Underwater structured environment line feature extraction method based on forward looking sonar

A technology of underwater structure and extraction method, which is applied in the direction of sound wave re-radiation, radio wave measurement system, utilization of re-radiation, etc., can solve problems such as easy ambiguity, low efficiency, poor real-time performance, etc., to overcome blindness and ambiguity performance, improve execution efficiency and real-time effect

Active Publication Date: 2018-05-22
HARBIN ENG UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for extracting underwater structured environmental line features based on forward-looking sonar in order to solve the problems of low efficiency, poor real-time performance and easy ambiguity when extracting underwater structured environmental line features by existing algorithms

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 structured environment line feature extraction method based on forward looking sonar
  • Underwater structured environment line feature extraction method based on forward looking sonar
  • Underwater structured environment line feature extraction method based on forward looking sonar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Example 1: Combining Figure 1 to Figure 6 The underwater structured environment line feature extraction method based on forward-looking sonar of the present invention comprises:

[0063] Step 1. Carry out dynamic threshold segmentation on the forward-looking sonar data, and obtain the total points of high echo intensity points and their polar coordinates under the carrier system;

[0064] Step 2: Randomly select two non-isolated and non-adjacent points from the high echo intensity points within the limited number of cycles to construct a straight line, select points whose distance from the straight line is less than the preset threshold to form a candidate point set, and calculate the candidate point set The ratio of the potential to the total number of points, if the ratio is not less than the threshold, the straight line is used as an auxiliary straight line and the loop is terminated;

[0065] Step 3. Based on the auxiliary straight line parameters and the distribu...

Embodiment 2

[0068] Embodiment 2: Based on the above embodiment, step 1 is specifically:

[0069] Step 11: Collect forward-looking sonar data within a certain sonar opening angle range, perform dynamic threshold segmentation on the forward-looking sonar data, obtain high echo intensity points and calculate the number of high echo intensity points.

[0070] It should be noted that the forward-looking sonar in the present invention mainly refers to single-beam mechanical scanning imaging sonar and 2D multi-beam imaging sonar. Both sonars realize environmental detection by detecting the echo intensity at equally spaced points within the detection distance, and the relative positions of the origins of their detection beams under the carrier system are as follows: figure 1 and figure 2 shown. For example, a single-beam mechanical scanning imaging sonar continuously emits a beam and scans in a certain direction. The detection distance of the sonar beam is 50m, and the sonar will return the de...

Embodiment 3

[0079] Embodiment 3: Based on the above embodiments, step 2 is specifically:

[0080] Step 21: Set the maximum calculation times of the auxiliary straight line.

[0081] In order to obtain the auxiliary straight line required in the subsequent steps in a short period of time, the algorithm must complete the calculation of the auxiliary straight line within a limited number of times, so a smaller fixed value not exceeding 10 is set as the maximum calculation times of the auxiliary straight line.

[0082] Step 2 and 2: Among the high echo intensity points, randomly select two points. The selected point cannot be the only isolated point on the entire beam whose echo intensity is greater than the threshold, and it should satisfy that the point is adjacent to two positions on the beam. The echo intensities are greater than the threshold; and the selected two points are on two different beams, and there is at least a certain number of beams between the two beams. The setting of the ...

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 provides an underwater structured environment line feature extraction method based on forward looking sonar. The method comprises steps: dynamic threshold segmentation is carried out onforward looking sonar data to acquire the total number of high echo intensity points and polar coordinates in a carrier system; within the limited cycle times, two not-isolated and not-adjacent pointsare randomly selected from the high echo intensity points to form a straight line, points with the distances with the straight line smaller than a preset threshold are selected to form a candidate point set, the ratio of the potential of the candidate point set to the total point number is calculated, if the ratio is no smaller than the threshold, the straight line is used as an auxiliary straight line, and the cycle is stopped; based on the parameters of the auxiliary straight line and the corresponding candidate point set distribution features, the voting space for structured environment line feature parameters is constructed, and a voting algorithm is used to extract line feature parameters; and based on the distribution condition of points near the line features, the line features arecut to line section features. The blindness of random sampling and the inefficiency of the voting algorithm can be overcome effectively.

Description

technical field [0001] The invention relates to a method for extracting features of underwater structured environment lines based on forward-looking sonar, and belongs to the field of intelligent perception and modeling of underwater environment acoustics. Background technique [0002] For robots, the ability to perceive and understand the underwater environment is an important factor that restricts the level of autonomy and intelligence of robots. Underwater structured environments such as ports and waterways are common working scenarios for underwater robots. Underwater robots usually detect these underwater structured buildings based on forward-looking sonar and describe them with line segments. Therefore, an accurate and efficient underwater structured environment line feature extraction algorithm is the fundamental guarantee for underwater robots to understand the underwater structured environment in real time and correctly. [0003] However, the current algorithm for ...

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
IPC IPC(8): G01S15/89
CPCG01S15/89
Inventor 张强牛伯城李晔盛明伟张雯隋炎橙马腾范彦福张国成曹建
Owner HARBIN ENG UNIV
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