Dangerous target identification method, device, system and medium based on millimeter wave signal

Abstract

The present invention discloses a dangerous target identification method, device, system and storage medium based on millimeter wave signals. The method includes: transmitting a first millimeter wave electromagnetic signal and a second millimeter wave electromagnetic signal to a target to be detected, and synchronously collecting image information of the target to be detected; identifying the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal; acquiring the physiological sign parameters of the target to be detected according to the echo signal of the second millimeter wave electromagnetic signal; and identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and image information. The embodiment of the present invention transmits a millimeter wave electromagnetic signal to the target to be detected to detect and identify the dangerous goods carrying information and physiological sign parameters of the target to be detected, and synchronously collects its image information, and fuses and judges the dangerousness of the target to be detected through the dangerous goods carrying information, physiological characteristic parameters and image information, thereby effectively improving the accuracy of dangerous target identification and ensuring the reliability of security work.

Description

Technical Field

[0001] The present invention relates to the field of security technology, and in particular to a method, device, system and storage medium for identifying dangerous targets based on millimeter wave signals. Background Art

[0002] Millimeter wave imaging technology is currently widely used in the field of security. It can effectively detect objects hidden in various parts of the body in a non-contact state. It also has the advantages of being harmless to the human body and having strong penetration, which effectively improves the objectivity, accuracy and efficiency of security inspections. However, due to the sharp increase in the number of people undergoing security inspections, radar detection blind spots and detection errors, millimeter wave imaging also has a certain probability of missing detection, which has a certain impact on the reliability and accuracy of security detection.

[0003] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a dangerous target identification method, device, system and storage medium based on millimeter wave signals, aiming to solve the problem of missed detection in millimeter wave radar hazard identification in the prior art, resulting in reduced security detection accuracy.

[0005] The technical solution of the present invention is as follows:

[0006] A method for identifying dangerous targets based on millimeter wave signals comprises the following steps:

[0007] transmitting a first millimeter wave electromagnetic signal and a second millimeter wave electromagnetic signal to a target to be measured respectively, and synchronously collecting image information of the target to be measured;

[0008] Identify the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal;

[0009] Acquiring physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal;

[0010] The danger level of the target to be detected is identified according to the dangerous goods carrying information, physiological characteristic parameters and image information.

[0011] In the dangerous target identification method based on millimeter wave signals, the step of identifying the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal includes:

[0012] receiving an echo signal of the first millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a first electrical signal;

[0013] Performing image reconstruction processing on the target to be measured according to the first electrical signal and then outputting a reconstructed image;

[0014] After performing dangerous goods identification on the reconstructed image, the dangerous goods carrying information of the target to be detected is obtained.

[0015] In the dangerous target identification method based on millimeter wave signals, the step of obtaining the physiological sign parameters of the target to be detected according to the echo signal of the second millimeter wave electromagnetic signal includes:

[0016] receiving an echo signal of the second millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a second electrical signal;

[0017] The vibration information of the chest wall of the target to be measured is obtained according to the analysis of the second electrical signal, and the heart rate and / or breathing rate of the target to be measured is obtained through the vibration information.

[0018] In the dangerous target identification method based on millimeter wave signals, after the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal are respectively transmitted to the target to be detected, and the image information of the target to be detected is synchronously collected, the method further includes:

[0019] Perform facial expression recognition and body behavior recognition on the image information of the target to be tested.

[0020] In the dangerous target identification method based on millimeter wave signals, the dangerous level identification of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and image information includes:

[0021] Judging whether the current target to be tested has abnormal expression or abnormal behavior according to the expression recognition and body behavior recognition results;

[0022] The danger level of the target to be detected is identified according to the dangerous goods carrying information, physiological characteristic parameters, and abnormal expression or abnormal behavior judgment results.

[0023] In the dangerous target identification method based on millimeter wave signals, the dangerous level identification of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and abnormal expression or abnormal behavior judgment results includes:

[0024] Determine whether the current target to be detected is carrying dangerous goods according to the dangerous goods carrying information, and if so, identify it as a confirmed dangerous target; otherwise, obtain physiological characteristic parameters and abnormal expression or abnormal behavior judgment results;

[0025] Compare the physiological characteristic parameters with the preset risk parameter range to determine whether the physiological characteristic parameters of the target to be measured currently fall within the preset risk parameter range;

[0026] When the physiological characteristic parameters of the target to be detected fall into the preset danger parameter range, or the target to be detected has an abnormal expression, or the target to be detected has abnormal behavior, it is identified as a suspected dangerous target; otherwise, it is identified as a safe target.

[0027] The dangerous target identification method based on millimeter wave signals also includes:

[0028] When a target is identified as a confirmed dangerous target or a suspected dangerous target, the corresponding alarm information is output.

[0029] Another embodiment of the present invention further provides a dangerous target identification device based on millimeter wave signals, the device comprising:

[0030] The first millimeter wave radar module is used to transmit a first millimeter wave electromagnetic signal to the target to be measured and receive its echo signal;

[0031] The second millimeter wave radar module is used to transmit a second millimeter wave electromagnetic signal to the target to be measured and receive its echo signal;

[0032] An image acquisition module is used to acquire image information of the target to be measured;

[0033] an identification module, used for acquiring the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal;

[0034] A vital sign parameter module, used for acquiring physiological vital sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal;

[0035] The fusion judgment module is used to identify the danger level of the target to be detected based on the dangerous goods carrying information, physiological characteristic parameters and image information.

[0036] Another embodiment of the present invention further provides a dangerous target identification system based on millimeter wave signals, the system comprising at least one processor; and

[0037] a memory communicatively connected to the at least one processor; wherein,

[0038] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned dangerous target identification method based on millimeter wave signals.

[0039] Another embodiment of the present invention further provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the one or more processors can execute the above-mentioned dangerous target identification method based on millimeter wave signals.

[0040] Another embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the above-mentioned dangerous target identification method based on millimeter wave signals.

[0041] Beneficial effects: The present invention discloses a dangerous target identification method, device, system and storage medium based on millimeter wave signals. Compared with the prior art, the embodiments of the present invention detect and identify the dangerous goods carrying information and physiological sign parameters of the target to be detected by emitting millimeter wave electromagnetic signals to the target to be detected, and synchronously collects its image information, and integrates the dangerousness of the target to be detected through the dangerous goods carrying information, physiological characteristic parameters and image information, thereby effectively improving the accuracy of dangerous target identification and ensuring the reliability of security work. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0043] Figure 1 A flowchart of a preferred embodiment of a dangerous target identification method based on millimeter wave signals provided by the present invention;

[0044] Figure 2 A schematic diagram of functional modules of a preferred embodiment of a dangerous target identification device based on millimeter wave signals provided by the present invention;

[0045] Figure 3 A schematic diagram of the hardware structure of a preferred embodiment of the dangerous target identification system based on millimeter wave signals provided by the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. The embodiments of the present invention are described below in conjunction with the accompanying drawings.

[0047] See also Figure 1 , Figure 1 The flowchart of the preferred embodiment of the dangerous target identification method based on millimeter wave signals provided by the present invention. Figure 1 As shown, it includes the following steps:

[0048] S100, transmitting a first millimeter wave electromagnetic signal and a second millimeter wave electromagnetic signal to a target to be measured, respectively, and synchronously collecting image information of the target to be measured;

[0049] S200, identifying the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal;

[0050] S300, obtaining physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal;

[0051] S400: Identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and image information.

[0052] In this embodiment, when the security dangerous goods inspection is realized by millimeter wave radar, the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal are respectively transmitted to the target to be detected, and the image information of the target to be detected is synchronously collected, the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal are both reflected by the person to be detected and then the corresponding echo signal is fed back, the dangerous goods carrying information of the target to be detected is identified according to the echo signal of the first millimeter wave electromagnetic signal, and the physiological sign parameters of the target to be detected are obtained according to the echo signal of the second millimeter wave electromagnetic signal, that is, electromagnetic signals of different frequencies are respectively transmitted to the personnel undergoing security inspection by two groups of millimeter wave radars arranged in advance, wherein the first millimeter wave electromagnetic signal is used to detect the dangerous goods carrying of the target to be detected The second millimeter-wave electromagnetic signal is used to detect the physiological sign parameters of the target to be detected, and the danger level of the target to be detected is identified according to the dangerous goods carrying information, physiological characteristic parameters and image information. When this embodiment realizes all-round security detection based on millimeter-wave signals, it not only performs millimeter-wave imaging identification on the carry-on items of the inspected person, but also detects the dangerous goods carrying information and physiological sign parameters respectively through two groups of millimeter-wave electromagnetic signals. While detecting through millimeter-wave radar, it also collects image information of the target to be detected. The three types of information of the target to be detected are used to fuse and judge its danger, and the safety of the target to be detected is detected in all directions, so as to avoid the reduction of the reliability of security inspection due to missed detection and false detection of millimeter-wave imaging recognition.

[0053] Furthermore, the step of identifying the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal includes:

[0054] receiving an echo signal of the first millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a first electrical signal;

[0055] Performing image reconstruction processing on the target to be measured according to the first electrical signal and then outputting a reconstructed image;

[0056] After performing dangerous goods identification on the reconstructed image, the dangerous goods carrying information of the target to be detected is obtained.

[0057] In this embodiment, when implementing millimeter wave imaging recognition, the echo signal of the first millimeter wave electromagnetic signal after being reflected by the target to be measured is first received and converted into a first electrical signal, and then the target to be measured is subjected to image reconstruction processing according to the first electrical signal and a reconstructed image is outputted, and then the dangerous goods carrying information of the target to be measured is obtained after dangerous goods identification is performed on the reconstructed image. Specifically, the first millimeter wave electromagnetic signal is transmitted to the target to be measured by a transmitting antenna array of a pre-arranged imaging millimeter wave radar, and the echo signal of the first millimeter wave electromagnetic signal after being reflected by the target to be measured is received by a corresponding receiving antenna array, and after receiving the echo signal, it is demodulated to obtain a corresponding first electrical signal, and before performing image reconstruction according to the first electrical signal, preferably, the first electrical signal is first filtered and amplified to obtain a stable and interference-free signal to improve imaging accuracy, and then the first electrical signal is subjected to analog-to-digital conversion to obtain an easily processable digital signal, and the image of the target to be measured is subjected to image reconstruction processing by the digital signal and a reconstructed image is outputted, and the specific image reconstruction method can adopt existing imaging processing The technical implementation will not be elaborated in the present invention. After that, the obtained reconstructed image is subjected to dangerous goods identification to obtain the dangerous goods carrying information of the target to be measured. Since dangerous goods such as guns and knives are different from the relatively smooth surface of human skin, they show sharp features. Therefore, there will be suspicious areas in the obtained reconstructed image. When performing dangerous goods identification, the suspicious area in the reconstructed image can be segmented first, and then the features of the items in the suspicious area can be further extracted. After that, the extracted item features are matched with the preset conventional dangerous goods features, and then the dangerous goods carrying information of the target to be measured is obtained, which realizes contactless dangerous goods carrying detection of the target to be measured, and provides an important basis for subsequent information fusion judgment.

[0058] Further, the acquiring of physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal includes:

[0059] receiving an echo signal of the second millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a second electrical signal;

[0060] The vibration information of the chest wall of the target to be measured is obtained according to the analysis of the second electrical signal, and the heart rate and / or breathing rate of the target to be measured is obtained through the vibration information.

[0061] In this embodiment, not only the millimeter wave radar is used for imaging recognition, but also the physiological sign parameters of the target to be measured are detected, specifically, by receiving the echo signal of the second millimeter wave electromagnetic signal after being reflected by the target to be measured and converting it into a second electrical signal, and then obtaining the vibration information of the chest wall of the target to be measured according to the analysis of the second electrical signal, and obtaining the heart rate and / or breathing rate of the target to be measured through the vibration information. That is, different from the imaging millimeter wave radar, another group of physical sign detection millimeter wave radars for physiological sign detection are pre-arranged at the security inspection place, and the second millimeter wave electromagnetic signal is transmitted to the chest position of the target to be measured through the transmitting antenna array of the physical sign detection millimeter wave radar, and the echo signal of the second millimeter wave electromagnetic signal after being reflected by the target to be measured is received through the corresponding receiving antenna array, and the physiological sign parameter detection is performed after the echo signal is converted into a second electrical signal. When the radio frequency signal of the millimeter wave radar reaches a target and is reflected, the movement of the target will produce frequency modulation, resulting in a corresponding shift in the frequency of the reflected signal. Therefore, when the chest cavity of the human body is used as the detection target of the radar, the displacement of the chest cavity wall will produce proportional modulation on the radar carrier phase, for example, using 60GH The millimeter-wave radar detects the beating of the heart, breathing, etc. The 1.25mm displacement produced by the target is 1 / 4 of the radar wavelength, and the phase change caused is 180°. Therefore, the second electrical signal obtained by demodulating the echo signal can obtain the time-varying phase information proportional to the time-varying displacement of the chest cavity, and then the heart rate and / or breathing rate can be detected from it, so as to realize the contactless and accurate detection of physiological parameters such as human heart rate and breathing through millimeter-wave radar signals. These physiological parameters can reflect the psychological state of the current target to be detected from the side. For example, the heart rate and breathing will change when the target is nervous, panicky, and afraid. By obtaining the physiological parameters of the target to be detected, auxiliary information is provided in the subsequent risk level identification, thereby reducing the probability of missed detection of dangerous targets.

[0062] Furthermore, after respectively transmitting the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal to the target to be measured and synchronously collecting image information of the target to be measured, the method further includes:

[0063] Perform facial expression recognition and body behavior recognition on the image information of the target to be tested.

[0064] In the present embodiment, after synchronously collecting the image information of the target to be tested, the image information is further subjected to expression recognition and body behavior recognition. Since the human body's expression and body behavior will change according to its inner activities, for example, when nervous and afraid, a corresponding expression will be revealed and the body movements will be unnatural, such as trembling, etc., these potentially dangerous expressions and body behaviors can be effectively identified through expression recognition and body behavior recognition, and thus can help identify potential dangerous targets without dangerous items during security inspections, reduce their threat to public safety, increase the coverage of dangerous target identification, and effectively combat various types of dangerous targets. Specific expression recognition and body behavior recognition can use existing recognition technology, for example, through pre-trained expression recognition models and body behavior recognition models based on convolutional neural networks to perform corresponding recognition and classification of the collected images, which will not be elaborated in the present invention.

[0065] Furthermore, the identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and image information includes:

[0066] Judging whether the current target to be tested has abnormal expression or abnormal behavior according to the expression recognition and body behavior recognition results;

[0067] The danger level of the target to be detected is identified according to the dangerous goods carrying information, physiological characteristic parameters, and abnormal expression or abnormal behavior judgment results.

[0068] In this embodiment, when performing a fusion judgment, it is first determined whether the current target to be tested has an abnormal expression or abnormal behavior based on the expression recognition and body behavior recognition results, and then the danger level of the target to be tested is identified based on the dangerous goods carrying information, physiological characteristic parameters, and the abnormal expression or abnormal behavior judgment results. For example, the expression abnormality type and the abnormal behavior type are pre-set, and the expression recognition results and the body behavior recognition results are matched with the preset expression abnormality type and the abnormal behavior type. When the expression recognition result matches any type of expression abnormality, it is considered that there is an expression abnormality. Similarly, when the body behavior recognition result matches any type of body behavior abnormality, it is considered that there is a behavior abnormality. Specific expression abnormality types may include anger, disgust, tension, excitement, etc., indicating that the current target to be tested is emotionally unstable. The behavior abnormality type can be set to multiple groups of limb joint positions according to different application scenarios, so as to flexibly judge the expression and behavior abnormalities of the target to be tested.

[0069] Furthermore, the step of identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters, and abnormal expression or abnormal behavior judgment results includes:

[0070] Determine whether the current target to be detected is carrying dangerous goods according to the dangerous goods carrying information, and if so, identify it as a confirmed dangerous target; otherwise, obtain physiological characteristic parameters and abnormal expression or abnormal behavior judgment results;

[0071] Compare the physiological characteristic parameters with the preset risk parameter range to determine whether the physiological characteristic parameters of the target to be measured currently fall within the preset risk parameter range;

[0072] When the physiological characteristic parameters of the target to be detected fall into the preset danger parameter range, or the target to be detected has an abnormal expression, or the target to be detected has abnormal behavior, it is identified as a suspected dangerous target; otherwise, it is identified as a safe target.

[0073] Furthermore, when making a fusion judgment, the dangerous goods carrying information is first judged, which is the most intuitive and direct dangerous behavior. Therefore, it is first judged whether the current target to be measured is carrying dangerous goods based on the dangerous goods carrying information. If so, it is identified as a confirmed dangerous target. Otherwise, the physiological characteristic parameters and the abnormal expression or behavior judgment results are obtained for further judgment. Specifically, the physiological characteristic parameters are compared with the preset dangerous parameter range to determine whether the physiological characteristic parameters of the current target to be measured fall within the preset dangerous parameter range. For example, the preset dangerous parameter range can be a heart rate greater than or equal to a first threshold, and a breathing rate greater than or equal to a second threshold. The specific values ​​can be flexibly set according to needs. By judging whether the physiological characteristic parameters of the current target to be measured are Whether the target falls into the preset danger parameter range is used to reflect whether it has abnormal performances such as accelerated heartbeat and rapid breathing. When the physiological characteristic parameters of the target fall into the preset danger parameter range, or the target has an abnormal expression or an abnormal behavior, it is identified as a suspected dangerous target, otherwise it is identified as a safe target. That is, as long as the target meets one of the above three abnormalities, it is identified as a suspected dangerous target. On the premise that no dangerous goods are carried, it is identified as a safe target only when there is no abnormal expression, behavior and physical sign parameters. This embodiment uses information fusion to more comprehensively identify and determine the danger level, effectively fills the loopholes in security inspections, eliminates blind spots in security detection, and improves the accuracy of security detection.

[0074] Furthermore, the dangerous target identification method based on millimeter wave signals also includes: outputting corresponding alarm information when a confirmed dangerous target or a suspected dangerous target is identified.

[0075] In this embodiment, when the target to be measured is identified as a confirmed dangerous target or a suspected dangerous target, the corresponding alarm information is output, and the security personnel are promptly informed of the abnormality and danger level of the current target to be measured, so that the security personnel can make rapid and targeted response actions, thereby improving the efficiency of eliminating dangers in security work. In specific implementation, the corresponding alarm information can be output through sound or light, and the two confirmed dangerous targets and the suspected dangerous targets can be distinguished by different sounds and different lights, helping the security personnel to know the dangerous target level at the first time.

[0076] It can be seen from the above method embodiments that the dangerous target identification method based on millimeter wave signals provided by the present invention detects and identifies the dangerous goods carrying information and physiological sign parameters of the target to be detected by emitting millimeter wave electromagnetic signals to the target to be detected, and synchronously collects its image information, and integrates the dangerousness of the target to be detected through the dangerous goods carrying information, physiological characteristic parameters and image information, thereby effectively improving the accuracy of dangerous target identification and ensuring the reliability of security work.

[0077] It should be noted that there is not necessarily a certain order between the above-mentioned steps. A person skilled in the art can understand, based on the description of the embodiments of the present invention, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, may be executed interchangeably, and so on.

[0078] Another embodiment of the present invention provides a portrait segmentation device based on deep learning, such as Figure 2 As shown, the device 1 comprises:

[0079] The first millimeter wave radar module 11 is used to transmit a first millimeter wave electromagnetic signal to the target to be measured and receive its echo signal;

[0080] The second millimeter wave radar module 12 is used to transmit a second millimeter wave electromagnetic signal to the target to be measured and receive its echo signal;

[0081] An image acquisition module 13 is used to acquire image information of the target to be measured;

[0082] An identification module 14, configured to obtain the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal;

[0083] A vital sign parameter module 15, used for acquiring physiological vital sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal;

[0084] The fusion judgment module 16 is used to identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological characteristic parameters and image information.

[0085] The first millimeter-wave radar module 11 is connected to the recognition module 14, the second millimeter-wave radar module 12 is connected to the vital sign parameter module 15, and the image acquisition module 13, the recognition module 14 and the vital sign parameter module 15 are all connected to the fusion judgment module 16. For the specific implementation method, please refer to the corresponding method embodiment above, which will not be repeated here.

[0086] Another embodiment of the present invention provides a dangerous target identification system based on millimeter wave signals, such as Figure 3 As shown, the system 10 includes:

[0087] One or more processors 110 and memory 120, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0088] The processor 110 is used to complete various control logics of the system 10, and it can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP and / or any other such configuration.

[0089] The memory 120, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to the dangerous target identification method based on millimeter wave signals in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the system 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, realizing the dangerous target identification method based on millimeter wave signals in the above method embodiment.

[0090] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the system 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the system 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0091] One or more units are stored in the memory 120, and when executed by one or more processors 110, the dangerous target identification method based on millimeter wave signals in any of the above method embodiments is executed, for example, the above described method is executed. Figure 1 The method comprises steps S100 to S400.

[0092] An embodiment of the present invention provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, to execute the above-described Figure 1 The method comprises steps S100 to S400.

[0093] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0094] Another embodiment of the present invention provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the dangerous target identification method based on millimeter wave signals of the above method embodiment. For example, the execution of the above described Figure 1 The method comprises steps S100 to S400.

[0095] In summary, in the dangerous target identification method, device, system and storage medium based on millimeter wave signals disclosed in the present invention, the method includes: transmitting a first millimeter wave electromagnetic signal and a second millimeter wave electromagnetic signal to the target to be measured, and synchronously collecting image information of the target to be measured; identifying the dangerous goods carrying information of the target to be measured according to the echo signal of the first millimeter wave electromagnetic signal; acquiring the physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal; and identifying the danger level of the target to be measured according to the dangerous goods carrying information, physiological characteristic parameters and image information. The embodiment of the present invention transmits a millimeter wave electromagnetic signal to the target to be measured to detect and identify the dangerous goods carrying information and physiological sign parameters of the target to be measured, and synchronously collects its image information, and integrates and judges the dangerousness of the target to be measured through the dangerous goods carrying information, physiological characteristic parameters and image information, thereby effectively improving the accuracy of dangerous target identification and ensuring the reliability of security work.

[0096] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer electronic device (which can be a personal computer, a server, or a network electronic device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0098] Conditional language such as "can," "can," "might," or "may," among other things, unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey that particular embodiments can include (while other embodiments do not) particular features, elements, and / or operations. Thus, such conditional language is also generally intended to imply that features, elements, and / or operations are anyway required for one or more embodiments or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.

[0099] What has been described herein in this specification and the accompanying drawings includes examples of dangerous target identification methods, devices, systems and storage media that can provide based on millimeter wave signals. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure. In addition, or in an alternative, other embodiments of the present disclosure may be apparent from consideration of this specification and the accompanying drawings and from the practice of the present disclosure as presented herein. It is intended that the examples set forth in this specification and the accompanying drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are employed herein, they are used in a general and descriptive sense and are not used for limiting purposes.

Claims

1. A dangerous target identification method based on millimeter wave signals, characterized in that: The steps include: transmitting a first millimeter wave electromagnetic signal and a second millimeter wave electromagnetic signal to a target to be measured respectively, and synchronously collecting image information of the target to be measured; Identify the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal; Acquiring physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal; Identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters and image information; The hazard level identification results include confirmed dangerous targets, suspected dangerous targets and safe targets; When a confirmed dangerous target or a suspected dangerous target is identified, the corresponding alarm information is output through sound or light, and different sounds and lights are used to distinguish confirmed dangerous targets from suspected dangerous targets; After the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal are respectively transmitted to the target to be measured and the image information of the target to be measured is synchronously collected, the method further includes: Performing facial expression recognition and body behavior recognition on the image information of the target to be tested; The step of identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters and image information includes: Acquire preset abnormal expression types and abnormal behavior types, wherein the abnormal behavior types include multiple groups of limb joint point positions set according to different application scenarios; According to the expression recognition and body behavior recognition results, the abnormal expression type and abnormal behavior type are matched to determine whether the current target to be tested has abnormal expression or abnormal behavior; Identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters, and abnormal expression or abnormal behavior judgment results; The step of identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters, and abnormal expression or abnormal behavior judgment results includes: Determine whether the current target to be detected is carrying dangerous goods according to the dangerous goods carrying information, and if so, identify it as a confirmed dangerous target; otherwise, obtain physiological sign parameters and abnormal expression or abnormal behavior judgment results; Compare the physiological sign parameters with the preset risk parameter range to determine whether the physiological sign parameters of the current target fall within the preset risk parameter range; When the physiological sign parameters of the target to be measured fall into the preset danger parameter range, or the target to be measured has an abnormal expression, or the target to be measured has abnormal behavior, it is identified as a suspected dangerous target; otherwise, it is identified as a safe target.

2. The dangerous target identification method based on millimeter wave signals according to claim 1 is characterized in that: The step of identifying the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal includes: receiving an echo signal of the first millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a first electrical signal; Performing image reconstruction processing on the target to be measured according to the first electrical signal and then outputting a reconstructed image; After performing dangerous goods identification on the reconstructed image, the dangerous goods carrying information of the target to be detected is obtained.

3. The dangerous target identification method based on millimeter wave signals according to claim 1 is characterized in that: The step of acquiring the physiological sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal includes: receiving an echo signal of the second millimeter wave electromagnetic signal after being reflected by the target to be measured and converting the echo signal into a second electrical signal; The vibration information of the chest wall of the target to be measured is obtained according to the analysis of the second electrical signal, and the heart rate and / or breathing rate of the target to be measured is obtained through the vibration information.

4. A dangerous target identification device based on millimeter wave signals, characterized in that: The device comprises: The first millimeter wave radar module is used to transmit a first millimeter wave electromagnetic signal to the target to be measured and receive its echo signal; The second millimeter wave radar module is used to transmit a second millimeter wave electromagnetic signal to the target to be measured and receive its echo signal; An image acquisition module is used to acquire image information of the target to be measured; an identification module, used for acquiring the dangerous goods carrying information of the target to be detected according to the echo signal of the first millimeter wave electromagnetic signal; A vital sign parameter module, used for acquiring physiological vital sign parameters of the target to be measured according to the echo signal of the second millimeter wave electromagnetic signal; A fusion judgment module is used to identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters and image information; The hazard level identification results include confirmed dangerous targets, suspected dangerous targets and safe targets; When a confirmed dangerous target or a suspected dangerous target is identified, the corresponding alarm information is output through sound or light, and different sounds and lights are used to distinguish confirmed dangerous targets from suspected dangerous targets; After the first millimeter wave electromagnetic signal and the second millimeter wave electromagnetic signal are respectively transmitted to the target to be measured and the image information of the target to be measured is synchronously collected, the method further includes: Performing facial expression recognition and body behavior recognition on the image information of the target to be tested; The step of identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters and image information includes: Acquire preset abnormal expression types and abnormal behavior types, wherein the abnormal behavior types include multiple groups of limb joint point positions set according to different application scenarios; According to the expression recognition and body behavior recognition results, the abnormal expression type and abnormal behavior type are matched to determine whether the current target to be tested has abnormal expression or abnormal behavior; Identify the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters, and abnormal expression or abnormal behavior judgment results; The step of identifying the danger level of the target to be detected according to the dangerous goods carrying information, physiological sign parameters, and abnormal expression or abnormal behavior judgment results includes: Determine whether the current target to be detected is carrying dangerous goods according to the dangerous goods carrying information, and if so, identify it as a confirmed dangerous target; otherwise, obtain physiological sign parameters and abnormal expression or abnormal behavior judgment results; Compare the physiological sign parameters with the preset risk parameter range to determine whether the physiological sign parameters of the current target fall within the preset risk parameter range; When the physiological sign parameters of the target to be measured fall into the preset danger parameter range, or the target to be measured has an abnormal expression, or the target to be measured has abnormal behavior, it is identified as a suspected dangerous target; otherwise, it is identified as a safe target.

5. A dangerous target identification system based on millimeter wave signals, characterized in that: The system includes at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the dangerous target identification method based on millimeter wave signals as described in any one of claims 1-3.

6. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the dangerous target identification method based on millimeter wave signals as described in any one of claims 1-3.

Images