CN106203264A - Dangerous goods detection method and device - Google Patents

Dangerous goods detection method and device Download PDF

Info

Publication number
CN106203264A
CN106203264A CN201610486706.2A CN201610486706A CN106203264A CN 106203264 A CN106203264 A CN 106203264A CN 201610486706 A CN201610486706 A CN 201610486706A CN 106203264 A CN106203264 A CN 106203264A
Authority
CN
China
Prior art keywords
dangerous goods
image
measured
article
obtains
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
Application number
CN201610486706.2A
Other languages
Chinese (zh)
Inventor
刘均
刘新
宋朝忠
欧阳张鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Launch Technology Co Ltd
Original Assignee
Shenzhen Launch Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Launch Technology Co Ltd filed Critical Shenzhen Launch Technology Co Ltd
Priority to CN201610486706.2A priority Critical patent/CN106203264A/en
Priority to PCT/CN2016/108915 priority patent/WO2018000732A1/en
Publication of CN106203264A publication Critical patent/CN106203264A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/20Scenes; Scene-specific elements in augmented reality scenes
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00Investigating materials by wave or particle radiation
    • G01N2223/03Investigating materials by wave or particle radiation by transmission
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00Investigating materials by wave or particle radiation
    • G01N2223/10Different kinds of radiation or particles
    • G01N2223/101Different kinds of radiation or particles electromagnetic radiation
    • G01N2223/1016X-ray

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

The invention discloses a kind of dangerous goods detection method, described method includes: the article to be measured in unmanned plane detection preset range, obtains the image of article to be measured;The image of described article to be measured is contrasted with the dangerous goods image that prestores, obtains the image of described article to be measured and the similarity of the described dangerous goods image that prestores;If described similarity is more than presetting similarity, then judge that described article to be measured are as dangerous goods.The invention also discloses a kind of dangerous goods detection device.The present invention solves the problem that traditional X-ray machine needs occupied ground, it is achieved that automatically detected the existence of article by unmanned plane, it is not necessary to manually goes to confirm the existence of dangerous goods, improves the detection efficiency of dangerous goods.

