Development and test of an electric precision seeder for small-size vegetable seeds

The number of wheat spikes has an important influence on wheat yield, and the rapid and accurate detection of wheat spike numbers is of great significance for wheat yield estimation and food security. Computer vision and machine learning have been widely studied as potential alternatives to human detection. However, models with high accuracy are computationally intensive and time consuming, and lightweight models tend to have lower precision. To address these concerns, YOLO-FastestV2 was selected as the base model for the comprehensive study and analysis of wheat sheaf detection. In this study, we constructed a wheat target detection dataset comprising 11,451 images and 496,974 bounding boxes. The dataset for this study was constructed based on the Global Wheat Detection Dataset and the Wheat Sheaf Detection Dataset, which was published by PP Flying Paddle. We selected three attention mechanisms, Large Separable Kernel Attention (LSKA), Efficient Channel Attention (ECA), and Efficient Multi-Scale Attention (EMA), to enhance the feature extraction capability of the backbone network and improve the accuracy of the underlying model. First, the attention mechanism was added after the base and output phases of the backbone network. Second, the attention mechanism that further improved the model accuracy after the base and output phases was selected to construct the model with a two-phase added attention mechanism. On the other hand, we constructed SimLightFPN to improve the model accuracy by introducing SimConv to improve the LightFPN module. The results of the study showed that the YOLO-FastestV2-SimLightFPN-ECA-EMA hybrid model, which incorporates the ECA attention mechanism in the base stage and introduces the EMA attention mechanism and the combination of SimLightFPN modules in the output stage, has the best overall performance. The accuracy of the model was P=83.91%, R=78.35%, AP= 81.52%, and F1 = 81.03%, and it ranked first in the GPI (0.84) in the overall evaluation. The research examines the deployment of wheat ear detection and counting models on devices with constrained resources, delivering novel solutions for the evolution of agricultural automation and precision agriculture.

Wheat, being a crucial global food crop, holds immense significance for food safety and agricultural economic stability, as the quality and condition of its grains are critical factors. Traditional methods of wheat grain detection are inefficient, and the advancements in deep learning offer a novel solution for fast and accurate grain recognition. This study proposes an improved deep learning model based on YOLOv8n, referred to as YOLO-SDL, aiming to achieve efficient wheat grain detection. A high-quality wheat grain dataset was first constructed, including images of perfect, germinated, diseased, and damaged grains. Multiple data augmentation techniques were employed to enhance the dataset’s complexity and diversity. The YOLO-SDL model incorporates the ShuffleNetV2 architecture in its backbone and combines depthwise separable convolutions (DWConv) with the large separable kernel attention (LSKA) mechanism in its neck structure, significantly improving detection speed and accuracy while ensuring the model remains lightweight. The results indicate that YOLO-SDL achieves superior performance in wheat grain detection, balancing lightweight design and performance optimization. The model achieved a P of 0.942, R of 0.903, mAP50 of 0.965, and mAP50-95 of 0.859, with low computational complexity, making it suitable for resource-constrained environments. These findings demonstrate the efficiency of the ShuffleNetV2, DWConv, and LSKA structures. The proposed YOLO-SDL model provides a new technical solution for agricultural automation and serves as a reliable reference for detecting other crops.

The lightweight, small diameter, and irregular shape of small vegetable seeds create difficulties for online monitoring of sowing quality. We propose a machine vision-based online monitoring method with a sowing test bench designed to address the challenges. Vision devices and image processing systems are employed to detect the quality of seed sowing. Firstly, the seed segmentation image is obtained by completing the steps of median filtering, graying and image segmentation.We then implement the Circumscribed circle method to detect the position of the seed. Afterward, the coordinate system is converted using calibrated results to eliminate non-seed impurities. Finally, we count the number of identified seeds to evaluate the recognition accuracy. The trial compared three algorithms: the image segmentation algorithm OTSU, the critical point localization algorithm SIFT, and the algorithm designed in the experiment. The algorithm we designed outperformed the others regarding recognition accuracy and processing time. The experimental method employed in the study encompasses various functionalities, including seeding counting, understanding detection, replaying, and monitoring deviations from seed bands during sowing. Cabbage seeds (1.50mm-2.00mm), tomato seeds (1.00mm-1.50mm), and radish seeds (0.50mm-1.00mm) were selected as the experimental subjects due to the uniform particle size distribution. The results demonstrate that the relative error between the online image recognition algorithm and the system’s seeding rate monitoring is below 3.0%. Moreover, the accuracy of missed seeding monitoring is 92.5%, while the accuracy of deviation monitoring during seeding is 92.0%. We observed that the image recognition algorithm employed in the system achieved a processing time of 0.29 seconds, with a seed band recognition rate of 96.8%, fulfilling the monitoring requirements for small seed sowing experiments. The processed images and collected data are presented in real-time on the upper computer terminal. This study significantly contributes to the advancement of small-grain vegetable seed sowing monitoring technology.