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

Remote sensing image target detection method based on multi-scale feature fusion

A multi-scale feature and target detection technology, which is applied in the fields of image processing and computer vision, can solve the problems of insufficient information extraction, difficulty in making full use of the context information of multi-scale feature maps to promote target detection, and insufficient target recognition ability. Achieve the effects of improving detection performance, enhancing feature representation capabilities, and enhancing recognition capabilities

Active Publication Date: 2019-08-09
TIANJIN UNIV
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The method of extracting context information in the existing CNN-based remote sensing image target detection technology is relatively simple, and the information extraction is not sufficient. It is difficult to give full play to the role of context information in multi-scale feature maps in promoting target detection. still not high enough

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 image target detection method based on multi-scale feature fusion
  • Remote sensing image target detection method based on multi-scale feature fusion
  • Remote sensing image target detection method based on multi-scale feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The embodiment of the present invention proposes a multi-scale feature map fusion method based on CNN. The method is based on the multi-scale feature map of CNN, and adds a deconvolution module and a prediction module according to the scale of the feature map to construct a multi-scale feature map fusion module. , and access CNN multi-scale feature map to extract context information, enhance CNN target recognition ability, the proposed network structure is as follows figure 1 As shown, the approximate implementation steps are as follows:

[0038] 101: Basic network construction for target detection based on multi-scale feature maps;

[0039] The target detection basic network based on the multi-scale feature map is used to complete the task of target detection, and can realize the positioning and classification of multi-scale targets in remote sensing images according to the predefined default frame. The target detection basic network constructed in the embodiment of t...

Embodiment 2

[0048] Combine below figure 1 and figure 2 The scheme in Example 1 is further introduced, see the following description for details:

specific Embodiment approach

[0049] The embodiment of the present invention extracts the context information of the network through the multi-scale feature map fusion module, enriches the feature map, and improves the target detection capability of the network. The fusion module proposed in the embodiment of the present invention can be applied to a detection network based on multi-scale feature maps, so the proposed detection network is composed of two parts: the basic target detection network based on multi-scale feature maps and the fusion module of multi-scale feature maps: The scale feature map is connected to the truncated VGG terminal to construct the basic network; multiple deconvolution modules and prediction modules are used to jointly construct a multi-scale feature map fusion module to extract context information and enhance the target recognition ability of the network. The specific implementation is as follows:

[0050] 201: Construction of basic network for target detection based on multi-s...

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 remote sensing image target detection method based on multi-scale feature fusion. The method comprises the following steps: constructing a target detection basic network composed of a truncation type VGG and a multi-scale feature map; constructing a multi-scale feature map fusion module composed of a deconvolution module and a prediction module, the multi-scale feature map fusion module being used for extracting context information of a multi-scale feature map in the target detection basic network and generating a multi-scale feature map; predefining a multi-length-to-width ratio and a multi-scale default frame according to the size of the receptive field of the multi-scale feature map, and completing positioning and classification of the target by using the default frame; training a target detection basic network; accessing a multi-scale feature map fusion module to the target detection basic network, fixing parameters of the target detection basic network during training, and only adjusting the parameters of the multi-scale feature map fusion module; and at the last stage, finely adjusting parameters of the target detection basic network and the multi-scale feature map fusion module at the same time to achieve a coupling effect.

Description

technical field [0001] The invention relates to the technical fields of image processing and computer vision, in particular to a remote sensing image target detection method based on multi-scale feature fusion. Background technique [0002] Remote sensing image object detection is an important application of image processing technology in the field of remote sensing. The remote sensing image target detection technology extracts the features of the target to be detected in the remote sensing image, and completes the positioning and classification of the target based on the obtained features. Remote sensing image target detection technology has been widely used in both civilian and military fields, providing a reliable source of information for urban planning, traffic management, monitoring, military strikes and other activities. Robust and efficient detection methods can overcome the interference of complex scenes in remote sensing images on target detection performance, red...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/13G06N3/045G06F18/253
Inventor 郑泽勋罗晓维雷建军王梦园牛力杰韩梦芯
Owner TIANJIN 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com