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

A moving target detection and recognition method in a large scene combined with positioning information

A technology for locating information and moving targets, applied in geographic information databases, structured data retrieval, character and pattern recognition, etc., can solve the problems of decreased final detection accuracy and increased difficulty of model training, so as to facilitate target detection and improve detection accuracy and accuracy, reducing the effect of data processing

Active Publication Date: 2021-07-13
北京天睿空间科技股份有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This will lead to an increase in the difficulty of model training in deep learning algorithms and a decrease in final detection accuracy

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 moving target detection and recognition method in a large scene combined with positioning information
  • A moving target detection and recognition method in a large scene combined with positioning information
  • A moving target detection and recognition method in a large scene combined with positioning information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] 1. Overall process

[0033] The overall process of the present invention is attached figure 1 shown.

[0034]First, after the large-scene video acquisition equipment (integrated panoramic camera or a group of spliced ​​cameras) is fixedly installed, the points in the scene space and their pixel coordinates in the video screen are calibrated, that is, the coordinates (x, y) and the latitude and longitude positioning information (l, t) of the positioning system, expressed as several quadruples (x, y, l, t). The corresponding relationship between the image coordinates and the longitude and latitude coordinates is used as the basis of the correspondence between the coordinate points (x, y) in the large scene image and the longitude and latitude positioning information (l, t) of the positioning system, instead of pre-setting each point The correspondence between image coordinates and latitude and longitude coordinates.

[0035] After the moving target detection is started...

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 relates to a method for detecting moving objects in a large scene combined with positioning information. It firstly calibrates the points in the scene space and their pixel coordinates in the video screen, and establishes a target database. After the detection of moving objects is started, for each A moving target with longitude and latitude positioning information is used to predict the area where it is located, and the predicted area is mapped to the screen of the large-scene video, and the image of the predicted area is scaled to a uniform scale and sent to the target detection processing module. When multiple targets are detected, Match all detected targets with corresponding types of targets in the target database to obtain the best matching results, and restore the coordinates to the large scene image. The invention greatly improves the processing speed and is beneficial to improve the accuracy of detection, and can be used for real-time video detection and tracking of airport aircraft and other occasions.

Description

technical field [0001] The invention relates to a method for detecting and recognizing a moving target in a large scene combined with positioning information, which belongs to the technical field of computer vision. Background technique [0002] In recent years, augmented reality (Augmented Reality, AR) technology has been more and more applied in large-scale scene control such as large-scale square security, airport scene activity guidance and control, port production operation area operation status monitoring, and industrial park control. . For example, in the control of aircraft, vehicles, and personnel in the airport flight area, in order to facilitate the understanding and command of managers, it is often necessary to enhance the display of these moving targets, that is, to display the relevant information of the target at the corresponding position of the moving target in the video screen, such as Aircraft flight number, vehicle type, personal information of operators...

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): G06K9/00G06F16/29G01S19/45
CPCG06F16/29G01S19/45G06V20/41G06V2201/07
Inventor 郑文涛林姝含李申达
Owner 北京天睿空间科技股份有限公司
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