Security check method, system and device and storage medium

Abstract

The invention relates to the technical field of equipment management, and discloses a security check method, system and equipment and a storage medium, and the method comprises the steps: carrying out the identification analysis of a cargo, so as to obtain the information of the cargo; adjusting working parameters of the security check system according to the cargo information; after the working parameters are adjusted, X-ray scanning is conducted on the goods through a dual-energy X-ray generating device, so that density distribution characteristics and marked areas are obtained; after the preset waiting time is over, radiation signal acquisition is carried out on the marked area by utilizing a radiation detector array to obtain radiation distribution characteristics; performing feature fusion on the density distribution feature and the radiation distribution feature to obtain a comprehensive feature vector; performing threat identification based on the comprehensive feature vector to obtain a security check result; according to the invention, threat identification based on a multi-source data fusion result is realized by scheduling multiple detection devices, and the detection precision and adaptability of a security check system are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the security inspection technical field, and in particular to a security inspection method, system, device and storage medium. BACKGROUND

[0002] In the field of cargo security inspection, the existing detection method usually relies on a single detection means (such as X-ray imaging), which makes it difficult to detect complex cargo background with insufficient detection accuracy. For example, when the cargo type is diverse or the internal structure is complex, a single detection means is difficult to obtain comprehensive cargo information, resulting in frequent misjudgment or missed detection, which seriously affects the reliability and adaptability of the security inspection system.

[0003] It can be seen that the prior art still has room for improvement. SUMMARY

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present application is to provide a security inspection method, system, device and storage medium, which realizes threat identification based on multi-source data fusion results by scheduling multiple detection devices, effectively improving the detection accuracy and adaptability of the security inspection system.

[0005] The first aspect of the present application provides a security inspection method applied to a security inspection system, wherein the security inspection system comprises a control device, a dual-energy X-ray generating device and a radiation detector array electrically connected to the control device; the security inspection method comprises the steps of: identifying and analyzing the cargo to obtain cargo information; adjusting the working parameters of the security inspection system according to the cargo information; after the working parameters are adjusted, using the dual-energy X-ray generating device to perform X-ray scanning on the cargo to obtain density distribution characteristics and marked areas; after a preset waiting time ends, using the radiation detector array to collect radiation signals of the marked areas to obtain radiation distribution characteristics; performing feature fusion on the density distribution characteristics and the radiation distribution characteristics to obtain a comprehensive feature vector; and performing threat identification based on the comprehensive feature vector to obtain a security inspection result.

[0006] Optionally, in the first implementation manner of the first aspect of the present application, the security inspection system further comprises a reader electrically connected to the control device; the identifying and analyzing the cargo to obtain the cargo information comprises: using the reader to read the identification on the cargo to obtain cargo identification information; and extracting key information from the cargo identification information to obtain the cargo information.

[0007] Optionally, in a second implementation form of the first aspect of the present application, the security inspection system further comprises a mechanical transmission module; the control device is electrically connected with the mechanical transmission module; the mechanical transmission module is configured to control the movement of the cargo in different detection areas; the adjusting the working parameters of the security inspection system according to the cargo information comprises: generating the adjusting data of the dual-energy X-ray generating device and the adjusting data of the radiation detector array in combination with the cargo information and the preset parameter table; obtaining the configuration parameters of the mechanical transmission module, and generating the mechanical transmission time window data according to the cargo information and the configuration parameters; and distributing the adjusting data of the dual-energy X-ray generating device, the adjusting data of the radiation detector array and the mechanical transmission time window data to corresponding devices to complete the adjustment of the working parameters.

[0008] Optionally, in a third implementation form of the first aspect of the present application, after the working parameters are adjusted, the cargo is scanned by the dual-energy X-ray generating device to obtain the density distribution feature and the marked area, which comprises: scanning the cargo by the dual-energy X-ray generating device to obtain the high-energy image and the low-energy image; comparing the density difference between the high-energy image and the low-energy image to obtain the density distribution feature; and screening the area that needs to be detected in the cargo according to the density distribution feature and the cargo information to obtain the marked area.

