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

Face-tracking method, device and terminal

A face tracking and tracking technology, applied in the field of face tracking, can solve the problems of low efficiency and large amount of calculation

Active Publication Date: 2019-02-12
ZDST COMM TECH CO LTD
View PDF11 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventors of the present invention found that the current face tracking technology often needs to perform face detection and recognition in each frame of image, which has a large amount of calculation and low efficiency

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
  • Face-tracking method, device and terminal
  • Face-tracking method, device and terminal
  • Face-tracking method, device and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] see figure 1 , figure 1 It is a schematic flowchart of a face tracking method provided by an embodiment of the present invention. Such as figure 1 As shown, the method includes:

[0037] 110. Acquire one or more human face images including human faces in a first video frame image in the video frame image sequence.

[0038] Wherein, the video frame image sequence includes several frame images, the first video frame image is one frame image in the video frame image sequence, and the frame image includes a human face. For example, assuming that the video frame image sequence includes 100 frame images, and a human face appears in the 50th frame image, then the first video frame image is the 50th frame image in the video frame image sequence.

[0039]Wherein, the human face image is the human face part detected in the first video frame image, a human face image only contains a human face, there are no other human faces, and the boundary of the human face image is almost ...

Embodiment 2

[0060] see Figure 4 , Figure 4 It is a schematic flowchart of an application scenario of a face tracking method provided by an embodiment of the present invention. When the face tracking method is applied to the suspect tracking system, such as Figure 4 As shown, the method includes:

[0061] 211. Acquire the first video frame image in the video frame image sequence;

[0062] 212. Obtain a face image in the first video frame image through the MTCNN algorithm;

[0063] 221. Extracting face feature vectors from face images through the FaceNet algorithm;

[0064] 222. According to the face feature vector, use the KNN algorithm to judge whether the face image matches the preset suspect face image;

[0065] 223. If it matches, use the face image as the face image to be tracked;

[0066] 224. Extracting the first sift feature value and the second hash feature value from the face image to be tracked;

[0067] 231. Continue to obtain the video frame image for protecting the ...

Embodiment 3

[0075] see Figure 5 , Figure 5 It is a schematic diagram of modules of a face tracking device provided by an embodiment of the present invention. The face tracking device 300 includes a first face detection module 310 , a face recognition module 320 , a second face detection module 330 , a similarity calculation module 340 , and a labeling module 350 .

[0076]Wherein, the first face detection module 310 is connected with the face recognition module 320, and the face recognition module 320 is connected with the similarity calculation module 340, and the second face detection module 330 is connected with the similarity calculation module 340, and the similarity calculation module 340 Connect with marking module 350 . The first human face detection module 310 is used to obtain one or more human face images containing human faces in a first video frame image in the video frame image sequence; the human face recognition module 320 is used to identify in the described human fac...

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 embodiment of the invention relates to the technical field of face tracking, and discloses a face tracking method, device and terminal. The face tracking method comprises the following steps of: acquiring one or more human face images including faces in a first video frame image in a video frame image sequence; identifying a face image to be tracked including a face to be tracked in the face image; extracting an image region to be detected including a human face from a subsequent video frame image of the video frame image sequence; calculating a similarity between the image region to be detected and the face image to be tracked; when there is an image region to be detected whose similarity is greater than a preset threshold value, marking the image to be detected visually in a video frame image. By the above mode, the embodiment of the invention can reduce the calculation amount of face tracking, thereby improving the efficiency.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face tracking, and in particular, to a face tracking method, device, and terminal. Background technique [0002] With the development of computer technology, image processing technology has been applied to more and more fields. Among them, the face tracking technology based on image sequences is a technology that detects faces from videos and captures information such as the position and size of faces in subsequent frames. [0003] In the process of implementing the present invention, the inventors of the present invention found that the current face tracking technology often needs to perform face detection and recognition in each frame of image, which has a large amount of calculation and low efficiency. Contents of the invention [0004] Embodiments of the invention of the present application provide a face tracking method, device, and equipment, which can reduce the calculation...

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
IPC IPC(8): G06T7/246G06T7/33
CPCG06T7/246G06T7/33G06T2207/10016G06T2207/30201
Inventor 刘海莹
Owner ZDST COMM TECH CO LTD
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