Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A high-purity face recognition sample extraction method based on tracking algorithm

A face recognition and tracking algorithm technology, applied in the field of computer vision, can solve problems such as general slowness

Active Publication Date: 2021-04-23
以萨技术股份有限公司 +1
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In contrast, deep learning-based tracking algorithms, such as GOTURN, are generally slow and cannot be applied industrially

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 high-purity face recognition sample extraction method based on tracking algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention.

[0024] According to an embodiment of the present invention, a relatively high-purity face recognition sample extraction method based on a tracking algorithm is provided.

[0025] Such as figure 1 As shown, the higher purity face recognition sample extraction method based on the tracking algorithm according to the embodiment of the present invention comprises the following steps:

[0026] Step S101, sample collection: pre-collect part of the real scene video, and extract some pictures from th...

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 relatively high-purity human face recognition sample extraction method based on a tracking algorithm, which includes the following steps: sample collection: pre-collect part of the real scene video, and extract part of the picture from the video, and manually mark the human face rectangle frame, collect face sample data; model training: use the collected face sample data to train the YOLOv2 network; face recognition: use the YOLOv2 network as a face detector for face recognition; IOU tracking: use ROI to detect The face is tracked and put into the ROI TrackingPool; analysis and storage: analyze the objects in the IOU TrackingPool, and send the target that meets the requirements to the DSST tracker. The present invention: through the face recognition sample extraction method based on the tracking algorithm, it can not only be used to extract the face to be tracked, but also can be used to track the extracted tracking target, and the extracted sample has high purity and usable value, and is simple Easy to implement and high computational efficiency.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a relatively high-purity face recognition sample extraction method based on a tracking algorithm. Background technique [0002] Target tracking is a general single target tracking. The first frame is given a rectangular frame. This frame is manually marked in the database. In actual situations, it is mostly the result of the detection algorithm, and then the tracking algorithm needs to follow this frame in subsequent frames. . It is generally accepted that target visual tracking can be divided into two categories: generative model method and discriminative model method. At present, the more popular method is the discriminative method, also called detection and tracking. In the generation method, the target area is modeled in the current frame, and the area most similar to the model is found in the next frame to predict the position. The more famous ones include Kalman fi...

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): G06K9/62G06K9/00G06T7/246
CPCG06T7/248G06T2207/10016G06T2207/30201G06V40/16G06F18/214
Inventor 武传营李凡平石柱国
Owner 以萨技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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