Target location method based on trifocal tensor pixel transfer

A technology of target positioning and pixel point, which is applied in the field of target positioning and can solve the problems of large size, high energy consumption of user nodes, and unsolved detection and positioning.

Inactive Publication Date: 2012-07-25
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In various applications, location information is crucial to the detection activities of the Internet of Things. The positioning can be realized through the global positioning system or the target positioning through the wireless sensor network. However, these positioning technologies need to place nodes on the target and send data through the nodes. package to obtain the specific position and orientation of the target, and the user nodes of the global positioning system usually have high energy consumption, large volume, high cost, and require fixed infrastructure, and the positioning is not accurate enough; while the positioning technology of the wireless sensor network is bulky Small, low energy consumption, low price, but the positioning results are not very stable
If an unknown target appears, how to detect and locate it is still unresolved

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 location method based on trifocal tensor pixel transfer
  • Target location method based on trifocal tensor pixel transfer
  • Target location method based on trifocal tensor pixel transfer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Need to carry out following preparatory work before implementing the present invention:

[0036] Prepare two or more digital cameras, an ordinary personal computer, and a ruler. The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0037] Such as figure 1 Shown as the overall flow chart of the present invention comprises the following steps:

[0038] Step 1: Before the target appears, use two or more cameras to shoot the scene, and the resulting image is read into the computer, assuming that the image size is m×n (pixel value);

[0039] Step 2: Before the target appears, use the ruler to mark the actual size coordinates of the main feature points of the scene captured by the camera in Step 1 to obtain a two-dimensional matrix, measure the actual size of the scene (length and width) M×N, and scale it to m×n, get a two-dimensional matrix of pixel coordinates;

[0040] Step 3: Read the images obt...

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 target location method based on trifocal tensor pixel transfer. The recovery of a three-dimensional structure of an object from a two-dimensional view is one important research direction of computer vision. The invention proposes the target location method based on the trifocal tensor pixel transfer by the research of a geometrical relationship among three images shot by different cameras in the same field and the performance that the trifocal tensor only depends on a relative position among the cameras and parameters in the cameras; the method inputs the images shot by two cameras on the ground in the same field and a virtual top view obtained by actual measurement to a computer to process before a target appears, and then obtains the trifocal tensor by calculation of a random sampling consensus algorithm; after the target appears, the method uses the trifocal tensor to recover pixel projection coordinates of the target on the virtual top view and finally amplifies the projection coordinates according to a proportion to obtain an actual direction of the target; and the method has an important theoretical significance and an actual application value for target location under a complex and sheltered environment.

Description

technical field [0001] The invention relates to the technical field of target positioning in an indoor occluded environment, in particular to a target positioning method based on trifocal tensor pixel point transfer. Background technique [0002] With the development of the Internet of Things, the application of sensor technology is becoming more and more extensive. The wireless sensor network composed of sensors can connect the physical world and the information world. At present, there have been researches in the world that have applied it to environmental monitoring and protection to find and locate the source of accidents in time. It has also been used in the positioning and tracking of military targets, and the control of aerospace landing points. In various applications, location information is crucial to the detection activities of the Internet of Things. The positioning can be realized through the global positioning system or the target positioning through the wirele...

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): G06T7/00
Inventor 刘峰韩蔚蔚
Owner NANJING UNIV OF POSTS & TELECOMM
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