Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A millimeter wave imaging dangerous goods detection method based on FPGA and depth learning

A millimeter wave imaging and dangerous goods technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve the problem of inability to accurately extract the irregular shape and outline of dangerous goods, and achieve fine concurrent operation granularity and concurrent execution efficiency. , fast processing speed, good function and customizability advantage

Inactive Publication Date: 2019-03-08
博微太赫兹信息科技有限公司
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that the existing technology cannot accurately extract the irregular contours of dangerous goods, and a method for detecting dangerous goods based on millimeter wave imaging based on FPGA and deep learning is provided.

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 millimeter wave imaging dangerous goods detection method based on FPGA and depth learning
  • A millimeter wave imaging dangerous goods detection method based on FPGA and depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The embodiments of the present invention are described in detail below. This embodiment is implemented on the premise of the technical solution of the present invention, and provides a detailed implementation manner and a specific operation process, but the protection scope of the present invention is not limited to the following implementation. example.

[0039] like figure 1 and figure 2 As shown, this embodiment includes two parts: offline model training and online detection, which are described as follows:

[0040] 1. Offline training of deep learning network model part:

[0041] Using the image semantic segmentation annotation tool labelme, the outlines of all dangerous objects in each image are marked separately as the input of the deep learning network.

[0042] The convolutional neural network used to extract features has a total of 8 layers, including 5 convolutional layers and 3 max-pooling layers. Normalize the input image data, adjust the image size to ...

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 millimeter wave imaging dangerous goods detection method based on FPGA and depth learning, which comprises the steps of obtaining the millimeter wave imaging pictures and identifying dangerous goods in the pictures; constructing the depth learning network model of hazardous materials detection, and using the labeled millimeter-wave imaging images to train the model to getthe trained detection model; locating the trained detection model into the detection system of FPGA platform; using the FPGA to detect the millimeter wave image to be measured; using the trained detection model to detect the collected millimeter-wave images; if the image to be measured contains hazardous materials, marking the hazardous materials category, alarming, and marking the coordinates ofthe irregular outline position of the hazardous materials at the same time. Based on the FPGA-based platform, using the depth neural network model trained by Mask R-CNN object detection framework forthe real-time foreign body detection, so that compared with ASIC chips, the method has better customizability.

Description

technical field [0001] The invention relates to a millimeter wave imaging dangerous object detection technology, in particular to a millimeter wave imaging dangerous object detection method based on FPGA and deep learning. Background technique [0002] Millimeter waves generally refer to electromagnetic waves with frequencies between infrared and microwaves in the 26.5-300 GHz band, which are in the transition stage from macro electronics to micro photonics. Compared with microwaves, millimeter waves have higher bandwidth characteristics and resolution capabilities; compared with light waves, millimeter waves have higher energy conversion efficiency and can image the surface of certain substances; compared with X-rays, their electron energy low, will not cause harm to human tissue. Active millimeter-wave imaging uses millimeter-wave transmitting devices to irradiate the inspected person and the items they are carrying, and then uses a receiving antenna to collect reflected ...

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
IPC IPC(8): G06K9/32G06K9/46G06K9/62G06N3/04
CPCG06V10/25G06V10/44G06N3/045G06F18/214
Inventor 刘晓光余开张月皓
Owner 博微太赫兹信息科技有限公司
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
Eureka Blog
Learn More
PatSnap group products