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

Heuristic underwater structured environment line feature extraction method

A technology of underwater structure and extraction method, which is applied in pattern recognition in signals, character and pattern recognition, radio wave measurement system, etc., and can solve the problem of low accuracy

Active Publication Date: 2018-03-06
HARBIN ENG UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the existing algorithms are difficult to apply to acoustic images severely disturbed by underwater noise, and the accuracy of structured environmental feature extraction for forward-looking sonar perception is low, so it is necessary to develop a new algorithm to improve structured environmental feature extraction the accuracy of

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
  • Heuristic underwater structured environment line feature extraction method
  • Heuristic underwater structured environment line feature extraction method
  • Heuristic underwater structured environment line feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] In recent years, with the continuous development of the marine industry, the requirements for the intelligence level of underwater robots are increasing day by day. As an important means for underwater robots to explore the ocean, underwater environment modeling is receiving more and more attention. In the working environment of underwater robots, structured environments such as ports and dams are very common. For underwater structured environments, underwater robots can only accurately extract the line features of structured environments from ports and dams to establish Only an accurate structured environment model can recognize environmental information, thereby effectively improving the local positioning and path planning capabilities of underwater robots.

[0056] Autonomous underwater vehicles (Autonomous Underwater Vehicles, referred to as AUV) usually use mechanical scanning imaging sonar (referred to as "imaging sonar") to sense structured environmental informati...

Embodiment 2

[0139] The invention relates to a heuristic method for extracting features of underwater structured environment lines. The method solves the problem of incomplete extraction of underwater structured environment line features by existing algorithms, and proposes a heuristic underwater structured environment line feature extraction method. Environment Line Feature Extraction Method.

[0140] Such as Figures 1 to 8 As shown, a heuristic underwater structured environment line feature extraction method of the present embodiment includes:

[0141] Step 1 obtains the raw data of mechanical scanning imaging sonar;

[0142] Step 2. Carry out dynamic threshold segmentation to the sonar raw data, and carry out binarization processing, obtain the set of candidate points for feature extraction;

[0143] Step 3. Use the voting algorithm under the carrier system to vote for the candidate point set in step 1 and then extract the straight line features of the structured environment;

[014...

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 belongs to the field of signal processing in the sonar technology, and specifically relates to a heuristic underwater structured environment line feature extraction method. The method includes the following steps: acquiring original data of mechanical scanning imaging sonar; processing the sonar data under a load system, and binarizing the sonar data to get a point set for feature extraction; carrying out voting through a voting algorithm under the load system to extract the line features of a structured environment; processing the line features through a heuristic method to getline segment features which can be used to describe the structured environment; and obtaining the location information and navigation attitude information of a carrier based on a navigation system, and transforming the extracted line segment features to a global coordinate system. The problem that the extraction of the line features of an underwater structured environment is not complete for the algorithm used by the existing mechanical scanning forward-looking sonar is solved. By using the method, the accuracy of the line segment features extracted from a structured environment is higher than90%. Moreover, the method of the invention is suitable for underwater simultaneous localization and mapping and underwater structured environment feature modeling.

Description

technical field [0001] The invention belongs to the field of signal processing in sonar technology, and in particular relates to a heuristic method for extracting features of underwater structured environment lines. Background technique [0002] The ocean occupies about 70% of the earth's surface area, and it is rich in minerals, natural gas, oil and other resources. As a country with a long coastline, China, considering the increasingly scarce land resources, whether it can reasonably exploit and utilize marine resources is very important. economic and strategic purposes. [0003] We use acoustic imaging technology to observe underwater topography and underwater objects. The so-called acoustic imaging technology is a computer image display and analysis technology that uses sound waves as the carrier of information transmission and uses various acoustic instruments as imaging equipment. The sound wave has the characteristics of a long distance in water and a large detection...

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): G06K9/00G01S7/539
CPCG01S7/539G06F2218/02G06F2218/08
Inventor 张强牛伯城马腾李晔范彦福黄海李岳明张国成曹建廖煜雷
Owner HARBIN ENG UNIV