Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Remote Sensing Ship Recognition Method Based on Dense Feature Fusion and Pixel-Level Attention

A feature fusion and attention technology, applied in character and pattern recognition, scene recognition, instruments, etc., can solve the problems of easy overlapping of bounding boxes, dense distribution, and large scale span of ship targets, so as to improve recognition stability and improve Visual effects, the effect of improving recognition accuracy

Active Publication Date: 2022-03-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to introduce a dense feature fusion network on the basis of the Fatser RCNN network for the problems of poor image quality, complex background, large scale span, extreme aspect ratio, and dense distribution of remote sensing images of ship targets. And pixel-level attention network and other improvement measures to overcome the limitations of classical neural networks in remote sensing image ship target recognition tasks, such as easy to identify multiple dense targets as one target, a large number of missed detection of small targets, and easy overlapping of bounding boxes. Improve recognition accuracy and robustness

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
  • Remote Sensing Ship Recognition Method Based on Dense Feature Fusion and Pixel-Level Attention
  • Remote Sensing Ship Recognition Method Based on Dense Feature Fusion and Pixel-Level Attention
  • Remote Sensing Ship Recognition Method Based on Dense Feature Fusion and Pixel-Level Attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and / or steps.

[0068] Combine below Figure 1 to Figure 9 The present invention will be described in detail.

[0069] A remote sensing image ship target recognition method based on dense feature fusion and pixel-level attention, the flow chart is as follows figure 1 As shown, it specifically includes the following steps:

[0070] Step 1: Divide the acquired remote sensing image dataset into datasets to obtain training sets and test sets, and perform data enhancement on the training set by means of random flipping, rotation, and adding Gaussian noise to reduce the risk of overfitting in the case of small-sample learning ;

[0071] Step 1.1: Divide the data set according to the number of images in the remote sensing image data set. Generally, if the number of images is on the order of 10 4 and below, the 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 belongs to the field of image target recognition, and provides a remote sensing ship recognition method based on dense feature fusion and pixel-level attention. Target recognition is a target, a large number of small targets are missed, and bounding boxes are easy to overlap. The main scheme is to divide the remote sensing image data set into data sets, obtain the training set and test set, and perform data enhancement on the training set; calculate the RGB three-channel average value r of the original remote sensing image data set mean , g mean , b mean , the RGB three-channel value of the image in the expanded data set and r mean , g mean , b mean Corresponding subtraction; input the obtained data set into the improved Faster RCNN network for training, the core modules of the network are dense feature fusion network and pixel-level attention network, and the network outputs candidate rotation boxes and their category scores; The non-maximum suppression of the rotating frame based on the skew IOU can obtain the recognition result of the ship target in the remote sensing image.

Description

technical field [0001] The invention relates to a remote sensing ship recognition method based on dense feature fusion and pixel-level attention, and belongs to the field of target recognition in remote sensing image processing. Background technique [0002] With the substantial increase in the real-time and operability of remote sensing technology, various remote sensing image products are developing towards the goal of multi-scale, multi-frequency, all-weather, high-precision, high-efficiency and fast. In the face of massive remote sensing images, manual interpretation is no longer competent, and data processing such as secondary information extraction and target recognition of remote sensing images has become more and more important, and has become the main research direction of remote sensing images. For the processing of remote sensing images It increasingly reflects the structure of the entire field and the most important measure of the level of software and hardware. ...

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 Patents(China)
IPC IPC(8): G06V20/10G06V20/54G06V10/44G06V10/766G06V10/774G06V10/80G06V10/82G06V10/25G06K9/62G06N3/04
CPCG06V20/13G06V10/25G06V10/454G06N3/045G06N3/044G06F18/214G06F18/24G06F18/253
Inventor 韩雅琪彭真明潘为年鲁天舒刘安王慧张天放
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products