Diaphorina citri intelligent detection method and device based on deep learning
The invention discloses a diaphorina citri intelligent detection method and device based on deep learning, and the method comprises the following steps: S1, collecting a diaphorina citri color image in a natural orchard scene, carrying out the preprocessing of the collected image, and making a diaph...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a diaphorina citri intelligent detection method and device based on deep learning, and the method comprises the following steps: S1, collecting a diaphorina citri color image in a natural orchard scene, carrying out the preprocessing of the collected image, and making a diaphorina citri data set; s2, improving a YOLOv5-s network model, performing iterative training on the improved YOLOv5-s network model by using the diaphorina citri dataset to obtain an optimal model, and taking the optimal model as a diaphorina citri detection model; s3, using two servo steering engines to form a rotatable holder, and carrying a zoom camera to form an image collector; deploying the phylloxera detection model on an embedded device, and using the embedded device to control an image collector; and S4, inputting the image obtained by the image collector into the diaphorina citri detection model for identification, and determining whether the diaphorina citri exists in the shot image and the position of th |
---|