Image extraction model construction method and device, image query method and device and video generation method and device

The invention discloses an image extraction model construction method and device, an image query method and device and a video generation method and device. The method comprises the steps of obtaining all video frame images in a video library; performing coding processing on each video frame image i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HUANG CHONGPENG, PENG XIAOGANG, LIN YIGANG
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 an image extraction model construction method and device, an image query method and device and a video generation method and device. The method comprises the steps of obtaining all video frame images in a video library; performing coding processing on each video frame image in all the video frame images to obtain a first video frame image coding sample set; performing data enhancement processing on each video frame image in all the video frame images, and encoding the enhanced images to obtain a second video frame image encoding sample set; and inputting the first video frame image coding sample set and the second video frame image coding sample set into the pre-trained image extraction model for training, so that the image extraction model can accurately extract the features of the video frames, and the accuracy of video frame image matching is improved. 本发明公开了一种图像提取模型构建、图像查询和视频生成方法、装置,所述方法包括获取视频库中的所有视频帧图像;对所有视频帧图像中的每一个视频帧图像进行编码处理,得到第一视频帧图像编码样本集;将所有视频帧图像中的每一个视频帧图像进行数据增强处理,并将增强后的图像进行编码