Beam field construction safety quality monitoring method and system based on AI identification

The invention provides a beam field construction safety quality monitoring method and system based on AI identification, and the method comprises the steps: in a debugging process of a construction safety monitoring network, carrying out the debugging of a construction safety monitoring network base...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHENG WEIYONG, HU CHANGJUN, ZHOU RAN, YAO XIONG, ZHANG SHUNWEN, ZHAO YONGZHI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a beam field construction safety quality monitoring method and system based on AI identification, and the method comprises the steps: in a debugging process of a construction safety monitoring network, carrying out the debugging of a construction safety monitoring network based on a preset safety distance, an image semantic descriptor of a beam field real-time monitoring image of each debugging learning sample, and an image semantic descriptor of a behavior reference image; a classification interface between debugging learning examples of different construction behaviors in P debugging learning examples is strengthened, so that a construction safety monitoring network can draw feature knowledge of descriptors including stability for image semantic deviation, and a beam field real-time monitoring image is accurately corresponding to a corresponding behavior reference image; the information deviation of images with indefinite construction behaviors is overcome, meanwhile, feature informat