CN114113165A - Luggage interpretation method for security inspection equipment - Google Patents
Luggage interpretation method for security inspection equipment Download PDFInfo
- Publication number
- CN114113165A CN114113165A CN202111516258.3A CN202111516258A CN114113165A CN 114113165 A CN114113165 A CN 114113165A CN 202111516258 A CN202111516258 A CN 202111516258A CN 114113165 A CN114113165 A CN 114113165A
- Authority
- CN
- China
- Prior art keywords
- image
- equipment
- luggage
- security check
- judging
- 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.)
- Granted
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
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/03—Investigating materials by wave or particle radiation by transmission
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/10—Different kinds of radiation or particles
- G01N2223/101—Different kinds of radiation or particles electromagnetic radiation
- G01N2223/1016—X-ray
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention relates to a luggage interpretation method for security check equipment, belongs to the technical field of security check, and solves the problem that the luggage interpretation method in the prior art can not provide a reasonable data acquisition mode for interpretation according to whether the security check equipment has a networking function or not. The method comprises the following steps: acquiring equipment information of the security check equipment, judging whether the security check equipment has a networking function, if so, accessing the security check equipment to a network, and acquiring an X-ray image formed by the security check equipment for interpretation processing; if not, the security check equipment is connected with the security check machine networking equipment through a video line, the security check machine networking equipment is connected into a network, the security check machine networking equipment collects video signals output by the security check equipment through the video line, and then X-ray images are obtained for interpretation processing.
Description
Technical Field
The invention relates to the technical field of security inspection, in particular to a luggage interpretation method for security inspection equipment.
Background
With the continuous development of informatization and networking technologies, especially the implementation of 5G communication technologies, networking of security check devices is becoming a common trend. Newly developed and produced equipment is provided with a networking module, networking functions are integrated in security check equipment, but a large part of existing security check equipment does not have the networking functions. For the security inspection equipment without networking function, the X-ray image generated by the security inspection equipment is usually output to a display, and a security inspector interprets the X-ray image through image information on the display, so that the security inspection equipment is difficult to adapt to the intelligent requirement of the security inspection equipment along with the development of the times; because the X-ray image can be directly obtained by the security inspection equipment with the networking function during interpretation, the X-ray image is difficult to directly obtain by the security inspection equipment without the networking function, so that the interpretation method of the security inspection equipment with the networking function is difficult to directly apply to the security inspection equipment without the networking function, and the networking of the security inspection equipment is realized by upgrading the hardware and software of the security inspection equipment, so that the cost is high, and the difficulty is high. Therefore, a method for judging a row packet is urgently needed, which can provide a reasonable data acquisition mode for judging according to whether the security check equipment has a networking function, and meets the intelligent requirement for judging of the security check equipment.
Disclosure of Invention
In view of the foregoing analysis, an embodiment of the present invention is directed to provide a row packet interpretation method for a security inspection device, so as to solve a problem that the conventional row packet interpretation method cannot provide a reasonable data acquisition manner for interpretation according to whether the security inspection device has a networking function.
The embodiment of the invention provides a luggage interpretation method for security inspection equipment, which comprises the following steps:
acquiring the equipment information of the security check equipment, judging whether the security check equipment has the networking function or not,
if yes, accessing the security check equipment to a network, and acquiring an X-ray image formed by the security check equipment for interpretation processing;
if not, the security check equipment is connected with the security check machine networking equipment through a video line, the security check machine networking equipment is connected into a network, the security check machine networking equipment collects video signals output by the security check equipment through the video line, and then X-ray images are obtained for interpretation processing.
Further, the security machine networking device acquires the X-ray image by performing the following operations:
the method comprises the steps of obtaining the on-off state of current security check equipment, and starting to obtain a video signal output by the current security check equipment when the current security check equipment is started;
and sequentially acquiring an X-ray image of luggage objects in the video signal according to each original frame image of the video signal.
Further, the X-ray images of the luggage items in the video signal are sequentially acquired by executing the following steps:
sequentially acquiring original frame images in the video signal, performing gray level conversion to obtain gray level frame images, and performing the following processing:
extracting k columns of data of the previous gray frame image from the initial column as a reference window; wherein k is greater than or equal to 1;
sliding a reference window column by column from an initial column in a current gray frame image, and acquiring the number of sliding columns of the reference window at the moment if column data same as that of the reference window is matched;
acquiring line data from an initial line to the sliding line number in an original frame image corresponding to the current gray frame image as an X-ray image of the row packet object generated by the current security inspection equipment;
wherein the initial column of the original frame image or the gray frame image corresponds to the column of the video signal in which the X-ray image is displayed first.
Further, the X-ray image is subjected to interpretation processing by performing the following steps:
sequentially numbering the column data of the obtained X-ray image, and judging a row packet image to which each column data belongs;
matching corresponding image judging terminals for each row of packet images in sequence based on the generation sequence of each row of packet images;
sequentially sending the acquired column data of the row packet images matched with the image judging terminal generated by the current security check equipment to the corresponding image judging terminal;
and sequentially displaying the column data by the image judging terminal according to the received serial numbers of the column data to form corresponding row packet images, further judging and reading, and returning a judging and reading result.
Further, security check machine networking equipment still includes:
judging a row packet image to which each column of data belongs based on the acquired X-ray image;
and intelligently judging the images of all the luggage images, judging whether the corresponding luggage objects are suspicious or not, and marking the luggage images of the suspicious luggage objects.
Further, security check machine networking equipment still includes:
acquiring security inspection equipment information, and uploading each row of packet images, corresponding label information and the security inspection equipment information to a remote server; the safety inspection equipment information comprises a safety inspection equipment model and GPS positioning information.
Further, the intelligently judging the image of each luggage image, judging whether the corresponding luggage object is suspicious, and marking the luggage image of the suspicious luggage object specifically comprises:
extracting the class characteristics of each row of bag images, and comparing the class characteristics with the class characteristics of each suspicious article stored in the security check machine networking equipment respectively;
if the classification characteristics of the suspicious articles are consistent with those of any suspicious articles, judging that the luggage articles corresponding to the luggage image are suspicious articles, and marking the luggage image.
