Method and device for obtaining character segment of video data and electronic equipment

Abstract

The embodiment of the invention provides a method and device for obtaining video data character fragments and electronic equipment, and the method comprises the steps: obtaining a to-be-processed video image; splitting the video image to be processed into a plurality of single-frame images which are continuous in time sequence; inputting the plurality of single-frame images into a preset first model for face recognition detection to obtain a target person image; inputting the obtained video images into a preset second model for scene classification to obtain classified scene images; matching the target person image with each classification scene image according to the timestamp to obtain a target person included in each classification scene image; and combining the classification scene images including the same target person to obtain a first video clip set. The human face recognition technology and the scene detection technology are combined together to generate the presentation segment of the target person, time is saved, and meanwhile scene type images are combined, so that the hops of actors in movie and television drama segments become small.

Description

technical field [0001] The present application relates to the technical field of Internet image processing, and in particular to a method, device and electronic equipment for acquiring character fragments of video data. Background technique [0002] With the development of the Internet, more and more users like to use the Internet to watch videos. Due to the influence of each user's own education, social experience, personality and other factors, they will have their own unique preferences for different actors. For example, some users I will have a strong interest in the performance of a certain actor in a certain scene in a film and television drama, but I am not interested in the fragments of other actors in a film and television drama. [0003] In the prior art, computer vision technology is used to analyze video data, extract video frames including target characters, and then splicing the videos into character segments for display. [0004] However, the inventors of the...

AI Technical Summary

Problems solved by technology

[0004] However, the inventors of the present application found that only extracting the video frames containing the target person is prone to jumping character segments, resulting in discontinuous character segments and poor character segment quality

Images