Method, device and computing device for dressing up video characters based on scene segmentation

Abstract

The present invention discloses a video character dress-up method, device, computing device and computer storage medium based on scene segmentation. The method includes: acquiring a current frame image containing a specific object in a video in real time; inputting the current frame image into a scene segmentation network , to obtain the scene segmentation result corresponding to the current frame image; according to the scene segmentation result corresponding to the current frame image, determine the contour information of the facial region of the specific object and / or the contour information of the facial features region of the specific object; according to the contour information of the facial region and / or the outline information of the facial features region, adding beautification effects to obtain a frame-processed image; covering the frame-processed image with the current frame image to obtain processed video data; displaying the processed video data. The technical solution can obtain the scene segmentation result corresponding to the frame image in real time and accurately, and based on the scene segmentation result can more accurately add beautification effects to the characters in the frame image.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device, computing device and computer storage medium for dressing up video characters based on scene segmentation. Background technique [0002] In the existing technology, image scene segmentation processing methods are mainly based on fully convolutional neural networks in deep learning. These processing methods use the idea of ​​transfer learning to migrate the network obtained through pre-training on large-scale classification data sets to image processing methods. The segmentation network is trained on the segmentation data set to obtain the segmentation network for scene segmentation, and then the segmentation network is used to segment the scene of the image. [0003] The network architecture used in the segmentation network obtained in the prior art directly uses the image classification network, and the size of the convolution block in the conv...

AI Technical Summary

Problems solved by technology

However, for image scene segmentation, the scene often contains objects of different sizes. Using a segmentation network with a fixed-size receptive field often causes problems when dealing with too large and too small objects. For example, for smaller objects, the receptive field It will capture too much background around the target, thereby confusing the target with the background, causing the target to be missed and misjudged as the background; for larger targets, the receptive field can only capture a part of the target, which makes the target category judgment biased, resulting in Discontinuous Segmentation Results

Therefore, the image scene segmentation processing method in the prior art has the problem of low accuracy of image scene segmentation, so the obtained segmentation results cannot be used to add beautification effects to the characters in the video frame image, and the obtained Display of processed video data is poor

Images