Multi-beam seabed sedimentary layer type estimation method and system based on transfer learning

A technology of seabed deposition and migration learning, which is applied in the fields of seabed detection and hydroacoustic physics, can solve the problems of reduced model generalization performance and reduced prediction accuracy, and achieves the effect of satisfying real-time processing, short time and good training effect.

Active Publication Date: 2021-11-12
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has obvious data dependence, that is, when the trained neural network model is applied to another sea area under the condition of a certain sea area, the generalization performance of the model will decrease due to the influence of different sea area environments. , the problem of reduced prediction accuracy

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
  • Multi-beam seabed sedimentary layer type estimation method and system based on transfer learning
  • Multi-beam seabed sedimentary layer type estimation method and system based on transfer learning
  • Multi-beam seabed sedimentary layer type estimation method and system based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Multi-beam data acquisition experiments have been carried out in a test sea area for two years. The water depth of the test sea area is 30-60m, figure 1 The route trajectory and seabed sediment type distribution of the two test navigation measurements are given, according to figure 1 As shown, it can be seen that the test route of the dotted line E1 to E2 is parallel to the test route 2 of the dotted line A to B, and the types of the covered seabed sediments (sea bottom) are basically the same, and the types of the seabed sediments are clay powder. Sand, sandy silt and silt. The same NORBIT WBMS Bathy 200 multi-beam bathymetric sonar system was used in the two tests, and the QINSY software was used to collect seabed backscatter data; in the two tests, the parameter settings of the sonar system used were the same. In the multi-beam data processing, in order to avoid the random fluctuation of the data, the data of the two experiments were overlapped and averaged by mult...

Embodiment 2

[0093] The present invention also provides a multi-beam seabed sediment type estimation system based on migration learning, the system specifically includes:

[0094] The migration module is used to use part of the data in the multi-beam echo intensity data on the survey line of the target sea area as migration data, and input it into the pre-trained deep convolutional neural network model, and the part of the deep convolutional neural network model Fine-tuning network node parameters to obtain a revised neural network model; and

[0095] The estimation module is used to input the real-time received multi-beam echo intensity data on the survey line of the target sea area into the corrected neural network model, and output the multi-beam seabed sediment layer type.

Embodiment 3

[0097] Embodiment 3 of the present invention may further provide a computer device, including: at least one processor, a memory, at least one network interface, and a user interface. The individual components in the device are coupled together via a bus system. It can be understood that the bus system is used to realize the connection communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus and a status signal bus.

[0098] Wherein, the user interface may include a display, a keyboard, or a pointing device (for example, a mouse, a trackball (trackball), a touch panel, or a touch screen, and the like.

[0099] It can be understood that the memory in the disclosed embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Wherein, the non-volatile memory may be a read-only memory (Read-Only Memory, ROM), a programmable read-on...

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 technical field of underwater acoustic physics, and particularly relates to a multi-beam seabed sedimentary layer type estimation method based on transfer learning, and the method comprises the steps: taking a part of data in multi-beam echo intensity data on a target sea area survey line as transfer data, and inputting the transfer data into a pre-trained deep convolutional neural network model, performing fine tuning on partial network node parameters of the deep convolutional neural network model to obtain a corrected neural network model; and inputting multi-beam echo intensity data received in real time on a target sea area survey line into the corrected neural network model, outputting a multi-beam seabed sedimentary layer type, and realizing estimation of the multi-beam seabed sedimentary layer type.

Description

technical field [0001] The invention belongs to the technical fields of underwater acoustic physics and seabed detection, and in particular relates to a multi-beam seabed sediment type estimation method and system based on migration learning. Background technique [0002] An in-depth understanding of the physical characteristics and spatial distribution of seabed sediments is of great significance to activities such as seabed resource exploration, marine environment monitoring, and submarine engineering construction. Using the acoustic remote sensing method of multi-beam bathymetry sonar, the backscattering intensity data of the seabed in a large area can be collected, and the backscattering intensity data under different sediment layer types can present different angles with the change of the incident angle of the sound wave The type of seafloor sediment layer is estimated based on the property of the response relationship. [0003] In recent years, data-driven neural netw...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/2415Y02A90/10
Inventor 倪海燕王文博肖旭曹怀刚鹿力成任群言马力
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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