Ammunition Recognition Method Based on Deep Convolutional Neural Network

A deep convolution and neural network technology, applied in the field of ammunition identification based on deep convolutional neural network, can solve various accidents, endanger personnel declaration safety and other problems, and achieve the goal of reducing hidden dangers, good applicability and accurate identification methods. Effect

Active Publication Date: 2020-02-07
王宇宁
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It solves the technical problems in the prior art that various accidents are likely to occur due to improper handling and endanger the safety of personnel declarations

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
  • Ammunition Recognition Method Based on Deep Convolutional Neural Network
  • Ammunition Recognition Method Based on Deep Convolutional Neural Network
  • Ammunition Recognition Method Based on Deep Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Ammunition identification method based on deep convolutional neural network, the steps are:

[0043] 1) Enter the shape data of the ammunition model: specify the main body of the ammunition as a rotating body formed by rotating a right-angled trapezoid with N straight waists on a straight line around the axis. Based on this, enter the shape data of the ammunition; divide its height H into 50 parts H 0 , the distance between each node and the vertex is S h , and then input the ammunition radius R corresponding to 50 nodes from top to bottom h .

[0044] 2) Generate a 3D model:

[0045] 2a) Read the shape data of the ammunition model obtained in step 1) and input it into the graphics engine. Starting from the vertex, take the position of 50 nodes as the center of the circle, corresponding to the radius R h As the radius, draw 50 rings whose center is on the bomb shaft, and each ring is divided into 200 points equally;

[0046] 2b) Define the ammunition axis as the x-...

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

An ammunition identification method based on a deep convolutional neural network, which does not require specific equipment. It only needs to enter the model information in the database first, and use a commonly used camera or photographic equipment to take pictures of the ammunition to be detected, and then use a specific identification and comparison method. Identify and compare. It solves the technical problem in the prior art that various accidents are likely to occur due to improper handling and endanger the life safety of personnel. Through the above method, the present invention provides an ammunition identification method with fast identification speed, high accuracy and good safety performance. The ammunition to be tested can be identified in real time, reducing the danger to personnel and ensuring public safety.

Description

technical field [0001] The invention relates to an ammunition identification method, in particular to an ammunition identification method based on a deep convolutional neural network. Background technique [0002] Due to historical issues, in some special areas underground or in other places, there will be some long-standing ammunition left over from wars. Because such ammunition is an unspecified ammunition left over, and it has not been properly preserved in the external environment for a long time, the external characteristics of the ammunition have changed. , the mark disappears, and it is difficult to identify the type and attributes of this type of ammunition with the naked eye. If they are all treated uniformly and blindly, it will easily lead to various accidents, and the consequences will be serious, which may endanger the lives of personnel. If systematic identification and classification are carried out, due to the lack of such equipment and targeted methods, the ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/64G06N3/045G06F18/2414
Inventor 王宇宁曹海庆张利刘万波李猛张鹤殷志军白冬龙邱硕张伟李国松赵英竣李志刚关向阳于宏波王怀志丁可心
Owner 王宇宁
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