WO2019128684A1 - 安全检查系统及其方法以及安检图像显示方法 - Google Patents

安全检查系统及其方法以及安检图像显示方法 Download PDF

Info

Publication number
WO2019128684A1
WO2019128684A1 PCT/CN2018/120067 CN2018120067W WO2019128684A1 WO 2019128684 A1 WO2019128684 A1 WO 2019128684A1 CN 2018120067 W CN2018120067 W CN 2018120067W WO 2019128684 A1 WO2019128684 A1 WO 2019128684A1
Authority
WO
WIPO (PCT)
Prior art keywords
sub
image data
local computer
areas
computer
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.)
Ceased
Application number
PCT/CN2018/120067
Other languages
English (en)
French (fr)
Inventor
陈志强
李元景
吴相豪
赵少治
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.)
Nuctech Co Ltd
Original Assignee
Nuctech 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 Nuctech Co Ltd filed Critical Nuctech Co Ltd
Publication of WO2019128684A1 publication Critical patent/WO2019128684A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H3/00—Measuring characteristics of vibrations by using a detector in a fluid
    • G01H3/005—Testing or calibrating of detectors covered by the subgroups of G01H3/00
    • 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
    • G01N23/046—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 using tomography, e.g. computed tomography [CT]
    • 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
    • G01N23/06—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 measuring the absorption
    • 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
    • G01N23/06—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 measuring the absorption
    • G01N23/083—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 measuring the absorption the radiation being X-rays
    • 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
    • G01V5/232—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays having relative motion between the source, detector and object other than by conveyor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image

Definitions

  • the present disclosure relates to the field of security inspection techniques, and in particular to the storage and reading of radiographic images of an object under inspection, such as a container.
  • Radiographic imaging scans an object with a beam of radiation, such as an X-ray, and the detector receives X-rays that pass through the object and converts them into electrical signals. After the electrical signal is converted to digital form by the analog/digital converter, it is input to the computer for processing. The obtained data is scanned, and the X-ray attenuation coefficient or the absorption coefficient of each voxel is obtained by calculation, and arranged in a matrix form, that is, a digital matrix is formed. Each digit in the digital matrix is converted into a small square of unequal gray scales from black to white by a digital/analog converter, called pixels, and arranged in the original matrix order to form a radiographic image.
  • a beam of radiation such as an X-ray
  • an X-ray image is a grayscale image composed of a certain number of pixels, which is a digital image, and may be a transmission image or a reconstructed tomographic image.
  • the resulting image is stored as a private dot-based format. This image is characterized by high definition, high number of pixels per unit size, and large image footprint.
  • the present disclosure proposes a security inspection system and method thereof that can improve the reading efficiency of a radiographic image.
  • a security inspection system comprising: at least one inspection subsystem that performs a ray scan on an object to be inspected to obtain ray image data of an object to be inspected; at least one local computer, and the checker A system communication connection, the at least one local computer configured to store the radiographic image data.
  • the at least one local computer is further configured to divide the radiographic image data into a plurality of sub-regions according to a predefined pattern, store image data of each sub-region separately in columns, and further store and represent between the sub-regions Relationship information.
  • the at least one local computer is deployed at an inspection site.
  • the at least one local computer includes a hardware device, an operating system, and an image processing application, the security check system further comprising: at least one remote image processing computer communicatively coupled to the local computer via at least one of a public network and a private network
  • the at least one remote image processing computer is configured to log in to the local computer by remote access, synchronize screen data of the local computer to the remote image processing computer, and perform an image review by an operator at the remote image processing computer.
  • the at least one local computer is further configured to store image data of the respective sub-areas in an HBase database, with the timestamps of the respective sub-areas indicating relationships between the respective sub-areas.
  • the at least one local computer is further configured to add a check field after the Value field of the HBase database for checksum calculation.
  • the at least one local computer is further configured to add a filler field after the Value field of the HBase database to adjust the total number of Key-Value bytes to a multiple of 8.
  • the size of the image data for each sub-region is less than a predetermined threshold.
  • the at least one local computer is further configured to store information representing a location relationship of the respective sub-areas in the HBase database.
  • the sub-area includes a front end, a vehicle body connecting portion, a vehicle chassis, and a passenger compartment.
  • a method for a security inspection system comprising: performing a ray scan on an object to be inspected by an inspection subsystem to obtain ray image data of an object to be inspected; and pre-defining the ray image data
  • the mode is divided into a plurality of sub-regions; image data of each sub-region is separately stored in columns in a local computer, and information indicating a relationship between the respective sub-regions is also stored.
  • the method further comprises: establishing a communication connection between the remote image processing computer and the local computer; at the remote image processing computer, logging in to the local computer by remote access, the screen of the local computer The data is synced to the remote image processing computer.
  • the method further comprises storing the image data of the respective sub-areas in the HBase database by at least one local computer, and using the timestamps of the respective sub-areas to represent the relationship between the respective sub-areas.
  • the method further comprises adding, by the local computer, a check field after the Value field of the HBase database for checksum calculation.
  • the method further comprises adding a filler field after the Value field of the HBase database for adjusting the total number of Key-Value bytes to a multiple of 8.
  • the method further comprises: reading, by the local computer, the image data of each sub-area according to the information stored in the database reflecting the relationship between the respective sub-areas, and synchronizing the image data of the combination of the at least two sub-areas Go to the remote image processing computer.
  • a security image display method comprising: reading image data of each sub-region according to a column according to information stored in a database reflecting a relationship between respective sub-regions; and displaying at least on the screen The combined image of the two sub-areas.
  • the method further comprises performing a checksum calculation on the read image data.
  • the reading efficiency of the massive ray image can be reduced.
  • FIG. 1 is a block diagram showing the structure of a security inspection system according to an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of a hardware structure of a computer in an embodiment in accordance with the present disclosure
  • FIG. 3 shows a schematic diagram of a logical architecture of a computer in an embodiment in accordance with the present disclosure
  • FIG. 4 shows a schematic flow chart of a method of a security inspection system in accordance with an embodiment of the present disclosure
  • FIG. 5 shows a schematic flowchart of a security image display method in an embodiment according to the present disclosure
  • FIG. 6 illustrates a schematic diagram of partitioning an X-ray image of a vehicle in a predefined pattern in accordance with an embodiment of the present disclosure
  • FIG. 7 illustrates a schematic diagram of combining image data of respective sub-areas in a security inspection system, according to another embodiment of the present disclosure.
  • references to "one embodiment”, “an embodiment”, “an” or “an” or “an” or “an” or “an” In at least one embodiment.
  • the appearances of the phrase “in one embodiment”, “in the embodiment”, “the” Furthermore, the particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and/or sub-combination.
  • the term “and/or” as used herein includes any and all combinations of one or more of the associated listed items.
  • Radiography is a technique that uses rays to observe the inside of an object. This technology can obtain information such as the structure and density of the object without destroying the object. It has been widely used in medical and health, national economy, scientific research and other fields. Hospital chest and station and airport security are the most common examples of everyday life. The most commonly used radiation is X-rays and gamma rays. At present, neutrons, protons, electrons, muons, heavy ions and other radiation have also been used more and more widely.
  • the image frame can be a single image of the smallest unit in the image animation, which is equivalent to each lens on the film.
  • a single frame can be a still picture, and continuous frames form an animation, such as a television image.
  • the so-called number of frames can refer to the number of frames of a picture transmitted in one second.
  • the graphics processor can be refreshed several times per second, usually expressed by fps (Frames Per Second).
  • fps Framework Per Second
  • Each frame is a still image, and displaying the frame in rapid succession creates an illusion of motion. High frame rates for smoother, more realistic animations. The more frames per second (fps), the smoother the displayed motion will be.
  • Digital-to-analog converter also known as D/A converter, referred to as DAC.
  • the DAC is a device that converts digital quantities into analog.
  • the D/A converter basically consists of four parts, namely a full resistance network, an operational amplifier, a reference power supply, and an analog switch.
  • An analog-to-digital converter, the A/D converter, referred to as an ADC is a device that converts a continuous analog signal into a discrete digital signal.
  • the inspection image for the container is usually about 30M-60M bytes, and the image generated each time in dual-energy mode is 60-120Mbytes. In the dual-energy dual-view mode, the image acquired each time can reach 120-240 Mbytes. Together with the images and data generated by the business, the overall value is very large. To store and read such large data efficiently, new storage and reading techniques are needed.
  • the embodiments of the present disclosure propose to store and describe an image by using a sub-region, including at least one of a standard attribute such as an image type, a size, an area, a creation time, a modification time, and the like, and application related attribute information (the image belongs to Type, sub-area type, sub-area bit depth, sub-area size, sub-region continuity, etc.) to store and describe the image.
  • a standard attribute such as an image type, a size, an area, a creation time, a modification time, and the like
  • application related attribute information the image belongs to Type, sub-area type, sub-area bit depth, sub-area size, sub-region continuity, etc.
  • FIG. 1 shows a block diagram of a security inspection system 100 in accordance with an embodiment of the present disclosure.
  • a security inspection system 100 in accordance with an embodiment of the present disclosure includes an X-ray source 110, a detector 130, a data collection device 150, a controller 140, and a computing device 160.
  • a security inspection is performed on the inspected object 120 such as a container truck, for example, whether or not dangerous goods/suspectable items are contained therein.
  • the detector 130 and the data acquisition device 150 are separately described in this embodiment, those skilled in the art will appreciate that they may also be integrated together as an X-ray detection and data acquisition device.
  • the X-ray source 110 described above may be an isotope, or may be an X-ray machine or an accelerator or the like.
  • the X-ray source 110 can be single energy or dual energy.
  • the object to be inspected 120 is scanned by X-ray source 110 and detector 150 and controller 140 and computing device 160 to obtain probe data.
  • the operator sends an instruction through the human-computer interaction interface of the computing device 160, and the X-ray source 110 is commanded to emit radiation, which is received by the detector 130 after passing through the object 120 to be inspected.
  • the signal is converted to an electrical signal, which is then converted to a digital signal by the data acquisition device 150 and processed by the computing device 160. This makes it possible to obtain a transmission image of the object 120 to be inspected.
  • the obtained transmission image is transmitted to the local live image processing computer 160 through a local line.
  • the live image processing computer 160 is connected by a public network or a private network 180.
  • the remotely deployed reviewing computers 191, 192, and 19n may be, for example, remote image processing computers deployed at the review center, and also connected to a public network or private network 180.
  • FIG. 2 shows a block diagram of the computing device 200.
  • the data signals detected by the detector 130 are collected by the data acquisition device, and the data is stored in the storage device 210 through the interface unit 280 and the bus 240.
  • Configuration information and a program of the computer data processor are stored in the read only memory (ROM) 220.
  • a random access memory (RAM) 230 is used to temporarily store various data during the operation of the processor 260.
  • a computer program for performing data processing such as a substance recognition program, an image processing program, and the like are also stored in the memory 210.
  • the internal bus 240 is connected to the above-described memory 210, read only memory 220, random access memory 230, input device 250, processor 260, display device 270, and interface unit 280.
  • the instruction code of the computer program instructs the processor 260 to execute a predetermined data processing algorithm.
  • the data processing result is displayed on the display device 270 such as an LCD display, or the processing result is directly outputted in the form of a hard copy such as printing.
  • FIG. 3 shows a schematic diagram of the logical architecture of a computer 300 in an embodiment in accordance with the present disclosure.
  • a computer in an embodiment of the present disclosure may have a four-layer logical structure such as a hardware layer 310, a driver layer 320, an operating system layer 330, and an application layer 340.
  • the hardware layer 310 includes, for example, various hardware as shown in FIG. 2, such as a CPU, an input device, a storage device, and the like.
  • the driver layer 320 includes drivers for driving the various hardware described above, which establishes a bridge between the hardware layer and the operating system so that hardware can be operated by software, such as input/output and the like.
  • the operating system is an operating system such as Windows or Linux that receives external input, allocates threads or resources, processes data or events, and outputs processing results.
  • the operating system has a remote login feature that allows remote computers to log in and can log in to other remote computers.
  • the application layer 340 is, for example, an image processing program such as edge enhancement, local enhancement, and grayscale stretching, and can process an X-ray image according to a user's operation to obtain a processing result.
  • a security inspection subsystem including, for example, an X-ray source 110, a detector 130, a data acquisition device 150, a controller 140, and a computing device 160 may be deployed at a customs inspection station site to perform a radiographic scan of the object under inspection 120. , to obtain a radiographic image of the object to be inspected.
  • the image processing computer 170 deployed at the inspection site may include hardware devices, operating systems, and image processing applications in communication with the security inspection subsystem to store and process X-ray images in real time.
  • the remotely deployed reviewing computer (image processing computer) 191, 192, 19n is communicatively coupled to the on-premises image processing computer 170 via a public network and/or a private network, and is logged into the image processing computer 170 via the remote access function to place the live image processing computer
  • the screen remote data of 170 is synchronized to the remote image processing computer 191, 192, 19n for review by an operator at the remote image processing computer. Since only part of the data displayed on the screen is synchronized to the remote reviewing computer, the radiographic image of the object to be inspected 120 can be reviewed without transmitting all the radiographic images of the object 120 to be inspected to the reviewing computer.
  • a distributed per-column storage scheme is employed to store images.
  • different plotting schemes can be predefined for different models.
  • a container vehicle it can be divided into four areas, namely, a front end, a vehicle body connecting portion, a vehicle chassis, and a passenger compartment.
  • Those skilled in the art can understand that other partitioning modes can also be adopted for other application fields.
  • the sub-region-based mass image storage technology not only realizes image storage, but also realizes flexible image sub-region retrieval.
  • Machine learning makes it easy to train specific areas of the image. Especially for large-size images generated by radiation, the preservation factor of the image area is reduced, the training factor of the image is reduced, the image training speed is improved, and the image training result and the overall image recognition effect are improved.
  • the storage of images is stored using the Hbase data structure.
  • the Key-Value storage structure can be refined, and the checksum and the filler fields are added after the Value field.
  • the checksum can be 8 bytes (64 bits). By adding blanks, each Key-Value byte array is an integer multiple of 8 bytes, making it more suitable for 64-bit systems.
  • a checksum calculation is first performed on the Value field, and a checksum field is written. Then, calculate the total size of the Key-Value byte array. If it is not an integer multiple of 8, a certain number of 0x00 bytes are stored in the filler field so that the total size is an integer multiple of 8.
  • the size of the storage area can be set to be less than a threshold in the massive image storage based on HBase.
  • the recommended data block does not exceed 1M at most
  • the threshold can be set to 1M.
  • a file that exceeds the block limit is sliced so that each slice is smaller than the size of the block, and then all slices are saved.
  • all sub-areas of the same image are recorded, and the order of the sub-areas is recorded to restore image data.
  • the timestamp TimeStamp in the Key-Value byte array of the HFile cell that is, use the timestamp TimeStamp to record the storage order.
  • All sub-regions of the image can be saved to the same RowKey, Family (corresponding to the nature of the image sub-region).
  • the type of family can have a front end, a car body connection part, a car chassis, and a car compartment, which are saved one by one in the order of sub-areas, and HBase will automatically put a TimeStamp.
  • FIG. 4 shows a schematic flow chart of a method of a security inspection system in accordance with an embodiment of the present disclosure.
  • FIG. 6 illustrates a schematic diagram of partitioning an X-ray image of a vehicle in a predefined pattern, in accordance with an embodiment of the present disclosure. As shown in FIG. 6, the vehicle body image is divided into a vehicle head 610, a vehicle body connecting portion 620, a vehicle chassis 630, and a passenger compartment 640.
  • step S410 the security inspection subsystem deployed at the customs inspection stations in various places performs X-ray scanning on the object to be inspected 220, for example, transmissive scanning of the container truck to obtain an X-ray image of the object to be inspected.
  • step S420 the radiographic image data is divided into a plurality of sub-regions according to a predefined pattern.
  • the above operation is performed in the live image processing computer 170 based on, for example, the vehicle head 610, the vehicle body connecting portion 620, the vehicle chassis 630, and the car 640.
  • step S430 the image data of each sub-area is separately stored in columns by the live image processing computer 170, and information indicating the relationship between the respective sub-areas is also stored.
  • image data of the front end 610, the vehicle body connecting portion 620, the vehicle chassis 630, and the car 640 are stored in columns, and time stamp information of each sub-area is recorded.
  • the live image processing computer 170 stores the image data of each sub-area in the HBase database, and the information indicating the relationship between the respective sub-areas is represented by the time stamp of each sub-area. For example, a check field is added after the Value field of the HBase database for checksum calculation. For another example, a filler field is added after the Value field of the HBase database, and the total number of Key-Value bytes is adjusted to a multiple of 8.
  • FIG. 5 shows a schematic flow chart of a security image display method in an embodiment in accordance with the present disclosure.
  • FIG. 7 illustrates a schematic diagram of combining image data of respective sub-areas in a security inspection system, according to another embodiment of the present disclosure.
  • step S510 data can be read from the HBase database before the image data is transferred from the live image processing computer to the remote image processing computer.
  • step S510 the image data of each sub-area is read in columns according to the information stored in the database reflecting the relationship between the respective sub-areas.
  • the image data of each sub-area may be read in a chronological order according to the time stamp information stored in advance, and the sub-areas may be combined. In this process, if the positional relationship between the respective sub-areas stored in advance is required, the respective sub-areas are further combined according to the positional relationship.
  • step S520 images combined by at least two sub-areas are displayed on the screen, and then the screen data is synchronized to the remote image processing computer.
  • the checksum calculation can be performed on the read image data, which ensures the correctness of the read data.
  • the above storage technology can improve the generation and storage technology of radiography, so that the generated image can meet the requirements of distributed storage and big data depth calculation, and provide basic support for intelligent image analysis and recognition.
  • the method according to an embodiment of the present disclosure can also be used in other fields, and utilizes different display and analysis requirements for different regions of an image, and performs image segmentation, domain description, convenient subsequent calculation and depth analysis according to predefined definitions. .
  • aspects of the embodiments disclosed herein may be implemented in an integrated circuit as a whole or in part, as one or more of one or more computers running on one or more computers.
  • a computer program eg, implemented as one or more programs running on one or more computer systems
  • implemented as one or more programs running on one or more processors eg, implemented as one or One or more programs running on a plurality of microprocessors, implemented as firmware, or substantially in any combination of the above, and those skilled in the art, in accordance with the present disclosure, will be provided with design circuitry and/or write software and / or firmware code capabilities.
  • signal bearing media include, but are not limited to, recordable media such as floppy disks, hard drives, compact disks (CDs), digital versatile disks (DVDs), digital tapes, computer memories, and the like; and transmission-type media such as digital and / or analog communication media (eg, fiber optic cable, waveguide, wired communication link, wireless communication link, etc.).

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Biochemistry (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Radiology & Medical Imaging (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Toxicology (AREA)
  • Pulmonology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Image Processing (AREA)

Abstract

一种安全检查系统以及一种安全检查方法。至少一个检查子系统对被检查对象进行射线扫描，得到被检查对象的射线图像数据（S410）。至少一个本地计算机与检查子系统通信连接，存储射线图像数据。本地计算机按照预定义的模式将射线图像数据划分为多个子区域（S420），将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间的关系的信息（S430）。

Description

安全检查系统及其方法以及安检图像显示方法
本申请要求于2017年12月27日提交的、申请号为201711452012.8的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及安全检查技术领域，具体涉及诸如集装箱之类的被检查物体的射线图像的存储和读取。
背景技术
射线成像是用诸如X线之类的射线束对物体检查进行扫描，由探测器接收透过该物体的X线，并转换成电信号。电信号经模拟/数字转换器转为数字形式后，输入计算机进行处理。扫描所得数据，经计算而获得每个体素的X线衰减系数或称吸收系数，排列成矩阵形式，即构成数字矩阵。数字矩阵中的每个数字经数字/模拟转换器转为由黑到白不等灰度的小方块，称之为像素(pixel)，并按原有矩阵顺序排列，即构成射线图像。因此，X射线图像是由一定数目像素组成的灰阶图像，是数字图像，可以是透射图像也可以是重建的断层图像。产生的图像存储为基于像素点的私有格式。这种图像的特点是清晰度高，单位尺寸像素数目高，且图像占用空间大。
在海关等大型检查系统中，一个集装箱卡车的X射线图像的存储容量高达30-60M字节。这样的海量图像数据对存储和读取技术都带来了新的挑战，需要提高图像的读取效率。
发明内容
本公开提出了一种安全检查系统及其方法，能够提高射线图像的读取效率。
在本公开的一个方面，提出了一种安全检查系统，包括：至少一个检查子系统，对被检查对象进行射线扫描，得到被检查对象的射线图像数据；至少一个本地计算机，与所述检查子系统通信连接，所述至少一个本地计算机配置为存储所述射线图像数据。其中，所述至少一个本地计算机还配置为按照预定义的模式将所述射线图像数据划分为多个子区域，将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间 的关系的信息。
根据一些实施例，所述至少一个本地计算机部署在检查现场。所述至少一个本地计算机包括硬件设备、操作系统和图像处理应用程序，所述安全检查系统还包括：至少一个远程图像处理计算机，通过公用网络和专用网络中的至少一个与所述本地计算机通信连接，所述至少一个远程图像处理计算机配置为借助远程访问登录所述本地计算机，将本地计算机的屏幕数据同步至远程图像处理计算机，并由远程图像处理计算机处的操作人员进行审图。
根据一些实施例，所述至少一个本地计算机还配置为将各个子区域的图像数据存储在HBase数据库中，用各个子区域的时间戳表示各个子区域之间的关系。
根据一些实施例，所述至少一个本地计算机还配置为在HBase数据库的Value域后增加校验域以便进行校验和计算。
根据一些实施例，所述至少一个本地计算机还配置为在HBase数据库的Value域后增加补白域，以便将Key-Value字节总数调整为8的倍数。
根据一些实施例，每个子区域的图像数据的大小小于预定的阈值。
根据一些实施例，所述至少一个本地计算机还配置为在HBase数据库中存储表示各个子区域的位置关系的信息。
根据一些实施例，所述子区域包括车头、车体连接部分、车底盘和车厢。
在本公开的另一方面，提出了一种安全检查系统的方法，包括：由检查子系统对被检查对象进行射线扫描，得到被检查对象的射线图像数据；将所述射线图像数据按照预定义的模式划分为多个子区域；在本地计算机中将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间的关系的信息。
根据一些实施例，所述的方法还包括：建立远程图像处理计算机与所述本地计算机之间的通信连接；在所述远程图像处理计算机，借助远程访问登录所述本地计算机，将本地计算机的屏幕数据同步至远程图像处理计算机。
根据一些实施例，所述方法还包括由至少一个本地计算机将各个子区域的图像数据存储在HBase数据库中，并用各个子区域的时间戳表示各个子区域之间的关系。
根据一些实施例，所述方法还包括由本地计算机在HBase数据库的Value域后增加校验域，以便进行校验和计算。
根据一些实施例，所述方法还包括由在HBase数据库的Value域后增加补白域，用 于将Key-Value字节总数调整为8的倍数。
根据一些实施例，所述方法还包括由本地计算机根据数据库中存储的反映各个子区域之间关系的信息按照列读取各个子区域的图像数据，并且将至少两个子区域组合后的图像数据同步到远程图像处理计算机。
在本公开的再一方面，提出了一种安检图像显示方法，包括：根据数据库中存储的反映各个子区域之间关系的信息按照列读取各个子区域的图像数据；以及在屏幕上显示至少两个子区域组合后的图像。
根据一些实施例，所述方法还包括：对读取的图像数据进行校验和计算。
基于上述实施例的技术方案，能够降低海量射线图像的读取效率。
附图说明
为了更好地理解本公开实施例，将根据以下附图对本公开实施例进行详细描述：
图1示出了根据本公开实施例的安全检查系统的结构示意图；
图2示出了在根据本公开的实施例中的计算机的硬件结构示意图；
图3示出了在根据本公开的实施例中的计算机的逻辑架构示意图；
图4示出了根据本公开的实施例的安全检查系统的方法的示意性流程图；
图5示出了根据本公开的实施例中的安检图像显示方法的示意性流程图；
图6示出了根据本公开的实施例中的对车辆的X射线图像按照预定义模式进行分区的示意图；以及
图7示出了根据本公开的另一实施例的在安全检查系统中对各个子区域的图像数据进行组合的示意图。
具体实施方式
下面将详细描述本公开的具体实施例，应当注意，这里描述的实施例只用于举例说明，并不用于限制本公开。在以下描述中，为了提供对本公开的透彻理解，阐述了大量特定细节。然而，对于本领域普通技术人员显而易见的是：不必采用这些特定细节来实行本公开。在其他实例中，为了避免混淆本公开，未具体描述公知的结构、材料或方法。
在整个说明书中，对“一个实施例”、“实施例”、“一个示例”或“示例”的提及意味着：结合该实施例或示例描述的特定特征、结构或特性被包含在本公开至少一个 实施例中。因此，在整个说明书的各个地方出现的短语“在一个实施例中”、“在实施例中”、“一个示例”或“示例”不一定都指同一实施例或示例。此外，可以以任何适当的组合和/或子组合将特定的特征、结构或特性组合在一个或多个实施例或示例中。此外，本领域普通技术人员应当理解，这里使用的术语“和/或”包括一个或多个相关列出的项目的任何和所有组合。
射线成像是一种利用射线观察物体内部的技术。这种技术可以在不破坏物体的情况下获得物体内部的结构和密度等信息，目前已经广泛应用于医疗卫生、国民经济、科学研究等领域。医院的胸透和车站、机场的安检是日常生活中最常见的例子。最常用的辐射是X射线和γ射线。目前，中子、质子、电子、μ介子、重离子等辐射也获得了越来越广泛的应用。
图像帧可以是影像动画中最小单位的单幅影像画面，相当于电影胶片上的每一个镜头。单帧可以是一副静止的画面，连续的帧形成动画，如电视图像等。通常所说的帧数可以是指1秒钟时间里传输的图片的帧数，也可以理解为图形处理器每秒钟能够刷新几次，通常用fps(Frames Per Second)表示。每一帧都是静止的图像，快速连续地显示帧便形成了运动的假象。高的帧率可以得到更流畅、更逼真的动画。每秒钟帧数(fps)愈多，所显示的动作就会愈流畅。
数模转换器，又称D/A转换器，简称DAC。DAC是把数字量转变成模拟的器件。D/A转换器基本上由4个部分组成，即全电阻网络、运算放大器、基准电源和模拟开关。模数转换器即A/D转换器，简称ADC，它是把连续的模拟信号转变为离散数字信号的器件。
通常对集装箱的检查图像大约是30M-60M字节，在双能模式下每次产生的图像要60-120M字节。如果是双能双视角模式，每次采集的图像可以达到120-240M字节。加上业务产生的图像和数据，整体的数值是非常大的。要把这么大的数据进行有效存储和读取，需要新的存储和读取技术。
针对上述问题，本公开实施例提出采用分区域对图像进行存储和描述，包括基于图像类型、大小、区域，创建时间、修改时间等标准属性中的至少一个，以及应用相关的属性信息(图像所属类型，子区域类型，子区域位深，子区域大小，子区域连续性等)来对图像进行存储和描述。
图1示出了根据本公开实施例的安全检查系统100的结构示意图。如图1所示，根 据本公开实施例的安全检查系统100包括X射线源110、探测器130、数据采集装置150、控制器140、和计算设备160。对诸如集装箱卡车之类的被检查物体120进行安全检查，例如判断其中是否包含了危险品/或可疑物品。虽然在该实施例中，将探测器130和数据采集装置150分开描述，但是本领域的技术人员应该理解也可以将它们集成在一起称为X射线探测和数据采集设备。
根据一些实施例，上述的X射线源110可以是同位素，也可以是X光机或加速器等。X射线源110可以是单能，也可以是双能。通过X射线源110和探测器150以及控制器140和计算设备160对被检查物体120进行透射扫描，得到探测数据。例如在被检查物体120行进过程中，操作人员借助于计算设备160的人机交互界面，通过控制器140发出指令，命令X射线源110发出射线，穿过被检查物体120后被探测器130接收，转换成电信号，再由数据采集设备150转换成数字信号，并且通过计算设备160对数据进行处理。这样可以获得被检查物体120的透射图像。
如图1所示，通过本地线路将获得的透射图像传输到本地的现场图像处理计算机160。现场图像处理计算机160通过公共网络或者专用网络180连接。远程部署的审图计算机191、192和19n可以是例如部署在审图中心的远程图像处理计算机，也与公共网络或者专用网络180连接。
图2示出了计算设备200的结构示意图。如图2所示，探测器130探测的数据信号通过数据采集装置采集，通过接口单元280和总线240将数据存储在存储设备210中。只读存储器(ROM)220中存储有计算机数据处理器的配置信息以及程序。随机存取存储器(RAM)230用于在处理器260工作过程中暂存各种数据。另外，存储器210中还存储有用于进行数据处理的计算机程序，例如物质识别程序和图像处理程序等等。内部总线240连接上述的存储器210、只读存储器220、随机存取存储器230、输入装置250、处理器260、显示设备270和接口单元280。
在用户通过诸如键盘和鼠标之类的输入装置250输入的操作命令后，计算机程序的指令代码命令处理器260执行预定的数据处理算法。在得到数据处理结果之后，将数据处理结果显示在诸如LCD显示器之类的显示设备270上，或者直接以诸如打印之类硬拷贝的形式输出处理结果。
图3示出了在根据本公开的实施例中的计算机300的逻辑架构示意图。如图3所示，本公开实施例中的计算机(计算设备)可以具有四层逻辑结构，例如硬件层310、驱动 层320、操作系统层330和应用程序层340。硬件层310例如包括如图2所示的各种硬件，如CPU、输入装置、存储设备等等。驱动层320包括驱动上述各种硬件的驱动程序，它在硬件层和操作系统之间建立桥梁，使得通过软件可以对硬件进行操作，例如输入/输出等。操作系统是例如Windows或者Linux之类的操作系统，接收外部的输入，分配线程或资源，对数据或者事件进行处理，将处理结果输出。例如，操作系统具有远程登录功能，允许远程计算机登录，也能够登录到其他远程计算机。应用程序层340例如是边缘增强、局部增强、灰度拉伸之类的图像处理程序，能够根据用户的操作对X射线图像进行处理，得到处理结果。
如图1所示，例如包括X射线源110、探测器130、数据采集装置150、控制器140和计算设备160的安全检查子系统可以部署在海关检查站现场，对被检查物体120进行射线扫描，得到被检查对象的射线图像。
部署在检查现场的图像处理计算机170可以包括硬件设备、操作系统和图像处理应用程序，与安全检查子系统通信连接，存储并实时处理X射线图像。
远程部署的审图计算机(图像处理计算机)191、192、19n通过公用网络和/或专用网络与现场部署的图像处理计算机170通信连接，借助远程访问功能登录图像处理计算机170，将现场图像处理计算机170的屏幕远程数据同步至远程图像处理计算机191、192、19n，由远程图像处理计算机处的操作人员进行审图。因为仅仅将屏幕显示的部分数据同步到远程审图计算机，所以不用将被检查物体120的全部射线图像传输到审图计算机，也能够对被检查物体120的射线图像进行审图。
根据本公开实施例，采用分布式的按列存储的方案来存储图像。例如，在进行图像的采集过程中，可以针对不同的车型，预定义不同的出图方案。例如，针对集装箱车辆，可以分为4个区域，分别是车头、车体连接部分、车底盘、车厢。本领域技术人员可以理解，针对其他的应用领域，也可以采用其他的划分模式。
例如，通过将图像属性信息与图像内容存储到一个大表中，可支持图像的多属性综合查询。此外，还可以根据应用需求，对子区域簇进行扩展以保存应用相关信息，从而可以灵活支持应用相关的图像查询。由此，基于子区域的海量图像存储技术不仅实现了图像存储，还实现了灵活的图像子区域检索。利用机器学习，便于对图像的不同区域进行有针对性的训练。特别针对射线产生的大尺寸图像，针对特征区域的保存方式，减少了图像的训练因子，提高了图像训练速度，提升了图像训练结果和整体的图像识别效果。
例如，对图像的存储利用Hbase数据结构进行存储。例如，可以增加校验域和补白域。这样可以验证图像数据的正确性，并且能够对齐Key-Value字节数组，提高读写效率。例如，可以对Key-Value存储结构进行完善，在Value域部分后面增加校验和及补白两个域。校验和可以为8个字节(64位)。通过补充空白部分，使每个Key-Value字节数组大小为8字节的整数倍，从而更加适合64位系统。本领域技术人员可以理解，做了上述调整后，在读写数据时都要进行相应改变。
根据本公开实施例，在写数据时，首先对Value域进行校验和计算，并写入校验和域。然后，计算Key-Value字节数组总大小。如果不是8的整数倍，则在补白域存储一定数量的0x00字节，使之总大小为8的整数倍。
在读数据时，读取Key和Value后，对Value进行校验和计算，并与校验域存储的值进行比较。如果相一致，则说明读出的Value是正确的。
此外，基于HBase的海量图像存储中可以将存储区域的大小设定为小于一个阈值。例如，推荐数据块最大不超过1M，可以将阈值设定为1M。可在具体应用场景，即使大多图像在1M以内，也可能存在少量图像超过1M，从而需要对基于HBase的海量图像存储技术进行改变。例如，将超过数据块限制的文件进行切片，使每片大小小于数据块的尺寸，然后将所有切片进行保存。
此外，根据本公开实施例，记录同一图像的所有子区域，并记录子区域的顺序，以便恢复图像数据。例如，使用HFile单元格的Key-Value字节数组中的的时间戳TimeStamp，也就是使用时间戳TimeStamp来记录存储顺序。可以将图像的所有子区域保存到同样的RowKey、Family(对应图像子区域的性质)。family的类型可以有车头、车体连接部分、车底盘、车厢，按照子区域顺序逐一保存，HBase会自动打上TimeStamp。如此以来，可根据RowKey+Family找到同一图像的所有子区域，然后按照每个子区域TimeStamp的时间顺序合并图像的子区域，即可恢复出原始图像。在其他的实施例中，除了存储时间戳信息外，还可以存储表示各个子区域之间的位置关系的信息，例如车厢在底盘的数据之上等信息。这样使得在读出数据后能够准确将各个子区域组合起来，便于审图。
图4示出了根据本公开的实施例的安全检查系统的方法的示意性流程图。图6示出了根据本公开的实施例中的对车辆的X射线图像按照预定义模式进行分区的示意图。如图6所示，车体图像被划分成车头610、车体连接部分620、车底盘630和车厢640。
如图4所示，在步骤S410，部署在各地海关检查站的安全检查子系统对被检查对象220进行X射线扫描，例如对集装箱卡车进行透射扫描，得到被检查物体的X射线图像。
在步骤S420，将射线图像数据按照预定义的模式划分为多个子区域。例如基于车头610、车体连接部分620、车底盘630、车厢640，在现场图像处理计算机170进行上述操作。
在步骤S430，由现场图像处理计算机170将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间的关系的信息。例如将车头610、车体连接部分620、车底盘630、车厢640的图像数据分别按列存储，并且记录各个子区域的时间戳信息。
现场图像处理计算机170将各个子区域的图像数据存储在HBase数据库中，用各个子区域的时间戳表示反映各个子区域之间的关系的信息。例如，在HBase数据库的Value域后增加校验域以便进行校验和计算。再如，在HBase数据库的Value域后增加补白域，用于将Key-Value字节总数调整为8的倍数。
图5示出了根据本公开的实施例中的安检图像显示方法的示意性流程图。图7示出了根据本公开的另一实施例的在安全检查系统中对各个子区域的图像数据进行组合的示意图。
如图5所示，在将图像数据从现场图像处理计算机传送到远程图像处理计算机之前，可以从HBase数据库中读取数据。在步骤S510，根据数据库中存储的反映各个子区域之间关系的信息，按照列读取各个子区域的图像数据。例如可以根据事先存储的时间戳信息，按照时间先后顺序按列读取各个子区域的图像数据，进行子区域的组合。在此过程中，如果需要事先存储的各个子区域之间的位置关系，则根据位置关系来进一步组合各个子区域。
在步骤S520，在屏幕上显示至少两个子区域组合后的图像，然后将屏幕数据同步到远程图像处理计算机。如上所述，可以对读取的图像数据进行校验和计算，这样可以确保读取数据的正确性。
上述存储技术使用，可以改善射线成像的生成和存储技术，使得生成的图像能够满足分布式存储和大数据深度计算的要求，为智能图像分析和识别提供基础的支持。根据本公开实施例的方法也可以用在其他领域，利用对于图像不同区域进行不同的展示和分析的要求，对图像按照预定义进行分域切分、分域描述、方便后续的计算和深度分析。
以上的详细描述通过使用示意图、流程图和/或示例，已经阐述了安全检查系统和方 法的众多实施例。在这种示意图、流程图和/或示例包含一个或多个功能和/或操作的情况下，本领域技术人员应理解，这种示意图、流程图或示例中的每一功能和/或操作可以通过各种结构、硬件、软件、固件或实质上它们的任意组合来单独和/或共同实现。在一个实施例中，本公开实施例所述主题的若干部分可以通过专用集成电路(ASIC)、现场可编程门阵列(FPGA)、数字信号处理器(DSP)、或其他集成格式来实现。然而，本领域技术人员应认识到，这里所公开的实施例的一些方面在整体上或部分地可以等同地实现在集成电路中，实现为在一台或多台计算机上运行的一个或多个计算机程序(例如，实现为在一台或多台计算机系统上运行的一个或多个程序)，实现为在一个或多个处理器上运行的一个或多个程序(例如，实现为在一个或多个微处理器上运行的一个或多个程序)，实现为固件，或者实质上实现为上述方式的任意组合，并且本领域技术人员根据本公开，将具备设计电路和/或写入软件和/或固件代码的能力。此外，本领域技术人员将认识到，本公开所述主题的机制能够作为多种形式的程序产品进行分发，并且无论实际用来执行分发的信号承载介质的具体类型如何，本公开所述主题的示例性实施例均适用。信号承载介质的示例包括但不限于：可记录型介质，如软盘、硬盘驱动器、紧致盘(CD)、数字通用盘(DVD)、数字磁带、计算机存储器等；以及传输型介质，如数字和/或模拟通信介质(例如，光纤光缆、波导、有线通信链路、无线通信链路等)。
虽然已参照几个典型实施例描述了本公开，但应当理解，所用的术语是说明和示例性、而非限制性的术语。由于本公开能够以多种形式具体实施而不脱离公开的精神或实质，所以应当理解，上述实施例不限于任何前述的细节，而应在随附权利要求所限定的精神和范围内广泛地解释，因此落入权利要求或其等效范围内的全部变化和改型都应为随附权利要求所涵盖。

Claims (16)

  1. 一种安全检查系统，包括：
    至少一个检查子系统，配置为对被检查对象进行射线扫描，得到被检查对象的射线图像数据；
    至少一个本地计算机，与所述至少一个检查子系统通信连接，所述至少一个本地计算机配置为存储所述射线图像数据，
    其中，所述至少一个本地计算机还配置为按照预定义的模式将所述射线图像数据划分为多个子区域，将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间的关系的信息。
  2. 如权利要求1所述的安全检查系统，其中所述至少一个本地计算机被部署在检查现场；所述至少一个本地计算机包括硬件设备、操作系统和图像处理应用程序，所述安全检查系统还包括：
    至少一个远程图像处理计算机，通过公用网络和专用网络中的至少一个与稀少一个所述本地计算机通信连接，至少一个远程图像处理计算机配置为借助远程访问登录所述至少一个本地计算机，将至少一个本地计算机的屏幕数据同步至远程图像处理计算机。
  3. 如权利要求1所述的安全检查系统，其中所述至少一个本地计算机还配置为将各个子区域的图像数据存储在HBase数据库中，并用各个子区域的时间戳表示各个子区域之间的关系。
  4. 如权利要求3所述的安全检查系统，其中所述至少一个本地计算机还配置为在HBase数据库的Value域后增加校验域，以便进行校验和计算。
  5. 如权利要求3所述的安全检查系统，其中所述至少一个本地计算机还配置为在HBase数据库的Value域后增加补白域，用于将Key-Value字节总数调整为8的倍数。
  6. 如权利要求3所述的安全检查系统，其中每个子区域的图像数据的大小小于预定的阈值。
  7. 如权利要求3所述的安全检查系统，其中所述至少一个本地计算机还配置为在HBase数据库中存储表示各个子区域的位置关系的信息。
  8. 如权利要求1所述的安全检查系统，其中所述子区域包括车头、车体连接部分、车底盘和车厢。
  9. 一种安全检查系统的方法，包括：
    通过检查子系统对被检查对象进行射线扫描，得到被检查对象的射线图像数据；
    将所述射线图像数据按照预定义的模式划分为多个子区域；
    由本地计算机将各个子区域的图像数据按照列分别存储，并且还存储表示各个子区域之间的关系的信息。
  10. 如权利要求9所述的方法，还包括：
    建立远程图像处理计算机与所述本地计算机之间的通信连接；
    由所述远程图像处理计算机，借助远程访问登录所述本地计算机，将本地计算机的屏幕数据同步至远程图像处理计算机。
  11. 如权利要求9所述的方法，还包括：由所述至少一个本地计算机将各个子区域的图像数据存储在HBase数据库中，并用各个子区域的时间戳表示反映各个子区域之间的关系的信息。
  12. 如权利要求9所述的方法，还包括：由所述本地计算机在HBase数据库的Value域后增加校验域，以便进行校验和计算。
  13. 如权利要求9所述的方法，还包括：由所述本地计算机在HBase数据库的Value域后增加补白域，以便将Key-Value字节总数调整为8的倍数。
  14. 如权利要求10所述的方法，还包括由所述本地计算机根据数据库中存储的反映各个子区域之间关系的信息，按照列读取各个子区域的图像数据，并且将至少两个子区域组合后的图像数据同步到远程图像处理计算机。
  15. 一种安检图像显示方法，包括：
    根据数据库中存储的反映各个子区域之间关系的信息按照列读取各个子区域的图像数据；以及
    在屏幕上显示至少两个子区域组合后的图像。
  16. 如权利要求15所述的方法，还包括：
    对读取的图像数据进行校验和计算。
PCT/CN2018/120067 2017-12-27 2018-12-10 安全检查系统及其方法以及安检图像显示方法 Ceased WO2019128684A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711452012.8A CN108195855B (zh) 2017-12-27 2017-12-27 安全检查系统及其方法
CN201711452012.8 2017-12-27

Publications (1)

Publication Number Publication Date
WO2019128684A1 true WO2019128684A1 (zh) 2019-07-04

Family

ID=62584850

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/120067 Ceased WO2019128684A1 (zh) 2017-12-27 2018-12-10 安全检查系统及其方法以及安检图像显示方法

Country Status (4)

Country Link
US (1) US20190197722A1 (zh)
EP (1) EP3506122A1 (zh)
CN (1) CN108195855B (zh)
WO (1) WO2019128684A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108195855B (zh) * 2017-12-27 2023-11-03 同方威视技术股份有限公司 安全检查系统及其方法
CN111368836A (zh) * 2018-12-25 2020-07-03 北京京东尚科信息技术有限公司 信息处理方法、装置、电子设备及介质
CN112598690B (zh) * 2020-12-11 2025-01-07 浙江大华技术股份有限公司 一种包裹切分方法、装置、设备及介质
CN113177982B (zh) * 2021-04-16 2023-03-10 杭州睿影科技有限公司 安检图像数据的处理方法、装置、设备及系统
CN113139950B (zh) * 2021-05-08 2024-04-16 佳都科技集团股份有限公司 一种目标对象识别的方法及装置
CN113554598B (zh) * 2021-06-24 2025-03-11 浙江大华技术股份有限公司 物品检测方法、装置、电子设备、计算机可读存储介质
CN115829502B (zh) * 2022-11-28 2026-07-10 同方威视科技江苏有限公司 机检查验任务展示方法、装置与电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320505A (zh) * 2008-07-04 2008-12-10 浙江大学 基于多路网络视频流并行处理的分区视频监控方法
JP2012216221A (ja) * 2012-06-04 2012-11-08 Meidensha Corp 作業者安全検査装置
CN104427310A (zh) * 2013-09-04 2015-03-18 杭州海康威视数字技术股份有限公司 图像存储方法及其装置
CN105869118A (zh) * 2016-04-19 2016-08-17 北京君和信达科技有限公司 安检服务器、移动检查终端、系统及处理安检图像的方法
CN106503121A (zh) * 2016-10-19 2017-03-15 公安部第三研究所 一种x光安检图像的结构化描述方法及系统
CN106934326A (zh) * 2015-12-29 2017-07-07 同方威视技术股份有限公司 用于安全检查的方法、系统和设备
CN108195855A (zh) * 2017-12-27 2018-06-22 同方威视技术股份有限公司 安全检查系统及其方法

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SG121906A1 (en) * 2004-10-11 2006-05-26 Stratech Systems Ltd Intelligent vehicle access control system
CN101699388A (zh) * 2009-11-18 2010-04-28 英华达(南昌)科技有限公司 一种用于液晶显示画面的图像处理方法及系统
KR101430121B1 (ko) * 2010-04-06 2014-08-14 삼성전자주식회사 멀티-에너지 Ｘ－ｒａｙ 시스템의 영상 처리 장치 및 그 방법
US8532383B1 (en) * 2010-09-16 2013-09-10 Pixia Corp. Method of processing a viewport within large format imagery
CN102651148A (zh) * 2011-02-24 2012-08-29 刘中库 安检值机监控系统的监控方法
CN103036981B (zh) * 2012-12-13 2015-10-14 北京奇虎科技有限公司 一种远程数据传输设备及方法
CN103018259B (zh) * 2012-12-18 2015-07-01 华南理工大学 基于嵌入式构架的多区域分割视觉检测系统及检测方法
JP6470567B2 (ja) * 2014-02-03 2019-02-13 株式会社プロスパークリエイティブ 画像検査装置及び画像検査プログラム
CN105445808B (zh) * 2014-08-19 2018-10-02 清华大学 对移动目标进行检查的设备及方法
CN104391338B (zh) * 2014-12-17 2018-11-16 清华大学 多剂量分区域扫描的车辆快速检查系统及方法
CN105787495A (zh) * 2014-12-17 2016-07-20 同方威视技术股份有限公司 具有车辆参考图像检索及比对功能的车辆检查系统和方法
CN104902193B (zh) * 2015-05-19 2018-06-22 上海集成电路研发中心有限公司 一种基于fpga对图像数据进行分割处理和显示的方法
CN105469374A (zh) * 2015-12-05 2016-04-06 中国航空工业集团公司洛阳电光设备研究所 一种高速大容量红外图像数据实时显示方法
CN206208795U (zh) * 2016-06-14 2017-05-31 广东和创电子科技有限公司 便携式x射线检查系统
CN106327421A (zh) * 2016-09-13 2017-01-11 首都师范大学 一种图像数据存储方法及装置
CN206431070U (zh) * 2017-01-25 2017-08-22 同方威视技术股份有限公司 安全检查系统
CN117571758A (zh) * 2017-01-25 2024-02-20 同方威视技术股份有限公司 安全检查系统
CN107515952B (zh) * 2017-09-21 2023-10-27 北京星闪世图科技有限公司 点云数据存储、并行计算和实时检索的方法及其系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320505A (zh) * 2008-07-04 2008-12-10 浙江大学 基于多路网络视频流并行处理的分区视频监控方法
JP2012216221A (ja) * 2012-06-04 2012-11-08 Meidensha Corp 作業者安全検査装置
CN104427310A (zh) * 2013-09-04 2015-03-18 杭州海康威视数字技术股份有限公司 图像存储方法及其装置
CN106934326A (zh) * 2015-12-29 2017-07-07 同方威视技术股份有限公司 用于安全检查的方法、系统和设备
CN105869118A (zh) * 2016-04-19 2016-08-17 北京君和信达科技有限公司 安检服务器、移动检查终端、系统及处理安检图像的方法
CN106503121A (zh) * 2016-10-19 2017-03-15 公安部第三研究所 一种x光安检图像的结构化描述方法及系统
CN108195855A (zh) * 2017-12-27 2018-06-22 同方威视技术股份有限公司 安全检查系统及其方法

Also Published As

Publication number Publication date
CN108195855B (zh) 2023-11-03
US20190197722A1 (en) 2019-06-27
CN108195855A (zh) 2018-06-22
EP3506122A1 (en) 2019-07-03

Similar Documents

Publication Publication Date Title
CN108195855B (zh) 安全检查系统及其方法
US8831305B2 (en) Pseudo dual-energy material identification system and method with undersampling
WO2019128683A1 (zh) 安全检查系统及检查方法
US10297050B2 (en) Methods for positioning a target in a three-dimensional CT image and CT systems for security inspection
JP2018113038A (ja) 検査機器および荷物における銃器を検出する方法
Khor et al. Region of interest-based tamper detection and lossless recovery watermarking scheme (ROI-DR) on ultrasound medical images
US10145977B2 (en) Method for positioning target in three-dimensional CT image and security check system
EP3416562B1 (en) System and method for medical imaging
US12046355B2 (en) Method and system for web-based medical image processing
CN112183583A (zh) 一种注意力导向的太赫兹图像中的小目标检测方法
Jiang MFCT-GAN: multi-information network to reconstruct CT volumes for security screening
Wu et al. End-to-end lung nodule detection in computed tomography
US20130076747A1 (en) Processing and Rendering of Large Image Files
Hu et al. Super‐Resolution Swin Transformer and Attention Network for Medical CT Imaging
WO2016095776A1 (zh) 一种定位三维ct图像中的目标的方法和安检ct系统
Perlman Visualizing and interacting with large imaging data
AU2022200601B2 (en) Apparatus and method for visualizing digital breast tomosynthesis and anonymized display data export
Tsai et al. Cascading AB‐YOLOv5 and PB‐YOLOv5 for rib fracture detection in frontal and oblique chest X‐ray images
Jia et al. Research on Improved Ray Casting Algorithm and Its Application in Three‐Dimensional Reconstruction
US11501121B2 (en) Binomial subsample data augmented CNN for image classification
US10803593B2 (en) Method and system for image compression
CN107221015A (zh) 一种基于时空标签技术的医学成像方法及系统
Greggio et al. Exploring digital twinning in MRI: A systematic review of current applications, barriers, and future opportunities
Macnab et al. Detectability of small objects in PET/computed tomography phantom images with Bayesian penalised likelihood reconstruction
Fan et al. Track Foreign Object Image Augmentation Based on the Proposed PLCA-pix2pixGAN Method

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: 18895520

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: 18895520

Country of ref document: EP

Kind code of ref document: A1