Description

Dangerous goods detection method and device
Technical field
The present invention relates to unmanned air vehicle technique field, particularly relate to a kind of dangerous goods detection method and device.
Background technology
Dangerous goods be possible dangerous health of human body, safety or article hurtful to property or material significantly, as Combustible and explosive articles, hazardous chemical and radioactive substance etc..Therefore, how the danger entrained by lawless person can quickly be detected Danger article, are urgent problems.
The most all use the detection dangerous goods of X-ray machine, i.e. after article to be measured enter sense channel, light will be stopped Barrier signal, detection signal is sent to control unit, triggers radiographic source emitting x-ray, thus obtain the image of article to be measured.But It is that existing X-ray machine is all located in ground, a part of place can be taken.When personnel are more, easily cause personnel's blocking.And And existing X-ray machine can be only done detection work, it is impossible to the existence of automatic decision dangerous goods, need manually detection image to be entered Row judges, and is responsible for the staff judging detection image, such as safety inspector, is to need through detection training, and needs To observe monitor screen for a long time, the workload causing safety inspector is relatively big, and the requirement to safety inspector is higher, thus also causes detection The inefficiency of dangerous goods.
Summary of the invention
Present invention is primarily targeted at a kind of dangerous goods detection method of offer and device, it is intended to solve existing existing For detecting the X-ray machine occupied ground of dangerous goods, detect dangerous goods inefficiency, it is impossible to automatic decision dangerous goods exist Technical problem.
For achieving the above object, a kind of dangerous goods detection method that the present invention provides, described dangerous goods detection method Including:
Article to be measured in unmanned plane detection preset range, obtain the image of article to be measured;
The image of described article to be measured is contrasted with the dangerous goods image that prestores, obtains the image of described article to be measured Similarity with the described dangerous goods image that prestores;
If described similarity is more than presetting similarity, then judge that described article to be measured are as dangerous goods.
Preferably, if described similarity is more than presetting similarity, then judge that described article to be measured are as dangerous goods After step, also include:
Follow the tracks of the personnel carrying described dangerous goods, obtain the positional information carrying described dangerous goods personnel place, and Described positional information is sent to the terminal being connected with described unmanned plane.
Preferably, the personnel of described dangerous goods are carried in described tracking, obtain and carry described dangerous goods personnel place Positional information, and described positional information is sent after the step of the terminal being connected with described unmanned plane, also include:
The warning message of described positional information is carried in output, with the law enfrocement official that prompting is relevant.
Preferably, if described similarity is more than presetting similarity, then judge that described article to be measured are as dangerous goods After step, also include:
The degree of danger of described dangerous goods is determined according to the relation table of insinuating between dangerous goods and degree of danger;
If the degree of danger of described dangerous goods reaches predeterminable level, then export warning message;
If the degree of danger of described dangerous goods is not up to described predeterminable level, then export information.
Preferably, described unmanned plane detection preset range in article to be measured, obtain article to be measured image step it After, also include:
The image of described article to be measured is carried out pretreatment, obtains the image of pretreated described article to be measured;
Described the image of described article to be measured is contrasted with the dangerous goods image that prestores, obtain described article to be measured Image includes with the step of the similarity of the described dangerous goods image that prestores:
The image of pretreated described article to be measured is carried out edge extracting, obtains the first figure of described article to be measured Picture;
First image of described article to be measured is carried out feature extraction, obtains the second image of described article to be measured;
Second image of described article to be measured is contrasted with the dangerous goods image that prestores, obtains described article to be measured Second image and the similarity of the described dangerous goods image that prestores.
Additionally, for achieving the above object, the present invention also provides for a kind of dangerous goods detection device, and described dangerous goods detect Device is applied to unmanned plane, and described dangerous goods detection device includes:
Detection module, for detecting the article to be measured in preset range, obtains the image of article to be measured;
Contrast module, for being contrasted with the dangerous goods image that prestores by the image of described article to be measured, obtains described The image of article to be measured and the similarity of the described dangerous goods image that prestores;
Determination module, if for described similarity more than presetting similarity, then judging that described article to be measured are as dangerous goods.
Preferably, described dangerous goods detection device includes:
Tracking module, for following the tracks of the personnel carrying described dangerous goods, obtains and carries described dangerous goods personnel place Positional information, and described positional information is sent to the terminal that is connected with described unmanned plane.
Preferably, described dangerous goods detection device also includes:
First output module, carries the warning message of described positional information for output, with the law enfrocement official that prompting is relevant.
Preferably, described dangerous goods detection device also includes:
Determine module, for determining described dangerous goods according to the relation table of insinuating between dangerous goods and degree of danger Degree of danger;
Second output module, if the degree of danger for described dangerous goods reaches predeterminable level, then exports warning message; If the degree of danger being additionally operable to described dangerous goods is not up to described predeterminable level, then export information.
Preferably, described dangerous goods detection device also includes:
Pretreatment module, for the image of described article to be measured is carried out pretreatment, obtains pretreated described to be measured The image of article;
Described contrast module includes:
Extraction unit, for the image of pretreated described article to be measured is carried out edge extracting, obtains described to be measured First image of article;It is additionally operable to the first image of described article to be measured is carried out feature extraction, obtains described article to be measured Second image;
Contrast unit, for being contrasted with the dangerous goods image that prestores by the second image of described article to be measured, obtains Second image of described article to be measured and the similarity of the described dangerous goods image that prestores.
The present invention obtains the image of article to be measured by unmanned plane, by the described image by described article to be measured and the danger that prestores Danger images of items contrasts, when the image of described article to be measured and the similarity of the described dangerous goods image that prestores are more than presetting During similarity, described unmanned plane judges that described article to be measured are as dangerous goods.Solve traditional X-ray machine and need occupied ground Problem, it is achieved that automatically detected the existence of article by unmanned plane, it is not necessary to manually go to confirm the existence of dangerous goods, improve The detection efficiency of dangerous goods.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of dangerous goods detection method first embodiment of the present invention;
Fig. 2 is the schematic flow sheet of dangerous goods detection method the second embodiment of the present invention;
Fig. 3 is the schematic flow sheet of dangerous goods detection method the 3rd embodiment of the present invention;
Fig. 4 is the high-level schematic functional block diagram of dangerous goods of the present invention detection device first embodiment;
Fig. 5 is the high-level schematic functional block diagram of dangerous goods of the present invention detection device the second embodiment;
Fig. 6 is the high-level schematic functional block diagram of dangerous goods of the present invention detection device the 3rd embodiment.
The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further referring to the drawings.
Detailed description of the invention
Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
The present invention provides a kind of dangerous goods detection method.
With reference to the schematic flow sheet that Fig. 1, Fig. 1 are dangerous goods detection method first embodiment of the present invention.
In the present embodiment, described dangerous goods detection method includes:
Step S10, the article to be measured in unmanned plane detection preset range, obtain the image of article to be measured;
When described unmanned plane receives the sense command that connected terminal is sent, described unmanned plane is from stacking area Flying to and detect region in territory, detects the article to be measured in preset range by the detection device being arranged in described unmanned plane, obtain The image of described article to be measured.Described terminal includes but not limited to smart mobile phone, personal computer and palm PC etc..In this reality Executing in example, described detection device is the device being mounted with X-ray.It should be noted that described detection device includes but not limited to It is mounted with the device of X-ray, it is also possible to for being mounted with that gamma-ray device or other can obtain described images of items to be measured Device.It is understood that described preset range is the scope that described unmanned plane can be detected by described detection region.
Step S20, contrasts the image of described article to be measured with the dangerous goods image that prestores, obtains described determinand The image of product and the similarity of the described dangerous goods image that prestores;
When described unmanned plane obtains the image of described article to be measured, described unmanned plane by the image of described article to be measured with The dangerous goods image prestored contrasts, and obtains the image of described article to be measured and the described dangerous goods prestored The similarity of image.Described unmanned plane has prestored the image of various dangerous goods.It is understood that described unmanned plane It is that the profile of article to be measured described in described images of items to be measured is contrasted with the profile of the dangerous goods prestored.When The profile of the article described to be measured that described unmanned plane obtains be less than described in prestore the profile of dangerous goods time, described unmanned Machine according to described in the profile of dangerous goods that prestores suitably expand the profile of described article to be measured, the most again by described to be measured The image of article contrasts with the dangerous goods image prestored, and the image obtaining described article to be measured is deposited in advance with described The similarity of the dangerous goods image of storage.The profile of the article described to be measured obtained when described unmanned plane prestores described in being more than The profile of dangerous goods time, described unmanned plane according to described in the profile of dangerous goods that prestores suitably reduce described to be measured The profile of article, contrasts the image of described article to be measured with the dangerous goods image prestored, obtains institute State the image of article to be measured and the similarity of the described dangerous goods image prestored.Described expansion or reduce described to be measured The scope of the profile of the article profile according to described article to be measured and the profile difference degree of the described dangerous goods prestored Depending on.
Step S30, if described similarity is more than presetting similarity, then judges that described article to be measured are as dangerous goods.
When the image of described article to be measured is similar more than presetting to the similarity of the described dangerous goods image prestored When spending, described unmanned plane then judges that described article to be measured are as dangerous goods.When the image of described article to be measured is deposited in advance with described When the similarity of the dangerous goods image of storage is less than or equal to described default similarity, described unmanned plane then judges described to be measured Article are normal goods, are not dangerous goods.It should be noted that described default similarity can set according to specific needs Put, as being set to 40%, or 50%, or 60% etc..
Further, after described step S10, also include:
Step a, carries out pretreatment to the image of described article to be measured, obtains the figure of pretreated described article to be measured Picture;
Further, when described unmanned plane obtains the image of described article to be measured, described unmanned plane is to described determinand The image of product carries out pretreatment, obtains the image of pretreated described article to be measured.The described image to described article to be measured The process carrying out pretreatment is: 1. image denoising;2. image enhaucament;3. image segmentation.The method of described image denoising include but It is not limited to Wavelet Denoising Method, mean filter and morphology scratch filter;It is right that the method for described image enhaucament includes but not limited to Than degree conversion, image operation, space filtering and multispectral conversion;The method of described image segmentation includes but not limited to that threshold value is divided Cut, edge segmentation and histogram method.
Described step S20 includes:
Step b, carries out edge extracting to the image of pretreated described article to be measured, obtains the of described article to be measured One image;
Step c, carries out feature extraction to the first image of described article to be measured, obtains the second figure of described article to be measured Picture;
Step d, contrasts the second image of described article to be measured with the dangerous goods image that prestores, obtains described to be measured Second image of article and the similarity of the described dangerous goods image that prestores.
When described unmanned plane obtains the image of pretreated described article to be measured, described unmanned plane is to pretreated The image of described article to be measured carries out edge extracting, obtains the image of article described to be measured through edge extracting, i.e. obtains institute State the first image of article to be measured.Described unmanned plane utilizes Profile invariant feature extracting method first to described article to be measured Image carries out feature extraction, obtains the second image of described article to be measured.The method of described edge extracting includes: 1. based on certain Fixing local operation's algorithm, such as differentiation, fitting process etc.;2. the overall extracting method with energy minimization as criterion, the party The feature of method is to use strict mathematical method to be analyzed this problem, and one-dimensional cost function extracts as optimum and depends on According to, extract edge from the viewpoint of global optimum, such as method of relaxation, analysis of neural network method etc.;3. with wavelet transformation, Mathematical Morphology The image edge extraction method that new and high technology is representative that the developed recentlies such as, analysis theories get up, as based on Analysis On Multi-scale Features Wavelet transformation extract image border method.
When described unmanned plane obtains the second image of described article to be measured, by the second image of described article to be measured with pre- The dangerous goods image first stored contrasts, and obtains the second image of described article to be measured and the described dangerous goods image that prestores Similarity.
The present embodiment obtains the image of article to be measured by unmanned plane, by described by the image of described article to be measured with prestore Dangerous goods image contrasts, when the image of described article to be measured and the similarity of the described dangerous goods image that prestores are more than pre- If during similarity, described unmanned plane judges that described article to be measured are as dangerous goods.Solve traditional X-ray machine and need occupied ground Problem, it is achieved that automatically detected the existence of article by unmanned plane, it is not necessary to manually go confirm dangerous goods existence, improve The detection efficiency of dangerous goods.
With reference to the schematic flow sheet that Fig. 2, Fig. 2 are dangerous goods detection method the second embodiment of the present invention, real based on first Execute example and propose dangerous goods detection method the second embodiment of the present invention.
In the present embodiment, described dangerous goods detection method includes:
Step S40, follows the tracks of the personnel carrying described dangerous goods, obtains the position carrying described dangerous goods personnel place Information, and described positional information is sent to the terminal being connected with described unmanned plane.
In the presence of described unmanned plane detects dangerous goods, described unmanned plane determines the people carrying described dangerous goods Member, starts tracking function, follows the tracks of the personnel carrying described dangerous goods, and by being arranged on the positioner in described unmanned plane Obtain the positional information carrying described dangerous goods personnel place in real time.Described dangerous goods are carried when described unmanned plane gets During the information of personnel position, will carry what the information transmission of described dangerous goods personnel position was extremely connected with described unmanned plane Terminal, is quickly found out the personnel carrying described dangerous goods for terminal use.It is understood that described positioner is peace Fill GPS (Global Positioning System, alignment system), or be mounted with that being similar to GPS can realize positioning merit The assembly of energy.
Further, described dangerous goods detection method includes:
The warning message of described positional information is carried in output, with the law enfrocement official that prompting is relevant.
Further, when described unmanned plane gets the positional information carrying described dangerous goods personnel place, according to The personnel position information carrying described dangerous goods generates warning message, with the relevant law enfrocement official of prompting, it has been found that dangerous Article, are quickly found out according to positional information entrained in described warning message for relevant law enfrocement official and carry described danger The personnel of product.
The present embodiment follows the tracks of the personnel carrying dangerous goods by unmanned plane, and described dangerous goods personnel institute is carried in acquisition Positional information, and described positional information is sent to the terminal that is connected with described unmanned plane.Can allow the use of described terminal Family, such as safety inspector, is quickly found out the personnel carrying described dangerous goods, improves the intelligent of unmanned plane.
With reference to the schematic flow sheet that Fig. 3, Fig. 3 are dangerous goods detection method the 3rd embodiment of the present invention, real based on first Execute example and propose dangerous goods detection method the 3rd embodiment of the present invention.
In the present embodiment, described dangerous goods detection method includes:
Step S50, determines the danger of described dangerous goods according to the relation table of insinuating between dangerous goods and degree of danger Degree;
When described unmanned plane judges described article to be measured as dangerous goods, according to the dangerous goods prestored with dangerous Mapping relations table between degree determines the degree of danger of described dangerous goods, as between described dangerous goods and degree of danger Mapping relations table is: gun, controlled knife etc. may jeopardize the dangerous journey corresponding to the article of human-body safety and property safety Degree is 1, and the degree of danger corresponding to radioactive substance is 2, and inflammable and explosive and that other degree of danger is higher chemical substance institute is right The degree of danger answered is 3.It should be noted that the relation of insinuating between described dangerous goods and degree of danger is not restricted to this Mapping relations described in embodiment.
Step S60, if the degree of danger of described dangerous goods reaches predeterminable level, then exports warning message;
Step S70, if the degree of danger of described dangerous goods is not up to described predeterminable level, then exports information.
After described unmanned plane determines the degree of danger of described dangerous goods, described unmanned plane judges described dangerous goods Whether degree of danger reaches predeterminable level.If the degree of danger of described dangerous goods reaches described predeterminable level, described unmanned plane Then export warning message, to point out related personnel, the danger that in the detection region at described unmanned plane place, dangerous degree is higher Danger article, process the most as early as possible.If the degree of danger of described dangerous goods is not up to described predeterminable level, then export information, To point out related personnel, the dangerous goods that in the detection region at described unmanned plane place, dangerous degree is relatively low, for relevant Personnel can take appropriate measures according to concrete working condition.Described related personnel is detection region, described unmanned plane place Staff, to the user of the terminal that described unmanned plane connects and relevant law enfrocement official etc..Described predeterminable level can root Arrange according to the safe coefficient required for the detection region at described unmanned plane place.As in the present embodiment, can be by described pre- If degree is set to 2.When as described in dangerous goods degree of danger equal to 2 or more than 2 time, described unmanned plane output alarm signal Breath;When the degree of danger of described dangerous goods is less than 2, described unmanned plane output information.
The present embodiment unmanned plane exports warning message or information by the degree of danger according to dangerous goods, for Related personnel takes appropriate measures according to the degree of danger of dangerous goods, improves unmanned plane in terms of detection dangerous goods Intelligent.
The present invention further provides a kind of dangerous goods detection device.
High-level schematic functional block diagram with reference to the first embodiment that Fig. 4, Fig. 4 are dangerous goods of the present invention detection device.
In the present embodiment, described dangerous goods detection device is applied to unmanned plane, described dangerous goods detection device bag Include:
Detection module 10, for detecting the article to be measured in preset range, obtains the image of article to be measured;
When described unmanned plane receives the sense command that connected terminal is sent, described unmanned plane is from stacking area Flying to and detect region in territory, detects the article to be measured in preset range by the detection device being arranged in described unmanned plane, obtain The image of described article to be measured.Described terminal includes but not limited to smart mobile phone, personal computer and palm PC etc..In this reality Executing in example, described detection device is the device being mounted with X-ray.It should be noted that described detection device includes but not limited to It is mounted with the device of X-ray, it is also possible to for being mounted with that gamma-ray device or other can obtain described images of items to be measured Device.It is understood that described preset range is the scope that described unmanned plane can be detected by described detection region.
Contrast module 20, for being contrasted with the dangerous goods image that prestores by the image of described article to be measured, obtains institute State the image of article to be measured and the similarity of the described dangerous goods image that prestores;
When described unmanned plane obtains the image of described article to be measured, described unmanned plane by the image of described article to be measured with The dangerous goods image prestored contrasts, and obtains the image of described article to be measured and the described dangerous goods prestored The similarity of image.Described unmanned plane has prestored the image of various dangerous goods.It is understood that described unmanned plane It is that the profile of article to be measured described in described images of items to be measured is contrasted with the profile of the dangerous goods prestored.When The profile of the article described to be measured that described unmanned plane obtains be less than described in prestore the profile of dangerous goods time, described unmanned Machine according to described in the profile of dangerous goods that prestores suitably expand the profile of described article to be measured, the most again by described to be measured The image of article contrasts with the dangerous goods image prestored, and the image obtaining described article to be measured is deposited in advance with described The similarity of the dangerous goods image of storage.The profile of the article described to be measured obtained when described unmanned plane prestores described in being more than The profile of dangerous goods time, described unmanned plane according to described in the profile of dangerous goods that prestores suitably reduce described to be measured The profile of article, contrasts the image of described article to be measured with the dangerous goods image prestored, obtains institute State the image of article to be measured and the similarity of the described dangerous goods image prestored.Described expansion or reduce described to be measured The scope of the profile of the article profile according to described article to be measured and the profile difference degree of the described dangerous goods prestored Depending on.
Determination module 30, if for described similarity more than presetting similarity, then judging that described article to be measured are as danger Product.
When the image of described article to be measured is similar more than presetting to the similarity of the described dangerous goods image prestored When spending, described unmanned plane then judges that described article to be measured are as dangerous goods.When the image of described article to be measured is deposited in advance with described When the similarity of the dangerous goods image of storage is less than or equal to described default similarity, described unmanned plane then judges described to be measured Article are normal goods, are not dangerous goods.It should be noted that described default similarity can set according to specific needs Put, as being set to 40%, or 50%, or 60% etc..
Further, described dangerous goods detection device also includes:
Pretreatment module, for the image of described article to be measured is carried out pretreatment, obtains pretreated described to be measured The image of article;
Further, when described unmanned plane obtains the image of described article to be measured, described unmanned plane is to described determinand The image of product carries out pretreatment, obtains the image of pretreated described article to be measured.The described image to described article to be measured The process carrying out pretreatment is: 1. image denoising;2. image enhaucament;3. image segmentation.The method of described image denoising include but It is not limited to Wavelet Denoising Method, mean filter and morphology scratch filter;It is right that the method for described image enhaucament includes but not limited to Than degree conversion, image operation, space filtering and multispectral conversion;The method of described image segmentation includes but not limited to that threshold value is divided Cut, edge segmentation and histogram method.
Described contrast module 20 includes:
Extraction unit, for the image of pretreated described article to be measured is carried out edge extracting, obtains described to be measured First image of article;It is additionally operable to the first image of described article to be measured is carried out feature extraction, obtains described article to be measured Second image;
Contrast unit, for being contrasted with the dangerous goods image that prestores by the second image of described article to be measured, obtains Second image of described article to be measured and the similarity of the described dangerous goods image that prestores.