Further, the matching of the image judging terminal corresponding to each row of packet images in turn includes:
detecting whether an idle state image judging terminal exists in the range of the available image judging terminal of the current security inspection equipment based on a preset condition;
if the image judging terminal in the idle state exists, taking the image judging terminal in the idle state at the earliest as the image judging terminal corresponding to the line packet image;
further, the sending the acquired column data of the row packet image matched with the image judging terminal generated by the current security inspection device to the corresponding image judging terminal includes:
establishing communication connection between the current security check equipment and a picture judgment terminal corresponding to the luggage image;
sequentially sending the column data belonging to the row packet image to the corresponding image judging terminal according to a set mode;
and when receiving the interpretation result returned by the corresponding image interpretation terminal, disconnecting the communication connection with the corresponding image interpretation terminal.
Further, the sending the column data belonging to the row packet image to the corresponding graph determining terminal according to the set mode includes:
and sequentially sending the acquired column data which are generated by the current security inspection equipment and belong to the row packet image to corresponding image judgment terminals by taking k columns as a group, wherein if the column data which belong to the row packet image are not more than k columns at last, the rest column data are taken as a group to be sent to the corresponding image judgment terminals, wherein k is more than or equal to 1 and less than the total column number of the row packet image column data.
Compared with the prior art, the invention can realize the following beneficial effects:
according to the luggage interpretation method for the security inspection equipment, provided by the invention, the X-ray image is directly obtained in the security inspection equipment with the networking function, the video signal which can be directly obtained is processed for the security inspection equipment without the networking function to obtain the X-ray image, the X-ray image is further interpreted, different X-ray image obtaining modes are provided according to whether the security inspection equipment has the networking function, the interpretation processing is further carried out, and the development requirement of the security inspection equipment can be better met; the security check equipment without the networking function is accessed to the network through the networking equipment of the security check machine, centralized interpretation can be simultaneously adopted with the security check equipment with the networking function, the workload of workers is balanced, the waste of the workers is avoided, the interpretation speed is improved, and the requirement of centralized interpretation of the security check equipment along with the development of the times is met; in addition, the security check equipment without the networking function is accessed into the network through the networking equipment of the security check machine, the acquired X-ray image can be intelligently judged, the X-ray image is uploaded to a remote server to be stored, the information such as the security check image acquired by the security check equipment in the actual service is conveniently stored and managed in a centralized manner through the network, and the backtracking query after the problem occurs is facilitated.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a schematic flowchart of a row packet interpretation method for a security inspection apparatus according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a process of acquiring an X-ray image when a security inspection apparatus does not have a networking function according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a centralized interpretation based on X-ray images according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a security inspection apparatus without a networking function in the embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
A specific embodiment of the present invention discloses a luggage interpretation method for a security inspection apparatus, as shown in fig. 1, including:
acquiring equipment information of the security inspection equipment, and judging whether the security inspection equipment has a networking function;
specifically, the device information of the security inspection device is a technical manual of the security inspection device, and whether the security inspection device has a networking function is judged according to whether the technical manual contains networking configuration information.
And if the security check equipment is available, accessing the security check equipment to a network, and acquiring the X-ray image formed by the security check equipment for interpretation processing.
If not, the security check equipment is connected with the security check machine networking equipment through a video line, the security check machine networking equipment is connected into a network, the security check machine networking equipment collects video signals output by the security check equipment through the video line, and then X-ray images are obtained for interpretation processing. Wherein, security check machine networking equipment possesses the networking function.
Specifically, network access information points are arranged around the security check equipment, and the security check equipment with a networking function or security check machine networking equipment with a networking function is connected with the network access information points, so that the security check equipment can be accessed to a network; the network can also be accessed by means of a wireless connection.
It is understood that the video signal of the security check device is a frame image generated from an X-ray image formed by the security check device, and the output video signal shows the change of the X-ray image frame by frame. The security check equipment with the networking function can extract the X-ray image and transmit the X-ray image through a network in the process of forming the X-ray image in the security check equipment, the security check equipment without the networking function cannot obtain the X-ray image in the security check equipment, and only the video signal generated by the security check equipment according to the X-ray image can be obtained at the output end of the security check equipment, so that the security check equipment with the networking function can directly obtain the formed X-ray image for interpretation, the security check equipment without the networking function cannot directly take out the X-ray image and can only obtain the output video signal for processing, and therefore, the X-ray image obtaining mode selected by the networking function is selected according to the fact that the security check equipment does not have the networking function.
Compared with the prior art, the luggage interpretation method provided by the embodiment directly acquires the X-ray image in the security inspection equipment with the networking function, processes the video signal which can be directly acquired to obtain the X-ray image for the security inspection equipment without the networking function, further interprets the X-ray image, provides different X-ray image acquisition modes according to whether the security inspection equipment is networked or not, and further interprets the X-ray image, and can better adapt to the development requirements of the security inspection equipment.
It should be noted that, as shown in fig. 4, the security check machine networking device is configured with an HDMI video input port, a video signal output by each security check device is converted into an HDMI signal through a conversion line and output to the HDMI video input port of the security check machine networking device, and the input video signal of the security check machine networking device is analyzed and processed, which is specifically as follows:
in practice, as shown in fig. 2, the security machine networking device acquires an X-ray image by performing the following operations:
the method comprises the steps of obtaining the on-off state of current security check equipment, and starting to obtain a video signal output by the current security check equipment when the current security check equipment is started;
and sequentially acquiring an X-ray image of luggage objects in the video signal according to each original frame image of the video signal.
