCNv2 increased mAP by 6.0%, Focal-EIoU by 3.5%, and CARAFE by 4.5%. Moreover, the combination of these three improvements was achieved the best performance. Compared with the mainstream models, the mAP of YOLOv7-DH was 15.3, 22.4, 29.4, and 21.8 percentage points higher than that of YOLOv5s, YOLOv7-tiny, Faster R-CNN, and SSD, respectively. At the same time, a real-time speed of 60.3 frames per second was met the needs of the field detection. In the verification of the frost damage index, the mean absolute error (MAE) of the model relative to manual measurement was 1.22, and the root mean square error (RMSE) was 1.36, indicating the high quantification accuracy. In general, the YOLOv7-DH was provided for an accurate, efficient, and lightweight solution to the multi-class frost damage detection of the rapeseed seedlings. DCNv2, Focal-EIoU and CARAFE were integrated to capture the complex frost features. This finding can provide the support for the cold-resistant variety screening after agricultural stress assessment using computer vision. An intelligent evaluation was also constructed for the rapeseed in the precision agriculture.