A security image acquisition method and device, a security system and a storage medium

Abstract

The application discloses a security check image acquisition method and device, a security check system and a storage medium, relates to the field of active millimeter wave human body security check technology, and can acquire high-quality millimeter wave human body security check images in real time. The method comprises the following steps: constructing target space distribution information of a target object surface contour according to distance information of a plurality of reflection points obtained by detecting the target object by using a ranging sensor; wherein the plurality of reflection points comprise points on the target object surface; determining a target amplitude value of a target position point in the target space distribution information according to echo signals obtained by detecting the target object by using a millimeter wave scanning array; the target position point is a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array; the target amplitude value is used for representing scattering intensity of the target position point to electromagnetic waves emitted by the millimeter wave scanning array; and determining a two-dimensional image of the target object according to the target space distribution information and the target amplitude value.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of active millimeter wave human security technology, and in particular to a security image acquisition method and device, a security system, and a storage medium. BACKGROUND

[0002] Currently, active millimeter wave human security instruments mainly include: horizontal linear array + vertical mechanical scanning, vertical linear array + cylindrical mechanical scanning, and sparse surface array scanning. Active millimeter wave human security image processing methods mainly include: near-field wave number domain range migration algorithm (RMA) and time domain back projection algorithm (BPA). Among them, using RMA to process active millimeter wave human security images can meet the demand for real-time imaging, but the image quality obtained by processing is relatively poor; using BPA to process active millimeter wave human security images can meet the demand for good imaging effect, but BPA needs to perform compensation integration operation on each grid point of the human body projection grid, and the amount of calculation is large, so the real-time performance of BPA is poor.

[0003] Therefore, there is an urgent need for a security image acquisition method that can meet real-time performance and obtain high-quality security images. SUMMARY

[0004] The present application provides a security image acquisition method, device, security system, and storage medium, which can at least realize real-time acquisition of high-quality millimeter wave human security images.

[0005] In a first aspect, the present application provides a security image acquisition method applied to a processor in a security system, the security system further comprising: a millimeter wave scanning array and a ranging sensor, the ranging sensor being configured to measure the distance between a target object and the millimeter wave scanning array; the method comprising: constructing target spatial distribution information of a target object surface contour according to distance information of a plurality of reflection points obtained by the ranging sensor detecting the target object; wherein the plurality of reflection points include points on the target object surface, and the distance information of the reflection points reflects the distance between the reflection points and the millimeter wave scanning array; determining a target amplitude value of a target position point in the target spatial distribution information according to a return signal obtained by the millimeter wave scanning array detecting the target object; the target position point being a point in a two-dimensional plane parallel to the scanning plane of the millimeter wave scanning array; the target amplitude value being used to represent the scattering intensity of the target position point to the electromagnetic wave emitted by the millimeter wave scanning array; and determining a two-dimensional image of the target object according to the target spatial distribution information and the target amplitude value.

[0006] It can be understood that the security image acquisition method provided by the embodiments of the present application adopts a ranging sensor to assist millimeter wave imaging, obtains information of a target object from multiple dimensions, such as distance information of a surface emission point of the target object, echo signals obtained by detecting the target object, and the like; further constructs target space distribution information of the target object according to the distance information of the surface reflection point of the target object, determines a target amplitude value of a target position point in the target space distribution information according to the echo signals obtained by detecting the target object; and finally obtains a two-dimensional image of the target object according to the target space distribution information and the target amplitude value. It can be understood that, compared with the existing millimeter wave detection method, the embodiments of the present application obtain data of the target object from multiple dimensions to obtain space distribution information that can accurately reflect the surface profile of the target object, and then obtain a high-quality security image according to the space distribution information. At the same time, by constructing the target space distribution information of the surface profile of the target object, projection processing is performed based on the target position point in the target space distribution information, the amount of image processing calculation in the detection process is reduced, and the real-time performance of the security image generation is ensured.

[0007] In a possible implementation, constructing the target space distribution information of the surface profile of the target object according to the distance information of the multiple reflection points obtained by detecting the target object by the ranging sensor comprises: constructing initial space distribution information of the surface profile of the target object according to the distance information of the multiple reflection points; determining an expansion value of the initial space distribution information in at least one coordinate dimension of a three-dimensional rectangular coordinate system; the expansion value is used to represent the number of expanded space steps; the space step represents the distance between two adjacent space position points; performing transformation processing on the reflection points in the initial space distribution information according to the expansion value based on the coordinate information of the reflection points in the initial space distribution information, to obtain expansion points of the initial space distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; and obtaining the target space distribution information according to the reflection points in the initial space distribution information and the expansion points of the initial space distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system.

[0008] In another possible implementation, the at least one coordinate dimension of the three-dimensional rectangular coordinate system includes: a horizontal dimension, a height dimension, or a distance dimension; the horizontal dimension is a width direction of the target object; the height dimension is a height direction of the target object; and the distance dimension is a thickness direction of the target object; and the extension value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system includes one or more of the following: determining the extension value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system according to a preset value corresponding to the different coordinate dimensions; or, in a case where the at least one coordinate dimension includes the horizontal dimension or the height dimension, determining the extension value of the initial spatial distribution information in the horizontal dimension according to a preset value corresponding to the horizontal dimension; or determining the extension value of the initial spatial distribution information in the height dimension according to a preset value corresponding to the height dimension; or, in a case where the at least one coordinate dimension includes the distance dimension, determining the extension value of the initial spatial distribution information in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object.

[0009] In another possible implementation, the method further includes: determining the clothing thickness of the target object according to the environment information; and the environment information is used to represent the clothing wearing condition of the target object.

[0010] In another possible implementation, the security inspection system further includes: an optical camera, configured to acquire an optical image of the target object; and the method further includes: inputting the optical image of the target object into a first clothing recognition model to obtain a clothing type of the target object; and determining the clothing thickness of the target object according to the clothing type of the target object; the first clothing recognition model is configured to recognize the clothing type of the target object according to the optical image of the target object; or inputting the optical image of the target object into a second clothing recognition model to obtain the clothing thickness of the target object; and the second clothing recognition model is configured to determine the clothing thickness of the target object according to the optical image of the target object.

[0011] In another possible implementation, the constructing, from the distance information of the plurality of reflection points, the initial spatial distribution information of the surface profile of the target object includes: constructing, from the distance information of the plurality of reflection points, first spatial distribution information of the surface profile of the target object; the first spatial distribution information is represented by using a cylindrical coordinate system; performing coordinate conversion processing on the first spatial distribution information to obtain second spatial distribution information of the surface profile of the target object; the second spatial distribution information is represented by using a three-dimensional rectangular coordinate system; performing conditional filtering on the reflection points in the second spatial distribution information according to a preset condition to obtain third spatial distribution information; the reflection points in the second spatial distribution information are profile points of the surface of the target object; the preset condition is that a coordinate value of a reflection point in a height dimension is in a height value range, a coordinate value of the reflection point in a width dimension is in a width value range, and a coordinate value of the reflection point in a thickness dimension is in a thickness value range; the height value range and the width value range are preset distance ranges; the thickness value range is determined by a depth of a standing area of the target object in the security inspection system; performing interpolation processing on the third spatial distribution information to obtain the initial spatial distribution information.

[0012] In another possible implementation, the determining, from the echo signal obtained by detecting the target object by using the millimeter wave scanning array, the target amplitude value of the target position point in the target spatial distribution information includes: determining, from the echo signal obtained by detecting the target object by using the millimeter wave scanning array, a plurality of candidate amplitude values corresponding to the target position point in the target spatial distribution information; the plurality of candidate amplitude values are amplitude values of spatial scanning points having the same two-dimensional coordinates as the target position point in a vertical direction of a scanning plane; and determining the target amplitude value of the target position point based on the plurality of candidate amplitude values.

[0013] In a second aspect, the present application provides a security inspection image acquisition device, applied to a processor in a security inspection system, the security inspection system further includes: a millimeter wave scanning array and a ranging sensor, the ranging sensor being configured to measure a distance between a target object and the millimeter wave scanning array; the security inspection image acquisition device includes: a construction module configured to construct target spatial distribution information of a surface profile of the target object according to distance information of a plurality of reflection points obtained by detecting the target object by using the ranging sensor; the plurality of reflection points include points on the surface of the target object, and the distance information of the reflection points reflects distances between the reflection points and the millimeter wave scanning array; a determination module configured to determine a target amplitude value of a target position point in the target spatial distribution information according to an echo signal obtained by detecting the target object by using the millimeter wave scanning array; the target position point is a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array in the target spatial distribution information; the target amplitude value is used to represent a scattering intensity of the target position point to electromagnetic waves emitted by the millimeter wave scanning array; and the determination module is further configured to determine a two-dimensional image of the target object according to the target spatial distribution information and the target amplitude value.

[0014] In a possible implementation, the construction module is specifically configured to: construct initial spatial distribution information of a surface profile of the target object according to distance information of the plurality of reflection points; determine an extension value of the initial spatial distribution information in at least one coordinate dimension of the three-dimensional rectangular coordinate system; the extension value is used to represent a number of extended spatial steps; the spatial step represents a distance between two adjacent spatial position points; perform transformation processing on the reflection points in the initial spatial distribution information according to the extension value based on coordinate information of the reflection points in the initial spatial distribution information, to obtain extension points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; and obtain target spatial distribution information according to the reflection points in the initial spatial distribution information and the extension points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system.

[0015] In another possible implementation, the at least one coordinate dimension of the three-dimensional rectangular coordinate system includes: a horizontal dimension, a height dimension, or a distance dimension; the horizontal dimension is a dimension of a width direction of the target object; the height dimension is a dimension of a height direction of the target object; and the distance dimension is a dimension of a thickness direction of the target object; and the determination module is specifically configured to: determine the extension value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system according to a preset value corresponding to the different coordinate dimensions; or, in a case where the at least one coordinate dimension includes the horizontal dimension or the height dimension, determine the extension value of the initial spatial distribution information in the horizontal dimension according to a preset value corresponding to the horizontal dimension; or determine the extension value of the initial spatial distribution information in the height dimension according to a preset value corresponding to the height dimension; or, in a case where the at least one coordinate dimension includes the distance dimension, determine the extension value of the initial spatial distribution information in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object.

[0016] In another possible implementation, the determination module is further configured to determine the clothing thickness of the target object according to environment information; and the environment information is used to represent a clothing wearing condition of the target object.

[0017] In another possible implementation, the security inspection instrument further includes: an optical camera, configured to acquire an optical image of the target object; and the determination module is further configured to: input the optical image of the target object into a first clothing recognition model to obtain a clothing type of the target object; and determine the clothing thickness of the target object according to the clothing type of the target object; the first clothing recognition model is configured to recognize the clothing type of the target object according to the optical image of the target object; or input the optical image of the target object into a second clothing recognition model to obtain the clothing thickness of the target object; and the second clothing recognition model is configured to determine the clothing thickness of the target object according to the optical image of the target object.

[0018] In another possible implementation, the construction module is specifically configured to construct the first spatial distribution information of the target object surface contour according to distance information of the plurality of reflection points; the first spatial distribution information is represented by using a cylindrical coordinate system; the first spatial distribution information is subjected to coordinate conversion processing to obtain second spatial distribution information of the target object surface contour; the second spatial distribution information is represented by using a three-dimensional rectangular coordinate system; the reflection points in the second spatial distribution information are subjected to conditional filtering according to a preset condition to obtain third spatial distribution information; the reflection points in the second spatial distribution information are contour points of the target object surface; the preset condition is that a coordinate value of the reflection point in a height dimension is in a height value range, a coordinate value of the reflection point in a width dimension is in a width value range, and a coordinate value of the reflection point in a thickness dimension is in a thickness value range; the height value range and the width value range are preset distance ranges; the thickness value range is determined by a depth of a standing area of the target object in the security inspection system; the third spatial distribution information is subjected to interpolation processing to obtain initial spatial distribution information.

[0019] In another possible implementation, the determination module is specifically configured to determine a plurality of candidate amplitude values corresponding to a target position point in the target spatial distribution information according to echo signals obtained by detecting the target object by using the millimeter wave scanning array; the plurality of candidate amplitude values are amplitude values of spatial scanning points having the same two-dimensional coordinates as the target position point in a vertical direction of a scanning plane; and determine the target amplitude value of the target position point based on the plurality of candidate amplitude values.

[0020] In a third aspect, the present application provides a security inspection image acquisition device, comprising: one or more processors; one or more memories; wherein the one or more memories are configured to store computer program codes, the computer program codes comprising computer instructions, when the one or more processors execute the computer instructions, the security inspection image acquisition device executes any one of the security inspection image acquisition methods provided in the first aspect.

[0021] In a fourth aspect, the present application provides a security inspection system, comprising: one or more processors; one or more memories; a millimeter wave scanning array configured to detect a target object; a ranging sensor configured to measure a distance between the target object and the millimeter wave scanning array; wherein the one or more memories are configured to store computer program codes, the computer program codes comprising computer instructions, when the one or more processors execute the computer instructions, the one or more processors are configured to implement any one of the security inspection image acquisition methods provided in the first aspect.

[0022] In a fifth aspect, the present application provides a computer readable storage medium, the computer readable storage medium stores computer execution instructions, when the computer execution instructions run on a computer, the computer is caused to execute any one of the security inspection image acquisition methods provided in the first aspect.

[0023] The description of the second aspect to the fifth aspect in the present application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second aspect to the fifth aspect can refer to the beneficial effect analysis of the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 Structure diagram of a security inspection system provided for an embodiment of the present application Figure 1 ;

[0025] Figure 2 Structure diagram of a millimeter wave scanning array provided for an embodiment of the present application

[0026] Figure 3 Structure diagram of a security inspection system provided for an embodiment of the present application Figure 2 ;

[0027] Figure 4 Structure diagram of a horizontal linear array provided for an embodiment of the present application

[0028] Figure 5 Structure diagram of a security inspection system provided for an embodiment of the present application Figure 3 ;

[0029] Figure 6 Structure diagram of a security inspection system provided for an embodiment of the present application Figure 4 ;

[0030] Figure 7 Flow of a security inspection image acquisition method provided for an embodiment of the present application Figure 1 ;

[0031] Figure 8 Flow of a security inspection image acquisition method provided for an embodiment of the present application Figure 2 ;

[0032] Figure 9 Diagram of a three-dimensional rectangular coordinate system provided for an embodiment of the present application

[0033] Figure 10 Diagram of a point cloud provided for an embodiment of the present application Figure 1 ;

[0034] Figure 11 Diagram of a point cloud provided for an embodiment of the present application Figure 2 ;

[0035] Figure 12 Flow of a security inspection image acquisition method provided for an embodiment of the present application Figure 3 ;

[0036] Figure 13A schematic diagram of security imaging provided by an embodiment of the present application

[0037] Figure 14 A structural schematic of a security image acquisition device provided by an embodiment of the present application Figure 1 ;

[0038] Figure 15 A structural schematic of a security image acquisition device provided by an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0039] The term "and / or" in the present document is merely used to describe associated objects, and means that three relationships can exist, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone.

[0040] The terms "first" and "second" and the like in the specification of the present application and the drawings are used to distinguish different objects, or to distinguish different treatments of the same object, and are not used to describe a specific order of the objects.

[0041] In addition, the terms "comprising" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0042] It should be noted that in the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present relevant concepts in a concrete manner.

[0043] In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0044] As described in the background, at present, the active millimeter wave human body security instrument mainly includes: horizontal linear array + vertical mechanical scanning, vertical linear array + cylindrical mechanical scanning and sparse surface array scanning. The active millimeter wave human body security image processing method mainly includes: near-field wave number domain distance migration algorithm (RMA) and time domain backward projection algorithm (BPA). Among them, the RMA algorithm is used to process the active millimeter wave human body security image, which can meet the real-time imaging demand, but the image quality obtained by processing is relatively poor; the BPA algorithm is used to process the active millimeter wave human body security image, which can meet the demand of good imaging effect, but the BPA algorithm needs to perform compensation integral operation on each grid point of the human body projection grid, and the calculation amount is large, so the real-time performance of the BPA algorithm is poor.

[0045] Therefore, there is an urgent need for a security image acquisition method which can meet the real-time performance and obtain high-quality security images.

[0046] Based on the above technical problems, the embodiment of the present application provides a security image acquisition method, the idea of which is to use a millimeter wave scanning array, a ranging sensor and an optical camera to obtain information of a target object from multiple dimensions, such as distance information of a surface emission point of the target object, echo signals obtained by detecting the target object, and optical images of the target object and the like; then construct target space distribution information of the target object according to the distance information of the surface reflection point of the target object and the clothing thickness of the target object obtained by analyzing the optical image (used to supplement the edge information), and determine target amplitude values of target position points in the target space distribution information according to the echo signals obtained by detecting the target object; finally obtain a two-dimensional image of the target object according to the target space distribution information and the target amplitude values. It can be understood that, compared with the existing millimeter wave detection method, the embodiment of the present application obtains data of the target object from multiple dimensions to obtain space distribution information which can accurately reflect the surface profile of the target object, and then obtains a high-quality security image according to the space distribution information; at the same time, through the construction of the target space distribution information of the surface profile of the target object, the projection processing is performed based on the target position points in the target space distribution information, which reduces the image processing calculation amount in the detection process and ensures the real-time performance of the security image generation.

[0047] The embodiments provided by the present application will be specifically introduced below in combination with the drawings of the specification.

[0048] Please refer to Figure 1 which shows a schematic diagram of a security system involved in a security image acquisition method provided by an embodiment of the present application. As shown in Figure 1 , the security system 100 includes a millimeter wave scanning array 110, a ranging sensor 120, an optical camera 130 and a processor 140.

[0049] The millimeter wave scanning array 110 is configured to detect a target object using electromagnetic waves and receive a return signal reflected by the target object.

[0050] The millimeter wave refers to electromagnetic waves with a frequency of 30 GHz to 300 GHz (wavelength of 1 mm to 10 mm). The millimeter wave has a wavelength between a centimeter wave and a light wave, and thus has the advantages of both microwave guidance and photoelectric guidance. In addition, the millimeter wave has a certain penetration, and can penetrate most clothes, thereby having the ability to detect hidden objects.

[0051] As shown in FIG. 1, the millimeter wave scanning array 110 can include a transmitter 111, a receiver 112, a transmitting array element 113, and a receiving array element 114. Figure 2

[0052] The transmitter 111 is a radio device configured to provide a millimeter wave scanning array 110 with a high-power radio frequency signal, and is capable of generating a high-power radio frequency signal modulated by a carrier wave, i.e., an electromagnetic wave. According to the modulation mode, the transmitter can be divided into two types: continuous wave transmitter and pulse transmitter. The transmitter is composed of a first radio frequency oscillator and a pulse modulator.

[0053] The receiver 112 is a device configured to perform frequency conversion, filtering, amplification, and demodulation in the millimeter wave scanning array 110. Through appropriate filtering, a weak high-frequency signal received by the antenna is selected from the accompanying noise and interference, and after amplification and detection, it is used for target detection, target imaging, or other radar signal processing.

[0054] The transmitting array element 113 is an element configured to transmit electromagnetic waves and determine the detection direction in the millimeter wave scanning array 110. When transmitting, the transmitting array element 113 concentrates energy to the direction to be irradiated.

[0055] The receiving array element 114 is an element configured to receive electromagnetic waves in the millimeter wave scanning array 110. When receiving, the receiving array element 114 receives a return signal in the detection direction, and distinguishes the azimuth and / or elevation of the target object.

[0056] In some embodiments, the return signal reflected by the target object received by the receiving array element 114 is subjected to signal processing such as mixing, sampling, digital down-conversion, pulse compression, calibration, etc., to obtain a discrete signal including the return signal of the target object. The discrete signal can be used by the processor 140 to obtain security imaging of the target object.

[0057] In some embodiments, the millimeter wave scanning array 110 is further configured to send the discrete signal of the return signal of the target object to the processor 140.

[0058] The ranging sensor 120 is configured to measure the distance between the target object and the millimeter wave scanning array 110.​

[0059] Optionally, the ranging sensor 120 can be arranged on a plane parallel to the millimeter wave scanning array 110, or the ranging sensor 120 can be arranged on the millimeter wave scanning array 110. In this way, it can be ensured that the ranging sensor 120 can accurately measure the distance between the target object and the millimeter wave scanning array 110.

[0060] Optionally, the ranging sensor 120 can be an ultrasonic ranging sensor, a laser ranging sensor, a depth camera, or other sensors with ranging function.

[0061] For example, the laser ranging sensor is taken as an example. When ranging, the laser ranging sensor emits a laser pulse to the target object, and after being reflected by the target object, the laser scatters in all directions. Part of the scattered light is received by the receiver of the ranging sensor. By calculating the time experienced by the laser pulse from the transmitter to the receiver, the distance of the target object can be determined.

[0062] It can be understood that, since the ranging sensor emits a pulse signal (such as a laser pulse) with a narrow beam (a very thin laser beam) when detecting the target object, the information of multiple points constituting the surface of the target object can be obtained when the target object is detected, and the contour of the surface of the target object can be accurately reflected.

[0063] In some embodiments, the ranging sensor 120 is further configured to send the distance information of the surface of the target object to the processor 140.

[0064] The optical camera 130 is configured to acquire an optical image of the target object.

[0065] In some embodiments, the optical camera 130 is further configured to send the acquired optical image to the processor 140, so that the processor 140 determines the clothing information (such as clothing category or clothing thickness) of the target object according to the optical image.

[0066] The processor 140 is configured to obtain a security image of the target object.

[0067] In some embodiments, the processor 140 determines the security image of the target object according to the discrete signals of the echo signals of the target object sent by the millimeter wave scanning array 110, the distance information of the surface of the target object sent by the ranging sensor 120, and the optical image of the target object sent by the optical camera 130.

[0068] In some embodiments, the processor 140 includes a trained clothing recognition model, which is configured to recognize the clothing type of the target object according to the optical image of the target object, or recognize the clothing thickness of the target object according to the optical image of the target object.

[0069] Optionally, processor 140 can be a server; or processor 140 can be a central processing unit (CPU), graphics processing unit (GPU), network processor (NP), digital signal processor (DSP), microprocessor, microcontroller, programmable logic device (PLD), or any combination thereof. Processor 140 can also be other devices with processing functions, such as circuits, devices, or software modules, and this application does not impose any limitations on this.

[0070] In some embodiments, the security inspection system 100 can be a horizontal linear array + vertical mechanical scan, a vertical linear array + cylindrical mechanical scan, or a sparse area array scan, etc.

[0071] For example, security inspection system 100 can be as follows: Figure 3 The security wall shown, employing a horizontal linear array and vertical mechanical scanning configuration, includes a horizontal linear array, vertical mechanical components, and an optical camera on the front side of the target object's standing position to acquire frontal information. The security wall on the back side of the target object's standing position has the same structure as the front side (not shown in the figure) and is used to acquire rear-side information. Specifically, the horizontal linear array forms a horizontal aperture to acquire the scattered echo from the target object along the horizontal direction; the vertical mechanical components drive the horizontal linear array to scan vertically, forming a height-oriented aperture to acquire the scattered echo from the target object along the height direction.

[0072] For example, such as Figure 4 As shown, the horizontal linear array includes: a ranging sensor (e.g., a lidar), receiving elements, and transmitting elements. The ranging sensor (e.g., a lidar) performs a horizontal scan at a preset scanning angle, less than 180 degrees, the specific angle depending on the distance between the target object's standing position and the ranging sensor. The transmitting elements are designed according to a timing sequence to complete a horizontal scan from left to right or right to left at extremely high speed. The receiving elements receive the echo signal reflected back from the target object. Optionally, the number of receiving elements and transmitting elements can be the same or different, i.e., it can be a single-transmitter single-receiver array, a single-transmitter multi-receiver array, or a multi-transmitter multi-receiver array, etc.

[0073] For example, the security inspection system 100 can also provide services such as Figure 5The sparse array scanning configuration shown includes a millimeter-wave array, one or more ranging sensors (e.g., LiDAR), and an optical camera on the front side of the target's standing position; the security wall on the back side of the target's standing position has the same structure as the front side (not shown in the figure).

[0074] Among them, such as Figure 6 As shown, the installation location and number of ranging sensors (e.g., LiDAR) depend on the distance between the two security gates and the scanning range of the ranging sensors (e.g., LiDAR). Therefore, this application does not limit the number of ranging sensors. Obtaining distance information of the target object by changing the installation location and number of ranging sensors, and using it to construct an imaging grid, is all within the protection scope of this invention.

[0075] The following is a detailed description of a security inspection image acquisition method provided by an embodiment of this application.

[0076] The security inspection image acquisition method provided in this application embodiment can be derived from, for example... Figure 1 The processor in the security inspection system shown executes the commands. Figure 7 As shown in the figure, this application provides a method for acquiring security inspection images, which includes the following steps:

[0077] S201. Based on the distance information of multiple reflection points obtained by the ranging sensor from detecting the target object, construct the target spatial distribution information of the surface contour of the target object.

[0078] The multiple reflection points include points on the surface of the target object, and the distance information of the reflection points reflects the distance between the reflection points and the millimeter-wave scanning array. For example, the distance information of the reflection points can be in coordinate form, such as cylindrical coordinates.

[0079] In some embodiments, the target spatial distribution information described above represents the spatial coordinate distribution of reflection points (or contour points) on the surface contour of the target object. Optionally, the target spatial distribution information can be a two-dimensional spatial information distribution; or, the target spatial distribution information can be a three-dimensional spatial information distribution. For example, the target spatial distribution information can be a point cloud composed of reflection points on the surface of the target object.

[0080] It is understandable that because the pulse signal (such as a laser pulse) emitted by the ranging sensor when detecting a target has a narrow beam (a very thin laser beam), when the target object's surface is detected, information about multiple reflection points that make up the target object's surface can be obtained, which can accurately reflect the spatial distribution of the target object's surface contour.

[0081] In some embodiments, such as Figure 8 As shown, step S201 above can be implemented as follows:

[0082] S2011, constructing initial spatial distribution information of the target object surface profile according to the distance information of the plurality of reflection points.

[0083] The initial spatial distribution information can be understood as a spatial distribution of profile points on the target object surface profile determined based on the distance information of the reflection points, without expansion or optimization of the profile points.

[0084] In some embodiments, the above step S2011 can be implemented as the following steps:

[0085] Step a1, constructing first spatial distribution information of the target object surface profile according to the distance information of the plurality of reflection points.

[0086] The first spatial distribution information is expressed in a cylindrical coordinate system.

[0087] In some embodiments, the first spatial distribution information includes the distance information of the plurality of reflection points, and the spatial distribution of the reflection points in the first spatial distribution information is uniform.

[0088] Step a2, performing coordinate conversion processing on the first spatial distribution information to obtain second spatial distribution information of the target object surface profile.

[0089] The second spatial distribution information is expressed in a three-dimensional rectangular coordinate system.

[0090] In some embodiments, due to the difference between the coordinate systems, the spatial distribution of the reflection points in the second spatial distribution information can be non-uniform. It can be understood that the position of the same reflection point in the cylindrical coordinate system can be different from the position in the three-dimensional rectangular coordinate system, and therefore, the spatial coordinate distribution obtained by converting from the cylindrical coordinate system to the three-dimensional rectangular coordinate system can not be uniform.

[0091] It can be understood that although the ranging sensor can be arranged on the millimeter wave scanning array, or the ranging sensor can be arranged on a plane parallel to the millimeter wave scanning array, the scanning modes of the two are different, for example, the millimeter wave scanning array (taking a horizontal linear array as an example) is horizontal scanning, and the ranging sensor is scanning in a counterclockwise direction. Therefore, the distance information of the reflection points of the target object surface detected by the ranging sensor is in the form of a cylindrical coordinate, but the echo signal of the target object detected by the millimeter wave scanning array is in the form of a three-dimensional rectangular coordinate, and therefore, the distance information of each reflection point in the first spatial distribution information needs to be converted in coordinates according to the positional relationship between the ranging sensor and the millimeter wave scanning array to obtain the second spatial distribution information of the target object surface profile.

[0092] For example, the three-dimensional rectangular coordinate system constructed by the embodiments of the present application can be as follows Figure 9In the form shown, the X-axis is the horizontal direction of the security door (the security door includes a millimeter wave scanning array, a ranging sensor, and an optical camera) (or the width direction of the target object), the Y-axis is the height direction of the security door (or the height direction of the target object), and the Z-axis is the width direction between the two security doors (or the thickness direction of the target object). Assuming that the distance information of the reflection point before conversion is (R, θ, h), and the distance information of the reflection point after conversion is (x, y, z), the coordinate conversion relationship can satisfy the following formula (1):

[0093]

[0094] wherein Z max is the channel spacing between the two security doors, x represents the coordinate of the reflection point on the X-axis of the three-dimensional rectangular coordinate system, y represents the coordinate of the reflection point on the Y-axis of the three-dimensional rectangular coordinate system, z represents the coordinate of the reflection point on the Z-axis of the three-dimensional rectangular coordinate system, R represents the value of the reflection point in the radial direction of the cylindrical coordinate system, θ represents the value of the reflection point in the circumferential direction of the cylindrical coordinate system, and h represents the value of the reflection point in the height direction of the cylindrical coordinate system. The value of 0.5 m as a parameter Q is exemplary and can be set according to requirements in actual applications.

[0095] Exemplarily, the second spatial distribution information of the surface profile of the target object can be in the form shown in Figure 10 wherein Figure 10 is the second spatial distribution information of the target object along the negative direction of the Z-axis, so the reflection points in the second spatial distribution information are mostly distributed in the plane of Z=0. It can be seen that the second spatial distribution information can roughly reflect the surface information of the target object, but there are still some obvious interference points that do not belong to the target object.

[0096] Step a3, conditionally filtering the reflection points in the second spatial distribution information according to a preset condition to obtain third spatial distribution information.

[0097] wherein the reflection points in the third spatial distribution information are profile points of the surface of the target object. It can be understood that the spatial distribution of the reflection points in the third spatial distribution information can be sparse and uneven. The above-mentioned preset condition can be set according to the profile information of the human body, so that the reflection points that do not meet the preset condition are filtered out through conditional filtering, and the reflection points in the third spatial distribution information obtained are profile points of the surface of the target object.

[0098] In some embodiments, the preset condition is that the coordinate value of the reflection point in the height dimension is in the height value range, the coordinate value of the reflection point in the width dimension is in the width value range, and the coordinate value of the reflection point in the thickness dimension is in the thickness value range.

[0099] The height value range and the width value range are preset distance ranges. For example, in the case of a human body as the target object, the height of a person is usually not more than 2 meters, and the width of the body is not more than 1 meter, so the height value range can be [0, 2m], and the width value range can be [0, 1m]. The thickness value range is determined by the depth of the standing area of the target object in the security inspection system.

[0100] For example, the preset condition can satisfy the following formula (2):

[0101]

[0102] Z start is the starting position of the standing area of the target object, Z end is the end position of the standing area of the target object (Z end can represent the depth of the standing area of the target object), and m represents a length unit of meters.

[0103] Step a4, performing interpolation processing on the third spatial distribution information to obtain initial spatial distribution information.

[0104] In some embodiments, among the plurality of first reflection points included in the third spatial distribution information, a plurality of second reflection points are uniformly inserted to obtain the initial spatial distribution information. The first reflection points are reflection points in the third spatial distribution information. The specific difference processing algorithm is not limited in the embodiments of the present application, and can be determined according to processing requirements.

[0105] In some embodiments, the distance information of the second reflection points is determined by the distance information of a plurality of first reflection points adjacent to the second reflection points.

[0106] For example, a linear interpolation method is used to calculate the distance information of a plurality of second reflection points inserted between any two adjacent first reflection points according to the distance information of the two reflection points.

[0107] It can be understood that according to the method provided in the above embodiments, reflection point data that obviously does not belong to the target object can be filtered out to obtain the third spatial distribution information reflecting the surface contour information of the target human body. Meanwhile, considering that the distance between two adjacent reflection points in the third spatial distribution information does not meet the millimeter wave imaging resolution requirement after condition filtering, the initial spatial distribution information that is uniform and has a resolution meeting the requirement can be obtained through interpolation.

[0108] S2012, determining an expansion value of the initial spatial distribution information in at least one coordinate dimension of a three-dimensional rectangular coordinate system.

[0109] The extension value is used to represent the number of extended space steps. The space step represents the distance between two adjacent spatial position points. For example, assuming that the distance between two adjacent spatial position points is Δz, i.e., the space step is Δz, and the extension value is 3, it means that 3 space steps Δz are extended. In this case, Δz < ρ z (ρ z is a millimeter wave scanning array distance resolution unit.

[0110] In some embodiments, the at least one coordinate dimension of the three-dimensional rectangular coordinate system includes: a horizontal dimension, a height dimension, or a distance dimension. The horizontal dimension is a dimension of a width direction of the target object. The height dimension is a dimension of a height direction of the target object. The distance dimension is a dimension of a thickness direction of the target object.

[0111] The above step S2012 can have one or more of the following implementation manners:

[0112] Implementation manner one: determining the extension value according to the preset value.

[0113] In some embodiments, the extension value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system is determined according to a preset value corresponding to the different coordinate dimensions.

[0114] The extension value of the height dimension can be determined according to a preset value of the height dimension, and is used to supplement the edge information of the height direction of the target object. For example, the preset value corresponding to the height dimension can be determined according to the distance between the hair edge and the shoulder edge of the target object.

[0115] The extension value of the horizontal dimension can be determined according to a preset value of the horizontal dimension, and is used to supplement the edge information of the width direction of the target object. For example, the preset value corresponding to the horizontal dimension can be determined according to the distance of the clothing edge of the target object.

[0116] The extension value of the distance dimension can be determined according to a preset value of the distance dimension, and is used to supplement the edge information of the thickness direction of the target object, such as the clothing thickness of the target object. For example, the preset value corresponding to the distance dimension (i.e., the preset value of the clothing thickness) can be determined according to the region, season, weather, and scene information.

[0117] Implementation manner two: determining the extension value according to the preset value and / or the actual detection value.

[0118] In some embodiments, in the case that the at least one coordinate dimension includes the horizontal dimension or the height dimension, the extension value of the initial spatial distribution information in the horizontal dimension is determined according to a preset value corresponding to the horizontal dimension, or the extension value of the initial spatial distribution information in the height dimension is determined according to a preset value corresponding to the height dimension.

[0119] In the case that the at least one coordinate dimension includes a distance dimension, the initial spatial distribution information is determined to have an expansion value in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object, so as to further improve the rationality of the expansion value.

[0120] In the case that the at least one coordinate dimension includes a distance dimension, the initial spatial distribution information is determined to have an expansion value in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object, so as to further improve the rationality of the expansion value.

[0121] In the case that the at least one coordinate dimension includes a distance dimension, the initial spatial distribution information is determined to have an expansion value in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object, so as to further improve the rationality of the expansion value.

[0122] In some embodiments, the clothing thickness of the target object is determined according to environmental information, and the environmental information is used to represent the clothing wearing condition of the target object.

[0123] In some embodiments, the clothing thickness of the target object is determined according to environmental information, and the environmental information is used to represent the clothing wearing condition of the target object.

[0124] For example, if the security inspection system is located in a northern region, the current season is winter, the weather is cold, and the temperature is between -5°C and 1°C, the clothing thickness can be set to 4-5cm; if the security inspection system is located in a southern region, the current season is summer, the weather is hot, and the temperature is between 28°C and 30°C, the clothing thickness can be set to 1-2cm. In addition, the clothing thickness can also be related to the scene in which the target object is located. For example, if the security inspection system is set in a room environment with open heating (for example, a cinema, an opera house, a sports stadium, etc.), even if the current season is winter, the weather is cold, and the temperature is low, the clothing thickness of the target object will not be too thick, and the clothing thickness can be set to 2-3cm.

[0125] That is, in the embodiments of the present application, the expansion value in the distance dimension can be determined based on the measurement deviation between the millimeter wave scanning array and the ranging sensor or the clothing thickness of the target object, or the expansion value in the distance dimension can be determined by simultaneously referring to the measurement deviation between the millimeter wave scanning array and the ranging sensor and the clothing thickness of the target object, so as to further improve the rationality of constructing the target spatial distribution information of the surface profile of the target object and the integrity of the surface profile information of the target object.

