CN111208577A - 一种基于太赫兹线性扫描的危险品检测方法 - Google Patents
一种基于太赫兹线性扫描的危险品检测方法 Download PDFInfo
- Publication number
- CN111208577A CN111208577A CN202010042319.6A CN202010042319A CN111208577A CN 111208577 A CN111208577 A CN 111208577A CN 202010042319 A CN202010042319 A CN 202010042319A CN 111208577 A CN111208577 A CN 111208577A
- Authority
- CN
- China
- Prior art keywords
- terahertz
- target
- image
- dangerous goods
- scanning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 231100001261 hazardous Toxicity 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000003384 imaging method Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 3
- 230000005855 radiation Effects 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 8
- 239000002360 explosive Substances 0.000 description 6
- 239000007788 liquid Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/59—Transmissivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10008—Still image; Photographic image from scanner, fax or copier
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Geophysics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
本发明公开了一种基于太赫兹线性扫描的危险品检测方法,采用太赫兹辐射源和线性阵列相机作为探测器采集的图像序列,通过扫描预处理,背景消除,归一化;采集多类别危险品的太赫兹图像,创建训练集;基于YOLO2,创建精简型框架YOLOS,对训练集中目标位置进行Kmean聚类,得到目标预测候选框;配置YOLOS训练参数,进行学习训练,得到权值文件;创建拼接图像缓存队列,太赫兹线性扫描危险品图像拼接,进入队列;创建目标检测进程,软件读取队列图像,进入目标检测进程进行处理等一列步骤,完成对危险品的检测。与现有技术相比,本发明能够通过太赫兹线性扫描改变现有危险品检测方法的不足,能对多种危险品进行实时检测,准确率高,速度快。
Description
技术领域
本发明涉及危险品检测技术领域,具体涉及一种基于太赫兹线性扫描的危险品检测方法。
背景技术
一般地,x射线穿透性较强,对塑胶凶器、塑胶炸弹、流体炸药、易燃易爆液体等危险品,不易成像。利用太赫兹成像技术,可以对x射线透过的物品,进行有效的检测。
太赫兹(THz)波是一种频率范围为 0.1THz-10THz,波长范围为 0.03-3mm,介于无线电波和光波之间的电磁波。具有高时空相干性、低光子能量、使用安全性高、定向性好、频谱宽等特性,近年来迅速发展,在军事、安全、医疗、生物、农业等科学领域得到广泛应用。目前国内有关于多目标识别的方法主要基于特征提取和分类器,需要根据特定的待检测目标设计特征,该方法对单类别或少量类别检测效果较好,对多类别目标检测识别能力有限。准确率低,实时性差。
专利申请号为201810654761.7 (一种基于深度学习的太赫兹危险品检测方法),采用的深度学习方法是CNN,主要用于分类,对于目标检测,需要采取另外的Selectivesearch算法。该方法属于早期的深度学习方法,用于目标检测准确率低,复杂度高。
专利名称为一种基于主动式太赫兹安检方法,(201810654764.0)文中主要是用于人体安检,主要是对正、负样本进行训练,只是一种分类方法,不能有效的检测、识别危险品。
发明内容
为解决上述技术缺陷,本发明的目的是提供一种基于太赫兹线性扫描的危险品检测方法,能够通过太赫兹线性扫描改变现有危险品检测方法的不足,能对多种危险品进行实时检测,准确率高,速度快。
为达到上述目的,本发明采用的技术方案是:一种基于太赫兹线性扫描的危险品检测方法,采用太赫兹辐射源和线性阵列相机作为探测器采集的图像序列,具体步骤在于:
步骤一、扫描预处理,背景消除,归一化;
步骤二、采集多类别危险品的太赫兹图像,创建训练集;
步骤三、基于YOLO2,创建精简型框架YOLOS,对训练集中目标位置进行Kmean聚类,得到目标预测候选框;
步骤四、配置YOLOS训练参数,进行学习训练,得到权值文件;
步骤五、创建拼接图像缓存队列,太赫兹线性扫描危险品图像拼接,进入队列;
步骤六、创建目标检测进程,软件读取队列图像,进入目标检测进程进行处理;
步骤七、加载权值、配置、类别文件,运行YOLOS,进行多类别目标检测、识别,得到目标类别和位置;
步骤八、图像输出显示,锁定目标区域。
本发明的有益效果是:实现了太赫兹线性扫描的图像拼接,危险品的太赫兹成像,以及多类别危险品检测,识别精度高,实时性好;利用太赫兹扫描仪对包裹进行线性扫描,得到危险品太赫兹图像,对图像中的多类别危险品目标进行实时检测;检测方法,基于YOLO2,将分类、检测两个任务和而为一,准确率高,速度快;对YOLO2网络结构进行精简,得到YOLOS,在保证精度的前提下,提高了检测速度。
附图说明
下面结合附图及实施例,对本发明的技术特征作进一步描述。
图1为本发明的流程示意图。
图2 是图1中YOLOS网络框架训练的原理示意图。
图3 是本发明的工作原理示意图。
具体实施方式
附图1-3是本发明的一种实施例,公开了一种基于太赫兹线性扫描的危险品检测方法,按以下步骤来实现:
步骤二、采集多类别危险品的太赫兹图像,创建训练集;对多类别危险品太赫兹线性扫描,生成太赫兹危险品图像;每个类别采集3000张图片,用标注工具对图像中危险品目标标注,生成标注文件集;对标注文件进行归一化,生成深度学习框架使用的文件;
步骤三、基于YOLO2,创建精简型框架YOLOS,对训练集中目标位置进行Kmean聚类,得到目标预测候选框;对YOLO2深度学习框架进行精简,得到识别率高、实时性好的深度学习框架;对训练集标注文件进行K-Means聚类,生成M个预测候选框尺寸,M为危险品类别个数;
