Abstract
A fully automatic plug seedling device is designed, its structure and working principle are introduced, and a plug seedling hole identification method based on CNN is proposed to address the issue of adjacent holes in order to increase the automation and intelligence of the vegetable transplanting machine. The issue of low recognition accuracy of plug seedlings is brought on by intertwined stems and leaves. This study first grows tomato seedlings in an artificial greenhouse and then utilizes an SLR camera to take pictures of those plants. The photos are then subjected to the appropriate preprocessing, such as separating the complete hole plate image into several hole images in accordance with the hole plate standards to facilitate recognition. The CNN model is then finished being trained after receiving the processed image. Relu, which has a better ability for classification, is chosen as the activation function of the convolutional layer after the network is enlarged on the basis of LeNet-5CNN. In addition, the over-fitting issue of the model is resolved using data augmentation technology, resulting in a recognition accuracy of the test set of the model that is as high as 0.985. The automatic vegetable transplanting machine can greatly increase the automation and intelligence level of the plug seedling recognition model based on CNN, which has high recognition accuracy and generalization ability. This model also solves the main technical problems of the plug seedling device and improves the machine's ability to transplant.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call