Video portrait file processing method and system thereof

A processing method and technology for portraits, which are applied in still image data retrieval, still image data indexing, metadata still image retrieval, etc., to achieve the effect of strong filing ability, high flexibility, and reduced computing time

Inactive Publication Date: 2019-02-15
南京物盟信息技术有限公司
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To sum up, the image-based face recognition technology has developed to a certain extent in various dimensions. Whether it is face recognition or one-person-one-file, it can be realized to a certain extent with the support of the above technologies. Lack of a flexible platform to support data management applications in complex scenarios

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
  • Video portrait file processing method and system thereof
  • Video portrait file processing method and system thereof
  • Video portrait file processing method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Embodiment 1: as figure 1 , a video portrait file processing method, the method mainly includes the following steps:

[0065] S101. Acquire a real-time image data set.

[0066] Specifically, the front-end data acquisition sources are mainly arranged in the entrance and exit areas of people, such as underground parking lots, railway traffic entrances and exits, hotels, hotels, hotels, office buildings, entertainment venues, etc.; data acquisition equipment can use analog cameras, digital cameras, network cameras or digital Cameras, etc. Various types of cameras can be added, modified and deleted during management, and the name is defined on the user interface according to the actual location of the camera, which is equivalent to recording the location information of the image here; the collected data can be video streams and images, and the corresponding File formats include image file formats of BMP, JPEG, JPG, JP2, TIFF, GIF, RAW, DAT and video file formats of MPG, MP...

Embodiment 2

[0082] Embodiment 2: a kind of video portrait file processing system, such as figure 2 with image 3 , the cameras arranged in each scene are connected to the access switch, the access switch is connected to the core switch, and the core switch is connected to other access switches. Some of the access switches are connected to the server and data storage center, and the other part of the access switch is connected to the network monitoring The client, the multi-screen display system and the digital matrix device transmit data through the aggregation switch and the core switch, and store the data through the data storage center and the server. Based on the video portrait file processing method of Embodiment 1, the portrait can be displayed in real time through the multi-screen display system Dynamic Information. The network monitoring client specifically includes:

[0083] The image acquisition module is used to obtain real-time image data collection;

[0084] The image prepr...

Embodiment 3

[0091] Embodiment 3, a kind of video portrait file processing method, comprises the following steps:

[0092] Obtain a collection of historical image data through a video image acquisition terminal (such as a camera), that is, obtain all historical image data within a certain time window. This type of data can be pictures or video clips. During the image acquisition process , by using image filtering software to filter the graphic data to remove meaningless pictures such as non-portraits and blurred pictures.

[0093] Set the target feature, the target feature is variable; in various fields of application, the target feature can be flexibly set, for example, the target feature can be age feature, height feature, gender feature, etc. Compare the target features with the historical image data set, calculate the associated weight of the two, and set the classification threshold. The classification threshold is an interval value. By defining the interval value, the error toleran...

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 video portrait file processing method and a system thereof, which are applied in the technical field of video surveillance and solve the technical problem of inaccurate portrait clustering analysis. The technical scheme essentials are a video portrait file processing method, comprising the following steps: collecting image information to obtain image data set; Acquiring the existing archives, identifying the portrait information in the image data set, comparing the portrait information with the portrait in the existing archives, and obtaining the contrast result as portrait matching degree; Comparing portrait matching degree and threshold, when portrait matching degree is greater than or equal to threshold, portrait information is classified into existing portraitarchives; when portrait matching degree is less than threshold, portrait archives are created, and portrait information is classified into new portrait archives. The technical effect is to establisha clear portrait archives and portrait relationship topology, so that portrait archives group according to the characteristics of clustering labeling, easy to analyze.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a method and system for processing video portrait files. Background technique [0002] With the promotion of big data-driven deep learning in portrait applications, portrait acquisition and face analysis technologies continue to mature and are gradually applied to work. Through real-time collection of personnel portrait photos, a large number of valuable personnel portrait photos have been accumulated. [0003] The current mainstream face recognition technology can basically be classified into three categories, namely: methods based on geometric features, methods based on templates and methods based on models. Specifically, such as Local Face Analysis, Eigenface or PCA. On the basis of traditional eigenfaces, the study of eigenvectors with large eigenvalues ​​(i.e., eigenfaces) is not necessarily the direction of good classification performance. Based on this, a variety...

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): G06F16/51G06F16/58
Inventor 梁少波
Owner 南京物盟信息技术有限公司
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