Unlock instant, AI-driven research and patent intelligence for your innovation.

Content-based detection method for inappropriate content in high-duration and complex scene videos

A complex scene and content detection technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of relying on labor, time-consuming, and detection methods for bad content in complex scenes and videos, and achieve the effect of overcoming inefficiency

Active Publication Date: 2022-07-15
LANZHOU UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing million-level resolution, video review method with a duration of more than 30 minutes, and complex scene changes that are highly dependent on manual work, take a long time, and consume huge computing resources, the present invention proposes a content-based high-duration complex scene video defect Content detection method for efficient and intelligent review

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Content-based detection method for inappropriate content in high-duration and complex scene videos
  • Content-based detection method for inappropriate content in high-duration and complex scene videos
  • Content-based detection method for inappropriate content in high-duration and complex scene videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] See figure 1 , the present invention's content-based high-duration complex scene video bad content detection method, comprising the steps:

[0044]S1: construct a high and low resolution feature map fusion unit module, and use the high and low resolution feature map fusion unit module to construct a multi-resolution image preprocessing network;

[0045] S2: Label the megapixel-level video data, input the multi-resolution imag...

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

No PUM Login to View More

Abstract

The invention discloses a content-based detection method for bad video content in high-duration and complex scene videos. Format; build a low-latency complex scene segmentation network; use the processed video dataset for training to obtain a low-latency complex scene segmentation model; use a low-latency complex scene segmentation model and a dual-process scheduling scheme to perform video thumbnails and key positions on videos Annotate; construct an S3D‑G network that separates the temporal and spatial domains for convolution; trains to obtain a video classification network model; inputs the processed abbreviated video into the video classification network model for video classification. The invention overcomes the disadvantages of low efficiency, high hardware requirements and high delay in processing long video with high resolution and complex scene changes in the prior art.

Description

technical field [0001] The present invention relates to a video content auditing method, in particular to a content-based detection method for bad video content in complex scenes with high duration. Background technique [0002] The rapid development of Internet technology and self-media has brought a lot of convenience to people's work and life. However, while online video resource sharing provides people with convenience, some bad videos such as violence and pornography seriously endanger the physical and mental health of young people. my country's "Constitution" and "Minors Protection Law" expressly prohibit harmful video content. This makes video review technology an indispensable and important technology for major video websites, which has attracted widespread attention. [0003] Existing video review methods mostly use manual methods, and video reviewers are often inefficient when reviewing. However, some intelligent recognition methods that do not require human inte...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/40G06V10/774G06V10/80G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214G06F18/24G06F18/253
Inventor 赵宏王奡隆张陈鹏党育杨策赵凡胡质彬倪志敏
Owner LANZHOU UNIVERSITY OF TECHNOLOGY