Pavement crack detection method based on visual neural network model

According to the pavement crack detection method based on the visual neural network model, filtering is carried out on a pavement detection visual image, so that the image detection recognition rate is improved; by combining weather marks, the visual neural network model of the pavement features is...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HE YAN, WANG FENGQIN, CHEN YAN, YANG YONGSHUANG, HU YING
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:According to the pavement crack detection method based on the visual neural network model, filtering is carried out on a pavement detection visual image, so that the image detection recognition rate is improved; by combining weather marks, the visual neural network model of the pavement features is established, and the recognition precision of the visual detection method on the image features is improved, so that the application effect of fixed pavement defect detection is improved. 本发明提出一种基于视觉神经网络模型的路面裂缝检测方法,通过对路面检测视觉图像实施滤波,提高图像检测识别率;通过结合天气标记,建立路面特征的视觉神经网络模型,提高视觉检测方法对图像特征的识别精度,从而改善固定式路面缺陷检测的应用效果。