Specifically, the security check machine networking equipment sets monitoring at a video signal output end of the security check equipment, and judges that the security check equipment is started when a video signal is generated; and when the video signal disappears, judging that the security check equipment is powered off. Preferably, when the change of the on-off state of the security inspection equipment is acquired, the security inspection equipment information, the on-off state of the security inspection equipment and the state change time of the current security inspection equipment are uploaded to a server for storage, so that the security inspection equipment is subjected to service-related data processing and analysis in the later period.
When the method is implemented specifically, the X-ray images of luggage articles in the video signal are sequentially acquired by executing the following steps:
sequentially acquiring original frame images in the video signal, performing gray level conversion to obtain gray level frame images, and performing the following processing:
extracting k columns of data of the previous gray frame image from the initial column as a reference window; wherein k is greater than or equal to 1;
sliding a reference window column by column from an initial column in a current gray frame image, and acquiring the number of sliding columns of the reference window at the moment if column data same as that of the reference window is matched;
acquiring line data from an initial line to the sliding line number in an original frame image corresponding to the current gray frame image as an X-ray image of the row packet object generated by the current security inspection equipment;
wherein the initial column of the original frame image or the gray frame image corresponds to the column of the video signal in which the X-ray image is displayed first
Preferably, time information is added to each column data of the obtained X-ray image, wherein the time information is the generation time of the original frame image in which the obtained X-ray image is located.
It should be noted that if the current gray frame image does not have the previous gray frame image, the current gray frame is not processed; or, the background gray frame image is used as the previous gray frame image of the current gray frame image; the background gray frame image is a frame image which is generated when the security inspection equipment does not scan the luggage objects and does not contain the gray conversion of the original frame image in the video signal of the X-ray image of the luggage objects.
It can be understood that, the reference window is slid column by column from the initial column in the current gray frame image, and if the column data same as the reference window is not matched, it is determined that newly formed X-ray image column data does not exist in the current gray frame image, and the column data extraction is not performed on the original frame image corresponding to the current gray frame image.
Optionally, the security check machine networking device further includes:
judging a row packet image to which each column of data belongs based on the acquired X-ray image;
and intelligently judging the images of all the luggage images, judging whether the corresponding luggage objects are suspicious or not, and marking the luggage images of the suspicious luggage objects.
Specifically, the safety inspection machine networking equipment integrates the sound and light warning device, and when a certain luggage article is marked as suspicious, the sound and light warning device can be used for reminding.
Further, security check machine networking equipment still includes:
acquiring security inspection equipment information, and uploading each row of packet images, corresponding label information and the security inspection equipment information to a remote server; the safety inspection equipment information comprises a safety inspection equipment model and GPS positioning information.
It should be noted that the acquired X-ray image can be uploaded to a remote server directly through a security check machine networking device without intelligent interpretation marking.
Specifically, the security check machine networking device integrates wired and wireless network interfaces, can set a local IP address and a server IP address, and automatically uploads the obtained security check device luggage image, corresponding marking information and security check device information to a specified remote server for storage.
It can be understood that the marked luggage image is uploaded to a remote server, so that the image generated by the security inspection equipment can be centrally stored and centrally managed through a network, and the backtracking query is convenient when a problem occurs in the later stage; meanwhile, the security check equipment information and the luggage image are uploaded together, so that the image data of each security check equipment can be distinguished.
More preferably, the quantity of the luggage articles is counted according to the luggage images obtained by each security inspection device, and the luggage images are uploaded to a designated server, so that the workload of a security inspector and a security inspection machine can be determined, performance evaluation or other service purposes can be performed, and the service requirements can be met.
Optionally, the output port of the security check machine networking device may be connected to a display matched with the original X-ray security check device through a video conversion line, and the received video signal may be selectively kept unchanged and output to the display matched with the X-ray security check device for display as it is, or the marked luggage images may be selectively output to the display matched with the X-ray security check device in sequence for display.
In specific implementation, the intelligent image judgment is performed on each luggage image, whether a corresponding luggage article is suspicious is judged, and the luggage image of the suspicious luggage article is marked, specifically:
extracting the class characteristics of each row of bag images, and comparing the class characteristics with the class characteristics of each suspicious article stored in the security check machine networking equipment respectively;
if the classification characteristics of the suspicious articles are consistent with those of any suspicious articles, judging that the luggage articles corresponding to the luggage image are suspicious articles, and marking the luggage image.
Illustratively, the intelligent judging graph model can be obtained by adopting the following method to further perform intelligent judging graph:
the method comprises the following steps of (1) contraband ray security inspection image data set production: obtaining a training sample of a radiographic image through scanning and shooting, respectively setting corresponding labels for different types of articles in each local area in the training sample, storing position information of the types of articles, and creating a radiographic image sample library; wherein the classes of the training samples include: the portable dangerous goods and the taxation goods which are forbidden to be carried and transported are specified by national laws and regulations such as cutters, police instruments, metal compression tanks, guns, blasting equipment, firework products and the like, the data set mainly comprises real samples and manual labels, and the data set is supplemented by combining with the dangerous goods samples which are manually placed.
Establishing an image recognition algorithm: according to the intelligent visible light image identification technology foundation and the algorithm framework, the deep convolutional neural network method is migrated to the function of identifying contraband in the aiming at the radiation image, the network structure is adjusted aiming at the specific scene characteristics, and the internal parameters are optimized and debugged; the specific scene is a typical scene of a civil aviation airport, and mass people flow and logistics distribution places such as stations and customs are taken into consideration.
Training a neural network model for image recognition; training and constructing a trained neural network model by using the labeled image data set, and training a neural network by adopting a parallel training method; the sample characteristics are automatically extracted through a computer, and high-quality detection accuracy and high real-time identification efficiency are realized. The method specifically comprises the following steps: designing an area generation network by using a convolution network, training aiming at a task for generating a detection suggestion frame, and simultaneously predicting the boundary and the score of an article; the generated suggestion region is accessed to two full connection layers and is respectively used for classification and frame regression; the full-connection layer used for classification comprises 2 elements and is used for judging the estimated probability of a target and a non-target; selecting the front recommended region as a candidate region according to the score of the recommended region, and performing target detection as the input of a detection neural network; and (4) judging the window type by utilizing the classification network, and finishing the correction of the position of the classification network window by utilizing a multitask loss function frame regression method.
Performing multi-model and multi-scene adaptation on the trained neural network model to obtain an intelligent judging map model; the high-speed light-weight network model and the high-accuracy large-scale network are fused step by step, and the various, high-speed and high-accuracy detection and identification of the contraband images are realized. Meanwhile, the definitions of contraband products oriented to different industries have obvious differences, and the automatic high-speed detection of dangerous goods is realized by evaluating the identification of the types of the contraband products according to different security scenes.
And judging the X-ray image of the luggage by using the obtained intelligent judging graph model, and judging whether the luggage is suspicious. When the radiographic image needs to be identified, inputting the radiographic image into the trained neural network model, firstly extracting features through a convolutional neural network, then carrying out regression correction according to a change window of a regression parameter prediction window, and finally marking the article type and a window area after the prediction correction.
Preferably, the security check machine networking device can be set through the following parameters:
the integrated ARM system is not larger than 450 × 250 × 95mm in overall size, integrates a CPU of an ARM instruction set and is not lower than an embedded operating system of android 7.1, integrates not less than 1 video input and 2 video outputs, integrates 5G and 2.4 GWIFISI in support, is independent and double-antenna, integrates a network interface not lower than 1000M, integrates a Graphics Processing Unit (GPU) with a video memory not lower than 2GB, integrates a solid state disk storage not lower than 64GB, and has the working temperature range of-20-60 ℃, the storage temperature range of-40-85 ℃ and the humidity environment of 5% -90% (without condensation). Through the setting, the video signal can be better set on the security check equipment without causing space interference, and the video signal is received and processed by the security check equipment, so that the intelligent interpretation requirement is met, and the interpretation result can be uploaded to a designated server for centralized management and storage.
It should be noted that when the security inspection device has a networking function, the X-ray image formed by the security inspection device is directly obtained, and when the security inspection device does not have the networking function, the X-ray image formed by the security inspection device is obtained based on the security inspection machine networking device, and is transmitted to the image judging terminal based on the obtained X-ray image, so as to perform centralized interpretation, specifically as follows:
in practice, as shown in fig. 3, the X-ray image is interpreted by performing the following steps:
s1, sequentially numbering the column data of the obtained X-ray image, and judging a row packet image to which each column data belongs;
specifically, for the security inspection equipment with the networking function, after the security inspection equipment is started, the serial numbering is carried out from the first column data of the X-ray image which is formed till the security inspection equipment is closed, namely, the column data belonging to different row packet images are not numbered again; for the security inspection equipment without the networking function, when the video signals begin to be generated, the first column data of the X-ray images which are acquired at the beginning are numbered continuously until the video signals disappear.
In step S1, the determining the row packet image to which each column of data belongs includes:
s11, if the column data generated by m continuous columns of the current row packet image from the initial column data are all larger than the air value image data, judging that the current row packet image is a normal row packet image; the air value image data is image data which does not contain luggage articles; wherein the value of m is related to the size of the luggage and is more than or equal to 1; it can be understood that, when the row packet image to which the column data belongs is judged, firstly, the generated column data is classified into one row packet image, and then whether the generated column data belongs to the same row packet image is judged, that is, after the initial column data is classified into the current row packet image, the subsequently generated column data is sequentially judged, and if all the subsequently generated m columns of data meet the above conditions, the current row packet image is considered to be the normal row packet image.
Specifically, after the radiation source and the detector of the current X-ray security inspection apparatus are already established, the image data value acquired when the current security inspection apparatus does not inspect any luggage article, that is, after the radiation is turned on toward an empty channel, is acquired as the background value, that is, the air value image data, on which the row-pack image to which the column data belongs is judged.
Specifically, if the column data generated by m consecutive columns of the current row packet image from the initial column data is not all greater than the air value image data, the current row packet image is judged to be an abnormal row packet image, the next column data of the column data of which the last column is less than or equal to the air value image data in the column data generated by m consecutive columns of the initial column data is used as the initial column data of the current row packet image, the judgment is performed again, and other data are used as abnormal data and are not processed.
S12, after the row packet image is judged to be normal, if column data generated by n continuous columns are less than or equal to air value image data, judging that the generation of the column data of the current row packet image is finished, taking the last column of column data before the column data generated by the n continuous columns as the last column of column data of the current row packet image, and taking the column data, which is larger than the air value image data, of the first column after the column data generated by the n continuous columns as the initial column data of the next row packet image, wherein the column data, which is larger than the air value image data, of the first column generated after the current security inspection equipment is started is taken as the initial column data of the first row packet image; wherein n is greater than or equal to 1. It can be understood that after the row packet image is judged to be normal, the determination of the row packet image column data is started again after the current row packet image is generated from the initial column data until the last column data is determined to be the column data of the current row packet image.
Preferably, m and n can be configured according to different security check equipment models and different application scenes, and for a 6550 model security check equipment for checking common passenger carry-on luggage, the m and n are configured to be 8.
It should be noted that, if there is a distance between two consecutive adjacent row-pack objects to be inspected in the security inspection apparatus, which can be distinguished according to the radiographic image, the row-pack data of the column data can be judged in the above manner; however, when there is no space between two adjacent row-pack articles to be inspected in the security inspection equipment, and even the row-pack images may be overlapped, the row-pack images formed cannot be distinguished according to the radiographic image, and therefore, the row-pack data to which the column data belongs is also judged in the following manner.
Preferably, in step S1, the determining the row packet image to which each column of data belongs further includes:
after the row packet image is judged to be normal, if the number of the columns from the initial column data of the current row packet image to the newly generated column data is a set column number threshold value and all the column data are greater than the air value image data, the newly generated column data is used as the last column data of the current row packet image, and the generated next column data is used as the initial column data of the next row packet data. That is, after the initial column data, until the column data with the column number being the threshold of the column number is generated, the column data of the image data less than or equal to the air value continuously does not exist, and the current row packet image is forced to be segmented.
