Live broadcast content screening method based on image, apparatus, equipment and storage medium thereof
A screening method and image technology, applied in the computer field, can solve the problems of low efficiency, non-uniform standards, high cost of live content screening, etc., and achieve the effect of high efficiency and fast evaluation speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] figure 1 It is a flow chart of the image-based live content screening method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of evaluating and screening live content. This method can be executed by an image-based live content screening device, and can be It is integrated in the live content screening server, specifically including the following steps:
[0030] S110. Acquire live video, and extract several video frame images from the video.
[0031] With the development of Internet technology, the concept of live broadcast has been expanded and developed. Through network signals, online watching of sports events, activities, news and entertainment performances has become the mainstream of current live broadcast. When the host is performing live broadcast, the video content in the live broadcast can be obtained through the live broadcast server.
[0032] Essentially, video consists of multiple consecutive frames. Theref...
Embodiment 2
[0042] figure 2 It is a schematic flowchart of an image-based live content screening method provided in Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, after extracting several video frame images from the video, before inputting the video frame images into the evaluation convolutional neural network classifier, the following steps are added : converting the video frame image into an image with a preset resolution; correspondingly, inputting the video frame image into the evaluation convolutional neural network classifier, specifically optimized as: inputting the image into the evaluation convolutional neural network classifier .
[0043] Correspondingly, the image-based live broadcast content screening method provided in this embodiment specifically includes:
[0044] S210. Acquire live video, and extract several video frame images from the video.
[0045] S220. Convert the video frame...
Embodiment 3
[0053] image 3 It is a schematic flowchart of an image-based live content screening method provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, before inputting the spectral image into the evaluation convolutional neural network classifier, the following steps are added: classify the video frame images according to the live scene; Correspondingly, the inputting the video frame image into the evaluation convolutional neural network classifier includes: inputting the video frame image into the evaluation convolutional neural network classifier corresponding to the live scene.
[0054] Correspondingly, the image-based live broadcast content screening method provided in this embodiment specifically includes:
[0055] S310. Acquire live video, and extract several video frame images from the video.
[0056] S320. Classify the video frame images according to live scenes.
[0057] At pr...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com