Method and device for live-streaming clothing dress-up based on adaptive threshold segmentation
An adaptive threshold and clothing technology, applied in the field of image processing, can solve the problems of low segmentation accuracy, addition, and poor segmentation effect of image scene segmentation, and achieve the effect of improving segmentation accuracy and processing efficiency, optimizing processing methods, and improving processing efficiency.
Active Publication Date: 2021-07-23
BEIJING QIHOO TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing image segmentation method does not consider the proportion of the foreground image in the frame image when performing scene segmentation processing, so when the proportion of the foreground image in the frame image is small, it is easy to use the existing image segmentation method Divide the pixels that actually belong to the edge of the foreground image into the background image, and the resulting image segmentation results have low segmentation accuracy and poor segmentation effect
Therefore, the image segmentation method in the prior art has the problem of low segmentation accuracy of image scene segmentation, and the obtained image segmentation results cannot be used to add clothing decoration effects to the body regions of the characters in the video well and accurately. , the resulting processed video data has a poor display effect
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0106] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0107] figure 1 It shows a schematic flow diagram of a live clothing dressing method based on adaptive threshold segmentation according to an embodiment of the present invention, as shown in figure 1 As shown, the method includes the following steps:
[0108] Step S100, acquiring in real time a current frame image of a specific object in the video captured and / or recorded by the image acquisition device.
[0109] In this embodime...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a live clothing dressing method, device, computing device and computer storage medium based on adaptive threshold segmentation. The method includes: acquiring a current frame image containing a specific object in a video in real time; performing scene segmentation processing on the current frame image , obtain the foreground probability information for a specific object, determine the proportion of the foreground area according to the foreground probability information, and perform mapping processing on the foreground probability information according to the proportion of the foreground area, and obtain the image segmentation result corresponding to the current frame image; according to the image segmentation As a result, determine the processed foreground image, and determine the limb area in the processed foreground image according to the processed foreground image; add clothing decoration effects to the limb area according to the clothing decoration selected by the user, and obtain the frame processing image; The processed image covers the current frame image to obtain the processed video data; the processed video data is displayed. The technical solution can accurately add clothing decoration effects to the characters.
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 live clothing dressing based on adaptive threshold segmentation. Background technique [0002] In the prior art, when the user needs to personalize the video, such as adding clothing effects to the characters in the video, the image segmentation method is often used to perform scene segmentation processing on the frame images in the video. The image segmentation method of deep learning can achieve the segmentation effect at the pixel level. However, the existing image segmentation method does not consider the proportion of the foreground image in the frame image when performing scene segmentation processing, so when the proportion of the foreground image in the frame image is small, it is easy to use the existing image segmentation method The pixels that actually belong to the edge of the foregr...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/11G06T7/194H04N21/2187
CPCG06T2207/10016G06T2207/20221G06T7/11G06T7/194H04N21/2187
Inventor 赵鑫邱学侃颜水成
Owner BEIJING QIHOO TECH CO LTD