Road surface hidden spalling point detection method and system based on depth image recognition
The invention discloses a pavement hidden peeling point detection method and system based on depth image recognition, and the method comprises the following steps: S1, collecting a pavement image in a wet state, and defining a region with a prominent shadow in the pavement image as a hidden peeling...
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 pavement hidden peeling point detection method and system based on depth image recognition, and the method comprises the following steps: S1, collecting a pavement image in a wet state, and defining a region with a prominent shadow in the pavement image as a hidden peeling point; s2, carrying out noise elimination preprocessing on the acquired pavement image; s3, marking hidden peeling points for the preprocessed pavement image; s4, learning the pavement image marked with the hidden spalling points by adopting a deep learning framework, and further constructing a pavement hidden spalling point detection model; and S5, using the pavement hidden peeling point detection model to perform hidden peeling point identification on the pavement image of which the hidden peeling points are not marked. Based on the idea of recognizing the initial state of pavement damage in a specific environment, an image recognition technology in a deep learning technology is adopted to recognize the hidden sp |
---|