步骤四、配置YOLOS训练参数,进行学习训练,得到权值文件;
步骤五、创建拼接图像缓存队列,太赫兹线性扫描危险品图像拼接,进入队列;创建一个长度为1000,尺寸为512x256的RGB格式拼接图像队列。线性阵列扫描仪每采集512列,合成一张图像,存入队列缓存尾;
步骤六、创建目标检测进程,软件读取队列图像,进入目标检测进程进行处理;创建目标检测进程,从队列头取出图像,进行目标检测识别;
步骤七、加载权值、配置、类别文件,运行YOLOS,进行多类别目标检测、识别,得到目标类别和位置;基于深度学习框架,加载权值、配置、类别文件,对输入图像进行目标检测,得到目标类别和位置信息;
步骤八、图像输出显示,锁定目标区域。软件界面读取经过目标检测的图像,显示在界面窗口,锁定目标所在区域,并显示类别信息。
通过上述方法,突破了x射线扫描仪对液态塑胶凶器、塑胶炸弹、流体炸药、易燃易爆液体等危险品,不易成像的局限性。采用太赫兹线性扫描仪作为透射成像手段,可以显现x射线扫描仪不能探测的危险品。突破了传统基于特征提取和分类器的目标检测方法对多类别目标检测准确率、实时性的局限性,优化了深度学习网络结构,能够对多类别、多目标包裹危险品进行实时、准确检测。
本发明的优点是实现了太赫兹线性扫描的图像拼接,危险品的太赫兹成像,以及多类别危险品检测,识别精度高,实时性好。
以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。
Claims (1)
1.一种基于太赫兹线性扫描的危险品检测方法,其特征在于包括以下步骤:
步骤二、采集多类别危险品的太赫兹图像,创建训练集;
步骤三、基于YOLO2,创建精简型框架YOLOS,对训练集中目标位置进行Kmean聚类,得到目标预测候选框;
步骤四、配置YOLOS训练参数,进行学习训练,得到权值文件;
步骤五、创建拼接图像缓存队列,太赫兹线性扫描危险品图像拼接,进入队列;
步骤六、创建目标检测进程,软件读取队列图像,进入目标检测进程进行处理;
步骤七、加载权值、配置、类别文件,运行YOLOS,进行多类别目标检测、识别,得到目标类别和位置;
步骤八、图像输出显示,锁定目标区域。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010042319.6A CN111208577A (zh) | 2020-01-15 | 2020-01-15 | 一种基于太赫兹线性扫描的危险品检测方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010042319.6A CN111208577A (zh) | 2020-01-15 | 2020-01-15 | 一种基于太赫兹线性扫描的危险品检测方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111208577A true CN111208577A (zh) | 2020-05-29 |
Family
ID=70786242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010042319.6A Pending CN111208577A (zh) | 2020-01-15 | 2020-01-15 | 一种基于太赫兹线性扫描的危险品检测方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111208577A (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112037243A (zh) * | 2020-08-13 | 2020-12-04 | 上海微波技术研究所(中国电子科技集团公司第五十研究所) | 被动式太赫兹安检方法、系统及介质 |
CN112485218A (zh) * | 2020-11-05 | 2021-03-12 | 电子科技大学中山学院 | 一种基于人工神经网络的太赫兹危险液体识别方法 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101806748A (zh) * | 2010-03-25 | 2010-08-18 | 哈尔滨工业大学 | 太赫兹二维面阵扫描成像方法及实现该方法的成像系统 |
US8564855B2 (en) * | 2008-11-05 | 2013-10-22 | I2S | Method for the three-dimensional digitization of books using terahertz radiation |
US20160265901A1 (en) * | 2015-03-12 | 2016-09-15 | Proton Products International Limited | Measurement of industrial products manufactured by extrusion techniques |
JP2016170168A (ja) * | 2015-03-12 | 2016-09-23 | プロトン プロダクツ インターナショナル リミテッド | 押出技術により製造された工業製品の測定 |
CN109948527A (zh) * | 2019-03-18 | 2019-06-28 | 西安电子科技大学 | 基于集成深度学习的小样本太赫兹图像异物检测方法 |
CN110297281A (zh) * | 2019-07-22 | 2019-10-01 | 浙江云特森科技有限公司 | 毫米波安检舱系统及安检方法 |
CN110555513A (zh) * | 2019-08-16 | 2019-12-10 | 国电南瑞科技股份有限公司 | 一种基于深度学习的电力设备缺陷集成诊断方法 |
-
2020
- 2020-01-15 CN CN202010042319.6A patent/CN111208577A/zh active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8564855B2 (en) * | 2008-11-05 | 2013-10-22 | I2S | Method for the three-dimensional digitization of books using terahertz radiation |
CN101806748A (zh) * | 2010-03-25 | 2010-08-18 | 哈尔滨工业大学 | 太赫兹二维面阵扫描成像方法及实现该方法的成像系统 |
US20160265901A1 (en) * | 2015-03-12 | 2016-09-15 | Proton Products International Limited | Measurement of industrial products manufactured by extrusion techniques |
