Scene-based edge analysis algorithm issuing method and device and storage medium

An edge analysis and algorithm technology, applied in the field of image processing and computing, can solve problems such as configuration errors, inappropriate applications, and cumbersome steps, and achieve the effects of algorithm configuration, simplification of cumbersome operations, and customer service pain points

Pending Publication Date: 2021-07-02
小视科技(江苏)股份有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is necessary to implant face / human body analysis, behavior early warning analysis, aircraft early warning analysis, population statistics, hot area analysis and other algorithm types on the edge analysis host. If it is subdivided, there will be dozens or hundreds of types. Algorithms, so it is necessary to manually configure the platform side for different application scenarios, and configure the camera service. The steps are cumbersome and troublesome. At the same time, configuration errors are prone to lead to inappropriate applications.

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
  • Scene-based edge analysis algorithm issuing method and device and storage medium
  • Scene-based edge analysis algorithm issuing method and device and storage medium
  • Scene-based edge analysis algorithm issuing method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] The installation site is a residential area, and the original camera is installed at the entrance and exit of the residential area. The original camera is mainly used for security monitoring at the entrance and exit of the residential area. It is relatively small. Through the pre-analysis of the system, it is concluded that the most suitable analysis functions in this scenario are face detection / face comparison similarity of 95%, area intrusion of 87%; the most unsuitable analysis functions are parking detection of 11%, thermal Area analysis is 9%; the platform pushes the analysis result to the operator for configuration. The result is also consistent with the characteristics of the camera. The field of view is small and the shooting range is limited. Parking detection and hot area analysis are really not suitable for this scene. Finally, through the recommendation of the platform and considering the needs of customers, the camera was finally configured with face detecti...

Embodiment 2

[0079] The installation location is a certain street (there are both installed cameras and uninstalled cameras). For the installed cameras, the pictures or video streams captured by the cameras are obtained for pre-analysis and the analysis results are pushed to the platform. The method is the same as the implementation case 1. For a certain scene on the street, if you need to install a new camera, you need to call the panoramic map through the platform, enter the street location in the panoramic map to search, and manually move the mouse to adjust in the map to find 2-3 Appropriate pre-installation location, and keep the panorama of the location and submit it to the system for analysis; if the panorama map of the street is not found through the panorama map, it is necessary to manually conduct the actual survey and upload the location picture of the on-site survey; the above steps have been obtained 2-3 pre-installation locations to analyze the materials. The system analyzes t...

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 scene-based edge analysis algorithm issuing method and device and a storage medium. The scene-based edge analysis algorithm issuing method comprises the following steps: acquiring an existing video stream or picture of an installed camera; performing scene recognition on the acquired video streams or photos by adopting a neural network model, and outputting a to-be-classified scene; and comparing the to-be-classified scene with a target scene in the platform side scene library, and configuring an edge analysis algorithm corresponding to the target scene in the scene library according to a comparison result. According to the invention, through pre-analysis of the edge analysis host and comparison of the scene library at the platform side, the most appropriate and most improper algorithm results are obtained, and through combination with simple configuration of personnel, the most reasonable scene algorithm application is obtained. The method has the greatest advantages that the complexity of personnel operation is simplified by utilizing the method, the most reasonable scheme recommendation is given, the use pain point of a customer is overcome, and the most rationalization of algorithm configuration is realized in combination with scene-based pre-analysis.

Description

technical field [0001] The invention relates to the field of image processing calculations, in particular to methods for issuing different algorithms for image processing. Background technique [0002] In recent years, the national government has continued to support the construction of safe cities and smart cities, and increased the construction of security projects using video surveillance as a technical means. The automatic monitoring, intelligent recording and alarming of vehicles, objects and events can improve the comprehensive security management level of the site. Therefore, it is necessary to implant face / human body analysis, behavior early warning analysis, aircraft early warning analysis, population statistics, hot area analysis and other algorithm types on the edge analysis host. If it is subdivided, there will be dozens or hundreds of types. Algorithms, so manual configuration on the platform side is required for different application scenarios to configure cam...

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 Applications(China)
IPC IPC(8): G06K9/62G06F16/55G06F16/75G06N3/04G06N3/08
CPCG06N3/084G06N3/08G06F16/55G06F16/75G06N3/045G06F18/22G06F18/214G06F18/241
Inventor 杨帆汪帮磊
Owner 小视科技(江苏)股份有限公司
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