When described unmanned plane obtains the image of pretreated described article to be measured, described unmanned plane is to pretreated The image of described article to be measured carries out edge extracting, obtains the image of article described to be measured through edge extracting, i.e. obtains institute State the first image of article to be measured.Described unmanned plane utilizes Profile invariant feature extracting method first to described article to be measured Image carries out feature extraction, obtains the second image of described article to be measured.The method of described edge extracting includes: 1. based on certain Fixing local operation's algorithm, such as differentiation, fitting process etc.;2. the overall extracting method with energy minimization as criterion, the party The feature of method is to use strict mathematical method to be analyzed this problem, and one-dimensional cost function extracts as optimum and depends on According to, extract edge from the viewpoint of global optimum, such as method of relaxation, analysis of neural network method etc.;3. with wavelet transformation, Mathematical Morphology The image edge extraction method that new and high technology is representative that the developed recentlies such as, analysis theories get up, as based on Analysis On Multi-scale Features Wavelet transformation extract image border method.
When described unmanned plane obtains the second image of described article to be measured, by the second image of described article to be measured with pre- The dangerous goods image first stored contrasts, and obtains the second image of described article to be measured and the described dangerous goods image that prestores Similarity.
The present embodiment obtains the image of article to be measured by unmanned plane, by described by the image of described article to be measured with prestore Dangerous goods image contrasts, when the image of described article to be measured and the similarity of the described dangerous goods image that prestores are more than pre- If during similarity, described unmanned plane judges that described article to be measured are as dangerous goods.Solve traditional X-ray machine and need occupied ground Problem, it is achieved that automatically detected the existence of article by unmanned plane, it is not necessary to manually go confirm dangerous goods existence, improve The detection efficiency of dangerous goods.
It is the high-level schematic functional block diagram that dangerous goods of the present invention detect the second embodiment of device with reference to Fig. 5, Fig. 5, based on The first embodiment of the present invention proposes the second embodiment of dangerous goods of the present invention detection device.
In the present embodiment, described dangerous goods detection device also includes:
Tracking module 40, for following the tracks of the personnel carrying described dangerous goods, obtains and carries described dangerous goods personnel institute Positional information, and described positional information is sent to the terminal that is connected with described unmanned plane.
In the presence of described unmanned plane detects dangerous goods, described unmanned plane determines the people carrying described dangerous goods Member, starts tracking function, follows the tracks of the personnel carrying described dangerous goods, and by being arranged on the positioner in described unmanned plane Obtain the positional information carrying described dangerous goods personnel place in real time.Described dangerous goods are carried when described unmanned plane gets During the information of personnel position, will carry what the information transmission of described dangerous goods personnel position was extremely connected with described unmanned plane Terminal, is quickly found out the personnel carrying described dangerous goods for terminal use.It is understood that described positioner is peace Fill GPS (Global Positioning System, alignment system), or be mounted with that being similar to GPS can realize positioning merit The assembly of energy.
Further, described dangerous goods detection device also includes:
First output module, carries the warning message of described positional information for output, with the law enfrocement official that prompting is relevant.
Further, when described unmanned plane gets the positional information carrying described dangerous goods personnel place, according to The personnel position information carrying described dangerous goods generates warning message, with the relevant law enfrocement official of prompting, it has been found that dangerous Article, are quickly found out according to positional information entrained in described warning message for relevant law enfrocement official and carry described danger The personnel of product.
The present embodiment follows the tracks of the personnel carrying dangerous goods by unmanned plane, and described dangerous goods personnel institute is carried in acquisition Positional information, and described positional information is sent to the terminal that is connected with described unmanned plane.Can allow the use of described terminal Family, such as safety inspector, is quickly found out the personnel carrying described dangerous goods, improves the intelligent of unmanned plane.
It is the high-level schematic functional block diagram that dangerous goods of the present invention detect the 3rd embodiment of device with reference to Fig. 6, Fig. 6, based on The first embodiment of the present invention proposes the 3rd embodiment of dangerous goods of the present invention detection device.
In the present embodiment, described dangerous goods detection device also includes:
Determine module 50, for determining described dangerous goods according to the relation table of insinuating between dangerous goods and degree of danger Degree of danger;
When described unmanned plane judges described article to be measured as dangerous goods, according to the dangerous goods prestored with dangerous Mapping relations table between degree determines the degree of danger of described dangerous goods, as between described dangerous goods and degree of danger Mapping relations table is: gun, controlled knife etc. may jeopardize the dangerous journey corresponding to the article of human-body safety and property safety Degree is 1, and the degree of danger corresponding to radioactive substance is 2, and inflammable and explosive and that other degree of danger is higher chemical substance institute is right The degree of danger answered is 3.It should be noted that the relation of insinuating between described dangerous goods and degree of danger is not restricted to this Mapping relations described in embodiment.
Second output module 60, if the degree of danger for described dangerous goods reaches predeterminable level, then exports alarm signal Breath;If the degree of danger being additionally operable to described dangerous goods is not up to described predeterminable level, then export information.
After described unmanned plane determines the degree of danger of described dangerous goods, described unmanned plane judges described dangerous goods Whether degree of danger reaches predeterminable level.If the degree of danger of described dangerous goods reaches described predeterminable level, described unmanned plane Then export warning message, to point out related personnel, the danger that in the detection region at described unmanned plane place, dangerous degree is higher Danger article, process the most as early as possible.If the degree of danger of described dangerous goods is not up to described predeterminable level, then export information, To point out related personnel, the dangerous goods that in the detection region at described unmanned plane place, dangerous degree is relatively low, for relevant Personnel can take appropriate measures according to concrete working condition.Described related personnel is detection region, described unmanned plane place Staff, to the user of the terminal that described unmanned plane connects and relevant law enfrocement official etc..Described predeterminable level can root Arrange according to the safe coefficient required for the detection region at described unmanned plane place.As in the present embodiment, can be by described pre- If degree is set to 2.When as described in dangerous goods degree of danger equal to 2 or more than 2 time, described unmanned plane output alarm signal Breath;When the degree of danger of described dangerous goods is less than 2, described unmanned plane output information.
The present embodiment unmanned plane exports warning message or information by the degree of danger according to dangerous goods, for Related personnel takes appropriate measures according to the degree of danger of dangerous goods, improves unmanned plane in terms of detection dangerous goods Intelligent.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.By above embodiment party The description of formula, those skilled in the art it can be understood that can add required general to above-described embodiment method by software The mode of hardware platform realizes, naturally it is also possible to by hardware, but a lot of in the case of the former is more preferably embodiment.Based on Such understanding, the part that prior art is contributed by technical scheme the most in other words can be with software product Form embody, this computer software product is stored in a storage medium (such as ROM/RAM, magnetic disc, CD), including Some instructions are with so that a station terminal equipment (can be mobile phone, computer, server, or the network equipment etc.) performs this Method described in each embodiment bright.
These are only the preferred embodiments of the present invention, not thereby limit the scope of the claims of the present invention, every utilize this Equivalent structure or equivalence flow process that bright description and accompanying drawing content are made convert, or are directly or indirectly used in other relevant skills Art field, is the most in like manner included in the scope of patent protection of the present invention.