[0009] Optionally, in a fourth implementation form of the first aspect of the present application, after the preset waiting time ends, the radiation signal of the marked area is collected by the radiation detector array to obtain the radiation distribution feature, which comprises: after the preset waiting time ends, the radiation signal of the marked area is collected by the radiation detector array to obtain the original radiation signal data; the background radiation level of the current environment is collected by the radiation detector array to obtain the background radiation signal data; and the original radiation signal data is compared with the background radiation signal data to eliminate the interference of the background radiation signal data on the original radiation signal data to obtain the radiation distribution feature.

[0010] Optionally, in a fifth implementation form of the first aspect of the present application, the density distribution feature and the radiation distribution feature are fused to obtain a comprehensive feature vector, which comprises: generating a feature weight according to the cargo information; and fusing the density distribution feature and the radiation distribution feature according to the feature weight to obtain the comprehensive feature vector.

[0011] Optionally, in a sixth implementation form of the first aspect of the present application, the threat is identified based on the comprehensive feature vector to obtain a security inspection result, which comprises: identifying an abnormal feature of the comprehensive feature vector to obtain an abnormal identification result; if the abnormal identification result is that there is an abnormal feature, performing energy spectrum analysis on the comprehensive feature vector to obtain an energy spectrum analysis result; and generating the security inspection result according to the abnormal identification result and the energy spectrum analysis result.

[0012] The second aspect of the present application provides a security inspection system, comprising a control device, and a dual-energy X-ray generating device and a radiation detector array electrically connected with the control device; the control device is used for executing the security inspection method according to any one of the above.

[0013] The third aspect of the present application provides a security inspection device, comprising a memory and at least one processor, wherein the memory stores instructions; and the at least one processor invokes the instructions in the memory to enable the computer device to execute the steps of the security inspection method according to any one of the above.

[0014] The fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and the instructions are executed by a processor to implement the steps of the security inspection method according to any one of the above.

[0015] In the technical solution of the present application, first, the goods are identified and analyzed to obtain detailed goods information, and the working parameters of the security inspection system are dynamically adjusted according to the detailed goods information, thereby enhancing the adaptability of the system. Then, the dual-energy X-ray generating device is used to obtain the density distribution characteristics, and the radiation detector array is used to collect the radiation distribution characteristics, and the two are fused to generate a comprehensive feature vector, thereby greatly improving the detection accuracy. Finally, threat identification is performed based on the comprehensive feature vector, and an accurate security inspection result is output. The present application realizes threat identification based on the fusion result of multiple sources by scheduling multiple detection devices, thereby effectively improving the detection accuracy and adaptability of the security inspection system. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which: Figure 1 The first flowchart of the security inspection method provided by the embodiments of the present application; Figure 2 The second flowchart of the security inspection method provided by the embodiments of the present application; Figure 3 The third flowchart of the security inspection method provided by the embodiments of the present application; Figure 4 The fourth flowchart of the security inspection method provided by the embodiments of the present application; Figure 5 The fifth flowchart of the security inspection method provided by the embodiments of the present application; Figure 6 The sixth flowchart of the security inspection method provided by the embodiments of the present application; Figure 7 The seventh flowchart of the security inspection method provided by the embodiments of the present application; Figure 8 A structure schematic diagram of a security inspection system provided for an embodiment of the present application is shown in the figure; Figure 9 A structure schematic diagram of a security inspection device provided for an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0017] The present application provides a security inspection method, system, device and storage medium, which first performs identification analysis on goods to obtain detailed goods information, and dynamically adjusts the working parameters of the security inspection system according to the detailed goods information, thereby enhancing the adaptability of the system. Then, the density distribution characteristics are obtained by using a dual-energy X-ray generating device, and the radiation distribution characteristics are collected by using a radiation detector array, and the comprehensive feature vector is generated through feature fusion of the two, thereby greatly improving the detection accuracy. Finally, threat identification is performed based on the comprehensive feature vector, and an accurate security inspection result is output. Through scheduling multiple detection devices, threat identification based on the fusion result of multiple source data is realized, and the detection accuracy and adaptability of the security inspection system are effectively improved.

[0018] The terms "first", "second", "third", "fourth" and the like in the description, claims, as well as throughout the figures of the present application, where they occur, are used for distinguishing between similar objects and are not necessarily used in a sequential or chronological sense. It is to be understood that the terms so used are interchangeable under appropriate circumstances and embodiments of the application described herein are capable of functioning in other sequences than those explicitly described or otherwise specifically referenced herein. Furthermore, the terms "comprise", "include", "contain", "have" and any variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, system, product or apparatus that comprises, includes or contains one step or unit, or a number of steps or units does not include, or contain, or is not only including or containing those steps or units expressly listed or the like.

[0019] For the convenience of understanding, the specific flow of the embodiment of the present application is described below. Please refer to Figure 1 One embodiment of the security inspection method in the embodiment of the present application comprises the following steps: The security inspection system comprises a control device, and a dual-energy X-ray generating device and a radiation detector array electrically connected to the control device; In the embodiment, the security inspection system specifically comprises the following: The control device can adopt a common industrial computer, such as a Wellin industrial computer IPC-610H. The control device serves as the central controller of the whole system, and is responsible for scheduling and coordinating the work of other devices. The dual-energy X-ray generating device can be a Hi-Scan10080 type dual-energy X-ray generator, which can generate X-rays of low and high energy for scanning the density distribution of goods. The radiation detector array can adopt a PMT-100 type gamma ray and neutron detector array, which is used to collect the radiation signal of the cargo; The reader can use a Symbol LS4278 type RFID / barcode reader, which is used to obtain the cargo identification information; The mechanical transmission module adopts a common motorized roller conveyor, such as a roller conveyor device based on a Doctor MSK series servo motor, which is responsible for controlling the movement of the cargo in the detection area; The control device is electrically connected with the dual-energy X-ray generating device, the radiation detector array, the reader and the mechanical transmission module through different communication interfaces; The control principle of the security inspection system is as follows: the reader scans the RFID tag or barcode on the cargo, and transmits the cargo identification information to the control device; the control device analyzes the information to generate key attributes such as cargo type and size; the control device queries the preset parameter table according to the cargo information, dynamically adjusts the energy ratio of the dual-energy X-ray generating device, the sampling frequency and sensitivity of the radiation detector array, and the speed and time window of the mechanical transmission module; the mechanical transmission module moves the cargo at the set speed, the dual-energy X-ray generating device emits low-energy and high-energy X-rays, the X-ray image of the cargo is collected and the density distribution feature is extracted, and the area needing to be detected is marked; then the mechanical transmission module moves the cargo to the detection area of the radiation detector array, after the preset waiting time ends, the radiation detector array collects the radiation signal of the marked area and transmits the data to the control device; the control device performs multi-source data fusion on the density distribution feature and the radiation distribution feature to generate a comprehensive feature result, and performs threat identification based on the result to output the final security inspection conclusion.

[0020] The security inspection method comprises the steps of: 101. Identifying and analyzing the cargo to obtain cargo information; In this embodiment, the system uses the reader to obtain the code information on the cargo identification object and analyzes it to generate detailed cargo information (such as type, size, weight, etc.), which provides basic data support for subsequent dynamic parameter adjustment.

[0021] 102. Adjusting the working parameters of the security inspection system according to the cargo information; In this embodiment, the specific working parameters of the dual-energy X-ray generating device, the radiation detector array and the mechanical transmission module are generated in combination with the cargo information and the preset parameter table, to ensure that the security inspection system can adapt to the needs of different types of cargo.

[0022] 103. After the working parameter adjustment is completed, the dual-energy X-ray generating device is used to perform X-ray scanning on the cargo to obtain the density distribution feature and the marked area; In the embodiment, the dual-energy X-ray generating device scans the cargo according to the adjusted parameters to generate high-energy images and low-energy images, analyzes the density difference between the two, extracts the density distribution characteristics, and screens out the marked area that needs to be detected, thereby providing a clear target area for subsequent radiation signal collection.

[0023] 104、After the waiting time ends, the radiation detector array collects radiation signals in the marked area to obtain radiation distribution characteristics; In the embodiment, after the waiting time ends, the radiation detector array collects radiation signals in the marked area and synchronously collects the background radiation level of the current environment; the influence of the background radiation on the collected data is deducted to generate accurate radiation distribution characteristics.

[0024] 105、The density distribution characteristics and the radiation distribution characteristics are fused to obtain a comprehensive feature vector; In the embodiment, the feature weight is generated according to the cargo information, and the density distribution characteristics and the radiation distribution characteristics are weighted and fused based on the feature weight to generate a comprehensive feature vector, thereby realizing the collaborative optimization of multi-modal data and providing more comprehensive data support for threat identification.

[0025] 106、Based on the comprehensive feature vector, threat identification is performed to obtain a security check result; In the embodiment, the system performs abnormal feature identification on the comprehensive feature vector, and if there is an abnormal feature, further performs energy spectrum analysis to confirm the specific radioisotope type, and finally generates a clear security check conclusion according to the abnormal identification result and the energy spectrum analysis result.

[0026] In the embodiment, the cargo is first identified and analyzed to obtain detailed cargo information, and the working parameters of the security check system are dynamically adjusted based on the information, thereby enhancing the adaptability of the system. Then, the dual-energy X-ray generating device is used to obtain the density distribution characteristics, and the radiation detector array is used to collect the radiation distribution characteristics, and the two are fused to generate a comprehensive feature vector, thereby greatly improving the detection accuracy. Finally, based on the comprehensive feature vector, threat identification is performed to output an accurate security check result. By scheduling multiple detection devices, threat identification based on multi-source data fusion results is realized, thereby effectively improving the detection accuracy and adaptability of the security check system.

[0027] Please refer to Figure 2 The two embodiments of the security check method in the embodiment include: The security check system further includes a reader electrically connected to the control device. In the embodiment, the reader reads the identifier on the goods (such as an RFID tag or a barcode) through wireless radio frequency or optical scanning technology; for example, the RFID tag can transmit data through a wireless radio frequency signal, and the barcode is decoded through optical scanning; the read identifier information is transmitted to the control device in real time through a serial port or a Wi-Fi module.

[0028] 201, reading the identifier on the goods by using the reader to obtain the goods identifier information; In the embodiment, when the goods enter the detection area, the reader automatically identifies and reads the code information in the goods identifier, thereby obtaining the goods identifier information; the goods identifier information generally includes basic information such as a unique code of the goods, a batch number, and a source.

[0029] 202, extracting key information from the goods identifier information to obtain goods information; In the embodiment, after the control device receives the goods identifier information, the key information is extracted through a preset rule library or database query, and the final goods information is generated, as follows: The control device performs preliminary analysis on the received identifier information, and extracts key fields such as the type of goods, weight, and specification; Subsequently, based on the built-in goods classification rule table, the control device further maps the extracted key fields to standardized goods attributes, that is, the goods information; for example, the generated goods information can be: “type—seafood”, “specification—standard box”, and “weight range—medium”; the generated goods information is stored in the memory or temporary database of the control device, and is called when dynamically adjusting the working parameters in the subsequent steps; Through the above two steps, the embodiment successfully realizes the conversion from the identifier information (such as “mass: 200 kg”) to the standardized goods information (such as “weight range: medium”); the key role of the conversion is to convert the specific values (such as weight, specification, etc.) in the original identifier information into standardized classification parameters (such as small, medium, and large; standard box, bulk, etc.); the standardized classification parameters can be used as an index to query the parameter table of the dual-energy X-ray generating device and the radiation detector array, so that the system can dynamically adapt to the best detection parameters according to different types and specifications of goods, thereby significantly improving the adaptability and detection efficiency of the security inspection system.

[0030] Please refer to Figure 3 The three embodiments of the security inspection method in the embodiment of the application include: The security inspection system further includes a mechanical transmission module; the control device is electrically connected with the mechanical transmission module; and the mechanical transmission module is used to control the movement of the goods in different detection areas. In this embodiment, the mechanical transmission module adopts a common electric roller conveyor, such as a roller conveying device based on a Dr. Boss MSK series servo motor, and the mechanical transmission module is responsible for controlling the movement of the goods in the detection area. 301、Combine the goods information and the preset parameter table to generate dual-energy X-ray generating device adjustment data and radiation detector array adjustment data; In this embodiment, the parameters of the dual-energy X-ray generating device and the radiation detector array are adjusted according to the specific goods information and the preset parameter table, as follows: For the dual-energy X-ray generating device, first, adjust the ratio of low-energy and high-energy X-rays according to the size and weight range of the goods, for example, for seafood goods of "medium-standard box", set the energy ratio to "low energy: high energy = 4:6"; then, set the exposure time of X-ray scanning according to the specific type of goods, for example, for high-density goods, the exposure time can be increased to 20ms, while for low-density goods, the exposure time can be reduced to 5ms; For the radiation detector array, the sampling frequency and sensitivity need to be set according to the type of goods; for example, for goods that may contain trace radioactive contamination, increase the sampling frequency to 10kHz; for low-risk goods, reduce the sampling frequency to 5kHz; for seafood goods, appropriately increase the sensitivity to distinguish natural radioactive substances; and for industrial goods, further increase the sensitivity to capture artificial radioactive contamination; By combining the goods information and the preset parameter table, accurate adjustment data is generated to ensure that the working parameters of the dual-energy X-ray generating device and the radiation detector array are fully adapted to the current goods characteristics, thereby improving the detection accuracy.

[0031] 302、Obtain the configuration parameters of the mechanical transmission module, and generate mechanical transmission time window data according to the goods information and the configuration parameters; In this embodiment, the control device generates mechanical transmission time window data according to the goods information and the configuration parameters of the mechanical transmission module, and the specific implementation details are as follows: First, read the physical limit parameters from the configuration file of the mechanical transmission module, then calculate the residence time of the goods in the X-ray scanning area and the radiation detection area according to the goods size (such as "standard box") and weight range (such as "medium"); for example, for goods of "medium-standard box", set the residence time in the X-ray scanning area to 3 seconds and the residence time in the radiation detection area to 5 seconds; when generating the mechanical transmission time window data, the acceleration and deceleration characteristics of the mechanical transmission module need to be considered to ensure smooth transition of the goods when entering and leaving the detection area, and to avoid detection errors caused by sudden changes in speed; By accurately calculating the mechanical transmission time window data, this step ensures that the residence time of the goods in different detection areas is adapted to their detection needs.

[0032] 303. Allocate the dual-energy X-ray generator adjustment data, radiation detector array adjustment data, and mechanical transmission time window data to the corresponding equipment to complete the adjustment of working parameters.

[0033] Please see Figure 4 The four embodiments of the security inspection method in this invention include: 401. Use a dual-energy X-ray generator to perform dual-energy X-ray scanning on the cargo to obtain high-energy and low-energy images; In this embodiment, the mechanical transmission module moves the cargo at a set speed to ensure that it stays in the X-ray scanning area for a sufficient time; the dual-energy X-ray generator alternately emits low-energy and high-energy X-rays to scan the cargo, generating high-energy images (reflecting the distribution of high-density materials) and low-energy images (reflecting the distribution of low-density materials); for seafood, high-energy images are used to display high-density areas such as shells or bones, while low-energy images are used to display low-density areas such as soft tissue or voids.

[0034] 402. Compare the density differences between high-energy and low-energy images to obtain density distribution characteristics; In this embodiment, the grayscale value difference between the high-energy image and the low-energy image is compared pixel by pixel to calculate the density value of each pixel. If the grayscale value of a pixel in the high-energy image is significantly higher than that in the low-energy image, the region is determined to be a high-density region. The image is divided into multiple density level regions according to the density value to generate a density distribution map. Key feature parameters, such as the area ratio and position distribution of each density region, are extracted from the density distribution map to form density distribution feature data. By comparing the density differences between high-energy and low-energy images, accurate density distribution features are generated, effectively distinguishing materials of different densities, thereby improving the detection capability of potential smuggled items.

[0035] 403. Based on density distribution characteristics and cargo information, select areas in the cargo that require key inspection to obtain marked areas; In this embodiment, a preset rule base is invoked based on the type field (e.g., "seafood") in the cargo information. For example, the rules for seafood cargo may include "focusing on high-density areas and their surroundings" and "ignoring uniformly distributed low-density areas." Subsequently, based on the density distribution characteristics, key areas that meet the rules are selected. If a high-density area is surrounded by low-density areas with drastic density changes, it is marked as a key detection area, thus obtaining the marked area. For example, for known high-density calcareous areas (e.g., shellfish), the system automatically lowers its priority, while for non-calcareous high-density areas (e.g., areas that may carry metal inclusions), its priority is increased to ensure that the radiation detector can focus on non-calcareous high-density areas that may contain man-made radioactive contamination. By combining the density distribution characteristics and the cargo information, the area needing to be detected is intelligently screened, and the detection accuracy is improved.

[0036] Please refer to Figure 5 The five embodiments of the security inspection method in the embodiment of the application include: 501, after the preset waiting time ends, the radiation signal of the marked area is collected by using the radiation detector array to obtain the original radiation signal data; In this embodiment, after the dual-energy X-ray scanning is completed, the system waits for a preset time to avoid the interference of X-ray scattering on the radiation detector array; the preset time is generally dynamically set according to the type and specification of the cargo; for example, for high-density cargo, the waiting time is generally longer, such as 6 seconds; and for low-density cargo, the waiting time is shorter, such as 4 seconds; the radiation detector array only collects signals from the marked area, ensuring that resources are concentrated in the area that may contain human radioactive contamination; under the set sampling frequency and sensitivity, the gamma ray and neutron signals in the marked area are collected to generate the original radiation signal data; By setting the waiting time and the marked area, the interference of X-ray scattering on the radiation signal collection is effectively avoided, and the unnecessary collection range is reduced, ensuring the quality and pertinence of the original radiation signal data.

[0037] 502, the background radiation level of the current environment is collected by using the radiation detector array to obtain the background radiation signal data; In this embodiment, while collecting the radiation signal of the marked area, the radiation detector array retains a part of the channel for collecting the background radiation level of the environment, and integrates the collected background radiation level of the environment into the background radiation signal data; the background radiation signal data is dynamically updated according to the actual detection environment, ensuring the accuracy of the correction process.

[0038] 503, the original radiation signal data is compared with the background radiation signal data to eliminate the interference of the background radiation signal data on the original radiation signal data to obtain the radiation distribution characteristics; In this embodiment, the received original radiation signal data and background radiation signal data are compared and analyzed, and the original radiation signal data and the background radiation signal data are compared pixel by pixel or region by region to eliminate the influence of the background radiation and generate a radiation distribution characteristic map; then, the area that is still higher than the preset threshold after eliminating the influence of the background radiation is marked as a key area for subsequent threat identification, i.e., the radiation distribution characteristics are obtained.

[0039] Please refer to Figure 6 The six embodiments of the security inspection method in the embodiment of the application include: 601, generating feature weights according to the cargo information; In this embodiment, first, according to the type field in the cargo information, a preset weight rule library is called to generate feature weights; for different types of goods, the system will automatically adjust the feature weights; for example, the rule for seafood goods may be "density distribution feature weight: 0.4, radiation distribution feature weight: 0.6", because there may be natural radioactive substances (such as potassium-40) in seafood goods, so more emphasis is placed on the radiation distribution feature; In this embodiment, the feature weights are dynamically generated according to the cargo information to ensure that the fusion process can adapt to the needs of different types of goods.

[0040] 602, according to the feature weight, the density distribution feature and the radiation distribution feature are fused to obtain a comprehensive feature vector; In this embodiment, first, the density distribution feature and the radiation distribution feature are normalized respectively to ensure that their numerical ranges are consistent; then, the normalized features are weighted and fused according to the feature weights, and the weighted fusion result is integrated into a comprehensive feature vector; when the features are fused, an abnormal enhancement mechanism is introduced, and if the radiation distribution feature of a certain area is significantly higher than the density distribution feature, the weight is appropriately increased during fusion to ensure that potential human radioactive contamination is not ignored; The comprehensive feature vector combines the density distribution feature and the radiation distribution feature, and can more comprehensively reflect the multi-modal information of the goods, thereby improving the detection accuracy and adaptability of the security inspection system.

[0041] Please refer to Figure 7 The seven embodiments of the security inspection method in the embodiment of the application include: 701, abnormal feature recognition is performed on the comprehensive feature vector to obtain an abnormal recognition result; In this embodiment, first, according to the preset abnormal detection rule library, the values in the comprehensive feature vector are compared dimension by dimension to determine whether they are outside the normal range, and if they are outside the normal range, it is preliminarily judged that there may be an abnormality; at this time, a built-in deep learning model (such as a convolutional neural network (CNN) or an attention mechanism (Attention Mechanism)) is used to analyze the overall distribution pattern of the comprehensive feature vector, and if the comprehensive feature vector shows that the density and radiation features of a certain area are significantly higher than those of the surrounding areas, the abnormal recognition result is marked as having an abnormal feature; In addition, the confidence of the evaluation result is evaluated during the abnormal feature recognition process, and if the confidence is lower than a preset threshold, secondary collection and analysis are triggered; In this embodiment, through abnormal feature recognition of the comprehensive feature vector, the possible threat area is quickly located.

[0042] 702, if the abnormal recognition result is that there is an abnormal feature, then the comprehensive feature vector is subjected to energy spectrum analysis to obtain an energy spectrum analysis result; In this embodiment, if the abnormality identification result is that there is an abnormal feature, the feature data related to the gamma-ray energy distribution is extracted from the comprehensive feature vector, the possible type of radioactive isotope is identified through the energy spectrum analysis algorithm (such as peak detection or curve fitting), and the energy spectrum analysis result is generated; for example, whether the energy distribution of a certain abnormal area contains the characteristic peak (such as the 662keV characteristic peak of Cs-137) of a specific radioactive isotope, so as to identify whether the corresponding radioactive isotope exists in the cargo; In addition, if the energy spectrum analysis result shows that there is a suspicious characteristic peak, but the intensity is low, the mechanical transmission module is required to pause the movement of the cargo, and secondary collection and analysis are carried out to ensure the reliability of the detection result. In this embodiment, based on the energy spectrum analysis technology, the specific type of threat is further confirmed, and the detection accuracy is improved.

[0043] 703. Generate the security inspection result according to the abnormality identification result and the energy spectrum analysis result; In this embodiment, if the abnormality identification result is that there is an abnormal feature, and the energy spectrum analysis result shows that Cs-137 is detected, the security inspection result is generated as "human radioactive contamination is detected"; if the security inspection result is "human radioactive contamination is detected", the alarm mechanism is triggered. If the abnormality identification result is that there is no abnormal feature, or the energy spectrum analysis does not detect any radioactive isotope, the security inspection result is generated as "the cargo is safe"; In this embodiment, the explicit security inspection conclusion is generated by combining the abnormality identification result and the energy spectrum analysis result, so that the output content is comprehensive and reliable.

[0044] The security inspection method in the embodiment of the application is described above, and the security inspection system in the embodiment of the application is described below, please refer to Figure 8 An embodiment of the security inspection system in the embodiment of the application includes: The security inspection system includes a control device 801, a dual-energy X-ray generating device 802 and a radiation detector array 803 electrically connected with the control device 801, and further includes a reader 804 and a mechanical transmission module 805 electrically connected with the control device 801.

[0045] Figure 9Fig. 9 is a schematic diagram of a structure of a security inspection device according to an embodiment of the present application. The security inspection device 900 can have a great difference due to different configurations or performances, and can include one or more central processing units (CPUs) 910 (e.g., one or more processors) and a memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and the storage media 930 can be temporary storage or persistent storage. The programs stored in the storage media 930 can include one or more modules (not shown in the figure), each of which can include a series of instruction operations on the security inspection device 900. Further, the processor 910 can be configured to communicate with the storage media 930 and execute the series of instruction operations in the storage media 930 on the security inspection device 900 to implement the steps of the security inspection method provided by the above-mentioned method embodiments.

[0046] The security inspection device 900 can further include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that the security inspection device 900 can further include other components that are not shown in the figure, or include more or fewer components than those shown in the figure, or combine some components, or arrange different components. Figure 9 The structure of the security inspection device shown in the figure does not constitute a limitation on the security inspection device, and can include more or fewer components than those shown in the figure, or combine some components, or arrange different components.

[0047] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores instructions, which, when executed on a computer, cause the computer to perform the steps of the security inspection method.

[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system or device, unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0049] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0050] Finally, it should be noted that: the above only for the preferred examples of the present application, and not for limiting the present application, although the present application is described in detail with reference to the foregoing embodiments, for those skilled in the art, it still can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A security inspection method, characterized in that, The system is applied to a security inspection system, which includes a control device and a dual-energy X-ray generator and a radiation detector array electrically connected to the control device; the security inspection method includes the following steps: The cargo is identified and analyzed to obtain cargo information; Adjust the operating parameters of the security inspection system according to cargo information; After the working parameters are adjusted, the cargo is scanned with X-rays using a dual-energy X-ray generator to obtain density distribution characteristics and marked areas. After the preset waiting time has elapsed, the radiation detector array is used to collect radiation signals from the marked area in order to obtain the radiation distribution characteristics. The density distribution characteristics and radiation distribution characteristics are fused to obtain a comprehensive feature vector; Threat identification is performed based on comprehensive feature vectors to obtain security inspection results.

2. The security inspection method according to claim 1, characterized in that, The security inspection system also includes a reader, which is electrically connected to the control device; the process of identifying and analyzing the cargo to obtain cargo information includes: The identification information of the goods is obtained by reading the markings on the goods using a reader; Key information is extracted from the cargo identification information to obtain cargo information.

3. The security inspection method according to claim 1, characterized in that, The security inspection system also includes a mechanical transmission module; the control device is electrically connected to the mechanical transmission module; the mechanical transmission module is used to control the movement of goods in different inspection areas; The adjustment of the security inspection system's operating parameters based on cargo information includes: Based on cargo information and preset parameter tables, adjust the dual-energy X-ray generator and radiation detector array; Obtain the configuration parameters of the mechanical transmission module, and generate mechanical transmission time window data based on cargo information and configuration parameters; The adjustment data of the dual-energy X-ray generator, the adjustment data of the radiation detector array, and the mechanical transmission time window data are allocated to the corresponding equipment to complete the adjustment of the working parameters.

4. The security inspection method according to claim 1, characterized in that, After the working parameters are adjusted, the cargo is scanned with X-rays using a dual-energy X-ray generator to obtain density distribution characteristics and marked areas, including: Dual-energy X-ray generators are used to scan cargo with dual-energy X-rays to obtain high-energy and low-energy images; By comparing the density differences between high-energy and low-energy images, density distribution characteristics can be obtained; Based on density distribution characteristics and cargo information, areas within the cargo that require focused inspection are selected to obtain marked areas.

5. The security inspection method according to claim 1, characterized in that, After the preset waiting time has elapsed, a radiation detector array is used to collect radiation signals from the marked area to obtain radiation distribution characteristics, including: After the preset waiting time has elapsed, the radiation detector array is used to collect radiation signals from the marked area to obtain raw radiation signal data. The background radiation level of the current environment is collected using a radiation detector array to obtain background radiation signal data; The original radiation signal data is compared with the background radiation signal data to eliminate the interference of the background radiation signal data on the original radiation signal data, so as to obtain the radiation distribution characteristics.

6. The security inspection method according to claim 1, characterized in that, The feature fusion of density distribution features and radiation distribution features to obtain a comprehensive feature vector includes: Generate feature weights based on cargo information; Based on the feature weights, the density distribution features and radiation distribution features are fused to obtain a comprehensive feature vector.

7. The security inspection method according to claim 1, characterized in that, The threat identification based on comprehensive feature vectors to obtain security inspection results includes: Anomaly identification is performed on the comprehensive feature vector to obtain anomaly identification results; If the anomaly identification result indicates the presence of abnormal features, then energy spectrum analysis is performed on the comprehensive feature vector to obtain the energy spectrum analysis results; Security inspection results are generated based on anomaly identification and energy spectrum analysis results.

8. A security inspection system, characterized in that, The security inspection system includes a control device and a dual-energy X-ray generator and a radiation detector array electrically connected to the control device; the control device is used to perform the security inspection method as described in any one of claims 1-7.

9. A security inspection device, characterized in that, The security inspection device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the security inspection device to perform the steps of the security inspection method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the security inspection method as described in any one of claims 1-7.

Images