Offshore oil-gas platform detection method based on structural recurrent neural network

A technology of recursive neural network and detection method, which is applied in the field of remote sensing image offshore oil and gas platform detection, can solve the problems of low target detection accuracy and large amount of calculation, and achieve the effect of strong feature capability, high detection rate accuracy and accurate detection

Active Publication Date: 2018-05-08
中国科学院电子学研究所苏州研究院
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a remote sensing image offshore oil and gas platform detection method based on structural recursive ne...

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
  • Offshore oil-gas platform detection method based on structural recurrent neural network
  • Offshore oil-gas platform detection method based on structural recurrent neural network
  • Offshore oil-gas platform detection method based on structural recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Embodiment 1: The present invention will be further described below in conjunction with the accompanying drawings.

[0053] figure 1 It is a block diagram of the main structure of the method of the present invention. The detection method of the remote sensing image offshore platform based on the recursive structural neural network and the bidirectional circular convolution neural network mainly includes two parts: the first part, the high-order remote sensing imaging of the offshore platform based on the structural recurrent neural network spatiotemporal features. In the second part, a two-way cyclic convolutional neural network deep learning architecture is established to achieve accurate detection of offshore oil and gas platforms. The input of the first part is the original image, the output of the first part is used as the input of the second part, and the output of the second part is the detection result.

[0054] figure 2 is a high-order spatio-temporal charac...

Embodiment 2

[0058] Embodiment 2: The technical solution of the present invention and the scientific principles on which it is based are described in detail below.

[0059] 1. Structural Recursive Neural Network (S-RNN)

[0060] (1) Share factors between nodes

[0061] Starting with the time-space image, each factor in the structural recursive neural network model is represented by a recursive neural network (Recursive Neural Network, RNN). The RNN model is connected by a structure that can capture the time-space image structure and interconnection. Each factor in the space-time graph has parameters, and similar nodes can share factors and parameters without learning the characteristics of each factor. Assuming that all factor nodes in the space-time graph can share common node factors and parameters, this model can strengthen the sharing between similar nodes, and can further strengthen the processing of spatio-temporal images through nodes without increasing parameters. flexibility. M...

Embodiment 3

[0081] Embodiment 3: The method for detecting offshore oil and gas platforms in remote sensing images based on structural recursive neural network. The specific implementation steps are as follows:

[0082] Step 1, according to the serialized structural characteristics of spatio-temporal images, a structural recurrent neural network model of maritime targets is established;

[0083] Step 1.1, select a certain number of multi-temporal optical remote sensing images with different resolutions and multi-viewpoints that can be visually recognized by the oil and gas platform, and then obtain the image set A1;

[0084] Step 1.2, manually calibrate the image set A1 obtained in step 1.1, mark the platform target and interference target, and then obtain the marked remote sensing target image set A2;

[0085] Step 1.3, perform basic image preprocessing on the remote sensing image set A1, and obtain the target saliency image set A3;

[0086] Step 1.4, on the basis of the image set A3, ac...

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 discloses an offshore oil-gas platform detection method based on a structural recurrent neural network. The method comprises: according to serialization structure characteristics of a space-time image, a structural recurrent neural network model of a seaborne target is established; parameter optimization adjustment is carried out on the established structural recurrent neural networkmodel and then a high-order space-time characteristic model of the seaborne target is established; on the basis of the high-order space-time characteristic model of the seaborne target, a high-orderspace-time characteristic of the seaborne target is obtained; a bi-directional circular convolution layer is constructed based on the high-order space-time characteristic of the seaborne target and abi-directional circular convolutional neural network with fusion of front and rear time phase features is established; and on the basis of parallel optimization adjustment of the bi-directional circular convolution layer, accurate detection of the seaborne moving target under the single time phase is realized. With the deep learning, the capability of obtaining the target feature is enhanced; andwith full utilization of the time-space features of the target, the target in the complex background interference can be detected. Moreover, the universality of the algorithm is enhanced.

Description

technical field [0001] The invention belongs to the field of remote sensing image target recognition, in particular to a remote sensing image offshore oil and gas platform detection method based on a structure recursive neural network. Background technique [0002] The detection is realized according to the platform's own characteristics such as relatively fixed geographical location, strong light at night, and scale invariance. For example, Li Qiang et al. proposed a convolution critical value method to extract offshore oil and gas platforms based on VIIRS data with strong nighttime light detection capabilities; Cheng L. et al. used dual-parameter CFAR to detect offshore targets, and then based on the relative triangle Based on the multi-scene and multi-temporal TerraSAR-X images, Wan Jianhua et al. extracted 5 oil and gas platforms in some areas of the South China Sea in combination with the relative invariance of platform positions. Yongxue Liu et al. used the multispect...

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): G06K9/00G06N3/04
CPCG06V20/13G06V2201/07G06N3/045
Inventor 付琨段贺彭晨乔雪陶家顺陈星刘久云华绿绿
Owner 中国科学院电子学研究所苏州研究院
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap