WO2020037935A1 - 一种安检过程中液体识别方法及其装置 - Google Patents

一种安检过程中液体识别方法及其装置 Download PDF

Info

Publication number
WO2020037935A1
WO2020037935A1 PCT/CN2019/070037 CN2019070037W WO2020037935A1 WO 2020037935 A1 WO2020037935 A1 WO 2020037935A1 CN 2019070037 W CN2019070037 W CN 2019070037W WO 2020037935 A1 WO2020037935 A1 WO 2020037935A1
Authority
WO
WIPO (PCT)
Prior art keywords
liquid
liquid container
image
container
ray
Prior art date
Application number
PCT/CN2019/070037
Other languages
English (en)
French (fr)
Inventor
斯科特•马修•罗伯特
黄鼎隆
王重
董登科
Original Assignee
深圳码隆科技有限公司
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 深圳码隆科技有限公司 filed Critical 深圳码隆科技有限公司
Publication of WO2020037935A1 publication Critical patent/WO2020037935A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating 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
    • G01N23/02—Investigating 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
    • G01N23/04—Investigating 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
    • G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
    • G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays

Definitions

  • the present application relates to the field of image processing technology, and more particularly, to a method and a device for identifying a liquid in a security inspection process.
  • Safety inspection is the inspection of the safety production laws and regulations, safety production conditions, labor conditions, accident hazards, etc. of the construction project, and its main contents include inspection thoughts, inspection of machinery and equipment, inspection of safety and health facilities, inspection of safety Education and training, investigation of production personnel's behavior, construction of protective equipment, investigation of injuries and deaths, etc.
  • X-rays are a stream of particles produced by the transition of electrons in atoms between two energy levels with very different energies, and are electromagnetic waves with wavelengths between ultraviolet and gamma rays. Its wavelength is very short between about 0.01 and 100 angstroms. Discovered by German physicist W.K. Roentgen in 1895, it is also called Roentgen ray.
  • X-rays have a high ability to penetrate, and can penetrate many substances that are opaque to visible light, such as ink paper and wood. This kind of invisible radiation can cause many solid materials to generate visible fluorescence, make photographic films sensitive, and effect air ionization.
  • X-rays were originally used in medical imaging diagnostics and X-ray crystallography. X-rays are also harmful to the human body, such as free radiation.
  • the security personnel can only observe the X-ray image obtained based on the X-ray technology to determine whether there is a liquid container filled with liquid, and if necessary, perform further detection, but When there are too many items to be detected, it is unavoidable that the situation of false alarms caused by visual observation is unavoidable, which greatly reduces the security inspection efficiency, increases the security inspection time, and is not conducive to the rapid passage of security personnel.
  • the present application provides a method and a device for identifying a liquid in a security inspection process to solve the shortcomings of the prior art.
  • the present application provides a liquid identification method during security inspection, including:
  • the laser pointer is controlled to directly shoot and track the actual position coordinates, so as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates.
  • the “determining whether the X-ray image contains a liquid container with a liquid through a pre-trained X-ray liquid recognition model” includes:
  • Each of the minimum screenshots is identified by an X-ray liquid recognition model, and it is determined whether each of the minimum screenshots in the X-ray image includes a liquid container having a liquid.
  • liquid sample is pure water
  • generating a pure water detection label corresponding to the liquid container so as to prompt that the liquid container is pure water according to the pure water detection label
  • a test report is generated, and a non-pure water detection label corresponding to the liquid container is created for the test report, and a prompt message is generated to detect the non-pure water detection label. Prompt that the liquid container is not pure water, and then perform physical and chemical detection on the liquid in the liquid container according to the prompt information.
  • Image acquisition of the liquid container according to the actual position coordinates through an image acquisition device to obtain an image of the suspected article corresponding to the liquid container; and acquire the surface temperature of the liquid container through an infrared temperature sensor;
  • the liquid container is a transparent container, performing ultraviolet wavelength scanning on the liquid in the transparent liquid container to obtain a first wavelength scanning chart;
  • Extracting liquid container characteristics of the liquid container in the suspect article image the liquid container characteristics include container transparency, liquid color, and liquid capacity;
  • the method further includes:
  • the method further includes:
  • the second wavelength scan pattern matches the first wavelength scan pattern, obtain an OD value for the liquid sample based on the second wavelength scan pattern, and add the OD value to the detection report.
  • the method further includes:
  • the pre-processing includes smoothing processing, median filtering, and contrast enhancement processing.
  • the present application also provides a liquid identification device during a security inspection process, including: a collection module, a judgment module, a positioning module, and an instruction module;
  • the acquisition module is configured to acquire an X-ray image of a target object based on X-ray imaging technology
  • the judging module is configured to judge whether the X-ray image includes a liquid container with a liquid through a pre-trained X-ray liquid recognition model
  • the positioning module is used to obtain the X-ray image coordinates of the liquid container in the X-ray image, and map the X-ray image coordinates to the liquid container of the target item to obtain the current actual Position coordinates;
  • the indication module is configured to control a laser pointer to directly shoot and track the actual position coordinates, so as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates.
  • the present application also provides a user terminal, including a memory and a processor, where the memory is used to store a liquid identification program during a security inspection process, and the processor runs the liquid identification program during a security inspection process so that The user terminal executes the liquid identification method in the security inspection process as described above.
  • the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a liquid identification program during security inspection, and is implemented when the liquid identification program is executed by a processor during security inspection.
  • the method of liquid identification during security inspection as described above.
  • the invention provides a liquid identification method and a device thereof in a security inspection process.
  • the method provided in this application includes: collecting an X-ray image of a target object based on X-ray imaging technology; determining whether the X-ray image contains a liquid container with a liquid through a pre-trained X-ray liquid recognition model; if so, then Acquiring X-ray image coordinates of the liquid container in the X-ray image in the image, and mapping the X-ray image coordinates to the liquid container of the target item to obtain current actual position coordinates; controlling a laser pointer Directly and track the actual position coordinates, so as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates.
  • This application uses a pre-trained X-ray liquid recognition model to determine whether the X-ray image contains a liquid container with a liquid, and then after the identification, locates the liquid container containing the liquid to obtain the current actual position coordinates, and A laser pointer traces the liquid container to prompt security personnel to verify it.
  • this application realizes the automatic identification of items that need to be inspected, thereby confirming the existence of liquid containers with liquids therein, and tracking the instructions with a laser pointer.
  • the image recognition quickly locates the suspected liquid container, and enables security personnel to quickly find the suspected liquid container according to the prompts, which greatly improves the security inspection efficiency and avoids false alarms and false alarms, thereby achieving rapid passage by the security personnel.
  • FIG. 1 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of a liquid identification method during a security inspection process of this application;
  • FIG. 2 is a schematic flowchart of a first embodiment of a liquid identification method during a security inspection process of this application;
  • FIG. 3 is a schematic flowchart of a second embodiment of a liquid identification method during a security inspection process of this application;
  • FIG. 4 is a schematic flowchart of a third embodiment of a liquid identification method during a security inspection process of this application;
  • FIG. 5 is a schematic flowchart of a fourth embodiment of a liquid identification method during a security inspection process of this application;
  • FIG. 6 is a schematic diagram of the functional modules of the liquid identification device during the security inspection process of this application.
  • first and second are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as “first” and “second” may explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality" is two or more, unless specifically defined otherwise.
  • the terms “installation,” “connected,” “connected,” and “fixed” should be broadly understood unless otherwise specified and limited. For example, they can be fixed connections or removable connections. , Or integrated; it can be mechanical or electrical connection; it can be directly connected, or it can be indirectly connected through an intermediate medium, it can be the internal connection of the two elements or the interaction between the two elements.
  • installation should be broadly understood unless otherwise specified and limited. For example, they can be fixed connections or removable connections. , Or integrated; it can be mechanical or electrical connection; it can be directly connected, or it can be indirectly connected through an intermediate medium, it can be the internal connection of the two elements or the interaction between the two elements.
  • FIG. 1 is a schematic structural diagram of a hardware operating environment of a terminal involved in a solution according to an embodiment of the present application.
  • the terminal may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display screen, an input unit such as a keyboard, a remote control, and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high-speed RAM memory or a stable memory, such as a magnetic disk memory.
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • the terminal may further include an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like.
  • the mobile terminal may be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which will not be repeated here.
  • the terminal shown in FIG. 1 does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or some components may be combined, or different component arrangements.
  • the memory 1005 as a computer-readable storage medium may include an operating system, a data interface control program, a network connection program, and a liquid identification program during a security inspection.
  • the invention provides a liquid identification method and a device thereof in a security inspection process.
  • the method realizes the intelligent positioning of key frames in the video stream of the included target area, so that the time stamp of the positioning frame can be determined in the video stream according to the label, and the outline of the positioning frame in the video stream can be obtained.
  • contour line coordinates which can further facilitate the editing of the video stream based on the updated tags, high positioning efficiency, short time and fast speed, which brings convenience to the work of supervisors.
  • a first embodiment of the present application provides a liquid identification method during a security inspection process, including:
  • Step S10 Collect an X-ray image of the target item based on the X-ray imaging technology
  • X-rays also known as Roentgen rays
  • Roentgen rays are a kind of rays that are invisible to the naked eye, but can cause certain compounds to generate fluorescence or make photographic films sensitive; it does not deflect in an electric or magnetic field, and can reflect, Refraction, interference, diffraction, etc .; it has the ability to penetrate matter, but it has different penetrating ability to different substances; it can ionize molecules or atoms; it has the effect of destroying cells, and different tissues of the human body have different sensitivities to X-rays. The degree of damage is also different. Therefore, X-rays enable the human body to form an image on a screen or film, based on the difference in density and thickness of human tissue.
  • X-ray imaging technology is applied to non-destructive security inspection fields, such as security inspections at important places such as airports, railway stations, bus stations, cinemas, exhibitions, conferences at home and abroad, and the like.
  • the X-ray imaging technology based on the items held by the security personnel helps to quickly check the items with a large number of test samples to quickly find the liquid container with the liquid in the target item.
  • Step S20 Determine whether the X-ray image includes a liquid container with a liquid through a pre-trained X-ray liquid recognition model
  • a neural network is a computing model that consists of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function, called an activation function. The connection between each two nodes represents a weighted value for the signal passing through the connection, called the weight, which is equivalent to the memory of an artificial neural network.
  • the X-ray liquid recognition model is trained to obtain a pre-trained model, and the acquired X-ray image is identified to determine whether the image contains a liquid container, and the liquid The container contains a liquid.
  • Step S30 if yes, obtain the X-ray image coordinates of the liquid container in the X-ray image, and map the X-ray image coordinates to the liquid container of the target item to obtain the current actual position coordinate;
  • the coordinates of the liquid container in the image are obtained and mapped to the actual target item to find the current actual position coordinates.
  • step S40 the laser pointer is controlled to directly shoot and track the actual position coordinates, so as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates.
  • the laser pointer is turned on, and direct irradiation is performed according to the obtained current actual position coordinates. Since the target object may be placed on the conveyor belt and is in a moving state, according to the image recognition technology, based on the movement of its current actual position coordinates, it is indicated by laser. The liquid container was tracked by the device to prompt security personnel to conduct further verification.
  • a pre-trained X-ray liquid recognition model is used to determine whether the X-ray image contains a liquid container with a liquid, and then after recognition, the liquid container containing the liquid is positioned to obtain the current actual position coordinates, and The liquid container is tracked by a laser pointer to prompt security personnel to carry out verification.
  • the combination of X-ray irradiation technology and image recognition technology is used to realize automatic identification of items that need to be inspected, thereby confirming the existence of a liquid container with a liquid therein, and using a laser pointer to track and indicate it. Quickly locate the suspected liquid container through image recognition, and enable the security personnel to quickly find the suspected liquid container according to the prompts, which greatly improves the security inspection efficiency, avoids false alarms and false alarms, and thus enables the security personnel to pass quickly.
  • a second embodiment of the present application provides a liquid identification method during security inspection. Based on the first embodiment shown in FIG. 2 described above, the step S20 is, “determining the Does the X-ray image contain a liquid container with a liquid? ”Includes:
  • Step S21 Locate different target items corresponding to the characteristics of the items in the X-ray image through a pre-trained X-ray liquid recognition model to obtain a positioning area;
  • the X-ray image may contain a plurality of different target objects.
  • the item to be identified is a suitcase, and a large number of personal belongings of passengers are placed in the suitcase; or the item to be identified is a bamboo basket with some sundries in the basket. Then, different target objects corresponding to the characteristics of the items in the collected X-ray image are located through a pre-trained X-ray liquid recognition model to obtain a positioning area.
  • the feature of an article is a feature corresponding to a variety of articles included in the X-ray image, such as a shape feature, a cultural feature, and so on.
  • step S21 may include:
  • the positioning area corresponding to the region is obtained.
  • Step S22 Perform edge detection and overlap area prediction on the positioning area to obtain the contour line of the image containing the target item corresponding to each positioning area;
  • the edge of each item is determined based on the total edge detection of the image recognition technology, and because there will be overlap when there are too many items, based on the neural network model, the items in its overlapping area are predicted, so that each determinable The outline of the image of the target item contained in the positioning area.
  • Step S23 Take a minimum screenshot of each of the target items included in the X-ray image according to the contour line;
  • each of the minimum screenshots is identified through an X-ray liquid recognition model, and it is determined whether each of the minimum screenshots in the X-ray image includes a liquid container having a liquid.
  • the screenshot is taken according to the outline to obtain the smallest screenshot containing the target item.
  • the image corresponding to each target item in the image to be identified is converted into the smallest screenshot containing the target item, and the smallest screenshot is identified and judged, so that It greatly reduces the occupation and waste of system resources by high-quality pictures; at the same time, each minimum screenshot is individually identified and positioned, which enables the system to perform multi-thread identification work, which greatly improves work efficiency.
  • a third embodiment of the present application provides a liquid identification method during security inspection.
  • the step S40 controls a laser pointer to directly shoot and track the actual position coordinates. So as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates ", further including:
  • Step S50 Sampling the liquid in the liquid container according to the current actual position coordinates indicated by the laser pointer to obtain a liquid sample
  • the liquid sample can be sampled by an automatic sampler or manually, and the taken liquid sample is placed in a magnetic resonance detection tube for further testing.
  • the automatic sampler can be a device including a puncture head and a sampling tube, which is connected to the MRI device.
  • the puncture head is automatically controlled to perform puncture sampling at a specified position to obtain a liquid sample.
  • Step S60 detecting the liquid sample according to MRI magnetic resonance imaging technology to determine whether the liquid sample is pure water;
  • MRI magnetic resonance imaging.
  • the full English name is: Magnetic Resonance Imaging.
  • the nucleus often used by people are: 1H, 11B, 13C, 17O, 19F, 31P.
  • NMR imaging nuclear magnetic resonance imaging.
  • NMR imaging a new medical technology, became more and more familiar to the public.
  • the word “nuclear” could easily lead hospital staff to another association of nuclear medicine in the magnetic resonance room. Therefore, in order to highlight the advantages of this inspection technology in that it does not produce ionizing radiation, and to distinguish it from nuclear medicine using radioactive elements, radiologists and equipment manufacturers have agreed to abbreviate "MRI” for short as “MRI ) ".
  • Magnetic resonance imaging is a type of tomography, which uses magnetic resonance phenomena to obtain electromagnetic signals from the human body and reconstruct human information.
  • Flelix Bloch of Stanford University and Edward Purcell of Harvard University independently discovered the phenomenon of nuclear magnetic resonance.
  • Magnetic resonance imaging technology is based on this physical phenomenon.
  • Magnetic resonance imaging technology has some common features with other tomography technologies (such as CT). For example, they can display the distribution of a certain physical quantity (such as density) in space. At the same time, it has its own characteristics. Magnetic resonance imaging can obtain any direction. Tomographic images, three-dimensional volume images, and even four-dimensional images of spatial-spectral distribution.
  • the liquid sample to be measured is quickly detected, and the properties of the liquid are measured through shimming and irradiation, so as to determine whether it is pure water.
  • step S70 if the liquid sample is pure water, a pure water detection label corresponding to the liquid container is generated, so as to prompt that the liquid container is pure water according to the pure water detection label;
  • step S80 if the liquid sample is not pure water, a test report is generated, and a non-pure water detection label corresponding to the liquid container is created for the test report, and a prompt message is generated to detect the non-pure water according to the non-pure water.
  • the water detection label indicates that the liquid container is not pure water, and then performs physical and chemical detection on the liquid in the liquid container according to the prompt information.
  • a label is constructed to correlate with the liquid sample to prompt the security inspector to make a determination based on the label, eliminate the suspect of the liquid sample, and determine as pure water. If the test is not pure water, a test report is generated. The test report is generated for items that are suspected, such as liquids that are not pure water. In addition, a label is created for the report, and a prompt message is generated to prompt the security personnel to perform further physical and chemical tests on the liquid.
  • the liquid needs to be qualitative, it can be spotted by thin layer chromatography to determine whether the sample is a flammable and explosive liquid, or GC-MS to determine whether the liquid is corrosive sulfuric acid and so on.
  • a fourth embodiment of the present application provides a liquid identification method during security inspection.
  • the step S40 controls a laser pointer to directly shoot and track the actual position coordinates.
  • the liquid container Sampling of liquid in the liquid to obtain a liquid sample also includes:
  • step S90 image acquisition is performed on the liquid container according to the actual position coordinates by an image acquisition device to obtain an image of the suspect article corresponding to the liquid container; and, the surface temperature of the liquid container is obtained through an infrared temperature sensor;
  • the image acquisition device may be a camera provided at a position where image acquisition of a target object can be performed. After obtaining the coordinates of the actual position of the liquid container, the camera can be used to collect image of the item to obtain the image of the suspected item, and then obtain the temperature of its outer surface through the infrared temperature sensor.
  • Some organic solvents will generate a certain amount of heat due to mixing or reaction during storage, especially during exercise, such as sulfuric acid, water and ethanol or methanol, etc. In order to know whether there are unstable liquids in them, eliminate hidden dangers , So you need to get its surface temperature.
  • Step S100 Perform image recognition on the suspect article image to determine whether the liquid container is a transparent container
  • image recognition can be used to determine whether an item is transparent or translucent. For example, it can be converted to an image gray histogram, and then the gray histogram of a semi-transparent or transparent object can be analyzed. The histogram data can be used. Smoothing algorithm, cubic spline difference algorithm, target recognition method and so on.
  • step S110 if the liquid container is a transparent container, the liquid in the transparent liquid container is scanned with an ultraviolet wavelength to obtain a first wavelength scanning chart;
  • Ultraviolet is the abbreviation of Ultravioletray or Ultravioletradiation, which was discovered by the German scientist Ritter.
  • Ultraviolet is a general term for radiation in the electromagnetic spectrum with a wavelength from 100-400nm (nanometer).
  • the UVA wavelength is 320-390nm, also known as the long-wave black spot effect ultraviolet. It has strong penetrating power and can penetrate most transparent glass and plastic. More than 98% of the long-wave ultraviolet rays contained in sunlight can penetrate the ozone layer and clouds to reach the earth's surface. UVA can reach the skin's dermis, destroy elastic fibers and collagen fibers, and tan our skin.
  • the 360nm UVA wavelength may conform to the phototaxis response curve of insects, which needs further study by scientists. UVA with a wavelength of 300-420nm can pass through a special colored glass tube that completely cuts off visible light. It only emits near-UV light centered at 365nm. It can be used for ore identification, stage decoration, banknote detection and other places.
  • UVB wavelength is 280-320nm, also known as medium wave erythema effect ultraviolet. Medium penetration. Its shorter wavelength will be absorbed by transparent glass. Most of the medium-wave ultraviolet rays contained in sunlight are absorbed by the ozone layer, and only less than 2% can reach the surface of the earth. It will be particularly strong in summer and afternoon. UVB has erythema effect on the human body, can promote mineral metabolism and the formation of vitamin D in the body, but long-term or excessive irradiation will tan the skin and cause redness and peeling. Ultraviolet health care lamps and plant growth lamps are made of special violet-transparent glass (which does not transmit light below 254nm) and phosphors with a peak around 300nm.
  • UVC wavelength is below 280nm, also known as short-wave sterilization ultraviolet. It has the weakest penetrating power and cannot penetrate most transparent glass and plastic.
  • the short-wave ultraviolet rays contained in sunlight are almost completely absorbed by the ozone layer. Short-wave ultraviolet rays are very harmful to the human body. Short-term exposure can burn the skin. Long-term or high-intensity exposure can also cause skin cancer.
  • Ultraviolet germicidal lamps emit short-wave UVC.
  • UVD band wavelength 100 ⁇ 200nm, also known as vacuum ultraviolet.
  • the UVV wavelength is above 390nm.
  • the principle of wavelength scanning is to measure the sample in a wavelength range, which reflects the absorbance of the sample at different wavelengths.
  • the measurement method needs to be set during operation, that is, whether T or A is measured, then the measurement range, the measurement range of the sample, and then the scanning wavelength.
  • the scanning interval refers to how many nanometers the instrument measures the sample. For example, 1nm is the scanning interval, the instrument starts from the set starting wavelength and takes a value of the sample every 1nm, and then points Together they are the desired images. Since different liquids or reagents have different ultraviolet absorptions and different OD values (ultraviolet absorption values), by scanning the ultraviolet wavelengths, a wavelength scanning chart can be obtained, and the maximum absorption wavelength of the sample can be obtained.
  • Step S120 extracting a liquid container characteristic of the liquid container in the suspect article image;
  • the liquid container characteristic includes a container transparency, a liquid color, and a liquid capacity;
  • the characteristics of the liquid container may include characteristics such as container transparency, liquid color, and liquid capacity, which are obtained through image recognition.
  • the sample container can also include the appearance characteristics of the sample container, such as label, color, volume, material, etc., so as to further know whether it is a commercially available beverage product, a labeled organic solvent, etc. by comparison, and By comparison, determine what the original purpose of the container is, for example, whether it is an organic solvent bottle, a wine bottle, a beverage bottle, etc., so as to provide certain clues for the further prediction of the liquid, to achieve Quick check.
  • step S80 "if the liquid sample is not pure water, generate a test report, and establish a non-pure water test label corresponding to the liquid container for the test report, and generate a prompt message to After the non-pure water detection label indicates that the liquid container is not pure water, and further performs physical and chemical detection on the liquid in the liquid container according to the prompt information, the method further includes:
  • Step S130 Add the suspected object image, the first wavelength scan image, the external temperature of the liquid container, and the characteristics of the liquid container to the detection report.
  • the test report is updated, and the obtained or obtained data information, including the suspected object image, the first wavelength scan chart, the external temperature of the liquid container, and the characteristics of the liquid container, are added to the test report.
  • Step S140 Scan the liquid sample with an ultraviolet wavelength to obtain a second wavelength scan image.
  • the liquid sample is a sample obtained by sampling the original liquid container, and the ultraviolet sample is scanned by wavelength to obtain a second wavelength scanning chart.
  • Step S150 if the second wavelength scan pattern matches the first wavelength scan pattern, obtain an OD value for the liquid sample based on the second wavelength scan pattern, and add the test report to the test report. OD value.
  • the first wavelength scan and the second wavelength scan may not be the same but can be matched, that is, their maximum absorption will not change, which can determine the correctness of the sample, that is, the The sample was determined to be removed from the liquid container.
  • the OD value of the sample was obtained under the maximum absorption. The value is updated in the test report. Therefore, a large number of reference physical and chemical parameter detections are provided for the detection of the liquid, which can further improve the detection efficiency and facilitate the rapid passage of the inspected personnel.
  • step S10 "acquiring an X-ray image of a target item based on X-ray imaging technology"
  • the method further includes:
  • Step S160 preprocessing the X-ray image; the preprocessing includes smoothing processing, median filtering, and contrast enhancement processing.
  • the median filtering method is a non-linear smoothing technique. It sets the gray value of each pixel to the median of the gray values of all pixels in a neighborhood window at that point.
  • Median filtering is a non-linear signal processing technology that can effectively suppress noise based on ranking statistical theory.
  • the basic principle of median filtering is to use the value of a point in a digital image or digital sequence with each point in a neighborhood of that point. Instead of making the surrounding pixel values close to the true value, thereby eliminating isolated noise points.
  • the method is to use a two-dimensional sliding template of a certain structure to sort the pixels in the board according to the size of the pixel values, and generate a monotonically rising (or falling) two-dimensional data sequence.
  • W is a two-dimensional template, usually 3 * 3, 5 * 5 area, and can also have different shapes, such as linear, circular, cross, circular, etc.
  • the smoothing process that is, in digital image processing, when the pixels are enlarged, the boundaries of the image will appear jagged.
  • the pixel resolution is increased to make the image thinner, that is, smoothing processing.
  • There are other methods of image processing such as density segmentation and contrast enhancement.
  • the contrast enhancement is to stretch or compress the range of brightness values in the image to the brightness display range specified by the display system, thereby improving the overall or partial contrast of the image.
  • Each brightness value in the input image passes a certain conversion function and corresponds to a display value of the output image.
  • the collected X-ray images can be identified and located more quickly in the further identification process, eliminating interference.
  • the present application also provides a liquid identification device during security inspection, including: a collection module 10, a determination module 20, a positioning module 30, and an instruction module 40;
  • the acquisition module 10 is configured to acquire an X-ray image of a target object based on X-ray imaging technology
  • the determining module 20 is configured to determine whether the X-ray image includes a liquid container having a liquid by using a pre-trained X-ray liquid recognition model;
  • the positioning module 30 is configured to obtain the X-ray image coordinates of the liquid container in the X-ray image, and map the X-ray image coordinates to the liquid container of the target item to obtain the current Actual position coordinates
  • the indication module 40 is configured to control a laser pointer to directly shoot and track the actual position coordinates, so as to mark the position of the liquid container with liquid corresponding to the current actual position coordinates.
  • the present application also provides a user terminal, including a memory and a processor, where the memory is used to store a liquid identification program during a security inspection process, and the processor runs the liquid identification program during a security inspection process so that The user terminal executes the liquid identification method in the security inspection process as described above.
  • the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a liquid identification program during security inspection, and is implemented when the liquid identification program is executed by a processor during security inspection.
  • the method of liquid identification during security inspection as described above.
  • the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better.
  • Implementation Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium (such as ROM / RAM) as described above. , Magnetic disk, optical disc), including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the embodiments of the present application.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Immunology (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

一种安检过程中液体识别方法及其装置，其中方法包括：采集目标物品的X光图像；判断X光图像中是否包含具有液体的液体容器；若是，则获取X光图坐标，并将X光图坐标映射于目标物品的液体容器，获得当前实际位置坐标；控制激光指示器直射并追踪实际位置坐标。该液体识别方法，使安检人员根据提示快速找到该具有嫌疑的液体容器，大大提高了安检效率，避免了漏报误报的情况，从而实现被安检人员的快速通过。

Description

一种安检过程中液体识别方法及其装置
本申请是以申请号为201810964555.6、申请日为2018年8月23日的中国专利申请为基础，并主张其优先权，该申请的全部内容在此作为整体引入本申请中。
技术领域
本申请涉及图像处理技术领域，更具体地说，涉及一种安检过程中液体识别方法及其装置。
背景技术
安全检查是对施工项目贯初安全生产法律法规的情况、安全生产状况、劳动条件、事故隐患等所进行的检查，其主要内容包括查思想、查制度直机械设备、查安全卫生设施、查安全教育及培训、查生产人员行为、在防护用品施工、查伤亡事故处理等。
X射线是由于原子中的电子在能量相差悬殊的两个能级之间的跃迁而产生的粒子流，是波长介于紫外线和γ射线之间的电磁波。其波长很短约介于0.01～100埃之间。由德国物理学家W.K.伦琴于1895年发现，故又称伦琴射线。x射线具有很高的穿透本领，能透过许多对可见光不透明的物质，如墨纸、木料等。这种肉眼看不见的射线可以使很多固体材料发生可见的荧光，使照相底片感光以及空气电离等效应。X射线最初用于医学成像诊断和X射线结晶学。X射线也是游离辐射等这一类对人体有危害的射线。
目前，现有的安检识别方法中，只能通过安检人员通过肉眼观察基于X光技术所得到的X光图像，以判断是否存在装有液体的液体容器，如果有的话进行进一步的检测，但是当所要检测物品过多时，则避免不了的由于肉眼观察所造成的漏报误报的情况，大大降低了安检效率，增加了安检时 间，不利于被安检人员的快速通过。
申请内容
有鉴于此，本申请提供一种安检过程中液体识别方法及其装置以解决现有技术的不足。
为解决上述问题，本申请提供一种安检过程中液体识别方法，包括：
基于X光成像技术采集目标物品的X光图像；
通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
若是，则获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；
控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。
优选地，所述“通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器”包括：
通过预先训练的X光液体识别模型对所述X光图像中的物品特征对应的不同的目标物品进行定位，获得定位区；
对所述定位区进行边缘检测和重叠区预测，得到每个定位区对应的包含有目标物品的图像的轮廓线；
根据所述轮廓线，截取所述X光图像中所包含的每个所述目标物品的最小截图；
通过X光液体识别模型对每个所述最小截图进行识别，判断所述X光图像中的每一个所述最小截图是否包含具有液体的液体容器。
优选地，所述“控制激光指示器直射并追踪所述实际位置坐标，以便 于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”之后，还包括：
根据所述激光指示器所标示出的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本；
根据MRI磁共振成像技术，对所述液体样本进行检测，判断所述液体样本是否为纯水；
若所述液体样本为纯水，则生成一与所述液体容器对应的纯水检测标签，以便于根据所述纯水检测标签提示该液体容器中为纯水；
若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测。
优选地，所述“控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”和所述“根据所述激光指示器所标示出的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本”之间，还包括：
通过图像采集装置，根据所述实际位置坐标对所述液体容器进行图像采集，获得所述液体容器对应的嫌疑物品图像；并且，通过红外温度传感器获取所述液体容器的表面温度；
对所述嫌疑物品图像进行图像识别，判断所述液体容器是否为透明容器；
若所述液体容器为透明容器，则对该透明的所述液体容器内的液体进行紫外波长扫描，得到第一波长扫描图；
提取所述嫌疑物品图像中的液体容器的液体容器特征；所述液体容器 特征包括容器透明度、液体颜色、液体容量；
在所述“若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测”之后，还包括：
在所述检测报告中加入所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征。
优选地，所述“在所述检测报告中加入所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征”之后，还包括：
对所述液体样本进行紫外波长扫描，得到第二波长扫描图；
若所述第二波长扫描图与所述第一波长扫描图匹配，则基于所述第二波长扫描图对所述液体样本进行OD值获取，并在所述检测报告中加入所述OD值。
优选地，所述“基于X光成像技术采集目标物品的X光图像”之后，还包括：
对所述X光图像进行预处理；
所述预处理包括平滑处理、中值滤波和对比度增强处理。
此外，为解决上述问题，本申请还提供一种安检过程中液体识别装置，包括：采集模块、判断模块、定位模块和指示模块；
所述采集模块，用于基于X光成像技术采集目标物品的X光图像；
所述判断模块，用于通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
所述定位模块，用于获取所述X光图像中的所述液体容器的在图像中 的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；
所述指示模块，用于控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。
此外，为解决上述问题，本申请还提供一种用户终端，包括存储器以及处理器，所述存储器用于存储安检过程中液体识别程序，所述处理器运行所述安检过程中液体识别程序以使所述用户终端执行如上述所述安检过程中液体识别方法。
此外，为解决上述问题，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有安检过程中液体识别程序，所述安检过程中液体识别程序被处理器执行时实现如上述所述安检过程中液体识别方法。
本申请提供的一种安检过程中液体识别方法及其装置。其中，本申请所提供的方法包括：基于X光成像技术采集目标物品的X光图像；通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；若是，则获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。本申请通过利用预先训练的X光液体识别模型判断所述X光图像中是否包含具有 液体的液体容器，进而在识别后，对包含有液体的液体容器进行定位，获得当前实际位置坐标，并通过激光指示器对该液体容器进行追踪指示，以提示安检人员进行核验。本申请通过X射线照射技术和图像识别技术相结合，实现了对于需要安检的物品的自动识别，从而确认其中存在的具有液体的液体容器，并通过激光指示器进行对其的跟踪指示，可通过图像识别快速定位具有嫌疑的液体容器，并且使安检人员根据提示快速找到该具有嫌疑的液体容器，大大提高了安检效率，避免了漏报误报的情况，从而实现被安检人员的快速通过。
附图说明
图1为本申请安检过程中液体识别方法实施例方案涉及的硬件运行环境的结构示意图；
图2为本申请安检过程中液体识别方法第一实施例的流程示意图；
图3为本申请安检过程中液体识别方法第二实施例的流程示意图；
图4为本申请安检过程中液体识别方法第三实施例的流程示意图；
图5为本申请安检过程中液体识别方法第四实施例的流程示意图；
图6为本申请安检过程中液体识别装置的功能模块示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
下面详细描述本申请的实施例，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本申请的 描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
在本申请中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”、“固定”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或成一体；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本申请中的具体含义。
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的终端的硬件运行环境的结构示意图。