Specifically, the set column number threshold is based on the maximum length of the row packet image corresponding to the detected row packet article in the actual use scene of the current security inspection device, that is, the total column number of the row packet image.
And S2, matching the corresponding graph judging terminals for each line packet image in sequence based on the generation sequence of each line packet image. It can be understood that, in the process of acquiring the current security inspection device to form each row of package images, the corresponding graph judgment terminals are sequentially matched.
In step S2, the matching of the graph determining terminals corresponding to each row packet image in sequence includes:
detecting whether an idle state image judging terminal exists in the range of the available image judging terminal of the current security inspection equipment based on a preset condition;
and if the image judging terminal in the idle state exists, taking the image judging terminal in the idle state as the image judging terminal corresponding to the line packet image.
Specifically, the preset condition may be a service attribute, for example, the service attribute may be an airport service, a subway service, a railway service, or the like, and the map determination terminal defines a range according to the service attribute and determines an available map determination terminal of the current security inspection device.
Specifically, after the initial column data of each row of packet images which are not matched with the graph judging terminal is generated, whether the graph judging terminal in an idle state exists or not is detected within the range of the available graph judging terminal of the current security inspection equipment, a detection time interval is set according to an actual situation, and detection is continuously performed when the corresponding graph judging terminal is not matched, that is, the row packet images are sequentially matched with the corresponding graph judging terminal according to the generation sequence of the row packet images, the row packet images which are generated earliest are preferentially matched with the corresponding graph judging terminal, and then the next row packet images are sequentially matched; and when all the generated luggage images of the current security inspection equipment are matched with the corresponding image judgment terminals, ending the detection.
For example, for a security inspection device with a networking function, after initial column data of a row packet image not matched with a graph judging terminal is generated, whether a graph judging terminal in an idle state exists or not is detected within a range of an available graph judging terminal of the current security inspection device, if no graph judging terminal in the idle state exists, after the initial column data, each column of column data is generated, and the graph judging terminal within the range of the available graph judging terminal is detected once until the row packet image is matched with a corresponding terminal. More specifically, if the current row packet image is generated and not matched with the corresponding graph judging terminal, detecting the next image by generating one column of data once, if an idle graph judging terminal is found, taking the graph judging terminal as the earliest generated row packet image which is not matched with the corresponding graph judging terminal, and so on, matching the corresponding graph judging terminal for the row packet image which is not matched with the corresponding graph judging terminal until the row packet images are all matched with the corresponding graph judging terminal, and ending the detection; that is, the time interval of column data generation is taken as the time interval of detection.
Preferably, the matching of the image judging terminal corresponding to each row of packet images in turn further includes:
and if the graph judging terminal in the idle state is not detected within the set time threshold, the graph judging terminal is not matched with the luggage image, the luggage image is judged locally, and the result is displayed and stored. It can be understood that if the graph judging terminal in the idle state is not detected after the time threshold is exceeded, the luggage image exceeds the set time of centralized interpretation, and the luggage image is directly interpreted, displayed and stored locally, so that delay in interpretation of the luggage image is avoided.
Specifically, the set time threshold may be set according to actual conditions.
S3, sequentially sending the acquired column data of the row packet images matched with the image judging terminal generated by the current security check equipment to the corresponding image judging terminal; it can be understood that the acquired row packet images of the matched graph judging terminals generated by the current security inspection device may include a plurality of row packet images, and the current security inspection device or the security inspection machine networking device may simultaneously transmit column data of each row packet image to the corresponding graph judging terminal.
In implementation, in step S3, the sending, to the corresponding image determination terminal, the acquired column data of the row packet image that is generated by the current security inspection device and matches the image determination terminal includes:
s31, establishing communication connection between the current security inspection equipment and the image judgment terminal corresponding to the luggage image;
s32, sequentially sending the column data belonging to the row packet image to the corresponding graph judging terminal according to a set mode;
and S33, when receiving the interpretation result returned by the corresponding graph judging terminal, disconnecting the communication connection with the corresponding graph judging terminal.
It should be noted that the security inspection equipment with the networking function directly establishes communication connection with the corresponding image judgment terminal; the security check equipment without networking function establishes connection with the corresponding graph judging terminal through the security check machine networking equipment; and the current security check equipment or the security check machine networking equipment actively breaks the communication connection with the corresponding graph judging terminal after receiving the interpretation result returned by the corresponding graph judging terminal.
Specifically, after the row packet image is matched with the corresponding graph judging terminal, the current security check device or the security check machine networking device is in communication connection with the graph judging terminal immediately.
More specifically, the communication connection is a network-based Socket connection, and the graph judging terminal is used as a connection server to always start monitoring; the security check equipment or the security check machine networking equipment sends a connection request to the corresponding graph judging terminal; after the graph judging terminal receives the connection request, connection is established; after the image judging terminal finishes the interpretation, the interpretation result is sent to the security check equipment or the security check machine networking equipment through the connection session; and the security check equipment or the security check machine networking equipment actively disconnects the connection with the image judging terminal after receiving the judging result.
More specifically, whether the connection is established successfully or not is judged through the network state, if the connection is not established successfully, the connection is firstly tried for a plurality of times, if the connection is not established successfully, the image judging terminal is marked as a fault, the image judging terminal is deleted from the matching range in the later period, and other image judging terminals are matched for the current luggage image again.
In step S32, the sending the column data belonging to the row packet image to the corresponding graph determining terminal according to the set mode includes:
and sequentially sending the column data which are generated by the current security inspection equipment and belong to the row packet image to corresponding image judgment terminals by taking k columns as a group, wherein if the column data which belong to the row packet image are not more than k columns finally, the rest column data are sent to the corresponding image judgment terminals by taking the rest column data as a group, wherein k is more than or equal to 1 and less than the total column number of the row packet image column data. It can be understood that the column data of the row packet image is transmitted in a group of k columns, and the transmission can be started in the process of forming the row packet image, so that the time delay caused by the need of transmitting the whole row packet image after being formed is avoided. Illustratively, k is set to 1, which represents that the security check device transmits column data column by column.
Specifically, k is set according to the distance between the image judging terminal and the security check equipment and the actual situation of the proportion of the number of the image judging terminals to the number of the security check equipment.
Preferably, k is set to 8, i.e. the security device transmits in a group of 8 columns of data.
In implementation, the sending the column data belonging to the row packet image to the corresponding graph determining terminal according to the set mode further includes:
comparing the acquired time interval between the earliest generated column data and the latest generated column data which belong to the row of package images and are generated by the current security inspection equipment with a set time interval threshold;
and if the time interval is larger than the set time interval, all the column data which are generated by the current security inspection equipment and belong to the row packet image are sent to the corresponding image judgment terminal.
Specifically, the set time interval is set according to the distance between the image judging terminal and the security check equipment and the actual situation of the proportion of the number of the image judging terminals to the number of the security check equipment.
Preferably, the time interval is set to 100 milliseconds, that is, when the time interval between generating the earliest column data and generating the latest column data of one row of packet images exceeds 100 milliseconds, the security inspection device will transmit all the column data generated by the row of packet images.
It should be noted that, the security inspection device generates column data, the acquired column data generated in the security inspection device is not timely transmitted to the graph determination terminal due to the small number of graph determination terminals or the small number of idle state, and if the time for waiting to transmit the same row of packet images is too long, the sequential transmission increases the time delay for transmitting the row of packet images, so that the waiting time of the row of packet images exceeds a set time interval, that is, exceeds the maximum time delay limit allowed in practice, and all the row of packet image data is transmitted.
Specifically, when the current security check device or the security check machine networking device sends each row of packet image line data, the row of packet image line data is cached, and when each row of line data is sent, whether the sending is successful or not is marked, and if the sending is wrong, the resending is attempted; and if the retransmission fails to indicate the network fault, re-determining the graph judging terminal, and retransmitting all column data of the row packet image.
And S4, sequentially displaying the column data by the image interpretation terminal according to the received column data serial numbers to form corresponding row packet images, further interpreting, and returning the interpretation results. It can be understood that the graph judging terminal receives a group of column data of the row packet images in sequence, displays the column data according to the serial numbers of the column data, can load and display the row packet images group by group, can judge through part or all of the displayed row packet images, and returns the judging result to the current security check equipment or security check machine networking equipment.
When the method is implemented, the interpretation result comprises a final interpretation result and/or an intermediate interpretation result, wherein the intermediate interpretation result is the interpretation result according to a part of the luggage images displayed by the interpretation terminal, and the final interpretation result is the interpretation result according to the complete luggage images displayed by the interpretation terminal.
It can be understood that the graph judging terminal gradually loads and displays the luggage images in the form of a reel, and when judging is performed, the displayed partial luggage images are questioned, or suspicious or forbidden articles in the luggage articles can be judged according to the displayed partial images, and the suspicious or forbidden articles can be immediately fed back to the security inspection equipment for response and treatment; and the interpretation feedback interpretation result can be interpreted according to the complete image generated by the image interpretation terminal.
Preferably, when the final image judging result is returned by the image judging terminal, the security check device or the security check machine networking device actively disconnects the connection with the image judging terminal, judges the complete image of the luggage image, ensures the accuracy of the judgment, and can store the complete luggage image for later inspection.
During implementation, if the current column data is the last column data of the affiliated row packet image, marking the column data as the end column data of the affiliated row packet image;
correspondingly, when the graph judging terminal corresponding to the row packet image receives the ending column data, judging that the complete image of the row packet image is received, judging according to the complete image to obtain a final judging result, and returning the final judging result to the current security check equipment or security check machine networking equipment.
Preferably, each graph judging terminal uploads the obtained images of each row of packages and corresponding security check equipment information to a designated remote server for centralized management and storage.
The security check machine networking equipment is used for accessing the security check equipment without the networking function into the network, centralized interpretation can be simultaneously adopted with the security check equipment with the networking function, the workload of workers is balanced, the waste of the workers is avoided, the interpretation speed is improved, and the requirement of centralized interpretation of the security check equipment along with the development of the times is met; in addition, the security check equipment without the networking function is accessed into the network through the networking equipment of the security check machine, the acquired X-ray image can be intelligently judged, the X-ray image is uploaded to a remote server to be stored, the information such as the security check image acquired by the security check equipment in the actual service is conveniently stored and managed in a centralized manner through the network, and the backtracking query after the problem occurs is facilitated.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A luggage interpretation method for security inspection equipment is characterized by comprising the following steps:
acquiring the equipment information of the security check equipment, judging whether the security check equipment has the networking function or not,
if yes, accessing the security check equipment to a network, and acquiring an X-ray image formed by the security check equipment for interpretation processing;
if not, the security check equipment is connected with the security check machine networking equipment through a video line, the security check machine networking equipment is connected into a network, the security check machine networking equipment collects video signals output by the security check equipment through the video line, and then X-ray images are obtained for interpretation processing.
2. The row packet interpretation method for a security inspection device according to claim 1, wherein the security inspection machine networking device acquires an X-ray image by performing the following operations:
the method comprises the steps of obtaining the on-off state of current security check equipment, and starting to obtain a video signal output by the current security check equipment when the current security check equipment is started;
and sequentially acquiring an X-ray image of luggage objects in the video signal according to each original frame image of the video signal.
3. The luggage interpretation method for security inspection equipment according to claim 2, wherein the X-ray images of luggage items in the video signal are sequentially acquired by performing the following steps:
sequentially acquiring original frame images in the video signal, performing gray level conversion to obtain gray level frame images, and performing the following processing:
extracting k columns of data of the previous gray frame image from the initial column as a reference window; wherein k is greater than or equal to 1;
sliding a reference window column by column from an initial column in a current gray frame image, and acquiring the number of sliding columns of the reference window at the moment if column data same as that of the reference window is matched;
acquiring line data from an initial line to the sliding line number in an original frame image corresponding to the current gray frame image as an X-ray image of the row packet object generated by the current security inspection equipment;
wherein the initial column of the original frame image or the gray frame image corresponds to the column of the video signal in which the X-ray image is displayed first.
4. The luggage interpretation method for security inspection equipment according to claim 2, characterized in that the X-ray image is interpreted by performing the following steps:
sequentially numbering the column data of the obtained X-ray image, and judging a row packet image to which each column data belongs;
matching corresponding image judging terminals for each row of packet images in sequence based on the generation sequence of each row of packet images;
sequentially sending the acquired column data of the row packet images matched with the image judging terminal generated by the current security check equipment to the corresponding image judging terminal;
and sequentially displaying the column data by the image judging terminal according to the received serial numbers of the column data to form corresponding row packet images, further judging and reading, and returning a judging and reading result.
5. The row packet interpretation method for the security inspection equipment according to claim 2, wherein the security inspection machine networking equipment further comprises:
judging a row packet image to which each column of data belongs based on the acquired X-ray image;
and intelligently judging the images of all the luggage images, judging whether the corresponding luggage objects are suspicious or not, and marking the luggage images of the suspicious luggage objects.
6. The row packet interpretation method for the security inspection equipment according to claim 5, wherein the security inspection machine networking equipment further comprises:
acquiring security inspection equipment information, and uploading each row of packet images, corresponding label information and the security inspection equipment information to a remote server; the safety inspection equipment information comprises a safety inspection equipment model and GPS positioning information.
7. The luggage interpretation method for the security inspection equipment according to claim 2, wherein the intelligent image judgment is performed on each luggage image, whether a corresponding luggage article is suspicious is judged, and the luggage image of the suspicious luggage article is marked, specifically:
extracting the class characteristics of each row of bag images, and comparing the class characteristics with the class characteristics of each suspicious article stored in the security check machine networking equipment respectively;
if the classification characteristics of the suspicious articles are consistent with those of any suspicious articles, judging that the luggage articles corresponding to the luggage image are suspicious articles, and marking the luggage image.
8. The luggage interpretation method for security inspection equipment according to claim 3, wherein the matching of the corresponding interpretation terminal for each luggage image in turn comprises:
detecting whether an idle state image judging terminal exists in the range of the available image judging terminal of the current security inspection equipment based on a preset condition;
and if the image judging terminal in the idle state exists, taking the image judging terminal in the idle state as the image judging terminal corresponding to the line packet image.
9. The row packet interpretation method for the security inspection equipment according to claim 3, wherein the step of sending the acquired column data of the row packet image, generated by the current security inspection equipment and matched with the graph judging terminal, to the corresponding graph judging terminal comprises:
establishing communication connection between the current security check equipment and a picture judgment terminal corresponding to the luggage image;
sequentially sending the column data belonging to the row packet image to the corresponding image judging terminal according to a set mode;
and when receiving the interpretation result returned by the corresponding image interpretation terminal, disconnecting the communication connection with the corresponding image interpretation terminal.
10. The row packet interpretation method for the security inspection equipment according to claim 8, wherein the sending the column data belonging to the row packet image to the corresponding graph interpretation terminal according to the set mode comprises:
and sequentially sending the acquired column data which are generated by the current security inspection equipment and belong to the row packet image to corresponding image judgment terminals by taking k columns as a group, wherein if the column data which belong to the row packet image are not more than k columns at last, the rest column data are taken as a group to be sent to the corresponding image judgment terminals, wherein k is more than or equal to 1 and less than the total column number of the row packet image column data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516258.3A CN114113165B (en) | 2021-12-08 | 2021-12-08 | Row package interpretation method for security inspection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516258.3A CN114113165B (en) | 2021-12-08 | 2021-12-08 | Row package interpretation method for security inspection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114113165A true CN114113165A (en) | 2022-03-01 |
| CN114113165B CN114113165B (en) | 2023-08-08 |
Family
ID=80364995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111516258.3A Active CN114113165B (en) | 2021-12-08 | 2021-12-08 | Row package interpretation method for security inspection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114113165B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
| CN115190144A (en) * | 2022-06-23 | 2022-10-14 | 深圳市易孔立出软件开发有限公司 | Data acquisition method, system, device, terminal equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020176535A1 (en) * | 2001-01-31 | 2002-11-28 | General Electric Company | Method and system monitoring image detection |
| JP2008022961A (en) * | 2006-07-19 | 2008-02-07 | Aloka Co Ltd | X-ray ct apparatus |
| CN101907581A (en) * | 2010-06-23 | 2010-12-08 | 北京航空航天大学 | Ray energy fluctuation correcting method suitable for high-energy X-ray DR scanning system |
| US20110188727A1 (en) * | 2008-09-24 | 2011-08-04 | Kromek Limited | Radiograpic Data Interpretation |
| US20130100294A1 (en) * | 2011-10-25 | 2013-04-25 | Guangzhou Sat Infrared Technology Co. Ltd. | System and method for processing digital signals of an infrared image |
| CN103308537A (en) * | 2013-06-13 | 2013-09-18 | 中北大学 | Gradient-energy X-ray imaging image fusion method |
| CN104834902A (en) * | 2015-04-21 | 2015-08-12 | 同方威视技术股份有限公司 | Safety check graph discrimination system including video analysis and graph discrimination method |
| CN206422869U (en) * | 2017-02-10 | 2017-08-18 | 厦门市龙坝科技有限公司 | A kind of safety check instrument view data stores analyzer |
| EP3279700A1 (en) * | 2016-08-04 | 2018-02-07 | Nuctech Company Limited | Security inspection centralized management system |
| CN208476830U (en) * | 2018-10-15 | 2019-02-05 | 深圳市方戟科技有限公司 | The system synchronous applied to the image capture and display of existing screening machine |
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN111652322A (en) * | 2020-06-11 | 2020-09-11 | 北京声迅电子股份有限公司 | Remote intelligent image judging system with image serialization |
| CN111741509A (en) * | 2019-03-25 | 2020-10-02 | 珠海格力电器股份有限公司 | Network distribution method and device, storage medium and processor |
| CN112444889A (en) * | 2020-11-13 | 2021-03-05 | 北京航星机器制造有限公司 | Rapid security inspection luggage remote centralized interpretation system and method |
| CN113709380A (en) * | 2021-10-20 | 2021-11-26 | 广州微林软件有限公司 | Control method based on external camera device |
-
2021
- 2021-12-08 CN CN202111516258.3A patent/CN114113165B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020176535A1 (en) * | 2001-01-31 | 2002-11-28 | General Electric Company | Method and system monitoring image detection |
| JP2008022961A (en) * | 2006-07-19 | 2008-02-07 | Aloka Co Ltd | X-ray ct apparatus |
| US20110188727A1 (en) * | 2008-09-24 | 2011-08-04 | Kromek Limited | Radiograpic Data Interpretation |
| CN101907581A (en) * | 2010-06-23 | 2010-12-08 | 北京航空航天大学 | Ray energy fluctuation correcting method suitable for high-energy X-ray DR scanning system |
| US20130100294A1 (en) * | 2011-10-25 | 2013-04-25 | Guangzhou Sat Infrared Technology Co. Ltd. | System and method for processing digital signals of an infrared image |
| CN103308537A (en) * | 2013-06-13 | 2013-09-18 | 中北大学 | Gradient-energy X-ray imaging image fusion method |
| CN104834902A (en) * | 2015-04-21 | 2015-08-12 | 同方威视技术股份有限公司 | Safety check graph discrimination system including video analysis and graph discrimination method |
| EP3279700A1 (en) * | 2016-08-04 | 2018-02-07 | Nuctech Company Limited | Security inspection centralized management system |
| CN206422869U (en) * | 2017-02-10 | 2017-08-18 | 厦门市龙坝科技有限公司 | A kind of safety check instrument view data stores analyzer |
| CN208476830U (en) * | 2018-10-15 | 2019-02-05 | 深圳市方戟科技有限公司 | The system synchronous applied to the image capture and display of existing screening machine |
| CN111741509A (en) * | 2019-03-25 | 2020-10-02 | 珠海格力电器股份有限公司 | Network distribution method and device, storage medium and processor |
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN111652322A (en) * | 2020-06-11 | 2020-09-11 | 北京声迅电子股份有限公司 | Remote intelligent image judging system with image serialization |
| CN112444889A (en) * | 2020-11-13 | 2021-03-05 | 北京航星机器制造有限公司 | Rapid security inspection luggage remote centralized interpretation system and method |
| CN113709380A (en) * | 2021-10-20 | 2021-11-26 | 广州微林软件有限公司 | Control method based on external camera device |
Non-Patent Citations (5)
| Title |
|---|
| JUNYAN ZHOU: "Real-time task scheduling and network device security for complex embedded systems based on deep learning networks", 《MICROPROCESSORS AND MICROSYSTEMS》, vol. 79 * |
| 张庸 等: "快件监查分层管理***的设计与实现", 《机电产品开发与创新》, vol. 30, no. 5 * |
| 张森 等: "基于网络化集中判图的城市轨道交通 新安检***设计", 《城市轨道交通研究》, vol. 24, no. 7 * |
| 张润铿: "浅析机动车安检机构移动终端智能监管***", 《科技风》, no. 12 * |
| 赵振武 等: "机场旅客随身行李安检***性能研究", 《安全与环境学报》, vol. 21, no. 5 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
| CN114660097B (en) * | 2022-03-23 | 2023-06-02 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
| CN115190144A (en) * | 2022-06-23 | 2022-10-14 | 深圳市易孔立出软件开发有限公司 | Data acquisition method, system, device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114113165B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182417B (en) | Shipment detection method and device, computer equipment and vending machine | |
| CN114113165B (en) | Row package interpretation method for security inspection equipment | |
| US10937144B2 (en) | Pipe feature identification using pipe inspection data analysis | |
| CN108830837B (en) | Method and device for detecting steel ladle corrosion defect | |
| US20160098636A1 (en) | Data processing apparatus, data processing method, and recording medium that stores computer program | |
| CN107145816A (en) | Object identifying tracking and device | |
| EP3158505B1 (en) | A method and a system for object recognition | |
| CN109374631B (en) | Tunnel state evaluation method | |
| WO2019105131A1 (en) | Image identification method and system for monitoring, computer device, and readable storage medium | |
| EP3099061A1 (en) | Image search system and image search method | |
| CN112613569B (en) | Image recognition method, training method and device for image classification model | |
| CN109977127A (en) | Data-updating method and device | |
| CN105787062A (en) | Method and equipment for searching for target object based on video platform | |
| CN110910415A (en) | Parabolic detection method, device, server and computer readable medium | |
| CN113361539A (en) | Instrument reading method and device of underground inspection robot and electronic equipment | |
| CN107223257A (en) | Method of testing, test server and system | |
| CN114113164B (en) | Image concentrated interpretation method for security inspection equipment | |
| US20220335724A1 (en) | Processing apparatus, processing method, and non-transitory storage medium | |
| CN111126112B (en) | Candidate region determination method and device | |
| KR101760930B1 (en) | An IoT system Method receiving data from outside data sources using virtual gateway | |
| CN113640321A (en) | Security check delay optimization method and device | |
| CN112212864A (en) | Fire scene navigation method and system based on deep learning and storage medium | |
| CN116110127A (en) | Multi-linkage gas station cashing behavior recognition system | |
| CN115546824B (en) | Taboo picture identification method, apparatus and storage medium | |
| CN114972500A (en) | Checking method, marking method, system, device, terminal, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |