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

Tracking and positioning rapid algorithm of zoom camera in zooming

A technology of tracking and positioning and fast algorithm, applied in the field of intelligent robots, can solve the problems of incomplete positioning and positioning frame drift

Active Publication Date: 2018-11-13
YIJIAHE TECH CO LTD
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with this method is that it can only locate a single target object, and in practice, it is found that due to a certain amount of drift in the position of the optical center of the camera, the positioning frame also drifts accordingly, making the positioning not completely accurate

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
  • Tracking and positioning rapid algorithm of zoom camera in zooming
  • Tracking and positioning rapid algorithm of zoom camera in zooming
  • Tracking and positioning rapid algorithm of zoom camera in zooming

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] An embodiment of the present invention is a fast algorithm for tracking and positioning a zoom camera during zooming. Specifically, the positioning frame under the second magnification is obtained through the following steps.

[0070] 1-1), positioning is performed at a certain magnification a (first magnification).

[0071] Positioning algorithms include template matching, neural network models, etc., which are relatively mature algorithms. Assume that when the magnification is a, (ax, ay) represents the obtained center of the positioning frame of the camera.

[0072] 1-2), get The current magnification a (first magnification) and The field of view at the target magnification b (second magnification), and calculate the focal length corresponding to magnification a and magnification b according to the field of view.

[0073] 1-2-1) Get The current magnification a and Field of view at target magnification b.

[0074] Calculate the angle of view at several discrete...

Embodiment 2

[0101] In another embodiment of the present invention, its working principle is basically the same as that of Embodiment 1, and the steps of obtaining the center of the positioning frame and the position of the optical center of the camera at the first magnification are basically the same as in Embodiment 1. The main difference is to obtain the first magnification. Steps for positioning the center of the frame at double magnification. Specifically, the positioning frame at the second magnification is obtained by simplifying the imaging model in Embodiment 1.

[0102] In practice, it is found that if the center of the region of interest is adjusted to coincide with the optical center position of the camera at that magnification, then when the magnification is changed to other magnifications during the zooming process of the camera, the center of the region of interest The center and the optical center position of the camera under the new magnification always coincide. Therefor...

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 tracking and positioning rapid algorithm of a zoom camera in zooming, belonging to the technical field of intelligent robots. The algorithm comprises the steps of positioningbased on a first magnification, and acquiring a positioning frame center based on the first magnification; acquiring angles of visual field based on the first magnification and a second magnification, and calculating focal lengths corresponding to the first magnification and the second magnification according to the angles of visual field; acquiring optical center positions of the camera based onthe first magnification and the second magnification; and calculating a positioning frame of the camera based on the second magnification. Through adoption of the tracking and positioning rapid algorithm of the zoom camera in zooming, the camera can automatically label an object area of interest rapidly and accurately in zooming, and can label multiple object areas of interest based on the secondmagnification when multiple object areas of interest exist based on the first magnification.

Description

technical field [0001] The invention belongs to the technical field of intelligent robots, and in particular relates to a fast algorithm for tracking and positioning a zoom camera during zooming. Background technique [0002] The zoom cameras used in surveillance equipment on the market today usually have the requirement to locate the target of interest at different magnifications, so that the observation of the target of interest from the whole to the details can be obtained. [0003] There are two methods used by existing cameras. One method is to position the zoom cameras separately at different magnifications, so templates at different magnifications are required. There are two ways to obtain the template, one is to re-acquire at different magnifications, and the workload of collecting templates in this way is relatively large; the other is to zoom in on the template at a certain magnification, but if the zoom ratio is too high, the template will Not very clear. Anoth...

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): G06T7/80G06K9/32H04N5/232
CPCG06T7/80G06V10/25H04N23/67
Inventor 毛成林王锋项导程敏
Owner YIJIAHE TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More