Claims (10)

1. a dangerous goods detection method, it is characterised in that described dangerous goods detection method includes:
Article to be measured in unmanned plane detection preset range, obtain the image of article to be measured;
The image of described article to be measured is contrasted with the dangerous goods image that prestores, obtains image and the institute of described article to be measured State the similarity of the dangerous goods image that prestores;
If described similarity is more than presetting similarity, then judge that described article to be measured are as dangerous goods.
2. dangerous goods detection method as claimed in claim 1, it is characterised in that if described similarity is more than presetting phase Like degree, then, after judging that described article to be measured are as the step of dangerous goods, also include:
Follow the tracks of the personnel carrying described dangerous goods, obtain the positional information carrying described dangerous goods personnel place, and by institute State positional information to send to the terminal being connected with described unmanned plane.
3. dangerous goods detection method as claimed in claim 2, it is characterised in that described dangerous goods are carried in described tracking Personnel, obtain the positional information carrying described dangerous goods personnel place, and are sent by described positional information to unmanned with described After the step of the terminal that machine connects, also include:
The warning message of described positional information is carried in output, with the law enfrocement official that prompting is relevant.
4. dangerous goods detection method as claimed in claim 1, it is characterised in that if described similarity is more than presetting phase Like degree, then, after judging that described article to be measured are as the step of dangerous goods, also include:
The degree of danger of described dangerous goods is determined according to the relation table of insinuating between dangerous goods and degree of danger;
If the degree of danger of described dangerous goods reaches predeterminable level, then export warning message;
If the degree of danger of described dangerous goods is not up to described predeterminable level, then export information.
5. the dangerous goods detection method as described in any one of Claims 1-4, it is characterised in that the detection of described unmanned plane is pre- If the article to be measured in scope, after the step of the image obtaining article to be measured, also include:
The image of described article to be measured is carried out pretreatment, obtains the image of pretreated described article to be measured;
Described the image of described article to be measured is contrasted with the dangerous goods image that prestores, obtain the image of described article to be measured Include with the step of the similarity of the described dangerous goods image that prestores:
The image of pretreated described article to be measured is carried out edge extracting, obtains the first image of described article to be measured;
First image of described article to be measured is carried out feature extraction, obtains the second image of described article to be measured;
Second image of described article to be measured is contrasted with the dangerous goods image that prestores, obtains the second of described article to be measured Image and the similarity of the described dangerous goods image that prestores.
6. a dangerous goods detection device, it is characterised in that described dangerous goods detection device is applied to unmanned plane, described danger Danger article detection apparatus includes:
Detection module, for detecting the article to be measured in preset range, obtains the image of article to be measured;
Contrast module, for being contrasted with the dangerous goods image that prestores by the image of described article to be measured, obtains described to be measured The image of article and the similarity of the described dangerous goods image that prestores;
Determination module, if for described similarity more than presetting similarity, then judging that described article to be measured are as dangerous goods.
7. dangerous goods detection device as claimed in claim 6, it is characterised in that described dangerous goods detection device includes:
Tracking module, for following the tracks of the personnel carrying described dangerous goods, obtains the position carrying described dangerous goods personnel place Confidence ceases, and sends described positional information to the terminal being connected with described unmanned plane.
8. dangerous goods detection device as claimed in claim 7, it is characterised in that described dangerous goods detection device also wraps Include:
First output module, carries the warning message of described positional information for output, with the law enfrocement official that prompting is relevant.
9. dangerous goods detection device as claimed in claim 6, it is characterised in that described dangerous goods detection device also wraps Include:
Determine module, for determining the danger of described dangerous goods according to the relation table of insinuating between dangerous goods and degree of danger Degree;
Second output module, if the degree of danger for described dangerous goods reaches predeterminable level, then exports warning message;Also use If the degree of danger in described dangerous goods is not up to described predeterminable level, then export information.
10. the dangerous goods detection device as described in any one of claim 6 to 9, it is characterised in that described dangerous goods detect Device also includes:
Pretreatment module, for the image of described article to be measured is carried out pretreatment, obtains pretreated described article to be measured Image;
Described contrast module includes:
Extraction unit, for the image of pretreated described article to be measured is carried out edge extracting, obtains described article to be measured The first image;It is additionally operable to the first image of described article to be measured is carried out feature extraction, obtains the second of described article to be measured Image;
Contrast unit, for being contrasted with the dangerous goods image that prestores by the second image of described article to be measured, obtains described Second image of article to be measured and the similarity of the described dangerous goods image that prestores.
CN201610486706.2A 2016-06-28 2016-06-28 Dangerous goods detection method and device Pending CN106203264A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201610486706.2A CN106203264A (en) 2016-06-28 2016-06-28 Dangerous goods detection method and device
PCT/CN2016/108915 WO2018000732A1 (en) 2016-06-28 2016-12-07 Dangerous article detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610486706.2A CN106203264A (en) 2016-06-28 2016-06-28 Dangerous goods detection method and device

