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

A moving ship detection method and device for low-resolution time-series remote sensing images

A remote sensing image and ship detection technology, applied in neural learning methods, image enhancement, image analysis, etc., can solve the problems of broken clouds and thick clouds, low spatial resolution, and difficulty in improving detection accuracy, so as to increase the accuracy. Effect

Active Publication Date: 2022-05-31
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the popular deep learning method has been able to realize ship detection in medium and high-resolution remote sensing images, but the imaging quality of low-resolution remote sensing images is poor, the spatial resolution is low, and the interference of broken clouds and thick clouds is serious, which leads to the detection of ships. A large number of missed detections and false alarms are prone to occur, and it is difficult to improve the detection 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
  • A moving ship detection method and device for low-resolution time-series remote sensing images
  • A moving ship detection method and device for low-resolution time-series remote sensing images
  • A moving ship detection method and device for low-resolution time-series remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] S21, splicing remote sensing images of different time series, and mapping to RGB color space.

[0061]

[0064]

[0067] S3, build a ship detection model based on the improved YOLOv4 network.

[0069] YOLOv4 uses CSPdarknet53 as the backbone network, spatial pyramid pooling module and path aggregation network module

[0070] Figure 5 shows a schematic diagram of the improved CSPdarknet53 network and spatial pyramid pooling module. Among them, by

[0072] S4, using the labeled image training set to train the ship detection model to obtain the initial ship detection model.

[0076] First, the preprocessed image training set is input into the network model shown in Figure 4. Using the built network model

[0078] Finally, the prediction error loss value is transmitted back to the backbone network CSPdarknet53, and the gradient feedback is performed to correct the network.

[0079] By calculating the error between the network detection result and the labeled true value, and re...

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 a moving ship detection method and device for low-resolution time-series remote sensing images. The detection method includes: acquiring low-resolution remote sensing images of different time series; splicing two remote sensing images of different time series and mapping to RGB color space , synthesize false color images; quantify the false color images, and mark the ship targets to obtain the marked image training set and image verification set; use the pre-built ship detection model based on the improved YOLOv4 network to be detected The features of low-resolution time-series remote sensing images are extracted, and the ship targets are marked. The invention can extract the timing features and space features of the remote sensing image, improve the detection accuracy of the ship target, and reduce the probability of missing detection and false alarm.

Description

Motion ship detection method and device for low-resolution time series remote sensing images technical field The present invention relates to the technical field of computer image processing, more specifically relate to a kind of low-resolution timing oriented A method and device for detecting moving ships in remote sensing images. Background technique [0002] Low-resolution remote sensing image ship detection technology has broad prospects in ocean monitoring, and can be effectively applied. In many aspects, such as port dynamic monitoring, maritime battlefield situational awareness, maritime security, and detection of military targets, it has significant research value. [0003] At present, popular deep learning methods have been able to achieve ship detection in medium and high resolution remote sensing images, However, low-resolution remote sensing images have poor imaging quality, low spatial resolution, and serious interference from broken clouds and thick cloud...

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): G06V20/13G06V10/40G06V10/774G06V10/82G06K9/62G06T5/00G06T5/20G06T5/50G06T7/90G06N3/08
CPCG06T5/002G06T5/20G06T5/50G06T7/90G06N3/08G06T2207/10032G06T2207/20032G06T2207/20081G06T2207/20084G06V20/13G06V10/40G06F18/214
Inventor 徐其志殷若婷
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com