CN116129153A - Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification - Google Patents
Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification Download PDFInfo
- Publication number
- CN116129153A CN116129153A CN202310180906.5A CN202310180906A CN116129153A CN 116129153 A CN116129153 A CN 116129153A CN 202310180906 A CN202310180906 A CN 202310180906A CN 116129153 A CN116129153 A CN 116129153A
- Authority
- CN
- China
- Prior art keywords
- forbidden band
- processing module
- identification
- image
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an intelligent analysis processing method for identifying forbidden band articles, which comprises the following steps: reconstructing the data into a security check image; the image recognition module is used for matching the pattern category and the position area in the image model; the data processing module judges whether the pattern category needs substance identification or not; the substance identification module matches a substance category in the substance model; the data processing module compares whether the pattern position area category and the substance category need to be identified; and carrying out synchronous matching, and obtaining video images of forbidden band object identifiers through the mapping relation. The invention also relates to an intelligent analysis processing system, an intelligent analysis processing device, an intelligent analysis processing processor and a storage medium for forbidden band article identification. The intelligent analysis processing method, the system, the device, the processor and the computer readable storage medium thereof for realizing the identification of the forbidden band articles are adopted to realize the rapid detection of various forbidden band articles including inflammable liquid, explosive and control appliances so as to improve the on-site inspection efficiency and reduce the working pressure of security inspection personnel.
Description
Technical Field
The invention relates to the field of safety inspection equipment, in particular to the field of X-ray safety inspection instruments, and specifically relates to an intelligent analysis processing method, system, device, processor and computer readable storage medium for realizing identification of forbidden band articles.
Background
The safety inspection equipment mainly comprising the X-ray safety inspection instrument is used for checking whether articles are forbidden to be carried or restricted to be carried (hereinafter referred to as "forbidden band articles") in a manual picture judging mode by workers, and continuously working in a period with dense passengers puts high requirements on the carrying capacity and experience of the safety inspection instrument, particularly, liquid, powder or particle objects are required to be taken out from package baggage and are secondarily detected through a special inspection instrument, and the process consumes a large amount of manpower time and causes site congestion, and meanwhile, the psychological burden of the safety inspection personnel is further increased, so that the follow-up working efficiency is low and even judgment errors are extremely easy.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an intelligent analysis processing method, an intelligent analysis processing system, an intelligent analysis processing device, an intelligent analysis processing processor and a computer readable storage medium thereof, wherein the intelligent analysis processing method, the intelligent analysis processing system, the intelligent analysis processing device, the intelligent analysis processing processor and the computer readable storage medium are accurate in judgment, high in efficiency and wide in application range and are used for identifying forbidden band objects.
To achieve the above object, the present invention provides an intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification, as follows:
the intelligent analysis processing method for identifying forbidden band articles is mainly characterized by comprising the following steps of:
(1) The data processing module collects data output by the detector of the X-ray security inspection device, reconstructs the data into security inspection images and inputs the security inspection images to the image recognition module;
(2) The image recognition module is used for matching the graph type and the position area in the image model and inputting the graph type and the position area into the data processing module;
(3) The data processing module judges whether the pattern category needs substance identification or not, and inputs the data needing substance identification into the substance identification module;
(4) The material identification module matches the material category in the material model and outputs the material category to the data processing module;
(5) The data processing module compares whether the pattern position area category and the substance category need to be identified or not, and inputs the warning area identification and the reconstructed security inspection image into the video processing module;
(6) And the video processing module synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module, and obtains a video image with the forbidden band object identifier through the mapping relation.
Preferably, the step (5) specifically includes the following steps:
the data processing module inputs the pattern position area category and the substance category into a forbidden band object database and compares the pattern position area category and the substance category, determines whether an object in the area needs to be identified, and obtains an alarm area identification;
and (5.2) the data processing module inputs the warning area identification and the reconstructed security check image to the video processing module.