Publications (1)

Publication Number Publication Date
CN106203264A true CN106203264A (en) 2016-12-07

Family

ID=57460888

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610486706.2A Pending CN106203264A (en) 2016-06-28 2016-06-28 Dangerous goods detection method and device

Country Status (2)

Country Link
CN (1) CN106203264A (en)
WO (1) WO2018000732A1 (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107620988A (en) * 2017-09-27 2018-01-23 珠海格力电器股份有限公司 The alarm method and device of micro-wave oven
CN108064394A (en) * 2017-08-11 2018-05-22 深圳前海达闼云端智能科技有限公司 Method and device for detecting security check article and electronic equipment
CN108205643A (en) * 2016-12-16 2018-06-26 同方威视技术股份有限公司 Image matching method and device
CN108414527A (en) * 2018-02-06 2018-08-17 深圳市满心科技有限公司 The method and computer storage media that cabinet, cell phone appearance integrality acquire
CN108764328A (en) * 2018-05-24 2018-11-06 广东工业大学 The recognition methods of Terahertz image dangerous material, device, equipment and readable storage medium storing program for executing
CN109187598A (en) * 2018-10-09 2019-01-11 青海奥越电子科技有限公司 Prohibited items detection system and method based on Digital Image Processing
CN109584907A (en) * 2018-11-29 2019-04-05 北京奇虎科技有限公司 A kind of method and apparatus of abnormal alarm
CN109664321A (en) * 2018-12-27 2019-04-23 四川文理学院 Mechanical arm, explosive trolley and method for searching
CN110529897A (en) * 2019-08-20 2019-12-03 珠海格力电器股份有限公司 A kind of kitchen ventilator and its security system of application
CN110619276A (en) * 2019-08-15 2019-12-27 杭州电子科技大学 Anomaly and violence detection system and method based on unmanned aerial vehicle mobile monitoring
CN110807753A (en) * 2018-07-20 2020-02-18 苏州微木智能系统有限公司 Radioactive source monitoring method and device and electronic equipment
CN111679695A (en) * 2020-08-11 2020-09-18 中航金城无人系统有限公司 Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology
CN111753582A (en) * 2019-03-27 2020-10-09 杭州海康威视数字技术股份有限公司 Dangerous goods positioning method and device
CN111798628A (en) * 2020-07-03 2020-10-20 陈泽坤 Management method of lock catch type labor tool
CN113850306A (en) * 2021-09-13 2021-12-28 北京科技大学 Ancient building fire-fighting dangerous goods rapid detection method and device based on improved YOLOX

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6978124B2 (en) * 2018-03-31 2021-12-08 つくばテクノロジー株式会社 X-ray inspection device for drones, X-ray inspection device using drones, X-ray generator for drones
CN110032956B (en) * 2019-03-27 2023-01-24 创新先进技术有限公司 Dangerous goods identification method and device
CN111751896A (en) * 2019-03-27 2020-10-09 北京快安科技有限公司 Three-dimensional display method for security inspection result
CN114037939A (en) * 2021-11-11 2022-02-11 中国铁路设计集团有限公司 Dangerous goods identification method, dangerous goods identification device, electronic equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577840A (en) * 2013-10-30 2014-02-12 汕头大学 Item identification method
CN103900973A (en) * 2014-04-24 2014-07-02 黄晓鹏 Hazardous article detecting device and detecting method
CN103926199A (en) * 2014-04-16 2014-07-16 黄晓鹏 Hazardous article detecting device and method
CN104345350A (en) * 2013-07-23 2015-02-11 清华大学 Human body safety check method and human body safety check system
CN105092485A (en) * 2015-08-27 2015-11-25 泉州装备制造研究所 Dangerous article detection method and device

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070221863A1 (en) * 2005-12-12 2007-09-27 Zipf Edward C Emission detector for the remote detection of explosives and illegal drugs
CN101358936B (en) * 2007-08-02 2011-03-16 同方威视技术股份有限公司 Method and system for discriminating material by double-perspective multi energy transmission image
US8240238B2 (en) * 2008-05-23 2012-08-14 Willner Byron J Methods and apparatuses for detecting and neutralizing remotely activated explosives
CN201514387U (en) * 2009-07-03 2010-06-23 公安部第一研究所 System for utilizing multi-view X ray to automatically detect explosive in luggage
CN105424644B (en) * 2016-01-18 2019-04-23 中国工程物理研究院流体物理研究所 A kind of near-infrared laser illumination imaging systems and method for safety inspection

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104345350A (en) * 2013-07-23 2015-02-11 清华大学 Human body safety check method and human body safety check system
CN103577840A (en) * 2013-10-30 2014-02-12 汕头大学 Item identification method
CN103926199A (en) * 2014-04-16 2014-07-16 黄晓鹏 Hazardous article detecting device and method
CN103900973A (en) * 2014-04-24 2014-07-02 黄晓鹏 Hazardous article detecting device and detecting method
CN105092485A (en) * 2015-08-27 2015-11-25 泉州装备制造研究所 Dangerous article detection method and device

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
孙长燕: "危险物品识别与图像识别算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
彭鹏菲等编著: "《舰载无人机系统及作战应用》", 31 January 2016, 国防工业出版社 *
桑艳君主编: "《世界军事百科系列 世界武器装备 3》", 31 May 2015, 中原农民出版社 *
那彦、焦李成主编: "《基于多分辨分析理论的图像融合方法》", 31 May 2007, 西安电子科技大学出版社 *
高佩华主编: "《安检仪器使用与维护》", 31 July 2015, 中国民航出版社 *

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108205643A (en) * 2016-12-16 2018-06-26 同方威视技术股份有限公司 Image matching method and device
CN108064394A (en) * 2017-08-11 2018-05-22 深圳前海达闼云端智能科技有限公司 Method and device for detecting security check article and electronic equipment
CN108064394B (en) * 2017-08-11 2021-12-03 深圳前海达闼云端智能科技有限公司 Method and device for detecting security check article and electronic equipment
CN107620988A (en) * 2017-09-27 2018-01-23 珠海格力电器股份有限公司 The alarm method and device of micro-wave oven
CN108414527A (en) * 2018-02-06 2018-08-17 深圳市满心科技有限公司 The method and computer storage media that cabinet, cell phone appearance integrality acquire
CN108764328A (en) * 2018-05-24 2018-11-06 广东工业大学 The recognition methods of Terahertz image dangerous material, device, equipment and readable storage medium storing program for executing
CN110807753A (en) * 2018-07-20 2020-02-18 苏州微木智能系统有限公司 Radioactive source monitoring method and device and electronic equipment
CN109187598A (en) * 2018-10-09 2019-01-11 青海奥越电子科技有限公司 Prohibited items detection system and method based on Digital Image Processing
CN109584907A (en) * 2018-11-29 2019-04-05 北京奇虎科技有限公司 A kind of method and apparatus of abnormal alarm
CN109664321A (en) * 2018-12-27 2019-04-23 四川文理学院 Mechanical arm, explosive trolley and method for searching
CN111753582A (en) * 2019-03-27 2020-10-09 杭州海康威视数字技术股份有限公司 Dangerous goods positioning method and device
CN110619276A (en) * 2019-08-15 2019-12-27 杭州电子科技大学 Anomaly and violence detection system and method based on unmanned aerial vehicle mobile monitoring
CN110619276B (en) * 2019-08-15 2021-12-21 杭州电子科技大学 Anomaly and violence detection system and method based on unmanned aerial vehicle mobile monitoring
CN110529897A (en) * 2019-08-20 2019-12-03 珠海格力电器股份有限公司 A kind of kitchen ventilator and its security system of application
CN111798628A (en) * 2020-07-03 2020-10-20 陈泽坤 Management method of lock catch type labor tool
CN111679695A (en) * 2020-08-11 2020-09-18 中航金城无人系统有限公司 Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology
CN111679695B (en) * 2020-08-11 2020-11-10 中航金城无人系统有限公司 Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology
CN113850306A (en) * 2021-09-13 2021-12-28 北京科技大学 Ancient building fire-fighting dangerous goods rapid detection method and device based on improved YOLOX

Also Published As

Publication number Publication date
WO2018000732A1 (en) 2018-01-04

Similar Documents

Publication Publication Date Title
CN106203264A (en) Dangerous goods detection method and device
Park et al. Hardhat-wearing detection for enhancing on-site safety of construction workers
US10347062B2 (en) Personal identification for multi-stage inspections of persons
CN206421481U (en) Movable security inspection system
CN108064394B (en) Method and device for detecting security check article and electronic equipment
EP3796051A1 (en) Personnel security inspection method and personnel security inspection system
CN105549119B (en) Multiple articles are carried out with the method and system of safety inspection
CN104700058A (en) Passenger luggage detection method and device
CN109978892B (en) Intelligent security inspection method based on terahertz imaging
CN112016528B (en) Behavior recognition method and device, electronic equipment and readable storage medium
CN108279244A (en) A kind of urban track traffic safe examination system
CN111126447A (en) Intelligent passenger security check luggage image automatic identification method
US10098432B2 (en) System and method for tracking baggage
CN109961029A (en) A kind of dangerous goods detection method, device and computer readable storage medium
CN110865415B (en) Security check method and device
CN102608672A (en) Suspicious article image display device of human body security check system
CN105425310A (en) Safety check system and safety check method used for common occasions
KR101668555B1 (en) Method and apparatus for recognizing worker in working site image data
CN101364257A (en) Human face recognizing method for recognizing image origin
Mei et al. Human intrusion detection in static hazardous areas at construction sites: Deep learning–based method
CN105911602A (en) Metal classification image display method and device
CN104980695B (en) Collaboration objects position data and video data
CN106291726A (en) A kind of human body safety check equipment and application thereof
CN106056686B (en) A kind of indoor patrol estimation analysis method based on three-D profile
CN108111802A (en) Video frequency monitoring method and device

Legal Events

Date Code Title Description
C06 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

Application publication date: 20161207

RJ01 Rejection of invention patent application after publication