A video content recognition method, device, medium and system

A technology for video content recognition and content recognition, applied in the field of video processing, can solve the problems of low recognition accuracy, high data transmission overhead, and high difficulty in equipment expansion and upgrading, and achieve the goal of ensuring accuracy, ensuring integrity, and reducing data transmission overhead. Effect

Active Publication Date: 2021-11-19
CHINA MOBILE COMM LTD RES INST +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] Embodiments of the present invention provide a video content recognition method, device, medium, and system, which are used to solve the problem of high data transmission overhead, high difficulty in equipment expansion and upgrade, or low recognition accuracy when video content is automatically recognized in real time in a security monitoring system. question

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
  • A video content recognition method, device, medium and system
  • A video content recognition method, device, medium and system
  • A video content recognition method, device, medium and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Embodiment 1 of the present invention provides a method for identifying video content, and the method describes the method for identifying video content from the side of a content distribution server. The step-by-step process can be as follows figure 1 shown, including:

[0064] Step 101, task generation.

[0065] In this step, the content distribution server may segment the video captured by the camera in real time. Specifically, it may, but is not limited to, segment the video captured by the camera in real time according to a set duration. And each video segment obtained by segmentation can be packaged as a video task.

[0066] Step 102, task allocation.

[0067] In this step, the content distribution server may, for each video task, assign the video task to a management node in the edge device, the edge device is pre-selected, and instruct the management node to assign the video task to at least one edge The device is configured to perform content identification...

Embodiment 2

[0082] Embodiment 2 of the present invention provides a method for identifying video content, and the method describes the method for identifying video content from the side of an edge device serving as a management node. The step-by-step process can be as follows image 3 shown, including:

[0083] Step 201, receiving a video task.

[0084] In this step, the edge device as the management node can receive the video task assigned by the content distribution server.

[0085] Step 202, task broadcasting.

[0086] In this step, the edge device serving as the management node may broadcast the task requirement corresponding to the video task to pre-selected edge devices, each edge device except itself.

[0087] Step 203, receiving an available resource prediction result.

[0088] In this step, the edge device as the management node can receive the available resource prediction result reported by the edge device, the available resource prediction result is predicted by the edge d...

Embodiment 3

[0099] Embodiment 3 of the present invention provides a method for identifying video content, and the method describes the method for identifying video content from the side of an edge device that is a non-management node. The step-by-step process can be as follows Figure 4 shown, including:

[0100] Step 301, receiving a broadcast.

[0101] In this step, the edge device as the non-management node may receive the task requirement corresponding to the video task broadcast by the edge device as the management node.

[0102] Step 302. Determine the forecast result of available resources.

[0103] In this step, the edge device as a non-management node may determine the available resource prediction result and report it to the edge device as a management node. The available resource prediction result is predicted, and the remaining available resource information after removing the resource loss corresponding to the task requirement among the currently available resources instru...

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 present invention relates to the technical field of video processing, in particular to a method, device, medium and system for identifying video content. Aiming at the problem that in the existing security monitoring system, when the video content is automatically recognized in real time, the resource occupancy rate of the video recognition terminal is high or the recognition accuracy is low, the embodiment of the present invention provides a real-time video processing on the edge side, based on the edge device Redundant resources and computing power to cooperate to complete the real-time video recognition scheme. This solution uses existing edge devices (such as set-top boxes, smart home gateways, etc.) to form an edge computing network, and completes real-time video processing on the edge side through a series of methods such as video task allocation, scheduling, and prediction of available resources.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a method, device, medium and system for identifying video content. Background technique [0002] In current security surveillance systems, camera equipment is used to capture video. After the video is collected, the existing technology generally adopts the following schemes for video content identification, and realizes security monitoring by identifying specified events in the video, such as falling objects, illegal parking, theft, etc.: [0003] 1. Manual video recognition: Through the real-time observation of video by monitoring personnel, the recognition of events in the video is completed. [0004] 2. Playback recognition after recording: record video in real time to storage device for subsequent recognition. [0005] 3. Cloud or server-side recognition: Real-time transmission of video to the cloud or server-side for recognition. [0006] 4. After the vid...

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): H04N21/4402H04N21/845H04N5/232
CPCH04N21/4402H04N21/8456H04N23/80
Inventor 杨凯
Owner CHINA MOBILE COMM LTD RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap