Cross-scene VOCs gas leakage detection method and system and storage medium

The invention discloses a cross-scene VOCs gas leakage detection method and system and a storage medium, and the method comprises the following steps: obtaining infrared video data with VOCs leakage and without leakage, and carrying out the data preprocessing of the infrared video data; removing a s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CAO YANG, KANG YU, XU ZHENYI, TAN JIFANG, XIA XIUSHAN
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 discloses a cross-scene VOCs gas leakage detection method and system and a storage medium, and the method comprises the following steps: obtaining infrared video data with VOCs leakage and without leakage, and carrying out the data preprocessing of the infrared video data; removing a static background of the infrared video by adopting GMM, and extracting a suspected VOCs leakage area in the infrared image; carrying out pre-training on a target detection model, namely a Faster RCNN neural network model; through the trained Faster RCNN neural network model, constructing a source domain feature data set and a target domain feature data set in transfer learning; and identifying the infrared suspected VOCs leakage region extracted by the GMM by using a domain adaptive transfer learning method. The defects of the existing method can be overcome, the domain knowledge of the VOCs gas area in the infrared video is fully utilized to segment the suspicious smoke area in the video frame, then the Faster RCN