如图1所示，该终端可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏、输入单元比如键盘、遥控器，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器，也可以是稳定的存储器，例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，终端还可以包括RF(Radio Frequency，射频)电路，传感器、音频电路、WiFi模块等等。此外，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
本领域技术人员可以理解，图1中示出的终端并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件 布置。
如图1所示，作为一种计算机可读存储介质的存储器1005中可以包括操作系统、数据接口控制程序、网络连接程序以及安检过程中液体识别程序。
本申请提供的一种安检过程中液体识别方法及其装置。其中，所述方法实现了对于包含的目标区域的视频流中的关键帧的智能定位，从而可根据标签确定视频流中包含有定位帧的时间戳，并获得视频流中的定位帧的轮廓线以及轮廓线坐标，从而可进一步的根据更新后的标签进行方便的对视频流的编辑，定位效率高、时间短速度快，为监管人员的工作带来了方便。
实施例1：
参照图2，本申请第一实施例提供一种安检过程中液体识别方法，包括：
步骤S10，基于X光成像技术采集目标物品的X光图像；
需要说明的是，X射线又称伦琴射线，它是肉眼看不见的一种射线，但可使某些化合物产生荧光或使照相底片感光；它在电场或磁场中不发生偏转，能发生反射、折射、干涉、衍射等；它具有穿透物质的本领，但对不同物质它的穿透本领不同；能使分子或原子电离；有破坏细胞作用，人体不同组织对于X射线的敏感度不同，受损害程度也不同。因此，X射线能使人体在荧屏上或胶片上形成影像，是基于人体组织有密度和厚度的差别。由于存在这种差别，当X线透过人体各种不同组织结构时，它被吸收的程度不同，所以到达荧屏或胶片上的X线的量有差异。在荧屏或X射线片上形成黑白对比不同的影像。因此，X射线一发现就在医疗上显示了巨大的应用价值，几个星期后，医学家就应用X射线准确地显示了人体断骨的位置。随着时间的推移，X射线已经成为现代医疗中不可缺少的设备。
在本实施例中，利用X光成像技术，应用于无损安全检查领域，例如 机场、火车站、汽车站、电影院、展览展会、国内外会议等重要场所的安全检查。对于被安检人员所持有的物品进行基于X光成像技术，有助于在对于检测样本数量庞大的物品进行快速检查，以快速找出目标物品中具有液体的液体容器。
步骤S20，通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
上述，需要说明的是，人工神经网络(Artificial Neural Network，即ANN)，是20世纪80年代以来人工智能领域兴起的研究热点。它从信息处理角度对人脑神经元网络进行抽象，建立某种简单模型，按不同的连接方式组成不同的网络。在工程与学术界也常直接简称为神经网络或类神经网络。神经网络是一种运算模型，由大量的节点(或称神经元)之间相互联接构成。每个节点代表一种特定的输出函数，称为激励函数(activation function)。每两个节点间的连接都代表一个对于通过该连接信号的加权值，称之为权重，这相当于人工神经网络的记忆。
上述，基于人工神经网络技术，对X光液体识别模型进行训练，从而得到经过预先训练的模型，并对所采集到的X光图像进行识别，判断图像中，是否包含有液体容器，并且该液体容器中包含有液体。
步骤S30，若是，则获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；
如果包含有具有液体的液体容器，则获得所述液体容器在图像中的坐标，并映射于实际的目标物品中，找到当前实际位置坐标。
步骤S40，控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。
上述，开启激光指示器，根据所得到的当前实际位置坐标进行直射，由于可能在目标物品放置于传送带上，处于移动状态，所以根据图像识别技术，基于其当前实际位置坐标的移动，通过激光指示器追踪该液体容器，以提示安检人员对其进行进一步的核验。
本实施例通过利用预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器，进而在识别后，对包含有液体的液体容器进行定位，获得当前实际位置坐标，并通过激光指示器对该液体容器进行追踪指示，以提示安检人员进行核验。本实施例通过X射线照射技术和图像识别技术相结合，实现了对于需要安检的物品的自动识别，从而确认其中存在的具有液体的液体容器，并通过激光指示器进行对其的跟踪指示，可通过图像识别快速定位具有嫌疑的液体容器，并且使安检人员根据提示快速找到该具有嫌疑的液体容器，大大提高了安检效率，避免了漏报误报的情况，从而实现被安检人员的快速通过。
实施例2：
参照图3，本申请第二实施例提供一种安检过程中液体识别方法，基于上述图2所示的第一实施例，所述步骤S20，“通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器”包括：
步骤S21，通过预先训练的X光液体识别模型对所述X光图像中的物品特征对应的不同的目标物品进行定位，获得定位区；
上述，X光图像可能包含有多个不同的目标物品。例如，待识别的物品为一行李箱，行李箱中放有大量旅客的个人物品；或者待识别的物品为一竹筐，竹筐中放有一些杂物。则通过预先训练的X光液体识别模型对所采集的X光图像中的物品特征对应的不同的目标物品进行定位，得到定位区。
上述，物品特征，为X光图像中所包含的多种物品所对应的特征，例如，形状特征、文理特征等等。
在本实施例中，步骤S21可以包括：
获取图像中的物品特征，根据所述物品特征进行匹配，根据匹配结果进行分类，从而将图像中的物品根据类别划分为不同区域；
根据不同的区域，获取区域对应的定位区。
步骤S22，对所述定位区进行边缘检测和重叠区预测，得到每个定位区对应的包含有目标物品的图像的轮廓线；
上述，根据图像识别技术总的边缘检测，对每个物品的边缘进行确定，并且，由于物品过多时会出现重叠现象，基于神经网络模型，预测其重叠区域的物品，从而得到每一个可确定的定位区所包含有的目标物品的图像的轮廓线。
步骤S23，根据所述轮廓线，截取所述X光图像中所包含的每个所述目标物品的最小截图；
步骤S24，通过X光液体识别模型对每个所述最小截图进行识别，判断所述X光图像中的每一个所述最小截图是否包含具有液体的液体容器。
上述，根据轮廓线进行截图，得到包含目标物品的最小截图，将待识别图像中的每一个目标物品对应的图像，转换为包含目标物品的最小截图，进而对于该最小截图进行识别和判断，从而大大降低了高质量图片对于系统资源的占用和浪费；同时，每个最小截图进行单独的识别和定位，使系统进行多线程的识别工作，大大提高了工作效率。
实施例3：
参照图4，本申请第三实施例提供一种安检过程中液体识别方法，基于上述图2所示的第一实施例，所述步骤S40，“控制激光指示器直射并追踪 所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”之后，还包括：
步骤S50，根据所述激光指示器所标示出的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本；
上述，在对包含有液体的液体容器进行通过激光指示器的定位后，可通过自动取样器，或人工进行取样，将所取的液体样本放置于磁共振检测管中，进行进一步的测试。其中，自动取样器，可以为包括有穿刺头和进样管的设备，与MRI设备相连接，当需要进行进一步检测时，自动控制穿刺头对指定位置进行穿刺取样，从而得到液体样本。
步骤S60，根据MRI磁共振成像技术，对所述液体样本进行检测，判断所述液体样本是否为纯水；
需要说明的是，MRI也就是磁共振成像，英文全称是：Magnetic Resonance Imaging。经常为人们所利用的原子核有：1H、11B、13C、17O、19F、31P。在这项技术诞生之初曾被称为核磁共振成像，到了20世纪80年代初，作为医学新技术的NMR成像(NMR Imaging)一词越来越为公众所熟悉。随着大磁体的安装，有人开始担心字母“N”可能会对磁共振成像的发展产生负面影响。另外，“nuclear”一词还容易使医院工作人员对磁共振室产生另一个核医学科的联想。因此，为了突出这一检查技术不产生电离辐射的优点，同时与使用放射性元素的核医学相区别，放射学家和设备制造商均同意把“核磁共振成像术”简称为“磁共振成像(MRI)”。
磁共振成像是断层成像的一种，它利用磁共振现象从人体中获得电磁信号，并重建出人体信息。1946年斯坦福大学的Flelix Bloch和哈佛大学的Edward Purcell各自独立的发现了核磁共振现象。磁共振成像技术正是基于这一物理现象。磁共振成像技术与其它断层成像技术(如CT)有一些共同 点，比如它们都可以显示某种物理量(如密度)在空间中的分布；同时也有它自身的特色，磁共振成像可以得到任何方向的断层图像，三维体图像，甚至可以得到空间一波谱分布的四维图像。
在本实施例中，通过利用MRI技术，对待测的液体样本进行快速检测，通过匀场、照射，从而测定出液体的性质，从而判断出是否为纯水。
步骤S70，若所述液体样本为纯水，则生成一与所述液体容器对应的纯水检测标签，以便于根据所述纯水检测标签提示该液体容器中为纯水；
步骤S80，若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测。
上述，如果液体样本为纯水，则构建一标签，对应关联与该液体样本，以提示安检人员根据标签进行确定，对液体样本进行排除嫌疑，确定为纯水。如果检测后不为纯水，则生成检测报告。该检测报告针对于有一定嫌疑的物品所生成的，例如，不为纯水的液体等。并且，为报告建立标签，生成提示信息，提示安检人员对该液体进行进一步的理化检测。
例如，如果需要对液体进行定性，可通过薄层色谱点样，从而确定样本是否为易燃易爆的液体，或者通过GC-MS，确定该液体是否为腐蚀性的硫酸盐酸等等。
实施例4：
参照图5，本申请第四实施例提供一种安检过程中液体识别方法，基于上述图4所示的第三实施例，所述步骤S40，“控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”和步骤S50，所述“根据所述激光指示器所标示出 的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本”之间，还包括：
步骤S90，通过图像采集装置，根据所述实际位置坐标对所述液体容器进行图像采集，获得所述液体容器对应的嫌疑物品图像；并且，通过红外温度传感器获取所述液体容器的表面温度；
上述，图像采集装置，可以为设置在可对目标物品进行图像采集的位置的摄像头。在获取到液体容器的实际位置坐标后，可通过摄像头，对该物品进行图像采集，获得嫌疑物品图象，进而通过红外温度传感器进行获取其外表面的温度。一部分有机溶剂，在放置过程中，尤其是运动过程中，会由于混合或发生反应产生一定的热量，例如硫酸、水和乙醇或甲醇，等等，为了获知其中是否存在不稳定的液体，排除隐患，所以需要对其表面温度进行获取。
步骤S100，对所述嫌疑物品图像进行图像识别，判断所述液体容器是否为透明容器；
上述，通过图像识别，从而判断液体容器是否为透明容器。
其中，通过图像识别可对物品是否为透明或半透明物品进行判断，例如，转换为图像灰度直方图，进而对半透明或透明物体的灰度直方图进行特征分析，其中可利用直方图数据的平滑算法、三次样条差值算法、目标识别方法等等算法进行识别。
步骤S110，若所述液体容器为透明容器，则对该透明的所述液体容器内的液体进行紫外波长扫描，得到第一波长扫描图；
上述，需要说明的是，uv是Ultravioletray或Ultravioletradiation的缩写，是由德国科学家里特发现的，紫外线是电磁波谱中波长从100-400nm(纳米)辐射的总称。
其中UVA波长在320-390nm，又称为长波黑斑效应紫外线。它有很强的穿透力，可以穿透大部分透明的玻璃以及塑料。日光中含有的长波紫外线有超过98％能穿透臭氧层和云层到达地球表面，UVA可以直达肌肤的真皮层，破坏弹性纤维和胶原蛋白纤维，将我们的皮肤晒黑。360nm波长的UVA紫外线可能符合昆虫类的趋光性反应曲线，还有待科学家进一步研究。300-420nm波长的UVA紫外线可透过完全截止可见光的特殊着色玻璃灯管，仅辐射出以365nm为中心的近紫外光，可用于矿石鉴定、舞台装饰、验钞等场所。
UVB波长在280-320nm，又称为中波红斑效应紫外线。中等穿透力，它的波长较短的部分会被透明玻璃吸收，日光中含有的中波紫外线大部分被臭氧层所吸收，只有不足2％能到达地球表面，在夏天和午后会特别强烈。UVB紫外线对人体具有红斑作用，能促进体内矿物质代谢和维生素D的形成，但长期或过量照射会令皮肤晒黑，并引起红肿脱皮。紫外线保健灯、植物生长灯发出的就是使用特殊透紫玻璃(不透过254nm以下的光)和峰值在300nm附近的荧光粉制成。
UVC波长在280nm以下，又称为短波灭菌紫外线。它的穿透能力最弱，无法穿透大部分的透明玻璃及塑料。日光中含有的短波紫外线几乎被臭氧层完全吸收。短波紫外线对人体的伤害很大，短时间照射即可灼伤皮肤，长期或高强度照射还会造成皮肤癌。紫外线杀菌灯发出的就是UVC短波紫外线。
UVD波段，波长100～200nm，又称为真空紫外线。
UVV波长在390nm以上。
波长扫描的原理就是在一个波长范围内，对样品进行测量，反映的是样品在不同波长下的吸光度值。操作时需设定测量方式，即测定的是T还 是A，然后是测量范围，样品的测定范围，然后是扫描波长，设定样品需要扫描的波长范围是从哪儿到哪儿。其次有扫描间隔，扫描间隔指的是仪器每隔多少纳米对样品进行测量，比如1nm为扫描间隔，则仪器从设定的起始波长开始，每隔1nm对样品进行取值，然后将各点连起来就是所需的图象。由于，不同的液体或试剂，具有不同的紫外吸收，具有不同的OD值(紫外吸收值)，所以通过紫外波长扫描，可获得波长扫描图，进而获知该样本的最大吸收波长。
步骤S120，提取所述嫌疑物品图像中的液体容器的液体容器特征；所述液体容器特征包括容器透明度、液体颜色、液体容量；
上述，液体容器特征中，可以包含有容器透明度、液体颜色、液体容量等特征，是通过图像识别所获得的。
其中，还可以包括，样品容器的外观特征，例如，标签、颜色、体积、材质等等，从而进一步可通过比对获知其是否为市售的饮料产品、有标签的有机溶剂等等，并可通过比对，判断该容器的原有目的是什么容器，例如，是否为有机溶剂瓶，是否为酒瓶，是否为饮料瓶等等，从而为进一步的对于液体的预判提供一定的线索，实现快速检测。
在所述步骤S80，“若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测”之后，还包括：
步骤S130，在所述检测报告中加入所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征。
上述，更新检测报告，将所或得到的数据信息，包括所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征，加 入该检测报告中。
步骤S140，对所述液体样本进行紫外波长扫描，得到第二波长扫描图；
上述，该液体样本为对于原有液体容器中取样后所得到的样本，并对其进行紫外去按波长扫描，得到第二波长扫描图。
步骤S150，若所述第二波长扫描图与所述第一波长扫描图匹配，则基于所述第二波长扫描图对所述液体样本进行OD值获取，并在所述检测报告中加入所述OD值。
上述，第一波长扫描图和第二波长扫描图，由于浓度或温度的影响，可能存在不完全相同但可匹配的情况，即其最大吸收不会改变，可判定该样本的正确性，即该样本确定为从液体容器中取出。通过将第一波长扫描图和第二波长扫描图进行匹配，从而确定液体的关联性，提高了进一步检测的准确度，防止误检或漏检。
进而在最大吸收下，获取一次该样本的OD值。并将该值更新入检测报告中。从而为对于该液体的检测提供了大量有参考意义的理化参数检测，可进一步提高检测效率，为被安检人员的快速通过提供了方便。
进一步的，所述步骤S10，“基于X光成像技术采集目标物品的X光图像”之后，还包括：
步骤S160，对所述X光图像进行预处理；所述预处理包括平滑处理、中值滤波和对比度增强处理。
中值滤波法是一种非线性平滑技术，它将每一像素点的灰度值设置为该点某邻域窗口内的所有像素点灰度值的中值。中值滤波是基于排序统计理论的一种能有效抑制噪声的非线性信号处理技术，中值滤波的基本原理是把数字图像或数字序列中一点的值用该点的一个邻域中各点值的中值代替，让周围的像素值接近的真实值，从而消除孤立的噪声点。方法是用某 种结构的二维滑动模板，将板内像素按照像素值的大小进行排序，生成单调上升(或下降)的为二维数据序列。二维中值滤波输出为g(x，y)＝med{f(x-k，y-1)，(k，l∈W)}，其中，f(x，y)，g(x，y)分别为原始图像和处理后图像。W为二维模板，通常为3*3，5*5区域，也可以是不同的的形状，如线状，圆形，十字形，圆环形等。
上述，平滑处理，即数字图像处理中，当像元放大后，图像的边界就会出现锯齿状，经过增加像元内插处理，加大像元分辨率，使图像细化，即平滑化处理。图像处理还有其它方法如，密度分割，反差增强。
上述，对比度增强是将图像中的亮度值范围拉伸或压缩成显示系统指定的亮度显示范围，从而提高图像全部或局部的对比度。输入图像中的每个亮度值通过一定的转换函数，对应于输出图像的一个显示值。
通过平滑、中值滤波和对比度增强，使所采集到的X光图像在进一步的进行识别过程中，排除干扰，更加快速的进行识别和定位。
此外，参考图6，为解决上述问题，本申请还提供一种安检过程中液体识别装置，包括：采集模块10、判断模块20、定位模块30和指示模块40；
所述采集模块10，用于基于X光成像技术采集目标物品的X光图像；
所述判断模块20，用于通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
所述定位模块30，用于获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；
所述指示模块40，用于控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位 置。
此外，为解决上述问题，本申请还提供一种用户终端，包括存储器以及处理器，所述存储器用于存储安检过程中液体识别程序，所述处理器运行所述安检过程中液体识别程序以使所述用户终端执行如上述所述安检过程中液体识别方法。
此外，为解决上述问题，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有安检过程中液体识别程序，所述安检过程中液体识别程序被处理器执行时实现如上述所述安检过程中液体识别方法。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (9)

  1. 一种安检过程中液体识别方法，其特征在于，包括：
    基于X光成像技术采集目标物品的X光图像；
    通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
    若是，则获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获得当前实际位置坐标；
    控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。
  2. 如权利要求1所述安检过程中液体识别方法，其特征在于，所述“通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器”包括：
    通过预先训练的X光液体识别模型对所述X光图像中的物品特征对应的不同的目标物品进行定位，获得定位区；
    对所述定位区进行边缘检测和重叠区预测，得到每个定位区对应的包含有目标物品的图像的轮廓线；
    根据所述轮廓线，截取所述X光图像中所包含的每个所述目标物品的最小截图；
    通过X光液体识别模型对每个所述最小截图进行识别，判断所述X光图像中的每一个所述最小截图是否包含具有液体的液体容器。
  3. 如权利要求1所述安检过程中液体识别方法，其特征在于，所述“控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”之后，还包括：
    根据所述激光指示器所标示出的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本；
    根据MRI磁共振成像技术，对所述液体样本进行检测，判断所述液体样本是否为纯水；
    若所述液体样本为纯水，则生成一与所述液体容器对应的纯水检测标签，以便于根据所述纯水检测标签提示该液体容器中为纯水；
    若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测。
  4. 如权利要求3所述安检过程中液体识别方法，其特征在于，所述“控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置”和所述“根据所述激光指示器所标示出的当前实际位置坐标，对所述液体容器中的液体进行取样，得到液体样本”之间，还包括：
    通过图像采集装置，根据所述实际位置坐标对所述液体容器进行图像采集，获得所述液体容器对应的嫌疑物品图像；并且，通过红外温度传感器获取所述液体容器的表面温度；
    对所述嫌疑物品图像进行图像识别，判断所述液体容器是否为透明容器；
    若所述液体容器为透明容器，则对该透明的所述液体容器内的液体进行紫外波长扫描，得到第一波长扫描图；
    提取所述嫌疑物品图像中的液体容器的液体容器特征；所述液体容器特征包括容器透明度、液体颜色、液体容量；
    在所述“若所述液体样本不为纯水，则生成检测报告，并为所述检测报告建立与所述液体容器对应的非纯水检测标签，并生成一提示信息，以根据所述非纯水检测标签提示所述液体容器中不为纯水，进而根据所述提示信息对所述液体容器中的液体进行理化检测”之后，还包括：
    在所述检测报告中加入所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征。
  5. 如权利要求4所述安检过程中液体识别方法，其特征在于，所述“在所述检测报告中加入所述嫌疑物品图像、所述第一波长扫描图、所述液体容器的外表温度和液体容器特征”之后，还包括：
    对所述液体样本进行紫外波长扫描，得到第二波长扫描图；
    若所述第二波长扫描图与所述第一波长扫描图匹配，则基于所述第二波长扫描图对所述液体样本进行OD值获取，并在所述检测报告中加入所述OD值。
  6. 如权利要求1所述安检过程中液体识别方法，其特征在于，所述“基于X光成像技术采集目标物品的X光图像”之后，还包括：
    对所述X光图像进行预处理；
    所述预处理包括平滑处理、中值滤波和对比度增强处理。
  7. 一种安检过程中液体识别装置，其特征在于，包括：采集模块、判断模块、定位模块和指示模块；
    所述采集模块，用于基于X光成像技术采集目标物品的X光图像；
    所述判断模块，用于通过预先训练的X光液体识别模型判断所述X光图像中是否包含具有液体的液体容器；
    所述定位模块，用于获取所述X光图像中的所述液体容器的在图像中的X光图坐标，并将所述X光图坐标映射于所述目标物品的液体容器，获 得当前实际位置坐标；
    所述指示模块，用于控制激光指示器直射并追踪所述实际位置坐标，以便于标示出所述当前实际位置坐标对应的具有液体的所述液体容器的位置。
  8. 一种用户终端，其特征在于，包括存储器以及处理器，所述存储器用于存储安检过程中液体识别程序，所述处理器运行所述安检过程中液体识别程序以使所述用户终端执行如权利要求1-6中任一项所述安检过程中液体识别方法。
  9. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有安检过程中液体识别程序，所述安检过程中液体识别程序被处理器执行时实现如权利要求1-6中任一项所述安检过程中液体识别方法。
PCT/CN2019/070037 2018-08-23 2019-01-02 一种安检过程中液体识别方法及其装置 WO2020037935A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810964555.6A CN108956657A (zh) 2018-08-23 2018-08-23 一种安检过程中液体识别方法及其装置
CN201810964555.6 2018-08-23

Publications (1)

Publication Number Publication Date
WO2020037935A1 true WO2020037935A1 (zh) 2020-02-27

Family

ID=64473927

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/070037 WO2020037935A1 (zh) 2018-08-23 2019-01-02 一种安检过程中液体识别方法及其装置

Country Status (2)

Country Link
CN (2) CN108956657A (zh)
WO (1) WO2020037935A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435543A (zh) * 2021-07-22 2021-09-24 北京博睿视科技有限责任公司 一种基于传送带标识的可见光和x光图像匹配方法及装置
CN114539586A (zh) * 2022-04-27 2022-05-27 河南银金达新材料股份有限公司 一种聚合物膜的表面处理生产工艺
CN116095428A (zh) * 2021-11-04 2023-05-09 中国联合网络通信集团有限公司 图像采集装置

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108956657A (zh) * 2018-08-23 2018-12-07 深圳码隆科技有限公司 一种安检过程中液体识别方法及其装置
CN109975885A (zh) * 2019-03-28 2019-07-05 上海中通吉网络技术有限公司 一种快递违禁物品识别方法及安检系统
CN111008676B (zh) * 2019-12-27 2022-07-12 哈尔滨工业大学 一种安检方法及安检系统
CN111383197A (zh) * 2020-03-16 2020-07-07 浙江大华技术股份有限公司 一种安检机显示不同图像的方法及装置
CN111612089A (zh) * 2020-05-29 2020-09-01 浙江大华技术股份有限公司 一种在安检机中危险品的标注方法及设备
CN114162551B (zh) * 2020-09-11 2023-02-24 同方威视技术股份有限公司 用于安检系统的判图任务控制方法与安检系统
CN113552118A (zh) * 2021-07-15 2021-10-26 海口市骨科与糖尿病医院(上海市第六人民医院海口骨科与糖尿病医院) 一种手术器械包内指示卡的检测方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003240735A (ja) * 2002-02-18 2003-08-27 Anritsu Sanki System Co Ltd Ｘ線検出装置及びｘ線異物検出装置
CN101943761A (zh) * 2010-09-12 2011-01-12 上海英迈吉东影图像设备有限公司 一种x射线检测方法
CN107051675A (zh) * 2017-05-20 2017-08-18 苏州亮磊知识产权运营有限公司 一种用于垃圾分类粉碎的装置及其控制方法
CN107271467A (zh) * 2017-07-26 2017-10-20 公安部第三研究所 一种基于x射线透视和散射技术的危险液体识别方法及系统
CN107741433A (zh) * 2017-09-26 2018-02-27 天津工业大学 一种基于神经网络物体分析的液体检测方法
CN108956657A (zh) * 2018-08-23 2018-12-07 深圳码隆科技有限公司 一种安检过程中液体识别方法及其装置

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0898704A1 (en) * 1997-01-24 1999-03-03 Quanta Vision, Inc. Inspection equipment using small-angle topography in determining an object's internal structure and composition
EP1630550A1 (en) * 2004-08-27 2006-03-01 Moller & Devicon A/S Methods and apparatuses of detecting foreign particles or faults in a plurality of filled containers
DE102004060610A1 (de) * 2004-12-16 2006-06-29 Yxlon International Security Gmbh Anordnung zum Messen des Impulsübertragungsspektrums von elastisch gestreuten Röntgenquanten sowie Verfahren zur Bestimmung dieses Impulsübertragungsspektrums
CN102565107B (zh) * 2007-10-05 2014-08-27 清华大学 液态物品检查方法和设备
GB2538730B (en) * 2015-05-26 2020-07-08 Process Vision Ltd Detecting the presence of liquid in a pressurised gas pipeline
CN106885813B (zh) * 2015-12-16 2019-06-07 清华大学 检查货物的方法、系统和装置
CN108303747B (zh) * 2017-01-12 2023-03-07 清华大学 检查设备和检测枪支的方法
CN106950232A (zh) * 2017-04-12 2017-07-14 北京君和信达科技有限公司 辐射检查方法和辐射检查系统
CN108288279A (zh) * 2018-01-25 2018-07-17 盛视科技股份有限公司 一种基于x光图像前景目标提取的物品甄别方法
CN108198227A (zh) * 2018-03-16 2018-06-22 济南飞象信息科技有限公司 基于x光安检机图像的违禁品智能识别方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003240735A (ja) * 2002-02-18 2003-08-27 Anritsu Sanki System Co Ltd Ｘ線検出装置及びｘ線異物検出装置
CN101943761A (zh) * 2010-09-12 2011-01-12 上海英迈吉东影图像设备有限公司 一种x射线检测方法
CN107051675A (zh) * 2017-05-20 2017-08-18 苏州亮磊知识产权运营有限公司 一种用于垃圾分类粉碎的装置及其控制方法
CN107271467A (zh) * 2017-07-26 2017-10-20 公安部第三研究所 一种基于x射线透视和散射技术的危险液体识别方法及系统
CN107741433A (zh) * 2017-09-26 2018-02-27 天津工业大学 一种基于神经网络物体分析的液体检测方法
CN108956657A (zh) * 2018-08-23 2018-12-07 深圳码隆科技有限公司 一种安检过程中液体识别方法及其装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435543A (zh) * 2021-07-22 2021-09-24 北京博睿视科技有限责任公司 一种基于传送带标识的可见光和x光图像匹配方法及装置
CN113435543B (zh) * 2021-07-22 2024-04-09 湖南声迅科技有限公司 一种基于传送带标识的可见光和x光图像匹配方法及装置
CN116095428A (zh) * 2021-11-04 2023-05-09 中国联合网络通信集团有限公司 图像采集装置
CN114539586A (zh) * 2022-04-27 2022-05-27 河南银金达新材料股份有限公司 一种聚合物膜的表面处理生产工艺
CN114539586B (zh) * 2022-04-27 2022-07-19 河南银金达新材料股份有限公司 一种聚合物膜的表面处理生产和检测工艺

Also Published As

Publication number Publication date
CN110186940A (zh) 2019-08-30
CN110186940B (zh) 2021-09-24
CN108956657A (zh) 2018-12-07

Similar Documents

Publication Publication Date Title
WO2020037935A1 (zh) 一种安检过程中液体识别方法及其装置
US9442212B2 (en) Methods and devices for inspecting liquid
Cooper et al. Society of Hair Testing guidelines for drug testing in hair
RU2445609C2 (ru) Способ и установка (варианты) для досмотра объектов, содержащих жидкости
JP5172582B2 (ja) 液体物の検査方法及び装置
KR100963186B1 (ko) 방사선을 이용하여 액체형태물품에 대한 보안검사를수행하는 방법 및 장치
WO2015067208A1 (zh) 检查方法和设备
US9746404B2 (en) Inspection methods and apparatuses for liquids
US20200249156A1 (en) Advanced thz system and method
CN108956526A (zh) 一种被动式太赫兹危险品检测装置、检测方法及其应用
US20060056586A1 (en) Method and equipment for detecting explosives, etc.
JP2018113038A (ja) 検査機器および荷物における銃器を検出する方法
CN106485268A (zh) 一种图像识别方法及装置
CN111257957B (zh) 基于被动式太赫兹成像的识别跟踪系统及方法
Cao et al. Terahertz spectral unmixing based method for identifying gastric cancer
WO2015010531A1 (zh) 人体安全检查方法和人体安全检查系统
CN109063741A (zh) 一种基于希尔伯特曲线变换与深度学习的能谱分析方法
CN106198445A (zh) 基于太赫兹时域光谱成像的胶囊鉴别技术
CN104914479B (zh) 一种食品异物的无损探测方法
Dallaire et al. Quantitative spectral quality assessment technique validated using intraoperative in vivo Raman spectroscopy measurements
CN206114926U (zh) 一种太赫兹成像系统及太赫兹安检装置
CN110716241A (zh) 单点扫描的毫米波安检系统及方法
Zhang et al. Multispectral heterogeneity detection based on frame accumulation and deep learning
CN114355462A (zh) 一种基于微多普勒特征的人体隐藏危险物检测方法及介质
Yu et al. Myocardial amyloidosis detection with terahertz spectroscopy

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19853096

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19853096

Country of ref document: EP

Kind code of ref document: A1