Target tracking method and device

A target tracking and target technology, applied in the field of image processing, can solve problems such as the inability to guarantee the quality of video shooting, and achieve the effect of improving the quality of video shooting

Active Publication Date: 2016-06-08
深圳市瀚德智能机器人有限公司
View PDF5 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of tracking and shooting the characters in the video, the shooting area and shooting angle of the camera can only be artificially changed by the video shooter, and the control operation of the artificial shooting area and shooting angle is relatively random, which cannot guarantee the shooting quality of the video

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
  • Target tracking method and device
  • Target tracking method and device
  • Target tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] see figure 2 , the present embodiment provides a target tracking method, comprising the following steps:

[0080] Step 200. Detect a moving target from a captured video stream, where the video stream includes each video image.

[0081] Each video image in each video image is each frame of video image captured by the camera.

[0082] When detecting a moving object, any existing moving object detection algorithm can be used to detect the moving object in the video image, and details will not be repeated here.

[0083] Step 202, searching for a human face image from the video image corresponding to the detected moving object.

[0084] Use the Adboost face detection algorithm to find the face image in the detected moving target, and determine the face image features of the found face image.

[0085] Step 204: Obtain face tracking features corresponding to each of the found face images, wherein the face tracking features include: face image features, the distance between...

Embodiment 2

[0141] see image 3 , the present embodiment provides another target tracking method, which is based on a single pan-tilt camera to detect and follow the target, and the camera state must be defined, and the camera state includes three states: static detection state, motion following state and automatic inspection state kind.

[0142] Among them, static detection state: when there is no moving target in the video, the camera is in the static detection state. In this state, the camera is in the preset position and remains still, and ordinary moving target detection can be performed based on fixed background modeling; when the detection When the moving target is reached, start the face detection module; motion following state: when the face is detected and the main target is determined, the camera enters the motion following state, using the face tracking technology based on the moving background to control the rotation of the pan / tilt to ensure the main target The face is alwa...

Embodiment 3

[0167] see Figure 8 , the present embodiment provides a target tracking device for performing the above-mentioned target tracking method, including: a moving target detection module 800, a face image search module 802, a face tracking feature acquisition module 804, a tracking target determination module 806 and a target Tracking module 808 .

[0168] Wherein, the moving target detection module 800 is used to detect the moving target from the video stream of shooting, wherein, the video stream includes each video image; the face image search module 802 is connected with the moving target detection module 800, and is used to detect Search the face image in the video image corresponding to the moving target; the face tracking feature acquisition module 804 is connected with the face image search module 802, and is used to obtain the corresponding face tracking feature of each face image found, wherein the face Tracking feature comprises: face image feature, the distance of peo...

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 provides a target tracking method and device. The method includes the following steps that: a moving object is detected from a shot video stream, wherein the video stream includes various video images; face images are searched from the video images corresponding to the detected moving object; facial tracking features corresponding to the searched face images are obtained, wherein the face tracking features include a facial image feature, the distance between a face and a camera and continuously-lasting time of the face in the video images; a tracking target is determined from the searched face images according to the face tracking features of the face images; and the tracking target is tracked. With the target tracking method and device of the invention adopted, the camera can actively track a figure to be photographed in a video, and the video photographing quality of the camera can be improved.

Description

technical field [0001] The present invention relates to the field of image processing, in particular, to a target tracking method and device. Background technique [0002] At present, when people go out to play or have a party, they will shoot videos with a handheld camera or a camera supported by a pan / tilt, so as to record the beautiful scenery during the game and the happy time with family and friends during the party. [0003] Existing video cameras can only confirm and detect the faces of people appearing in the video when shooting video, but cannot track the people appearing in the video. When it is necessary to track and shoot the characters in the video, the video shooter can only change the shooting area and shooting angle of the camera to track and shoot the characters in the video. [0004] In the process of tracking and shooting the characters in the video, the shooting area and shooting angle of the camera can only be artificially changed by the video shooter, ...

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): G06T7/20G06K9/62
CPCG06T2207/10016G06T2207/30201G06F18/214
Inventor 闫振雷郑慧杨雪慧
Owner 深圳市瀚德智能机器人有限公司
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