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

Enhanced remote sensing image target detection method and system

A target detection and remote sensing image technology, applied in the field of satellite remote sensing image target detection, can solve the problems of poor detection accuracy and difficult to extract effective information, and achieve the effects of high speed, improved detection accuracy, and strong practicability.

Pending Publication Date: 2021-12-03
武汉九天高分遥感技术有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of difficult extraction of effective information and poor detection accuracy in target detection of current high-resolution remote sensing images, the present invention provides an enhanced remote sensing image target detection scheme to increase the feature extraction ability and detection accuracy of the model

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
  • Enhanced remote sensing image target detection method and system
  • Enhanced remote sensing image target detection method and system
  • Enhanced remote sensing image target detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The technical solutions of the present invention will be specifically described below in conjunction with the drawings and embodiments.

[0039] see figure 1 , the embodiment of the present invention is a target detection network model method based on high-resolution remote sensing images, which can use Python programming language for experiments, and can also use C / C++ programming language for engineering applications.

[0040] An embodiment of the present invention provides an enhanced remote sensing image target detection method, see figure 1 , including the following steps:

[0041] Step 1, data construction, including inputting a labeled high-resolution remote sensing image dataset;

[0042] This step can perform data processing of remote sensing images, including automatic cropping and data preprocessing of high-resolution remote sensing images.

[0043] The embodiment adopts my country's Gaofen-2 panchromatic image data and some high-resolution remote sensing ...

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 provides an enhanced remote sensing image target detection method and system. The method comprises the steps of inputting a high-resolution image data set with labels; setting an enhanced target detection model, to be more specific, building the enhanced target detection model by means of embedded connection and jump connection, realizing feature up-sampling processes of different spatial resolutions through the embedded connection, and supplementing lost detail information by means of the jump connection to realize enhancement of model feature characterization capability. A first-order target detection framework is provided to realize a high-resolution remote sensing image target detection task; the enhanced target detection model is trained, and target detection is performed on the input image according to the trained model to obtain a result. The enhanced remote sensing image target detection method provided by the invention not only can effectively improve the performance of a traditional method, but also can be applied to an on-orbit target real-time detection task in an on-satellite limited environment.

Description

technical field [0001] The invention belongs to the field of satellite remote sensing image target detection, in particular relates to a high-resolution remote sensing image target detection scheme, and proposes an enhanced target detection network to realize the high-resolution remote sensing image target recognition task. Background technique [0002] In recent years, my country has completed a series of remote sensing satellite launch missions and built a space-based observation system with high spatial resolution and high temporal resolution. For this reason, the acquisition of high-resolution remote sensing images has become easier and easier. For high-resolution remote sensing image target detection tasks, such as airport aircraft detection and model identification, maritime ship detection, high-speed vehicle detection, etc., it is of great significance to quickly and accurately extract the target of interest. [0003] With the continuous development of artificial int...

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): G06K9/62G06K9/34G06K9/00G06N3/04
CPCG06N3/045G06F18/214
Inventor 王密项韶谢广奇张致齐
Owner 武汉九天高分遥感技术有限公司
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