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

Deep convolutional neural network-based submerged oil sonar detection image recognition method

A technology of detecting images and deep convolution, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of high noise of detection data, high manual participation, low recognition efficiency, etc., to achieve efficient and accurate recognition, fully automated process, high precision effect

Inactive Publication Date: 2020-09-11
QINGDAO TECHNOLOGICAL UNIVERSITY
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The technical problem to be solved by the present invention is that in the process of sonar detection and identification of sinking oil, there are many problems in the detection data such as high noise, difficult to interpret, difficult to distinguish, many manual participation, and low identification efficiency.

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
  • Deep convolutional neural network-based submerged oil sonar detection image recognition method
  • Deep convolutional neural network-based submerged oil sonar detection image recognition method
  • Deep convolutional neural network-based submerged oil sonar detection image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The data used in this example come from the outdoor pool of the safety and environmental protection branch of CNOOC Energy Development Co., Ltd., and the sonar detection images obtained by detecting the bottom oil at different angles and depths through BlueView M900-2250 image sonar (800kHz) .

[0047] 1. Sonar detection image preprocessing module

[0048] Preprocessing the acquired sonar detection images includes three processes: image filtering S1-1, image enhancement S1-2, and threshold segmentation S1-3, which are described in detail as follows.

[0049] (1) Image filtering

[0050] Such as figure 2 As shown, the obtained original picture background 2 contains a lot of noise, and the existence of background noise will directly affect the final effect of segmenting the bottom oil target 1. Therefore, it is necessary to filter the picture to reduce the interference of noise on the segmented picture. The filtered bottom oil image is as follows: image 3 shown. T...

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 the technical field of bottom oil detection, in particular to a deep convolutional neural network-based bottom oil sonar detection image recognition method. The method comprises a sonar detection image preprocessing module and a deep convolutional neural network bottom oil target identification module. According to the method, a deep convolutional neural network algorithmis introduced into bottom oil detection and identification; the key problems of automatic sinking-to-bottom oil target identification, automatic leakage position positioning, automatic sinking-to-bottom oil pollution area estimation and the like are solved. The method provides a basis for emergency decision and disposal of marine oil spill accidents, improves the level of a bottom oil detection and identification technology in China, provides technical support for national marine safety and petroleum safety, and has important engineering significance and application value.

Description

Technical field: [0001] The invention relates to the technical field of detection and identification of sunken bottom oil, in particular to a sonar detection image recognition method for sunken bottom oil based on a deep convolutional neural network. Background technique: [0002] Energy is the economic lifeline of a country and an important support for the continuous growth of the national economy. With the development of my country's economy and technology, the country's demand for energy such as oil and gas is also increasing. According to statistics, my country's offshore oil and gas reserves are extremely rich. The geological reserves of petroleum in the South China Sea alone have reached 23-30 billion tons, of which 70% are stored in deep sea areas. With the continuous expansion of the scale of offshore oil development and utilization, oil spill accidents have also increased. The main causes of marine oil spill accidents include: collisions of transport ships, accide...

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): G06K9/00G06K9/54G06K9/34G06K9/62
CPCG06V20/10G06V10/267G06V10/20G06F18/2414
Inventor 曹金凤郭继鸿安伟李建伟撒占友
Owner QINGDAO TECHNOLOGICAL UNIVERSITY
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