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

A method for automatically positioning coordinates of scenes in real-time video

A real-time video and automatic positioning technology, which is applied in the field of automation and information technology, can solve the problems of high hardware investment, high requirements for image processing hardware configuration, and large number of urban supervision video channels.

Active Publication Date: 2021-05-11
成都川江信息技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Defects: The above algorithm is mainly to process each detection image and then locate it. It has high requirements for image quality, lighting conditions, and image processing hardware configuration. At present, the number of video channels for urban supervision is large, especially hundreds of channels of video, and hardware investment particularly high

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 method for automatically positioning coordinates of scenes in real-time video
  • A method for automatically positioning coordinates of scenes in real-time video
  • A method for automatically positioning coordinates of scenes in real-time video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0087] A method for automatically positioning coordinates of a scene in a real-time video in this embodiment includes the following steps:

[0088] The first step is to obtain PTZ parameters, such as figure 1 shown.

[0089] PTZ represents the omnidirectional coordinates of the pan / tilt. Among the PTZ parameters, PTZ(X): the horizontal orientation of the pan / tilt; PTZ (Y): the vertical orientation of the pan / tilt; PTZ (P): the multiple of the lens; Realize the horizontal rotation, vertical rotation, lens zoom and lens zoom control of the dome camera or PTZ camera.

[0090] One way to obtain PTZ parameters is to obtain them from the SDk of the dome camera or PTZ camera.

[0091] Another way to obtain PTZ parameters is: each time the dome camera or PTZ camera is restarted, set an initial PTZ for the dome camera or PTZ camera and save it, obtain the PTZ parameters, and when the dome camera or PTZ camera During horizontal rotation, vertical rotation, lens zoom and lens zoom, 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 method for automatically positioning coordinates of a scene in a real-time video, including S1, obtaining PTZ parameters; S2, determining the coordinates of the video display area, taking the scene to be obtained as a reference object, and manually calibrating it to obtain a reference Object coordinates; S3. According to the obtained PTZ parameters, perform steps A and B at the same time: A. Calculate the matching relationship between the PTZ operation of the dome camera or the PTZ camera and the scene coordinates in the screen, determine the scene coordinates in the screen video and mark them for storage; B . Calculate the matching relationship between the PTZ operation of the dome camera or the PTZ camera and the screen coordinates, and determine the real-time video display area of ​​the screen; S4. Mark and display the scene coordinates in the screen video. The present invention realizes video structuring of scene positions in real-time videos; facilitates fast retrieval of scene positions in massive videos; only processes coordinate data, occupies less hardware resources, facilitates massive video processing, and is not affected by image quality and lighting conditions , with high accuracy.

Description

technical field [0001] The invention belongs to the fields of information technology and automation technology, and in particular relates to a method for automatically positioning coordinates of a scene in a real-time video. Background technique [0002] Video object localization includes object localization based on contrast analysis, object localization based on matching and object localization based on motion detection. [0003] Target positioning based on contrast analysis: It mainly uses the contrast difference between the target and the background to realize the detection and positioning of the target. [0004] Target positioning based on matching: Target positioning is mainly achieved through feature matching between the front and rear frames. Features are the properties of objects that can be distinguished from other things, and have the characteristics of distinguishability, reliability, independence and sparsity. Matching-based object localization algorithms need...

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): G01C11/00
CPCG01C11/00G01C11/36
Inventor 李晓倩庾农韩彦向子荣侯睿常乐邓博杨董笑宇
Owner 成都川江信息技术有限公司
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