Unlock instant, AI-driven research and patent intelligence for your innovation.

Target tracking method based on moving head camera

A target tracking and camera technology, applied in the field of visual tracking, can solve problems such as large amount of computation, complex models, and unstable tracking

Active Publication Date: 2020-10-27
ZHUHAI RAYSHARP TECH
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention proposes a target tracking method based on a moving head camera, which solves the problems in the prior art of large amount of computation, complex models, unstable tracking and shaking of the head shaking machine

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 based on moving head camera
  • Target tracking method based on moving head camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1: A method of target tracking based on a moving head camera.

[0045] refer to figure 1 , a method for tracking a target based on a moving head camera, specifically comprising the following steps:

[0046] For human-shaped / human-face targets, the present invention provides a target tracking method based on a moving head camera, which specifically includes the following steps:

[0047] S1. Human figure / face detection and positioning: For human figure and face detection, detect human figure or human face in the video by setting the detection mode and the score threshold of human figure and human face;

[0048] S2. Human figure / face position prediction and ID allocation: For the current frame, use the target position predicted by the Kalman filter, combined with the actual target position detected in step S1, by calculating the IOU value between the predicted position and the actual position As a weight, the IOU value is the ratio of the intersection and unio...

Embodiment 2

[0058] Embodiment 2: A target tracking method based on a moving head camera.

[0059] refer to figure 2 As shown, for the target tracking of the foreground moving block, a target tracking method based on a moving head camera specifically includes the following steps:

[0060] S1. Target positioning: For the detection of moving blocks, use the background difference method to complete the detection of foreground moving targets;

[0061] S2. Determine the tracking target block:

[0062] S21. For the moving blocks detected by the background difference method, filter out the blocks whose area is smaller than 20 pixels;

[0063] S22. Judging whether the target number of motion blocks meeting the conditions is zero, if it is zero, return to the next frame for processing; otherwise, arrange the areas of the reserved motion blocks in descending order;

[0064] S23, when the shaking head motor is still, count the number of frames of the video; at the same time, for the motion blocks...

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 based on a moving head camera. The method specifically comprises the steps of human shape / human face detection and positioning, human shape / human face position prediction and ID distribution, determination of a tracked human shape / human face target, calculation of the distance between the target and the center of a picture in the horizontal and vertical directions, control of a head shaking machine to rotate the target to the center of the picture, judgment of whether the head shaking machine needs to return to a home position or not and the like. According to the invention, simple mathematical calculation, multi-frame filtering, Kalman prediction and Hungary matching methods are applied to achieve the purpose of tracking the human shape / faceand the moving target block in real time; and in the tracking process, the situation that the oscillating machine oscillates disorderly due to false detection of target detection is avoided, and theproblems that in the prior art, the operand is large, the model is complex, and tracking is unstable are solved.

Description

[0001] This application is a divisional application with application number: 202010091403.7, application date: 2020.02.13, and title of invention: a method for tracking objects based on moving head cameras. technical field [0002] The invention relates to the technical field of visual tracking, in particular to a method for tracking a target based on a moving head camera. Background technique [0003] In the field of computer vision, target tracking is one of the most challenging problems, and the directions involved are mainly single target tracking and multi-target tracking, while multi-target tracking is the most widely used in the security field. The main tracking processes of multi-target tracking include detection, feature extraction / trajectory prediction, similarity calculation, and ID assignment. The existing technology mainly uses correlation filters and deep learning methods for tracking, which are mainly used to predict the target position in the next frame and p...

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): G06T7/277G06T7/254G06T7/246G06T7/62G06K9/00H04N5/232
CPCG06T7/277G06T7/254G06T7/246G06T7/62G06T2207/10016G06T2207/30201G06T2207/10141G06T2207/20224G06T2207/30196G06T2207/20076G06V40/161G06V40/103G06V2201/07H04N23/611H04N23/695
Inventor 唐自兴马玉涛徐少辉杨亮亮杨运红江发钦申雷李志洋宋庆丰庞继锋
Owner ZHUHAI RAYSHARP TECH