Target recognition method and device

A target recognition and target technology, applied in the field of target recognition, can solve the problems of difficult multi-source fusion recognition and low fusion recognition accuracy, and achieve the effect of improving the efficiency and accuracy of recognition, improving the ability to represent, and improving the accuracy.

Active Publication Date: 2021-08-06
中国人民解放军91977部队
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the main purpose of the object recognition method and device provided by the present invention is to solve the problems in the prior art that multi-source fusion recognition is difficult and the accuracy of fusion recognition is not high

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
  • Target recognition method and device
  • Target recognition method and device
  • Target recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The technical scheme of the method described in this embodiment comprises the following steps:

[0033] Step 1: Collect multi-source detection data of the same target from different sensors;

[0034] Multi-source refers to the data obtained from multiple different types of sensors, including but not limited to satellites, drones, radars, AIS, recording equipment, etc.; different types of sensors obtain different types of data, for example, the type of data obtained by satellites is Image data, radar can obtain location data, recording equipment can obtain voice data, etc. Multi-source probe data types include image, text, speech, and location-level data.

[0035] Step 2: Build a deep neural network model for target recognition, including feature extraction network and multi-source attention fusion;

[0036] figure 1 A schematic diagram of a target recognition deep neural network model in a target recognition method based on multi-source data fusion provided by an emb...

Embodiment 2

[0076] Further, another embodiment of the present invention also provides an object recognition device as an implementation of the methods shown in the above embodiments. This device embodiment corresponds to the foregoing method embodiment. For the convenience of reading, this device embodiment does not repeat the details in the foregoing method embodiment one by one, but it should be clear that the device in this embodiment can correspond to the foregoing method implementation. Everything in the example. In the device of this embodiment, there are following modules:

[0077] 1. Data acquisition module: configured to collect multi-source detection data of the same target from different sensors; this module corresponds to step 1 in Embodiment 1.

[0078] 2. Model building module: configured to build a deep neural network model for target recognition, including the feature extraction network and multi-source attention fusion sub-modules; the feature extraction network is 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
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a target recognition method and device, which belong to the technical field of target recognition, and mainly solve the problems that in the prior art, multi-source fusion recognition is difficult to carry out, and the fusion recognition accuracy is not high. According to the method, the multi-source attention fusion module is constructed, the feature representation vectors of the multi-source detection data are fused according to the mutual similarity and importance degree, the fusion feature representation of the multi-source detection data is obtained, the importance degree of the feature representation of the multi-source detection data can be corrected, the important features are enhanced, the purpose of weakening non-important features is achieved, the characterization capacity of the fused features is improved, and then the accuracy of multi-source fusion recognition is improved.

Description

technical field [0001] The present invention relates to the technical field of target recognition, in particular to a method and device for target recognition. Background technique [0002] Target recognition has always been a research hotspot in the field of data processing. Its purpose is to obtain the salient features of the target through the feature extraction of data information, and realize the identification of target identity information; How to make full use of the complementary advantages of multi-source information and realize the fusion and recognition of multi-source detection information is the key to improving the recognition accuracy of detection targets, and then can form accurate situation judgment and behavior prediction. [0003] In the research of target recognition, there are few studies on multi-source fusion recognition, mainly because the heterogeneity and heterogeneity among multi-source information form barriers to multi-source information fusion....

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/00G06N3/044G06N3/045G06F18/22G06F18/214G06F18/253
Inventor 吕亚飞张筱晗熊伟崔亚奇姚立波黄猛王雅芬
Owner 中国人民解放军91977部队
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap