Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Deep Learning Detection Method for Dense Targets in Remote Sensing Images

A technology of dense targets and remote sensing images, applied in the field of high-resolution remote sensing image recognition, can solve the problem that extremely dense targets are difficult to be effectively extracted, and achieve the effect of ground object positioning and high-precision ground object positioning.

Active Publication Date: 2022-06-03
WUHAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it only works on dense targets adjoining surrounding targets
[0004] Although the above methods have greatly improved the performance of dense object detection, it is still difficult to effectively extract extremely dense objects.

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 Deep Learning Detection Method for Dense Targets in Remote Sensing Images
  • A Deep Learning Detection Method for Dense Targets in Remote Sensing Images
  • A Deep Learning Detection Method for Dense Targets in Remote Sensing Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following examples will further illustrate the outstanding features and significant progress of the present invention, which are only intended to illustrate the present invention and never limit the present invention.

[0027] A method for deep learning detection of dense targets in remote sensing images provided by an embodiment of the present invention specifically includes the following steps:

[0028] (1) Using self-labeled high spatial resolution remote sensing image dense greenhouse object detection dataset (GHDOERS), the GH DOERS training dataset contains 1290 Google Earth images, the test set and the validation set are 430 and 862 respectively. is 512 x 512 pixels. The dataset contains 6 provinces and regions across the country, including: Hubei Province, Liaoning Province, Shandong Province, Xinjiang Uygur Autonomous Region, Shaanxi Province, and Jiangsu Province.

[0029] 1.1. Select the training set and test set TrainA and TestB in the data set, which ar...

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 deep learning detection method for dense targets in remote sensing images, which is used for extracting dense targets in remote sensing images. First, the image is input into the deep CNN base network to obtain the feature map; second, the deep convolutional features are input into the dense object extraction framework for region of interest extraction (RPN branch), object classification and rectangular frame regression. For the RPN branch, a high-density bias sampler is proposed to mine more samples with high density (hard samples) to improve detection performance. Soft‑NMS is adopted after the dense object extraction framework to retain more positive objects. Finally, the refined rectangular frame is output to realize the number statistics of dense objects.

Description

technical field [0001] The invention belongs to the field of high-resolution remote sensing image recognition, and particularly relates to a deep learning detection method for dense targets in remote sensing images. Background technique [0002] The rapid development of remote sensing technology can now provide a large number of high-resolution remote sensing images. Compared with low-resolution images, high-resolution remote sensing images contain more detailed spatial information, which not only brings opportunities, but also challenges the identification of remote sensing images. Recognition and analysis based on high-resolution remote sensing image technology have been used in remote sensing image target detection tasks. Among them, plastic greenhouse detection is a very important research direction. Greenhouse cultivation is the cultivation of crops such as vegetables, tobacco and fruit by creating a micro-environment. Monitoring and mapping greenhouse areas is inter...

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): G06V20/13G06V10/774G06V10/764G06V10/25G06V10/82G06N3/04
CPCG06V20/13G06V10/25G06V2201/07G06N3/045G06F18/241G06F18/214Y02A40/25
Inventor 马爱龙陈鼎元钟燕飞郑卓
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products