CN113671589A

CN113671589A - Safety detection match physical system

Info

Publication number: CN113671589A
Application number: CN202111073794.0A
Authority: CN
Inventors: 赵自然; 陈志强; 李元景; 张丽; 李荐民; 王学武; 康克军; 王子野
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2021-09-14
Filing date: 2021-09-14
Publication date: 2021-11-19

Abstract

The embodiment of the invention discloses a physical system for safely detecting Saybolt, which comprises: object scanning equipment and environment detection equipment dispersed in different areas; the intelligent control center acquires object scanning data transmitted by object scanning equipment in a region, determines a security check scene according to the environment scanning data, and sends networking signals to a networking information processor in the region according to the security check scene; the networked information processor matches and networks the object scanning equipment in the region with the object scanning equipment in other regions with the same security check scene, and calls the detection information of other regions with the same security check scene as the region; the data storage center stores historical detection information of the area where the data storage center is located; the intelligent control center calls the object recognition model, trains the object recognition model according to the detection information and the historical detection information of other areas, and inputs the object scanning data into the trained object recognition model so as to recognize whether the object to be detected carries or is filled with suspicious articles.

Description

Safety detection match physical system

Technical Field

The invention relates to the field of security detection, in particular to a security detection match physical system.

Background

In order to avoid the occurrence of terrorist attack events, etc., a security detection system is generally required to be installed in a specific scene (such as an airport security inspection port or a large-scale event entrance port, etc.) to perform security detection on an object to be inspected. Wherein the object to be examined may comprise a human body or an item of baggage or the like.

At present, a safety detection system can only scan and detect an object to be detected in a certain specific area, and the detection reliability is low.

Disclosure of Invention

The embodiment of the application provides a safety inspection match bo physical system, includes: the system comprises physical detection equipment, an intelligent control center, a data storage center and a networking information processor;

the physical detection device includes: object scanning devices dispersed in different areas and environment detecting devices dispersed in different areas; the object scanning device is used for scanning the object to be detected in the area to obtain object scanning data; the environment detection equipment is used for scanning the environment of the area to obtain environment scanning data;

the object scanning equipment of each area is matched with an environment detection device, an intelligent control center, a data storage center and a networking information processor;

the intelligent control center is used for acquiring object scanning data transmitted by object scanning equipment in the area, determining a security check scene of the object scanning equipment in the area according to the environment scanning data transmitted by environment detection equipment in the area, and sending a networking signal to a networking information processor in the area according to the security check scene, wherein the networking signal is used for indicating that the object scanning equipment in other areas with the same security check scene as the object scanning equipment in the area is matched and networked;

the networking information processor is used for matching and networking the object scanning equipment in the area with the object scanning equipment in other areas with the same security check scene after receiving the networking signal, and calling the detection information of other areas with the same security check scene as the area, wherein the detection information of other areas comprises: the object scanning data scanned by the object scanning equipment in other areas with the same security check scene as the object scanning equipment in the area and the detection result of the object scanning data;

the data storage center is used for storing historical detection information of an area where the data storage center is located, and the historical detection information comprises: historical object scanning data scanned by an object scanning device of the area and detection results of the historical object scanning data;

the intelligent control center is further configured to invoke an object recognition model, train the object recognition model according to the detection information of the other region and the historical detection information, input the acquired object scanning data of the region into the trained object recognition model, so as to recognize the object scanning data of the region and provide a detection result, where the detection result includes: the object to be examined carries or contains a suspicious object, or the object to be examined does not carry or contain a suspicious object.

Compared with the prior art, the safety detection match physical system provided by at least one embodiment of the application has the following beneficial effects: the equipment scattered in different areas in the same security check scene can be integrated into a total system, so that intelligent sensing of full information, linkage control of the scattered security check equipment and interconnection and intercommunication of information are realized, and automatic detection of the security of the object to be detected is realized. And the historical detection information of the region and the detection information of other regions in the same security check scene can be used as a training library of the object identification model, so that the capacity of the training library can be enlarged, and the accuracy of security detection and identification can be improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. Other advantages of the present application may be realized and attained by the instrumentalities and combinations particularly pointed out in the specification and the drawings.

Drawings

The accompanying drawings are included to provide an understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the examples serve to explain the principles of the disclosure and not to limit the disclosure.

Fig. 1 is a schematic structural diagram of a physical system for security detection of a tournament in an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a physical detection device provided in the practice of the present invention.

Detailed Description

The present application describes embodiments, but the description is illustrative rather than limiting and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or instead of any other feature or element in any other embodiment, unless expressly limited otherwise.

The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive concept as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive aspects to form yet another unique inventive aspect, as defined by the claims. Thus, it should be understood that any of the features shown and/or discussed in this application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not limited except as by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.

Further, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other orders of steps are possible as will be understood by those of ordinary skill in the art. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Further, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.

Fig. 1 is a schematic structural diagram of a security detection tournament physical system according to an embodiment of the present invention, and as shown in fig. 1, the security detection tournament physical system may include: the system comprises a physical detection device P, an intelligent control center C, a data storage center D and a networking information processor N.

In this embodiment, the intelligent control center C can communicate and exchange data with the physical detection device P, the data storage center D and the networked information processor N in the area through the interfaces P (0), D (0), N (0) and M (0) individually, in parallel, in series and/or in a network.

The Cyber Physical System (CPS) refers to a complex System with a computing unit and a physical object highly integrated through a communication network, and is formed by mutually embedding and continuously fusing the Cyber physical System and the Cyber physical System containing a digital space so as to achieve the process of interconnection and intercommunication, and finally, a series of intelligent operations such as state perception, real-time analysis, autonomous decision making, accurate execution and the like can be realized.

In this embodiment, a safety detection saibo physical system may be provided, which may be applied to various scenes requiring safety detection, such as a boarding gate, an entry port, a rail transit entrance, or a large-scale activity entrance.

Fig. 2 is a schematic structural diagram of a physical detection device provided in the implementation of the present invention, and as shown in fig. 2, the physical detection device may include: object scanning apparatuses 100 dispersed in different areas and environment detecting apparatuses 200 dispersed in different areas; the object scanning device is used for scanning the object to be detected in the area to obtain object scanning data; and the environment detection equipment is used for scanning the environment of the area to obtain environment scanning data. The object scanning device of each region can be matched with an environment detection device, an intelligent control center, a data storage center and a networking information processor.

In an example, the object to be inspected may include an inspector, and the security detection saiblo physical system may intelligently sense the environment, the inspector and articles carried under the clothing thereof to detect whether the articles carried by the human body are filled with dangerous articles or prohibited articles. And the system can be interconnected and intercommunicated with physical detection equipment and data storage centers distributed in other areas, and a differentiated imaging scheme is provided after perception information and interaction information are integrated, so that an optimized detection result is obtained, and the accuracy of human body security check is greatly improved.

In an example, the object to be inspected can include the luggage to be inspected, and the security detection saibo physical system can carry out intelligent perception to the environment, the luggage to be inspected and the articles contained in the luggage to be inspected to detect whether the human body non-hand-carried luggage is filled with dangerous articles or prohibited articles. And the system can be interconnected and intercommunicated with physical detection equipment and data storage centers distributed in other areas, and a differentiated imaging scheme is provided after perception information and interaction information are integrated, so that an optimized detection result is obtained, and the accuracy of article security inspection is greatly improved.

The luggage to be detected is a general name of packages capable of containing objects in a to-be-detected area, and the side of the luggage to be detected is used for luggage articles which are not carried by a human body. The inspection box may include: express packages, shopping bags, handbags, hand bags, purses, backpacks, rucksacks, satchels, waist bags, various draw-bar boxes and the like.

In this embodiment, one region may be provided with: the system comprises an object scanning device, an environment detection device, an intelligent control center, a data storage center and a networked information processor.

In this embodiment, the intelligent control center C may communicate with the physical detection device P in the area to obtain physical data information detected by the physical detection device P in the area, such as object scan data and environment scan data in this embodiment.

The physical probing apparatus P may be composed of a series of object scanning apparatuses 100 and a series of environment detecting apparatuses 200. The object scanning data of each area during the security check is acquired by object scanning devices scattered in different areas, and the environment scanning data of each area during the security check is acquired by environment detection devices scattered in different areas.

In this embodiment, the object scanning data of each region may be acquired by the object scanning device in each region, where the object scanning data is obtained by scanning the object to be detected in the region where the object scanning device is located.

In an example, the object scan data may include: the object scanning equipment scans the human body scanning data obtained by scanning the person to be detected in the area, and the human body scanning data can comprise the information of articles carried by the person to be detected or the information of articles hidden under clothes. Therefore, whether the person to be detected carries the information of articles such as a mobile phone, a wallet, a key, a certificate and a bank card with the person can be determined through the human body scanning data, and whether suspicious articles are hidden under clothes of the person to be detected can be determined, wherein the suspicious articles can comprise dangerous articles or forbidden articles and the like.

In an example, the object scan data may include: the object scanning equipment scans the to-be-detected luggage in the area to obtain article scanning data, and the article scanning data can comprise the to-be-detected luggage and article information contained in the to-be-detected luggage. Therefore, whether the suspected article is contained in the to-be-detected luggage can be determined through the article scanning data, and the suspected article can comprise dangerous articles or forbidden articles and the like.

In this embodiment, the high integration and complexity of the physical system of the tournament may be utilized to integrate devices dispersed in different areas into one overall system, and especially, a plurality of object scanning devices (which may be referred to as security inspection devices) and a plurality of environment detection devices may be integrated to realize the linkage control of full-information intelligent sensing and distributed security inspection devices and the mutual sharing of information.

In this embodiment, the security inspection scene of the area where the object scanning device is located may be determined by the environment scanning data acquired by the environment detection device in the area where the object scanning device is located. The environment scanning data may include environment data around the object scanning device, and the environment data around the object scanning device for human body security check may help to determine a security check scene where the object scanning device is located.

In an example, a security check scenario may include: a gate, an entry port, a rail transit entrance or a large-scale activity entrance. Different security inspection scenes have different requirements on the articles which are mainly required to be detected and the detection severity, for example, the security inspection at a gate of an airport needs to be more strict, and the detection of powdery explosives and the like needs to be paid more attention to because the harm of the explosives can be enhanced by the closed space on the airplane.

The large-scale activity entrance means that the number of people participating in the activity exceeds a set number of people, such as 100 people, and the specific value of the set number of people can be determined according to the actual situation or experience value.

In an example, an environment detection device may include: the camera is used for scanning the surrounding environment of the area where the camera is located to obtain environment scanning data, and the environment scanning data is used for determining the security check scene of the object scanning equipment in the same area with the camera.

In this embodiment, the environmental scanning data may include an environmental video image around the object scanning device captured by the camera, and the environmental video image captured by the camera is helpful for determining a security check scene where the object scanning device is located.

In an example, as shown in fig. 2, the physical detection device may further include: a scanning information center 300; each object scanning device and each environment detection device can be respectively provided with an interface, and all the interfaces are connected with a scanning information center; and the scanning information center is used for respectively acquiring the object scanning data scanned by the object scanning equipment and the environment scanning data scanned by the environment detection equipment through corresponding interfaces, and transmitting the acquired object scanning data and the acquired environment scanning data to the intelligent control center.

In this embodiment, the object scanning data and the environment scanning data respectively acquired by the object scanning device and the environment detection device may be transmitted to the intelligent control center of the area through the scanning information center. As shown in fig. 2, the

object scanning apparatuses

110, 120, and 130 … … N have

interfaces

111, 121, and 131 … … N (1), respectively, which are connected to the scanning information center 300 for data transmission, respectively, ensuring that the scanning information center 300 can receive the object scanning data acquired by the object scanning apparatus 100. The

environment detection devices

210, 220, 230, … … M have

interfaces

211, 221, 231, … … M (1), respectively, which are connected to the scanning information center 300 for data transmission, respectively, ensuring that the scanning information center 300 can receive the environment scanning data acquired by the environment detection device 200.

After receiving the data from the object scanning device and the environment detection device, the scanning information center 300 first performs certain preprocessing (such as filtering, screening, and fusing), and then transmits the preprocessed object scanning data and environment scanning data to the intelligent control center in the area through the data transmission interface P (0).

The intelligent control center can be used for acquiring object scanning data transmitted by object scanning equipment in the area, determining a security check scene of the object scanning equipment in the area according to the environment scanning data transmitted by environment detection equipment in the area, and sending a networking signal to a networking information processor in the area according to the security check scene, wherein the networking signal is used for indicating that the object scanning equipment in the area is matched with the object scanning equipment in other areas with the same security check scene and is networked.

In this embodiment, an intelligent control center of the local area may be disposed around the object scanning device of each area, and the intelligent control center C may respectively communicate with the object scanning device and the environment detection device of the local area to obtain the object scanning data and the environment scanning data respectively scanned by the object scanning device and the environment detection device of the local area, that is, obtain the object scanning data and the environment scanning data of the local area. The intelligent control center C can communicate with the networking information processor N of the local area to instruct the networking information processor N to match and network the object scanning equipment of the local area with the object scanning equipment of other areas with the same security check scene.

In this embodiment, after the intelligent control center determines the security check scene of the object scanning device in the area according to the environment scanning data, the object scanning device can be automatically matched with the object scanning devices in other areas in the same security check scene through the networking information processor and networked, so as to integrate a plurality of object scanning devices dispersed in different areas in the same security check scene, thereby realizing linkage control of the object scanning devices in the plurality of areas and mutual sharing of information.

The same security check scene refers to a security check scene with the same function, for example, all airport security checks are one security check scene, all entry port operations are one security check scene, similar large activities are the same security check scene, for example, all large unions with similar security levels are the same security check scene, or all singing unions are the same security check scene.

The networking information processor is used for matching and networking the object scanning equipment in the area with the object scanning equipment in other areas with the same security check scene after receiving the networking signal, and calling the detection information of other areas with the same security check scene in the area, wherein the detection information of other areas comprises: the object scanning data scanned by the object scanning device of other areas having the same security check scene with the object scanning device of the area where the object scanning device is located and the detection result of the object scanning data.

In this embodiment, one networking information processor in each region may be arranged around the object scanning device in each region, the networking information processor may communicate with the intelligent control center in the region to acquire the networking signal sent by the intelligent control center, the networking signal may include the security inspection scene of the object scanning device in the region, and the networking information processor may match and network the object scanning devices in all regions having the same security inspection scene according to the security inspection scene of the object scanning device in the region.

In this embodiment, the networked information processors in each area may communicate with each other, the networked information processors may set a network according to a security check scene of the object scanning device in the area where the networked information processors are located, the networked information processors in the area where the networked information processors are located may send networked information to the networked information processors in other areas, the networked information may include the security check scene and a network that needs to be connected to the same security check scene, the networked information processors in other areas having the same security check scene compare the received security check scene with the security check scene in the area where the networked information processors are located, and if the received security check scene is the same as the security check scene, join the network that needs to be connected to the same security check scene that is sent; if not, ignoring the received networking information.

The networked information processors in other areas can communicate with the intelligent control center of the area to acquire the security check scene of the area where the networked information processors are located, or the networked information processors in other areas can communicate with the data storage center of the area to acquire the security check scene of the area where the networked information processors are located.

In this embodiment, after the object scanning devices in other areas having the same security check scene are matched and networked, the networked information processor may invoke the detection information of the other areas having the same security check scene as the area where the object scanning device is located, and may assist the identification of the security detection of the object to be detected according to the detection information of the other areas.

The networked information processors in other areas can communicate with the networked information processors in other areas with the same security check scene, the networked information processors in other areas can communicate with the intelligent control center in the area where the networked information processors are located, the intelligent control center calls data stored in the data storage center to acquire object scanning data stored in the area where the networked information processors are located and detection results of the object scanning data, and therefore detection information of other areas can be obtained.

The data storage center is used for storing historical detection information of the area, and the historical detection information comprises: historical object scan data scanned by an object scanning device of the region and detection results of the historical object scan data.

In this embodiment, a data storage center of the region may be disposed around the object scanning device of each region, and the data storage center of each region is used to store the historical detection information of the region where the data storage center is located, and may assist in identifying the security detection of the object to be detected according to the historical detection information of the region where the data storage center is located.

The intelligent control center may be further configured to invoke an object recognition model, train the object recognition model according to the detection information and the history detection information of other areas, input the acquired object scanning data of the area into the trained object recognition model, so as to recognize the object scanning data of the area and provide a detection result, where the detection result may include: the object to be detected carries or is filled with suspicious articles, or the object to be detected does not carry or is not filled with suspicious articles, or the object to be detected carries or is filled with suspicious articles and marks the position of the suspicious articles.

In this embodiment, the historical detection information of the located area and the detection information of other areas in the same security check scene may be used as auxiliary information for security check, and the historical detection information of the located area and the detection information of other areas in the same security check scene may be used as a training library of the object identification model to train the object identification model. The historical detection information of the area and the detection information of other areas of the same security check scene are used as the training library of the object identification model, so that the capacity of the training library can be enlarged, and the accuracy of the detection and identification at this time is improved.

The training of the object recognition model is trained through a large number of images, for example, the object recognition model can be trained through a large number of historical detection information of the area where the object recognition model is located and detection information of other areas of the same security check scene. The object recognition model may be an intelligent recognition algorithm including pattern recognition or neural network algorithms.

In an example, training the object recognition model based on the detection information and the historical detection information of the other regions may include: and taking a large amount of object scanning data in the historical detection information of the located area and the detection information of other areas of the same security check scene as input parameters of the object identification model, and taking detection results in the historical detection information of the located area and the detection information of other areas of the same security check scene as expected output parameters of the object identification model to train the object identification model.

In this embodiment, the intelligent control center C may call, through communication with the networking information processor N in the area where the intelligent control center C is located, detection information of other areas having the same security check scene as the area where the intelligent control center C is located, acquired by the networking information processor N through the interface N (0). The intelligent control center C can communicate with the data storage center D of the area, and the historical detection information stored in the data storage center D of the area is called through the interface D (0).

In this embodiment, in the physical system of the safety detection saibo, a series of object scanning devices and corresponding environment detection devices are respectively connected to the intelligent control center in the area where the object scanning devices are located, the object scanning devices are used to scan the object to be detected and the articles carried or contained by the object to be detected, the environment detection devices extract the environment information around the person to be detected, the object scanning devices and the environment detection devices upload the information to the intelligent control center after acquiring data, and perform adaptive and intelligent data processing by combining the historical detection information stored in the data storage center (which may be referred to as a database) in the area where the object scanning devices are located and the networking information acquired by the networking information processor, thereby generating a detection result.

The safety detection Saybolt physical system provided by the embodiment of the invention can utilize the correspondence and the intercommunity formed by mutually embedding and fusing the digital space and the physical space by the Saybolt physical system, and can integrate the devices dispersed in different areas in the same security check scene into a total system, so as to realize intelligent sensing of full information, linkage control of the dispersed security check devices and mutual sharing of information interconnection and intercommunication, and realize automatic safety detection of an object to be detected. And the historical detection information of the region and the detection information of other regions in the same security check scene can be used as a training library of the object identification model, so that the capacity of the training library can be enlarged, and the accuracy of security detection and identification can be improved.

In an example embodiment of the present invention, an object scanning apparatus may include: the millimeter wave human body detection device is used for scanning a person to be detected in the region by adopting a millimeter wave imaging detection technology to obtain human body scanning data; the detection result may include: the person to be examined carries the suspicious object with him or the person to be examined does not carry the suspicious object with him.

In practical application, when an object to be detected comprises a human body, the detection object of the existing human body safety detection system comprises small articles such as a mobile phone, a wallet, a key, a certificate, a bank card and the like which are carried by the human body besides the human body. However, the detection of the personal belongings carried by the human body by the current human body safety detection system mainly requires that the person to be detected draws out the carried personal belongings, and then the security inspector uses the metal detector and adopts a direct hand contact manner to check whether the person to be detected still carries the personal belongings so as to manually detect whether the personal belongings belong to dangerous articles, so that the detection efficiency is low.

In this embodiment, the human detection equipment of accessible millimeter wave scans personnel of treating examining and the article under its clothing, carries out safety inspection to the human body to whether the article that detects human body and hand-carry is dangerous goods or contraband. Wherein the millimeter waves can penetrate through the clothing and have the capability of inspecting articles hidden under the clothing. The millimeter wave human body detection device scans the person to be detected and the articles under the clothes thereof by adopting a millimeter wave imaging detection technology, which is the same as the millimeter wave scanning principle in the prior art, and the millimeter wave human body detection device is not limited and repeated in the embodiment.

In this embodiment, a Human Security detection seebo physical System (HS-CPS for short) can be provided based on the field of Human Security detection, and can be applied to various scenes requiring Human Security detection, such as a gate, an entry port, a track traffic entry, a large-scale activity entry, and the like. Human safety inspection Sabo physical system can carry out intelligent perception to the environment, wait to examine article and article that carry under personnel and the clothing, simultaneously with the physical detection equipment and interconnection such as data storage center that distribute in other regions, provides differentiated imaging scheme after integration perception information and mutual information, and then obtains optimized testing result, promotes human safety inspection's efficiency and accuracy by a wide margin.

In an example embodiment of the present invention, an object scanning apparatus may include: the X-ray article detection equipment is used for scanning the to-be-detected luggage in the area by adopting an X-ray detection technology to obtain article scanning data; the detection result may include: the case to be detected is filled with suspicious articles or the case to be detected is not filled with suspicious articles.

In this embodiment, accessible X ray article check out test set treats examining case and bag and the article in examining the case and bag scan, carries out safety inspection to article to whether be equipped with dangerous goods or contraband article in the luggage article that human body non-hand-carried in the detection. The X-ray article detection equipment adopts an X-ray detection technology to scan the luggage to be detected and the articles in the luggage to be detected, and the X-ray scanning principle in the prior art is the same, and the embodiment is not limited and repeated herein.

In this embodiment, an Item Security-Cyber Physics System (IS-CPS for short) can be provided based on the field of article Security inspection, and can be applied to various scenes requiring non-portable baggage article detection of a human body, such as a gate, an entry port, a track traffic entrance, or a large activity entrance. The goods safety inspection Sabo physical system can carry out intelligent perception to the environment, wait to examine the article of examining that the case and bag is equipped with and wait to examine article, simultaneously with the physical detection equipment and the interconnection such as data storage center that distribute in other regions, provide differentiated imaging scheme after integration perception information and mutual information, and then obtain the testing result of optimization, promote the efficiency and the accuracy of article safety inspection by a wide margin.

In an exemplary embodiment of the present invention, as shown in fig. 1, the intelligent control center may include: a data fusion module C1, an imaging algorithm module C2, an intelligent judging map module C3 and a decision control module C4.

In this embodiment, the intelligent control center can select a new round of data processing, imaging and recognition algorithms according to the imaging data and the detection results accumulated before through the data fusion module, the imaging algorithm module, the intelligent image judgment module and the decision control module, and automatically optimize the imaging and detection results. The safety detection is mainly divided into three steps: 1. scanning to obtain information, 2, obtaining information through scanning to reconstruct an image, and 3, processing the image and identifying the suspicious dangerous goods.

And the data fusion module is used for screening and fusing data transmitted by the physical detection equipment, the data storage center and the networking information processor in the area to obtain object scanning data of the area, environment scanning data of the area, historical detection information of the area and detection information of other areas with the same security inspection scene as the area.

In this embodiment, the data fusion module mainly performs intelligent screening and intelligent fusion on data transmitted from the object scanning device, the environment detection device, the data storage center, and the networked information processor in the area where the data fusion module is located.

And the imaging algorithm module is used for selecting a preset imaging algorithm to reconstruct an image according to the object scanning data of the region and the environment scanning data of the region to obtain an object reconstruction image of the region.

In this embodiment, the imaging algorithm module may select an imaging algorithm (may also be referred to as an image reconstruction algorithm) according to the screened and fused data to perform data processing and image reconstruction, where the imaging algorithm mainly reconstructs the data into a visual image and marks the suspicious dangerous goods by using an automatic target identification technology.

The imaging algorithm module has the function of automatically selecting an optimal imaging algorithm for data processing and image reconstruction according to object scanning information, environment scanning data (surrounding environment information), past detection results and the like provided by the preprocessed and fused data. The imaging algorithm is flexible, if the requirement on the detection speed is high and the requirement on the detection precision is low, a fast image reconstruction algorithm can be selected, otherwise, an algorithm with low speed and high imaging precision is selected. Besides the two extreme cases, algorithms with moderate imaging speed and image precision exist, and the standard for selecting the imaging algorithm is obtained by integrating information such as object scanning data, surrounding environment information, imaging algorithm selection of similar scenes, selection of past imaging algorithms of the detection area and the like.

In this embodiment, different imaging algorithms may be selected for image reconstruction according to different acquired data, that is, the preset imaging algorithm may be specifically determined according to the object scanning data of the located area, the environment scanning data of the located area, the historical detection information, and the detection results in the object scanning data, the historical detection information, and the detection information of other areas.

Among them, the imaging algorithm (including the imaging algorithm of millimeter wave and X-ray) may include: an echo reconstruction algorithm and a back projection algorithm based on spherical wave expansion, and a compressed sensing or sparse reconstruction algorithm and the like can be adopted according to the requirements on the accuracy and the speed of the reconstructed image. The reconstruction speed, reconstruction accuracy and requirements on computing equipment of different imaging algorithms are different, so that different imaging algorithms can be selected according to different requirements on detection accuracy and speed in a scene and different conditions of the computing equipment. For example, to ensure the flow speed of the passengers or the bags to be detected, a relatively quick algorithm with low reconstruction accuracy can be used for scanning and image reconstruction of all the passengers or the bags to be detected. After the blurred location is found, the location may be scanned and reconstructed more accurately, in which case a slower but more accurate reconstruction algorithm may be used. In this embodiment, the selection of different imaging algorithms is mainly to achieve a balance between the scan reconstruction speed and the accuracy, i.e., to balance the passenger flow (or the luggage to be inspected) speed and the inspection accuracy.

In this embodiment, after the object scanning data of the located area, the environment scanning data of the located area, the historical detection information of the located area, and the detection information of other areas having the same security check scene as the located area are obtained, by using the artificial intelligence-based adaptive imaging algorithm and the intelligent detection method, the intelligent analysis of the differentiated environment and the information to be detected can be realized, and further, the autonomous decision can be made on the detection scheme and the result, so that the accuracy of the security detection is significantly improved.

And the intelligent image judging module is used for substituting the object reconstruction image of the region into the trained object recognition model to determine the object to be detected carrying or containing articles in the region.

In this embodiment, the intelligent image determining module is configured to, after the imaging algorithm module forms the reconstructed image, automatically identify and intelligently determine the articles carried by the human body or the articles in the trunk according to the reconstructed image and the information of the database of the explosives, and provide the detection result of whether there is a danger and the information of the possible dangerous articles.

In this embodiment, after the reconstructed image is obtained, the intelligent image judging module may train the object identification model according to the detection information of other areas and the historical detection information of the area where the object is located, and the intelligent image judging module performs automatic identification and intelligent judgment on a potential suspicious object carried or contained by the object to be detected according to the reconstructed image and the object identification model to identify whether the object to be detected is carried with or contains an object, so as to provide the object to be detected carried or contained with an object in the area where the object is located.

In an example, the training of the object recognition model is trained through a large number of images, and the training of the object recognition model by the intelligent graph judging module according to the detection information of other areas and the historical detection information of the areas may include: selecting an optimal imaging algorithm to reconstruct an image according to object scanning data in a large amount of historical detection information and detection information of other areas, wherein the optimal imaging algorithm is used as an input parameter of an object identification model; and selecting an optimal imaging algorithm to reconstruct an image according to detection results in a large amount of historical detection information and detection information of other areas, wherein the optimal imaging algorithm is used as an expected output parameter of the object recognition model to train the object recognition model.

The decision control module is used for respectively carrying out the following operations on each object to be detected carrying or containing articles: determining the position of the carried or contained article, extracting the article information at the position in the object reconstruction image, and comparing the article information at the position with the pre-stored article attribute information to determine whether the article at the position is a suspicious article.

In this embodiment, the decision control module mainly identifies each object to be inspected carrying or containing an article, and provides a detection result of whether the article carried or contained by the object to be inspected is suspicious and possible suspicious article information.

In this embodiment, the decision control module mainly has the functions of: and giving out the detection result and subsequent operations required by a security inspector according to the detection image obtained by the intelligent image judging module. Specifically, the decision control module makes a detection judgment according to the image with the dangerous goods mark provided by the intelligent image judging module, judges whether suspicious dangerous goods exist or not and the position of the suspicious dangerous goods exist, and displays the judgment to a left operator of the security inspection operation.

The decision control module gives a subsequent operation instruction according to the detection image provided by the intelligent judging module, and the operation instruction may include: whether the luggage needs to be unpacked for inspection or a human body needs to be subjected to contact type hand inspection; if necessary, specific operations are given, such as opening the luggage and performing an important inspection on a certain part of the luggage, or performing a contact type hand inspection on a human body and performing an important inspection on a certain part of the human body.

In this embodiment, the intelligent image determining module may mark the position of the article carried by the human body or the article contained in the bag by using an existing automatic target identification algorithm, and the decision control module extracts data information (i.e., article information) at the position in the object reconstruction image after finding the position of the article carried by the human body or the article contained in the bag, and determines whether the article at the position is a suspicious article according to the extracted information. The implementation principle of extracting data information at a preset position in an object reconstructed image by the decision control module is the same as that of extracting partial information from an image in the existing scheme, and this embodiment is not limited and described herein.

In one example, existing human body security inspection and/or article security inspection technologies may be used to determine positions of different articles in articles or baggage carried by a human body, and after determining the position of a good article, determine whether the article is a suspicious dangerous article.

The determination of the positions of different articles in articles carried by the human body or luggage by adopting the existing human body security check and/or article security check technology can include: after the image is reconstructed, the object reconstructed image is processed by using a trained pattern recognition or neural network algorithm, namely, a recognition algorithm is trained by using a large number of security inspection images marked with the positions of the objects, and the security inspection image marked with the positions of the suspicious objects can be obtained by processing the security inspection scanning image (namely, the object reconstructed image) by using the recognition algorithm, so that the positions of the carried or loaded objects can be determined. After determining the grade of the article, determining whether the article is a suspicious dangerous article may include:

during article security inspection, the dual-energy or multi-energy X-ray technology can be adopted to roughly mark the material types of different articles, and the neural network or the pattern recognition algorithm is matched to obtain more accurate judgment on the material types of the articles.

In human body security inspection, common suspicious objects such as powder, metal and other substances can be judged according to target physical properties such as dielectric property, polarization property, reflection property and the like.

The intelligent image judging module and the decision control module can replace manual image judging and manual system maintenance, so that the labor intensity and the labor amount of security check personnel are greatly reduced, and the manual training and maintenance cost is greatly reduced.

In an example, the data storage center may be further configured to store item attribute information, where the item attribute information includes: secure item information and hazardous item information; the step of comparing the article information at the position with the pre-stored article attribute information by the decision control module to determine whether the article at the position is a suspicious article may include:

determining that the item at the location is a non-suspect item when the item information at the location matches the security item information; when the item information at the location matches the hazardous item information, it is determined that the item at the location is a suspect item.

In this embodiment, the article attribute information may include: and the data of the dielectric property, the reflection property and other physical properties of the suspicious dangerous goods and the non-dangerous goods are common. Comparing the extracted article information with article attribute information stored in a data storage center, and if the extracted article information is matched with a common non-dangerous article, judging that the article carried or loaded by the object to be detected is a safe article; and if the extracted article information is matched with the common dangerous articles, judging that the articles carried or contained by the object to be detected are unsafe articles. When waiting to examine the object including waiting to examine the personnel, if the article attribute information that draws can't match with the article attribute information of storage, then need wait to examine the personnel cooperation show its article of carrying and make the explanation, need the security check personnel to examine the personnel and carry out further contact safety inspection when necessary.

In an example, data stored in the data storage center can be updated according to a detection result of the intelligent control center in the area, so that data updating of the data storage center is realized. And the updating and upgrading of data stored in the data storage centers in all the areas in the whole network can be realized through networking intercommunication, namely, if a certain area detects a novel suspicious dangerous article or the data storage center of the area is updated, the data storage centers in all the other areas in the same security inspection scene can share the distinguishing capability of the dangerous article through interconnection.

In an exemplary embodiment of the present invention, as shown in fig. 1, the intelligent control center may further include: and the networking updating module C4 is used for receiving the networking interactive information and updating and automatically upgrading according to the interactive information.

In this embodiment, the networking update module has a main function of receiving networking interactive information, performing self-update and automatic update according to the interactive information, and updating the whole network equipment through networking to realize self-adaptive dynamic control and autonomous intelligent update.

In an example, the networked updating module receives the networked interactive information and performs updating and automatic upgrading according to the interactive information, and may include:

and transmitting the detection result given by the intelligent control center to a data storage center of the area where the intelligent control center is located, and updating and upgrading when the transmission times reach the set times.

In this embodiment, the detection result may be transmitted and summarized to the data storage center, and when the number of times of transmission and summarization reaches a certain number, automatic update and upgrade of the system are started.

In this embodiment, the updating and upgrading of the networking update module may include: and respectively updating the object recognition model and/or the preset imaging algorithm according to the updated data of the data storage center.

In one example, the object recognition model (recognition algorithm) used by the intelligent control center can be updated according to detection experience and input cases during the use process, so that the object recognition model (recognition algorithm) can be updated and upgraded, and the object recognition model (recognition algorithm) of the intelligent control center in each area in the whole network can be updated and upgraded through networking intercommunication.

In one example, the imaging algorithm used by the intelligent control center can be updated according to the detection experience and the input case, so that the updating and upgrading of the imaging algorithm can be realized, and the updating and upgrading of the imaging algorithm of the intelligent control center in each area in the whole network can be realized through networking intercommunication. The imaging algorithm may be specifically determined according to the updated historical detection information of the local area data storage center and the updated detection information of other areas of other area data storage centers.

In an example, the updating and upgrading by the networked updating module may include: and when the article carried or contained by the object to be detected is a new dangerous article or a safe article, updating the article attribute information stored in the data storage center. In this embodiment, when new dangerous goods and safe goods are found, the property information of the goods in the data storage center can be updated, so that the goods can be accurately detected.

In one example, for an important dangerous article or a certain type of article specified to be detected, the article can be accurately detected through special training of a detection scheme and an imaging algorithm.

In an example, the networking update module may be connected to the networking information processor, and before each detection starts or when networking information is needed, the networking update module sends an instruction (networking signal) to the networking information processor, and invokes the networking information through the networking information processor, for example, invokes other detection devices for detecting areas with similar scenes, that is, obtains the networking information needed by the data fusion module.

In an example, when the networking update module receives an upgrade instruction of the entire system, that is, when the entire system needs to be upgraded, the networking update module receives the instruction first, and starts updating by calling the networking information.

In this embodiment, the physical space and the digital space are embedded and fused by the physical match system to form correspondence and interoperability, and the physical device can be automatically upgraded and adapted to the application scene by updating and evolving the digital space.

In an example embodiment of the present invention, the environment detection apparatus may further include: the infrared detector is used for detecting infrared imaging information of the object to be detected, and the infrared imaging information is used for assisting the object scanning equipment to safely detect the object to be detected.

In this embodiment, the infrared imaging information of the object to be detected and the carried or contained article captured by the infrared detector can be used to assist the millimeter wave or X-ray precise imaging. Because infrared imaging can carry the article with the human body and the better differentiation of human body itself comes, consequently can provide supplementary information for millimeter wave imaging, avoid confusing human organ and carrying the article mutually. Meanwhile, in the scene of the current epidemic situation, infrared detection can automatically provide body temperature information of the person to be detected, and epidemic prevention work in the security inspection link can be facilitated. Accordingly, infrared imaging can better distinguish the articles in the luggage from the luggage itself, and therefore, auxiliary information can be provided for X-ray imaging, and the luggage is prevented from being confused with the articles in the luggage.

In an example embodiment of the present invention, the environment detection apparatus may further include: the infrared detector is used for detecting the ambient temperature or the ambient humidity, and the ambient temperature or the ambient humidity is used for assisting the object scanning equipment to safely detect the object to be detected.

In practical application, because the dielectric characteristics of some hazardous materials, such as powdery materials, that is, the response to electromagnetic waves (including millimeter waves and X-rays), will change with temperature, humidity, etc., in this embodiment, the temperature and humidity information of the current environment can be captured by the infrared detector, the temperature and humidity information of the current environment can be known in advance, and the composition and classification of the materials carried or loaded by the object to be detected can be more accurately determined through millimeter wave or X-ray imaging and data processing.

In an exemplary embodiment of the present invention, as shown in fig. 1, the physical system for security detection of a tournament may further include: and the monitoring and control equipment M is used for monitoring and displaying the detection result of the intelligent control center in the area.

In this embodiment, the physical system for security detection and match game may include a physical detection device P, a data storage center D, a networking information processor N, an intelligent control center C, and a monitoring and control device M, where the intelligent control center C may communicate and exchange data with the physical detection device P, the data storage center D, the networking information processor N, and the monitoring and control device M through interfaces P (0), D (0), N (0), and M (0), respectively, in an independent, parallel, serial, and/or network manner.

In the safety detection Saybook physical system, a series of security check devices and corresponding environment detection devices are respectively connected with an intelligent control center of an area where the security check devices are located, the security check devices are used for scanning an object to be detected and articles carried or contained by the object to be detected, the environment detection devices extract environment information around the object to be detected, the environment detection devices and the object to be detected upload the information to the intelligent control center after acquiring data, and self-adaptive and intelligent data processing is carried out by combining historical detection information stored in a data storage center of the area where the security check devices are located and networking information acquired by a networking information processor, so that a detection result is generated and output through monitoring and control devices.

In an example, the monitoring and control device M may not only display the detection result, but also serve as a manual control platform for modifying the system, so as to implement configuration adjustment and technology upgrade of the entire physical system of the tournament. Therefore, the possibility of reconfiguration needs to be considered in the monitoring and control device M and the intelligent control center C.

It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.

Claims

1. A security detection tournament physical system, comprising: the system comprises physical detection equipment, an intelligent control center, a data storage center and a networking information processor;

the intelligent control center is used for acquiring object scanning data transmitted by object scanning equipment in the area, determining a security check scene of the object scanning equipment in the area according to the environment scanning data transmitted by environment detection equipment in the area, and sending a networking signal to a networking information processor in the area according to the security check scene, wherein the networking signal is used for indicating that the object scanning equipment in the area is matched and networked with the object scanning equipment in other areas with the same security check scene;

the intelligent control center is further configured to invoke an object recognition model, train the object recognition model according to the detection information of the other region and the historical detection information, input the acquired object scanning data of the region into the trained object recognition model, so as to recognize the object scanning data of the region and provide a detection result, where the detection result includes: the object to be detected carries or is filled with suspicious articles, or the object to be detected does not carry or is not filled with suspicious articles, or the object to be detected carries or is filled with suspicious articles and marks the position of the suspicious articles.

2. The system of claim 1, wherein the intelligent control center comprises: the system comprises a data fusion module, an imaging algorithm module, an intelligent image judging module and a decision control module;

the data fusion module is used for screening and fusing data transmitted by the physical detection equipment, the data storage center and the networking information processor in the area to obtain object scanning data of the area, environment scanning data of the area, historical detection information of the area and detection information of other areas with the same security inspection scene as the area;

the imaging algorithm module is used for selecting a preset imaging algorithm to reconstruct an image according to the object scanning data of the region and the environment scanning data of the region to obtain an object reconstruction image of the region;

the intelligent image judging module is used for substituting the object reconstruction image of the area into the trained object recognition model to determine the object to be detected carrying or containing articles in the area;

3. The system of claim 2, wherein the data storage center is further configured to store item attribute information, the item attribute information comprising: secure item information and hazardous item information;

the decision control module compares the article information at the position with pre-stored article attribute information to determine whether the article at the position is a suspicious article, and the decision control module comprises:

determining that the item at the location is a non-suspect item when the item information at the location matches the security item information;

when the item information at the location matches the hazardous item information, determining that the item at the location is a suspicious item.

4. The system of claim 2, wherein the intelligent control center further comprises:

the network updating module is used for receiving the interactive information of the network and updating and automatically upgrading according to the interactive information;

the networking updating module receives the networking interactive information and updates and automatically upgrades the networking interactive information according to the interactive information, and comprises the following steps:

transmitting the detection result given by the intelligent control center to a data storage center of the area where the detection result is located, and updating and upgrading the detection result when the transmission times reach set times;

the updating and upgrading of the networking updating module comprises the following steps: respectively updating the object recognition model and/or the preset imaging algorithm according to the updated data of the data storage center;

and/or the presence of a gas in the gas,

the updating and upgrading of the networking updating module comprises the following steps: and when the article carried or contained by the object to be detected is a new dangerous article or a safe article, updating the article attribute information stored in the data storage center.

5. The system of claim 1, wherein the object scanning device comprises: the millimeter wave human body detection device is used for scanning a person to be detected in the region by adopting a millimeter wave imaging detection technology to obtain human body scanning data;

the detection result comprises: the person to be examined carries the suspicious object with him or the person to be examined does not carry the suspicious object with him.

6. The system of claim 1, wherein the object scanning device comprises: the X-ray article detection equipment is used for scanning the to-be-detected luggage in the area by adopting an X-ray detection technology to obtain article scanning data;

the detection result comprises: the case to be detected is filled with suspicious articles or the case to be detected is not filled with suspicious articles.

7. The system according to claim 5 or 6, wherein the environment detection device comprises: the camera is used for scanning the surrounding environment of the area to obtain environment scanning data, and the environment scanning data is used for determining the security check scene of the object scanning equipment in the same area as the camera;

the security inspection scene comprises: a gate, an entry port, a rail transit entrance or a large-scale activity entrance.

8. The system of claim 7, wherein the environment detection device further comprises: the infrared detector is used for detecting infrared imaging information of the object to be detected, and the infrared imaging information is used for assisting the object scanning equipment to safely detect the object to be detected;

and/or the presence of a gas in the gas,

the infrared detector is used for detecting the ambient temperature or the ambient humidity, and the ambient temperature or the ambient humidity is used for assisting the object scanning equipment to safely detect the object to be detected.

9. The system of claim 1, wherein the physical detection device further comprises: scanning an information center;

each object scanning device and each environment detection device are respectively provided with an interface, and all the interfaces are connected with the scanning information center;

the scanning information center is used for respectively acquiring object scanning data scanned by the object scanning equipment and environment scanning data scanned by the environment detection equipment through corresponding interfaces, and transmitting the acquired object scanning data and the acquired environment scanning data to the intelligent control center.

10. The system of claim 1, further comprising:

and the monitoring and control equipment is used for monitoring and displaying the detection result of the intelligent control center in the area.