Preferably, the step (6) specifically includes the following steps:
(6.1) the video processing module collects images output by a display screen of the security inspection machine;
(6.2) the video processing module matches the video stream with the data stream, and synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module to obtain the mapping relation of the two images;
and (6.3) matching the warning area identification to an image output by a display screen of the security inspection machine through a mapping relation by the video processing module to obtain a video image with the forbidden band object identification, and outputting the video image.
Preferably, in the step (6.2), the video processing module matches the video stream with the data stream, and specifically includes the following steps:
(6.2.1) obtaining device pretreatment parameters by a special matched test body:
(6.2.2) selecting a video correspondence area for forbidden band article identification;
(6.2.3) geometrically transforming the reconstructed image by means of the pre-processing parameters;
(6.2.4) monitoring the input video image, and selecting a fixed frame with specific continuous change;
(6.2.5) comparing the result of the geometric transformation with the result of a specific continuously changing fixed frame to find a mapping relation;
and (6.2.6) matching the mapping relation to the data through the preprocessing parameters to obtain a matching result of the video image and the data.
Preferably, the method further comprises the steps of:
(7) Judging whether rechecking is needed according to the video image, if so, taking out suspicious objects according to the identification position of the warning area output by the video image, and placing the suspicious objects on a special independent checking tray; otherwise, ending the step;
(8) And (3) continuing to carry out independent inspection on suspicious objects in the step (1), and informing security inspection personnel to check if the suspicious objects are warned again.
The intelligent analysis processing system for forbidden band object identification is mainly characterized by comprising the following components:
the data processing module is used for receiving the data stream of mirror image data of the X-ray security inspection equipment, reconstructing an image by using the data, and comparing the image substance database of the forbidden band object;
the video processing module is connected with the data processing module, and is used for receiving the video stream of the video image of the X-ray security inspection equipment, matching the video stream with the data stream, completing the forbidden band object identification according to the matching result and outputting the video stream of the video image of the forbidden band object identification;
the image recognition module is connected with the data processing module and is used for collecting X-ray images of various articles as training data, extracting data features from the X-ray images through the deep learning model and obtaining a recognition model of the X-ray images;
and the substance identification module is connected with the data processing module and is used for collecting X-ray images and data of various packages as training data, establishing a packaging material substance attribute algorithm model and obtaining an algorithm model for extracting internal substance attributes by removing influences of packaging materials.
Preferably, the video processing module completes the forbidden band object identification according to the matching result, specifically:
and finishing the forbidden band object identification of the video image output by the original security inspection equipment through the warning area identification output by the data processing module according to the matching result.
The intelligent analysis processing device for realizing forbidden band object identification is mainly characterized by comprising the following components:
a processor configured to execute computer-executable instructions;
and a memory storing one or more computer-executable instructions which, when executed by the processor, perform the steps of implementing the intelligent analysis processing method for forbidden band article identification described above.
The processor for realizing intelligent analysis processing for forbidden band object identification is mainly characterized in that the processor is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the intelligent analysis processing method for forbidden band object identification are realized.
The computer readable storage medium is characterized in that the computer program is stored thereon, and the computer program can be executed by a processor to implement the steps of the intelligent analysis processing method for forbidden band article identification.
The intelligent analysis processing method, the system, the device, the processor and the computer readable storage medium thereof for realizing forbidden band object identification are adopted to realize the rapid detection of various forbidden band objects including inflammable liquid, explosive and control devices based on a deep learning model and an X-ray substance attribute analysis method so as to improve the on-site inspection efficiency and reduce the working pressure of security inspection personnel.
Drawings
Fig. 1 is a schematic diagram of a hardware implementation form of an intelligent analysis device for realizing forbidden band object identification according to the present invention.
FIG. 2 is a schematic diagram of functional modules and a workflow for implementing an intelligent analysis processing method for forbidden band article identification according to the present invention.
Fig. 3a is a front perspective view of a special stand-alone inspection tray of the present invention.
Fig. 3b is a perspective view of a side of a special individual inspection tray of the present invention.
Fig. 4 is a schematic diagram of a matching test in the process of matching a video stream with a data stream according to the present invention.
Detailed Description
In order to more clearly describe the technical contents of the present invention, a further description will be made below in connection with specific embodiments.
The intelligent analysis processing method for forbidden band article identification comprises the following steps:
(1) The data processing module collects data output by the detector of the X-ray security inspection device, reconstructs the data into security inspection images and inputs the security inspection images to the image recognition module;
(2) The image recognition module is used for matching the graph type and the position area in the image model and inputting the graph type and the position area into the data processing module;
(3) The data processing module judges whether the pattern category needs substance identification or not, and inputs the data needing substance identification into the substance identification module;
(4) The material identification module matches the material category in the material model and outputs the material category to the data processing module;
(5) The data processing module compares whether the pattern position area category and the substance category need to be identified or not, and inputs the warning area identification and the reconstructed security inspection image into the video processing module;
(6) And the video processing module synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module, and obtains a video image with the forbidden band object identifier through the mapping relation.
As a preferred embodiment of the present invention, the step (5) specifically includes the steps of:
the data processing module inputs the pattern position area category and the substance category into a forbidden band object database and compares the pattern position area category and the substance category, determines whether an object in the area needs to be identified, and obtains an alarm area identification;
and (5.2) the data processing module inputs the warning area identification and the reconstructed security check image to the video processing module.
As a preferred embodiment of the present invention, the step (6) specifically includes the steps of:
(6.1) the video processing module collects images output by a display screen of the security inspection machine;
(6.2) the video processing module matches the video stream with the data stream, and synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module to obtain the mapping relation of the two images;
and (6.3) matching the warning area identification to an image output by a display screen of the security inspection machine through a mapping relation by the video processing module to obtain a video image with the forbidden band object identification, and outputting the video image.
As a preferred embodiment of the present invention, the matching between the video stream and the data stream by the video processing module in the step (6.2) specifically includes the following steps:
(6.2.1) obtaining device pretreatment parameters by a special matched test body:
(6.2.2) selecting a video correspondence area for forbidden band article identification;
(6.2.3) geometrically transforming the reconstructed image by means of the pre-processing parameters;
(6.2.4) monitoring the input video image, and selecting a fixed frame with specific continuous change;
(6.2.5) comparing the result of the geometric transformation with the result of a specific continuously changing fixed frame to find a mapping relation;
and (6.2.6) matching the mapping relation to the data through the preprocessing parameters to obtain a matching result of the video image and the data.
As a preferred embodiment of the present invention, the method further comprises the steps of:
(7) Judging whether rechecking is needed according to the video image, if so, taking out suspicious objects according to the identification position of the warning area output by the video image, and placing the suspicious objects on a special independent checking tray; otherwise, ending the step;
(8) And (3) continuing to carry out independent inspection on suspicious objects in the step (1), and informing security inspection personnel to check if the suspicious objects are warned again.
The intelligent analysis processing system for forbidden band object identification is mainly characterized by comprising the following components:
the data processing module is used for receiving the data stream of mirror image data of the X-ray security inspection equipment, reconstructing an image by using the data, and comparing the image substance database of the forbidden band object;
the video processing module is connected with the data processing module, and is used for receiving the video stream of the video image of the X-ray security inspection equipment, matching the video stream with the data stream, completing the forbidden band object identification according to the matching result and outputting the video stream of the video image of the forbidden band object identification;
the image recognition module is connected with the data processing module and is used for collecting X-ray images of various articles as training data, extracting data features from the X-ray images through the deep learning model and obtaining a recognition model of the X-ray images;
and the substance identification module is connected with the data processing module and is used for collecting X-ray images and data of various packages as training data, establishing a packaging material substance attribute algorithm model and obtaining an algorithm model for extracting internal substance attributes by removing influences of packaging materials.
As a preferred embodiment of the present invention, the video processing module completes the forbidden band article identification according to the matching result, specifically:
and finishing the forbidden band object identification of the video image output by the original security inspection equipment through the warning area identification output by the data processing module according to the matching result.
The intelligent analysis processing device for realizing forbidden band object identification comprises:
a processor configured to execute computer-executable instructions;
and a memory storing one or more computer-executable instructions which, when executed by the processor, perform the steps of implementing the intelligent analysis processing method for forbidden band article identification described above.
The processor for implementing intelligent analysis processing for forbidden band article identification according to the present invention, wherein the processor is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of implementing the intelligent analysis processing method for forbidden band article identification described above.
The computer readable storage medium of the present invention has a computer program stored thereon, the computer program being executable by a processor to perform the steps described above for implementing the intelligent analysis processing method for forbidden band article identification.
In a specific embodiment of the invention, an intelligent auxiliary device of an X-ray security inspection instrument and a forbidden band object identification method are provided, and the technical scheme is as follows: and acquiring output data of a detector of the X-ray security inspection equipment and an output image (video stream) of a display screen, identifying forbidden band object areas and categories by a method of fusion image analysis and data analysis, mapping an identification result to the output image of the display screen of the security inspection equipment by a method of matching the video stream and the data stream, and finally enabling the output image to be consistent with the original security inspection equipment and have forbidden band object identifications, wherein a specific hardware implementation form is displayed as shown in fig. 1.
As shown in fig. 2, the functional modules of the intelligent auxiliary device include a video processing module, a data processing module, an image recognition module, and a substance recognition module, and the specific workflow is as follows:
(1) The data processing module acquires data output by a detector of the X-ray security inspection equipment;
(2) The data processing module reconstructs the data into a security check image;
(3) The data processing module inputs the reconstructed security inspection image to the image recognition module;
(4) The image recognition module is used for matching the pattern category and the position area in the image model;
(5) The image recognition module inputs the graphic category and the position area into the data processing module;
(6) The data processing module judges whether the pattern category needs substance identification or not;
(7) The data processing module inputs the data needing to be identified to the material identification module;
(8) The substance identification module matches a substance category in the substance model;
(9) The substance identification module outputs the substance category to the data processing module;
(10) The data processing module inputs the pattern position area category and the substance category into the forbidden band object database for comparison, and determines whether the area object needs to be identified or not, so as to obtain an alarm area identification;
(11) The data processing module inputs the warning area identification and the reconstructed security inspection image to the video processing module;
(12) The video processing module acquires images (video streams) output by a display screen of the security inspection machine;
(13) The video processing module synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module through a video/data matching method to obtain a mapping relation of the image output by the display screen of the security inspection machine and the security inspection image;
(14) The video processing module matches the warning area identifier to an image output by a display screen of the security inspection machine through a mapping relation to obtain a video image with the forbidden band object identifier;
(15) The video processing module outputs video images;
(16) The security inspection equipment staff judges whether rechecks are needed according to the video image;
(17) If rechecking is needed, taking suspicious objects out according to the warning area identification position output by the video image, and placing the suspicious objects on a special independent checking tray, wherein the special tray has the following significance as shown in fig. 3: the method is used for improving the identification accuracy of inflammable liquid, explosive or toxic and harmful substance components, on one hand, the influence of interfering substances and shielding substances can be eliminated through independent inspection, on the other hand, various canned objects are fixed, sliding or rolling in the inspection process is prevented, and the identification accuracy is prevented from being influenced;
(18) Separately checking suspicious objects through the steps (1) - (15);
(19) And if the alarm is again given, notifying security personnel to check.
The image recognition module technology is realized: and collecting X-ray images of various articles in mass as training data, extracting data features from the training data through a deep learning model, and optimizing the recognition capability of the training data under a complex scene to obtain a recognition model of the X-ray images.
The material identification module technology is realized: collecting X-ray images and data of various packaged liquids, powders or particulate matter as training data, the packaging material comprising: glass, porcelain, metal, plastic, paper and the like, a packaging material substance attribute algorithm model is established, the shielding and interference removing capability under a complex scene is optimized, and the algorithm model for extracting the internal substance attribute by removing the influence of the packaging material is obtained, wherein the algorithm model is equivalent to atomic number, density and the like.
The data processing module comprises data reconstruction image and forbidden band object image substance database comparison, wherein the important significance of the data reconstruction image is as follows: 1, compared with data, the image output by the original security inspection equipment is less in a lot of information, and the data processing module can select a plurality of data processing and image reconstruction modes to adapt to the requirements of different scene recognition, just as security inspection staff can select images with different attenuation coefficients and contrasts to judge the image on the similar principle, the anti-interference and shielding capacity is stronger, and the accuracy of recognizing forbidden band objects is effectively improved; 2, the image output by the intelligent analysis module is a mirror image of the original security inspection equipment image, so that the data reconstruction image is matched with the original security inspection equipment image, and the forbidden band object identification result can be identified on the output image. The forbidden band object image substance database is a standardized database formed by processing object data forbidden or limited to be carried in public places such as railways, urban rail transit, airports and the like through operation extraction features and the like, is used for comparing input results of the image analysis module and the substance analysis module, and finally outputs an area and a mark needing to be warned.
The video processing module functions include matching the video stream with the data stream and disabling the band-limited object identification. The matching process of the video stream and the data stream is to find the data position corresponding to the video image output by the original security inspection equipment and complete one-to-one matching at the pixel level; the forbidden band object identification is to complete the forbidden band object identification of the video image output by the original security inspection equipment through the matching result of the warning area identification output by the data processing module.
Video stream and data stream matching process:
(1.1) acquiring device pretreatment parameters by special matching test bodies (test bodies composed of different materials and shapes are easier to obtain shape characteristics in security inspection images): longitudinal ratio, transverse ratio, longitudinal and transverse mirror relationship, initial position;
(1.2) selecting a video correspondence area for forbidden band item identification;
(1.3) geometrically transforming the reconstructed image by means of the preprocessing parameters;
(1.4) monitoring the input video image, and selecting a fixed frame with specific continuous change;
(1.5) comparing the result (1.4) with the result (1.3) to find a mapping relation;
and (1.6) matching the mapping relation in the step (1.5) to data through preprocessing parameters to obtain a matching result of the video image and the data.
The invention transmits more than image video stream, but combines the real-time data of the detector from the original security inspection equipment and the image video stream, and the real-time data contains far-beyond-image information, which brings the advantages that:
finer decisions can be made about the composition of matter (details can be described simply if needed), including distinguishing whether the package is a safe solution or flammable and explosive liquid contraband, whether it contains toxic (drugs or psychotropic drugs, etc.) or explosive components, and the packaging material can be analyzed to eliminate the effect of analysis of the composition of the internal matter (details can be described simply if needed), which is not the case with video streaming.
Establishing unified data reconstruction image standard (details can be simply described if needed), so that the security inspection image of the final input deep learning intelligent image judgment model has unified color and texture definition, the stability of the recognition accuracy of the intelligent image judgment of different security inspection devices can be ensured, if only an image video stream means that the deep learning intelligent image judgment model needs to train the security inspection images of different security inspection devices, the data quantity is huge, and the stability of the final recognition accuracy is more difficult to ensure;
the data can give more detail than the two above, such as the identification of objects at extreme low and high attenuation (details can be described simply if needed), which is also not available in the video stream.
The specific implementation manner of this embodiment may be referred to the related description in the foregoing embodiment, which is not repeated herein.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or part of the steps carried out in the method of the above embodiments may be implemented by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium, where the program when executed includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented as software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The intelligent analysis processing method, the system, the device, the processor and the computer readable storage medium thereof for realizing forbidden band object identification are adopted to realize the rapid detection of various forbidden band objects including inflammable liquid, explosive and control devices based on a deep learning model and an X-ray substance attribute analysis method so as to improve the on-site inspection efficiency and reduce the working pressure of security inspection personnel.
In this specification, the invention has been described with reference to specific embodiments thereof. It will be apparent, however, that various modifications and changes may be made without departing from the spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (10)
1. An intelligent analysis processing method for identifying forbidden band articles is realized, which is characterized by comprising the following steps:
(1) The data processing module collects data output by the detector of the X-ray security inspection device, reconstructs the data into security inspection images and inputs the security inspection images to the image recognition module;
(2) The image recognition module is used for matching the graph type and the position area in the image model and inputting the graph type and the position area into the data processing module;
(3) The data processing module judges whether the pattern category needs substance identification or not, and inputs the data needing substance identification into the substance identification module;
(4) The material identification module matches the material category in the material model and outputs the material category to the data processing module;
(5) The data processing module compares whether the pattern position area category and the substance category need to be identified or not, and inputs the warning area identification and the reconstructed security inspection image into the video processing module;
(6) And the video processing module synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module, and obtains a video image with the forbidden band object identifier through the mapping relation.
2. The intelligent analysis processing method for forbidden band article identification according to claim 1, wherein the step (5) specifically comprises the following steps:
the data processing module inputs the pattern position area category and the substance category into a forbidden band object database and compares the pattern position area category and the substance category, determines whether an object in the area needs to be identified, and obtains an alarm area identification;
and (5.2) the data processing module inputs the warning area identification and the reconstructed security check image to the video processing module.
3. The intelligent analysis processing method for forbidden band article identification according to claim 1, wherein the step (6) specifically comprises the following steps:
(6.1) the video processing module collects images output by a display screen of the security inspection machine;
(6.2) the video processing module matches the video stream with the data stream, and synchronously matches the image output by the display screen of the security inspection machine with the security inspection image output by the data processing module to obtain the mapping relation of the two images;
and (6.3) matching the warning area identification to an image output by a display screen of the security inspection machine through a mapping relation by the video processing module to obtain a video image with the forbidden band object identification, and outputting the video image.
4. The intelligent analysis processing method for forbidden band article identification according to claim 3, wherein the video processing module in the step (6.2) matches the video stream with the data stream, and specifically comprises the following steps:
(6.2.1) obtaining device pretreatment parameters by a special matched test body:
(6.2.2) selecting a video correspondence area for forbidden band article identification;
(6.2.3) geometrically transforming the reconstructed image by means of the pre-processing parameters;
(6.2.4) monitoring the input video image, and selecting a fixed frame with specific continuous change;
(6.2.5) comparing the result of the geometric transformation with the result of a specific continuously changing fixed frame to find a mapping relation;
and (6.2.6) matching the mapping relation to the data through the preprocessing parameters to obtain a matching result of the video image and the data.
5. The intelligent analysis processing method for forbidden band article identification according to claim 1, further comprising the steps of:
(7) Judging whether rechecking is needed according to the video image, if so, taking out suspicious objects according to the identification position of the warning area output by the video image, and placing the suspicious objects on a special independent checking tray; otherwise, ending the step;
(8) And (3) continuing to carry out independent inspection on suspicious objects in the step (1), and informing security inspection personnel to check if the suspicious objects are warned again.
6. An intelligent analysis processing system for forbidden band article identification implementing the method of claim 1, said system comprising:
the data processing module is used for receiving the data stream of mirror image data of the X-ray security inspection equipment, reconstructing an image by using the data, and comparing the image substance database of the forbidden band object;
the video processing module is connected with the data processing module, and is used for receiving the video stream of the video image of the X-ray security inspection equipment, matching the video stream with the data stream, completing the forbidden band object identification according to the matching result and outputting the video stream of the video image of the forbidden band object identification;
the image recognition module is connected with the data processing module and is used for collecting X-ray images of various articles as training data, extracting data features from the X-ray images through the deep learning model and obtaining a recognition model of the X-ray images;
and the substance identification module is connected with the data processing module and is used for collecting X-ray images and data of various packages as training data, establishing a packaging material substance attribute algorithm model and obtaining an algorithm model for extracting internal substance attributes by removing influences of packaging materials.
7. The intelligent analysis processing system for forbidden band article identification according to claim 1, wherein the video processing module completes forbidden band article identification according to the matching result, specifically:
and finishing the forbidden band object identification of the video image output by the original security inspection equipment through the warning area identification output by the data processing module according to the matching result.
8. An intelligent analysis processing device for realizing forbidden band article identification, which is characterized in that the device comprises:
a processor configured to execute computer-executable instructions;
a memory storing one or more computer-executable instructions which, when executed by the processor, perform the steps of implementing the intelligent analysis processing method for forbidden band article identification of any one of claims 1 to 5.
9. A processor for implementing intelligent analysis processing for forbidden band article identification, wherein the processor is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of implementing the intelligent analysis processing method for forbidden band article identification of any one of claims 1 to 5.
10. A computer readable storage medium having stored thereon a computer program executable by a processor to perform the steps of the intelligent analysis processing method for forbidden band item identification of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310180906.5A CN116129153A (en) | 2023-03-01 | 2023-03-01 | Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310180906.5A CN116129153A (en) | 2023-03-01 | 2023-03-01 | Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116129153A true CN116129153A (en) | 2023-05-16 |
Family
ID=86306371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310180906.5A Pending CN116129153A (en) | 2023-03-01 | 2023-03-01 | Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116129153A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116401587A (en) * | 2023-06-08 | 2023-07-07 | 乐山师范学院 | Object category identification method based on X-rays |
| CN117557551A (en) * | 2023-12-18 | 2024-02-13 | 厦门民航凯亚有限公司 | Deep learning-based aviation security check luggage image analysis method |
-
2023
- 2023-03-01 CN CN202310180906.5A patent/CN116129153A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116401587A (en) * | 2023-06-08 | 2023-07-07 | 乐山师范学院 | Object category identification method based on X-rays |
| CN116401587B (en) * | 2023-06-08 | 2023-08-18 | 乐山师范学院 | Object category identification method based on X-rays |
| CN117557551A (en) * | 2023-12-18 | 2024-02-13 | 厦门民航凯亚有限公司 | Deep learning-based aviation security check luggage image analysis method |
| CN117557551B (en) * | 2023-12-18 | 2024-07-05 | 厦门民航凯亚有限公司 | Deep learning-based aviation security check luggage image analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116129153A (en) | Intelligent analysis processing method, system, device, processor and computer readable storage medium for forbidden band article identification | |
| KR101792927B1 (en) | Object inspection method, display method and device | |
| CN109522913B (en) | Inspection method and inspection apparatus, and computer-readable medium | |
| CN106485268A (en) | A kind of image-recognizing method and device | |
| CN104636707B (en) | The method of automatic detection cigarette | |
| CN102663164B (en) | Pass control algorithm test device and method based on multiobjective test case generation | |
| CN110751079A (en) | Article detection method, apparatus, system and computer readable storage medium | |
| CN107607562A (en) | A kind of prohibited items identification equipment and method, X-ray luggage security check system | |
| CN104809437B (en) | A kind of moving vehicles detection and tracking method based on real-time video | |
| JP2018113038A (en) | Inspection device, and method of detecting firearm in luggage | |
| US10163200B2 (en) | Detection of items in an object | |
| CN103900503A (en) | Shape characteristic extraction method, safety inspection method and device | |
| Jaccard et al. | Tackling the X-ray cargo inspection challenge using machine learning | |
| CA3140559A1 (en) | Automated inspection method for a manufactured article and system for performing same | |
| US11182637B2 (en) | X-ray image processing system and method, and program therefor | |
| CN111382762A (en) | Empty box identification method and system | |
| CN106932414A (en) | Inspection and quarantine inspection system and its method | |
| CN110414421A (en) | A kind of Activity recognition method based on sequential frame image | |
| Rosso et al. | Review on deep learning in structural health monitoring | |
| KR102032796B1 (en) | Image analysis apparatus and method | |
| KR102158967B1 (en) | Image analysis apparatus, image analysis method and recording medium | |
| CN105787919A (en) | Operation method and apparatus for safety inspection CT three-dimensional images | |
| CN114792300B (en) | X-ray broken needle detection method based on multi-scale attention | |
| CN110992324A (en) | Intelligent dangerous goods detection method and system based on X-ray image | |
| Fairuzi et al. | Performance analysis of YOLOv4 and SSD Mobilenet V2 for foreign object debris (FOD) detection at airport runway using custom dataset |
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 |