JP2016170168A (ja) * | 2015-03-12 | 2016-09-23 | プロトン プロダクツ インターナショナル リミテッド | 押出技術により製造された工業製品の測定 |
CN109948527A (zh) * | 2019-03-18 | 2019-06-28 | 西安电子科技大学 | 基于集成深度学习的小样本太赫兹图像异物检测方法 |
CN110297281A (zh) * | 2019-07-22 | 2019-10-01 | 浙江云特森科技有限公司 | 毫米波安检舱系统及安检方法 |
CN110555513A (zh) * | 2019-08-16 | 2019-12-10 | 国电南瑞科技股份有限公司 | 一种基于深度学习的电力设备缺陷集成诊断方法 |
Non-Patent Citations (2)
Title |
---|
刘宁宁: "基于太赫兹的危险品智能识别系统", 《信息与电脑》 * |
刘建国等: "基于YOLOv2的行人检测方法研究", 《数字制造科学》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112037243A (zh) * | 2020-08-13 | 2020-12-04 | 上海微波技术研究所(中国电子科技集团公司第五十研究所) | 被动式太赫兹安检方法、系统及介质 |
CN112485218A (zh) * | 2020-11-05 | 2021-03-12 | 电子科技大学中山学院 | 一种基于人工神经网络的太赫兹危险液体识别方法 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10013615B2 (en) | Inspection methods and devices | |
EP3349048B1 (en) | Inspection devices and methods for detecting a firearm in a luggage | |
CN109544563B (zh) | 一种面向违禁物安检的被动毫米波图像人体目标分割方法 | |
US20210150699A1 (en) | Visual inspection system for automated detection of particulate matter in flexible medical containers | |
CN111257957B (zh) | 基于被动式太赫兹成像的识别跟踪系统及方法 | |
Hu et al. | A method of citrus epidermis defects detection based on an improved YOLOv5 | |
CN111208577A (zh) | 一种基于太赫兹线性扫描的危险品检测方法 | |
Li et al. | Thermal infrared small ship detection in sea clutter based on morphological reconstruction and multi-feature analysis | |
Xu et al. | YOLO-MSFG: toward real-time detection of concealed objects in passive terahertz images | |
CN112508955A (zh) | 基于深度神经网络对活体细胞形态检测的方法及相关产品 | |
Gao et al. | Small foreign metal objects detection in X-ray images of clothing products using faster R-CNN and feature pyramid network | |
Huang et al. | GCS-YOLOV4-Tiny: A lightweight group convolution network for multi-stage fruit detection | |
Jaccard et al. | Using deep learning on X-ray images to detect threats | |
CN115457026A (zh) | 一种基于改进YOLOv5的纸病检测方法 | |
Vaidya et al. | Leveraging YOLOv7 for plant disease detection | |
Kumar et al. | An Optimized Approach to Clinical Object Identification using YOLO v3 in the Cloud Environment | |
CN114037671A (zh) | 一种基于改进Faster RCNN的显微高光谱白细胞检测方法 | |
Nguyen et al. | Detection of weak micro-scratches on aspherical lenses using a Gabor neural network and transfer learning | |
Chen et al. | Identification of blurred terahertz images by improved cross-layer convolutional neural network | |
Ge et al. | Lightweight YOLOv7 algorithm for multi-object recognition on contrabands in terahertz images | |
Zhu et al. | PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions | |
Galvez et al. | Threat object detection and analysis for explosive ordnance disposal robot | |
Kukreja et al. | Automated Red Chilli Disease Recognition using Combined CNN-SVM Model: Enhancing Crop Management and Yield Optimization | |
Seetharaman et al. | Detection of Disease in Banana Fruit using Gabor Based Binary Patterns with Convolution Recurrent Neural Network. | |
CN112991304B (zh) | 一种基于激光定向能量沉积监测系统的熔池溅射检测方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |