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

Underwater artificial target detection method in isolated forest based on fractal theory

A fractal theory and target detection technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of high error rate and low precision, achieve low error rate, high accuracy, and reduce data calculation effects

Active Publication Date: 2022-03-11
XIAN UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for detecting underwater artificial targets in isolated forests based on fractal theory, which solves the problems of low accuracy and high error rate of traditional single detection methods

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
  • Underwater artificial target detection method in isolated forest based on fractal theory
  • Underwater artificial target detection method in isolated forest based on fractal theory
  • Underwater artificial target detection method in isolated forest based on fractal theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0095] The implementation process of the method for detecting underwater artificial targets in isolated forests based on fractal theory is illustrated below through an operation example of a set of simulation data.

[0096] (1) First, execute step 1 and step 2, merge the original data document information into one document, and normalize the data, Figure 4 and Figure 5 is the original document graph, Figure 4 Contains only X, Y, and I three-dimensional information, Figure 5 Contains only X, Y, Z three-dimensional information, Figure 6 It is the merged data file, which contains information of four dimensions X, Y, Z, and I. Figure 7 are images before and after data preprocessing, where the left side is the data image before preprocessing, and the right side is the data image after preprocessing. After preprocessing, the noise in the image is removed and the missing points are filled.

[0097] (2) Execute step 3 to get the number of difference boxes in each window, an...

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 method for detecting an underwater artificial target in an isolated forest based on the fractal theory disclosed by the present invention first obtains sonar image data; secondly, firstly normalizes the original sonar image data, and then fills in missing values ​​to obtain image data for eliminating defects; Then the preprocessed image data is divided into several small areas, and the fractal dimension of each area is calculated; finally, the abnormal data and normal data points in the image data are obtained by establishing separation trees and isolation forests. Compared with the traditional detection method, the invention reduces the calculation amount of data, improves the detection precision and reduces the false detection rate.

Description

technical field [0001] The invention belongs to the technical field of computer digital image processing, and in particular relates to a method for detecting an underwater artificial target in an isolated forest based on fractal theory. Background technique [0002] A 3D scanner is used to scan the external shape of an object or environment in real life, and obtain a large amount of appearance point cloud data, so as to obtain a digital model of the real object or environment. These models are often used in target detection and segmentation, 3D reconstruction and other directions. There are two types of 3D scanners, one is the contact type, the scanner obtains the actual depth information of the object by touching the actual object, but compared with other types of scanners, the scanning time of the contact type scanner is relatively long; One is non-contact, and this type of scanner is divided into two types: active scanning and passive scanning. Active scanning means tha...

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): G06V10/25G06V10/764G06K9/62G06T7/48
Inventor 金海燕田玉泉肖照林蔡磊李秀秀
Owner XIAN UNIV OF TECH