[0126] Exemplarily, in the distance dimension, the extension value can include a first extension value in the direction close to the millimeter wave scanning array and a second extension value in the direction away from the millimeter wave scanning array, the first extension value in the direction close to the millimeter wave scanning array can be determined according to the measurement deviation between the millimeter wave scanning array and the ranging sensor, and the second extension value in the direction away from the millimeter wave scanning array can be determined according to the clothing thickness of the target object.

[0127] In some embodiments, the security inspection system further comprises an optical camera configured to acquire an optical image of the target object, and the clothing thickness of the target object can be determined according to the optical image of the target object.

[0128] Exemplarily, the optical image of the target object is input into a first clothing recognition model to obtain a clothing type of the target object, and the clothing thickness of the target object is determined according to the clothing type of the target object. The first clothing recognition model is configured to recognize the clothing type of the target object according to the optical image of the target object.

[0129] Exemplarily, the optical image of the target object is input into a second clothing recognition model to obtain the clothing thickness of the target object. The second clothing recognition model is configured to determine the clothing thickness of the target object according to the optical image of the target object.

[0130] The specific training of the above two modules is not limited in the embodiments of the present application, and can be implemented according to the training principle of the existing model on the basis of ensuring the function implementation of the model.

[0131] In some embodiments, in the case that at least one coordinate dimension includes a distance dimension, the extension value on the side close to the security door is k1, and the extension value on the side away from the security door is k2, and k1 < k2.

[0132] The value of k1 is determined by the measurement deviation between the millimeter wave scanning array and the ranging sensor, and exemplarily, k1 can be 1 or 2, and the specific value can depend on the accuracy of the ranging sensor (when the accuracy of the ranging sensor is high enough, for example, millimeter level, at this time, the value of k1 can be 0); the value of k2 is determined by the clothing thickness of the target object, and the value of k2 determines whether the hidden object can be found, and it is necessary to ensure that the extension value is as low as possible while not losing important information, so the value of k2 is relatively critical. Exemplarily, the value of k2 can satisfy the following formula (3):

[0133]

[0134] wherein, represents an upward rounding function, D represents the thickness of the clothes, for example, D can be 1 cm (centimeter), 2 cm, 5 cm, etc. The value 2 cm in formula 3 is also an example of the value of the parameter q. The value of the parameter q can be reasonably determined according to the actual application, and the parameter q is not limited to the value of 2 cm.

[0135] S2013, based on the coordinate information of the reflection points in the initial spatial distribution information, the reflection points in the initial spatial distribution information are transformed according to the expansion value, and the expansion points of the initial spatial distribution information in at least one coordinate dimension of the three-dimensional rectangular coordinate system are obtained.

[0136] Among them, the above-mentioned expansion point is an expanded point, which is not necessarily a reflection point actually existing on the surface of the target object.

[0137] Optionally, the transformation processing can be expansion or translation, etc.

[0138] In some embodiments, in the case that the at least one coordinate dimension includes a horizontal dimension, the reflection points in the initial spatial distribution information are expanded (or translated) in the horizontal dimension according to the expansion value of the horizontal dimension, to obtain the expansion points in the horizontal dimension; in the case that the at least one coordinate dimension includes a height dimension, the reflection points in the initial spatial distribution information are expanded (or translated) in the height dimension according to the expansion value of the height dimension, to obtain the expansion points in the height dimension; in the case that the at least one coordinate dimension includes a distance dimension, the reflection points in the initial spatial distribution information are expanded (or translated) in the distance dimension according to the expansion value of the distance dimension, to obtain the expansion points in the distance dimension.

[0139] S2014, according to the reflection points in the initial spatial distribution information and the expansion points of the initial spatial distribution information in at least one coordinate dimension of the three-dimensional rectangular coordinate system, the target spatial distribution information is obtained.

[0140] For example, the target spatial distribution information can be in the form as shown in Figure 11 It can be understood that the expansion points in the horizontal dimension supplement the edge information of the clothes of the target object, the expansion points in the height dimension supplement the edge information of the hair edge and the shoulder edge of the target object, and the expansion points in the distance dimension supplement the thickness of the clothes of the target object and the measurement error between the ranging sensor and the millimeter wave scanning array. Therefore, the target spatial distribution information obtained according to the reflection points in the initial spatial distribution information and the expansion points in at least one coordinate dimension can completely include the surface contour information and the edge information of the target object, and therefore, the image reconstruction according to the target spatial distribution information can obtain a high-quality security image.

[0141] S202, determining a target amplitude value of a target position point in the target spatial distribution information according to the echo signal obtained by detecting the target object by using the millimeter wave scanning array.

[0142] The target amplitude value is used to represent a scattering intensity of the electromagnetic wave transmitted by the millimeter wave scanning array at the target position point.

[0143] In some embodiments, the target position point is a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array in the target spatial distribution information. It can be understood that the standing direction of the target object is parallel to the scanning plane of the millimeter wave scanning array, and therefore the two-dimensional plane is a two-dimensional plane constituted by the height dimension and the horizontal dimension of the target object, and the target position point is any position point in the two-dimensional plane.

[0144] In some embodiments, as shown in FIG. 2, the step S202 can be implemented as: Figure 12

[0145] S2021, determining a plurality of candidate amplitude values corresponding to the target position point in the target spatial distribution information according to the echo signal obtained by detecting the target object by using the millimeter wave scanning array.

[0146] The plurality of candidate amplitude values are amplitude values corresponding to spatial scanning points having the same two-dimensional coordinates as the target position point in the vertical direction of the scanning plane.

[0147] The vertical direction of the scanning plane is the distance dimension of the target object, and therefore the spatial scanning points having the same two-dimensional coordinates as the target position point in the vertical direction of the scanning plane include the spatial contour points of the target object and the spatial points inside the target object penetrated by the electromagnetic wave.

[0148] For example, assuming that the target position point is (x n , y n ), then there are (k1+k2+1) spatial scanning points in the vertical direction of the scanning plane, and each spatial scanning point corresponds to an amplitude value, and therefore there are (k1+k2+1) candidate amplitude values.

[0149] It can be understood that, since the security inspection system projects the target spatial distribution information along the distance dimension (i.e., on a projection plane constituted by the horizontal dimension and the height dimension) to obtain a two-dimensional image of the target object, therefore, on the projection plane constituted by the horizontal dimension and the height dimension, one position point corresponds to a plurality of spatial scanning points in the distance dimension.

[0150] In some embodiments, the step S2021 can be implemented according to the following steps:

[0151] ​Step b1, processing the echo signal obtained by detecting the target object according to the millimeter wave scanning array to obtain a discrete signal of the echo signal.

[0152] In some embodiments, the echo signal is processed by mixing, sampling, digital down-conversion and pulse compression to obtain a discrete signal of the echo signal. The discrete signal of the echo signal includes the scattering amplitude and distance information of the scattering points of the target object. For example, the discrete signal of the echo signal satisfies the following formula (4):

[0153]

[0154] Wherein, S ref represents the discrete signal of the echo signal, R n represents the distance from the point (x n , y n , z n ) to the distance of the group of transceiver elements of the millimeter wave scanning array.

[0155] Step b2, determining the amplitude value of each reflection point in the target spatial distribution information according to the discrete signal of the echo signal.

[0156] In some embodiments, a time-domain back-projection algorithm (BP algorithm) is used to calculate the amplitude value of each reflection point in the target spatial distribution information according to the discrete signal of the echo signal.

[0157] For example, the amplitude value of each reflection point can satisfy the following formula (5):

[0158]

[0159] Wherein, σ n represents the target amplitude value of each reflection point, R nj represents the slant range from the i th transmitting element to the n th reflection point, R nj represents the slant range from the j th receiving element to the n th reflection point.

[0160] Step b3, determining a plurality of candidate amplitude values corresponding to the target position point in the target spatial distribution information according to the amplitude value of each reflection point in the target spatial distribution information.

[0161] In some embodiments, the target position point is first determined from each reflection point in the target spatial distribution information, and then a plurality of reflection points having the same two-dimensional coordinates as the target position point in the vertical direction of the scanning plane are determined to be spatial scanning points, and the amplitude values corresponding to the spatial scanning points are taken as the plurality of candidate amplitude values.

[0162] S2022, determining the target amplitude value of the target position point based on the plurality of candidate amplitude values.

[0163] Optionally, according to actual requirements, the maximum value, the minimum value, the intermediate value or the average value of the plurality of candidate amplitude values is taken as the target amplitude value of the target position point.

[0164] For example, assuming that the target position point is (x n , y n ), the plurality of candidate amplitude values has (k1+k2+1) values, the maximum value of the plurality of candidate amplitude values (k1+k2+1) can be taken as the target amplitude value σ xnyn of the target position point (x n , y n ).

[0165] It can be understood that, since one position point corresponds to a plurality of candidate amplitude values, thus the user can select the target amplitude value from the plurality of candidate amplitude values according to actual requirements (for example, resolution requirements of the security image), for imaging of the target object.

[0166] S203, determining the two-dimensional image of the target object according to the target spatial distribution information and the target amplitude value.

[0167] In some embodiments, the target spatial distribution information is projected along the direction of the distance dimension to obtain two-dimensional projection information of the target point cloud on a plane constituted by the horizontal dimension and the height dimension, the two-dimensional projection information being the coordinates of the target spatial distribution information in the horizontal dimension (for example, the X-axis in Figure 9 ) and the height dimension (for example, the Y-axis in Figure 9 ); and then the two-dimensional image of the target object is determined according to the target amplitude value corresponding to each position point (x n , y n ) in the two-dimensional projection information.

[0168] In some embodiments, the above method further comprises: performing normalization processing on the amplitude value corresponding to each position point (or coordinate point) in the two-dimensional image to obtain a normalized gray image, and finally displaying the normalized gray image. For example, the normalized gray image can be in the form as shown in Figure 13 From Figure 13 , it can be clearly seen that the mobile phone and the work card on both sides of the human body are clear in outline and details, and there is no background clutter.

[0169] It can be understood that the method provided by the embodiment of the application obtains information of the target object from multiple dimensions, such as distance information of a surface emitting point of the target object, a return signal obtained by detecting the target object, and an optical image of the target object, by using a millimeter wave scanning array, a ranging sensor, and an optical camera; further constructs target space distribution information of the target object according to the distance information of the surface reflecting point of the target object and a clothing thickness of the target object obtained by analyzing the optical image (used for supplementing edge information), and determines a target amplitude value of a target position point in the target space distribution information according to the return signal obtained by detecting the target object; and finally obtains a two-dimensional image of the target object according to the target space distribution information and the target amplitude value. It can be understood that, compared with the existing millimeter wave detection method, the embodiment of the application obtains data of the target object from multiple dimensions to obtain space distribution information that can accurately reflect a surface contour of the target object, and then obtains a high-quality security image according to the space distribution information; meanwhile, by constructing the target space distribution information of the surface contour of the target object, projection processing is performed based on the target position point in the target space distribution information, the calculation amount of image processing in the detection process is reduced, and the real-time performance of generating the security image is ensured.

[0170] As shown in Figure 14 , the embodiment of the application provides a security image acquisition device for executing the security image acquisition method as shown in Figure 7 . The security image acquisition device 300 comprises a construction module 301 and a determination module 302.

[0171] The construction module 301 is configured to construct target space distribution information of a surface contour of a target object according to distance information of a plurality of reflecting points obtained by detecting the target object by using a ranging sensor; wherein the plurality of reflecting points comprise points on the surface of the target object, and the distance information of the reflecting points reflects distances between the reflecting points and a millimeter wave scanning array.

[0172] The determination module 302 is configured to determine a target amplitude value of a target position point in the target space distribution information according to a return signal obtained by detecting the target object by using the millimeter wave scanning array; the target position point is a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array in the target space distribution information; and the target amplitude value is used to represent a scattering intensity of the target position point to electromagnetic waves emitted by the millimeter wave scanning array.

[0173] The determination module 302 is further configured to determine a two-dimensional image of the target object according to the target space distribution information and the target amplitude value.

[0174] In a possible implementation, the construction module 301 is specifically configured to: construct initial spatial distribution information of a surface profile of the target object according to distance information of the plurality of reflection points; determine an expansion value of the initial spatial distribution information in at least one coordinate dimension of the three-dimensional rectangular coordinate system; the expansion value is used to represent a number of expanded spatial steps; the spatial step represents a distance between two adjacent spatial position points; perform transformation processing on the reflection points in the initial spatial distribution information according to the expansion value based on coordinate information of the reflection points in the initial spatial distribution information, to obtain expanded points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; and obtain target spatial distribution information according to the reflection points in the initial spatial distribution information and the expanded points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system.

[0175] In another possible implementation, the at least one coordinate dimension of the three-dimensional rectangular coordinate system includes: a horizontal dimension, a height dimension, or a distance dimension; the horizontal dimension is a width direction dimension of the target object; the height dimension is a height direction dimension of the target object; and the distance dimension is a thickness direction dimension of the target object. The determination module 302 is specifically configured to: determine the expansion value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system according to a preset value corresponding to the different coordinate dimensions; or, in a case where the at least one coordinate dimension includes the horizontal dimension or the height dimension, determine the expansion value of the initial spatial distribution information in the horizontal dimension according to a preset value corresponding to the horizontal dimension; or determine the expansion value of the initial spatial distribution information in the height dimension according to a preset value corresponding to the height dimension; or, in a case where the at least one coordinate dimension includes the distance dimension, determine the expansion value of the initial spatial distribution information in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object.

[0176] In another possible implementation, the determination module 302 is further configured to determine the clothing thickness of the target object according to environment information; the environment information is used to represent a clothing wearing condition of the target object.

[0177] In another possible implementation, the security inspection instrument further includes: an optical camera, configured to acquire an optical image of the target object; and the determination module 302 is further configured to: input the optical image of the target object into a first clothing recognition model to obtain a clothing type of the target object; and determine the clothing thickness of the target object according to the clothing type of the target object; the first clothing recognition model is configured to recognize the clothing type of the target object according to the optical image of the target object; or input the optical image of the target object into a second clothing recognition model to obtain the clothing thickness of the target object; and the second clothing recognition model is configured to determine the clothing thickness of the target object according to the optical image of the target object.

[0178] In another possible implementation, the construction module 301 is specifically configured to construct first spatial distribution information of the target object surface contour according to distance information of the plurality of reflection points; the first spatial distribution information is represented using a cylindrical coordinate system; the first spatial distribution information is subjected to coordinate conversion processing to obtain second spatial distribution information of the target object surface contour; the second spatial distribution information is represented using a three-dimensional rectangular coordinate system; the reflection points in the second spatial distribution information are subjected to conditional filtering according to a preset condition to obtain third spatial distribution information; the reflection points in the second spatial distribution information are contour points of the target object surface; the preset condition is that a coordinate value of the reflection point in a height dimension is in a height value range, a coordinate value of the reflection point in a width dimension is in a width value range, and a coordinate value of the reflection point in a thickness dimension is in a thickness value range; the height value range and the width value range are preset distance ranges; the thickness value range is determined by a depth of a standing area of the target object in the security inspection system; the third spatial distribution information is subjected to interpolation processing to obtain initial spatial distribution information.

[0179] In another possible implementation, the determination module 302 is specifically configured to determine a plurality of candidate amplitude values corresponding to a target position point in the target spatial distribution information according to echo signals obtained by detecting the target object using the millimeter wave scanning array; the plurality of candidate amplitude values are amplitude values of spatial scanning points having the same two-dimensional coordinates as the target position point in a vertical direction of a scanning plane; and determine a target amplitude value of the target position point based on the plurality of candidate amplitude values.

[0180] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiment of the present application provides another possible structural diagram of the security inspection image acquisition device involved in the above-mentioned embodiments. As shown in the figure, the security inspection image acquisition device 400 includes a processor 402, a communication interface 403, and a bus 404. Optionally, the security inspection image acquisition device 400 can further include a memory 401. Figure 15

[0181] The processor 402 can be various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor 402 can be a central processor, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor 402 can also be a combination of computing functions, such as one or more microprocessor combinations, DSP and microprocessor combinations, etc.

[0182] ​The communication interface 403 is configured to connect with other devices through a communication network. The communication network can be an Ethernet, a wireless access network, a wireless local area network (WLAN), or the like.

[0183] The memory 401 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this.

[0184] As a possible implementation, the memory 401 can exist independently of the processor 402, and the memory 401 can be connected with the processor 402 through the bus 404, for storing instructions or program codes. When the processor 402 invokes and executes the instructions or program codes stored in the memory 401, the security check image acquisition method provided by the embodiments of the present application can be implemented.

[0185] In another possible implementation, the memory 401 can also be integrated with the processor 402.

[0186] The bus 404 can be an extended industry standard architecture (EISA) bus or the like. The bus 404 can be divided into an address bus, a data bus, a control bus, and the like. For the convenience of representation, Figure 15 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0187] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the security check image acquisition device is divided into different functional modules to complete all or part of the above described functions.

[0188] The embodiment of the present application further provides a security check system, comprising: one or more processors; one or more memories; a millimeter wave scanning array, configured to scan and detect a target object; and a ranging sensor, configured to measure a distance between the target object and the millimeter wave scanning array; wherein the one or more memories are configured to store computer program codes, the computer program codes comprising computer instructions, and when the one or more processors execute the computer instructions, the one or more processors are configured to implement any of the security check image acquisition methods provided in the above embodiments.

[0189] The embodiment of the present application further provides a computer readable storage medium. All or part of the processes in the above method embodiments can be instructed by computer instructions to be completed by related hardware, and the program can be stored in the computer readable storage medium. When the program is executed, the program can include the processes of the above method embodiments. The computer readable storage medium can be the memory of any of the above embodiments. The computer readable storage medium can also be an external storage device of the security check image acquisition apparatus, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both an internal storage unit of the security check image acquisition apparatus and an external storage device. The computer readable storage medium is used to store the computer program and other programs and data required by the security check image acquisition apparatus. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0190] The embodiment of the present application further provides a computer program product, which contains a computer program, and when the computer program product runs on a computer, the computer program product makes the computer execute any of the security check image acquisition methods provided in the above embodiments.

[0191] Although the present application is described herein in conjunction with various embodiments, those skilled in the art, upon viewing the drawings, the disclosure, and the appended claims, can understand and implement other variations of the disclosed embodiments in implementing the claimed present application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. Some measures are described in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0192] Although the present application has been described in connection with certain specific features and embodiments thereof, it is to be understood that it is intended to cover all modifications and variations of this application that are within the scope of the appended claims and their equivalents. Accordingly, the description and drawings are to be regarded as illustrative in nature and not as restrictive.

[0193] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any change or replacement within the technical scope disclosed by the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A security image acquisition method, characterized by, A processor applied to a security inspection system, the security inspection system further comprising: a millimeter wave scanning array and a ranging sensor, the ranging sensor being configured to measure a distance between a target object and the millimeter wave scanning array; the method comprising: constructing target spatial distribution information of a surface profile of the target object according to distance information of a plurality of reflection points obtained by detecting the target object using the ranging sensor; wherein the plurality of reflection points include points on the surface of the target object, and the distance information of the reflection points reflects a distance between the reflection points and the millimeter wave scanning array; determining a target amplitude value of a target position point in the target spatial distribution information according to echo signals obtained by detecting the target object using the millimeter wave scanning array; the target position point being a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array; the target amplitude value being configured to represent a scattering intensity of the target position point to electromagnetic waves emitted by the millimeter wave scanning array; determining a two-dimensional image of the target object according to the target spatial distribution information and the target amplitude value; the constructing target spatial distribution information of a surface profile of the target object according to distance information of a plurality of reflection points obtained by detecting the target object using the ranging sensor comprises: constructing initial spatial distribution information of the surface profile of the target object according to the distance information of the plurality of reflection points; determining an expansion value of the initial spatial distribution information in at least one coordinate dimension of a three-dimensional rectangular coordinate system; the expansion value being configured to represent a number of expanded spatial steps; the spatial step representing a distance between two adjacent spatial position points; transforming the reflection points in the initial spatial distribution information according to the expansion value based on coordinate information of the reflection points in the initial spatial distribution information, to obtain expansion points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; obtaining the target spatial distribution information according to the reflection points in the initial spatial distribution information and the expansion points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; the determining the expansion value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system comprises: determining the expansion value of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system according to preset values corresponding to different coordinate dimensions; or, in a case where the at least one coordinate dimension includes a distance dimension, determining the expansion value of the initial spatial distribution information in the distance dimension according to a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object; wherein the distance dimension is a dimension of a thickness direction of the target object.

2. The method of claim 1, wherein, the at least one coordinate dimension of the three-dimensional rectangular coordinate system further comprises: a horizontal dimension or a height dimension; the horizontal dimension being a dimension of a width direction of the target object; the height dimension being a dimension of a height direction of the target object; The determination of the extension value of the initial spatial distribution information in at least one coordinate dimension of a three-dimensional rectangular coordinate system comprises: In the case that the at least one coordinate dimension comprises the horizontal dimension or the height dimension, the extension value of the initial spatial distribution information in the horizontal dimension is determined according to a preset value corresponding to the horizontal dimension, or the extension value of the initial spatial distribution information in the height dimension is determined according to a preset value corresponding to the height dimension.

3. The method of claim 1, wherein, The method further comprises: According to environmental information, the clothing thickness of the target object is determined; the environmental information is used to represent the clothing wearing condition of the target object.

4. The method of claim 1, wherein, The security inspection system further comprises an optical camera used to acquire an optical image of the target object; the method further comprises: The optical image of the target object is input into a first clothing recognition model to obtain the clothing type of the target object; according to the clothing type of the target object, the clothing thickness of the target object is determined; the first clothing recognition model is used to recognize the clothing type of the target object according to the optical image of the target object; Or, the optical image of the target object is input into a second clothing recognition model to obtain the clothing thickness of the target object; the second clothing recognition model is used to determine the clothing thickness of the target object according to the optical image of the target object.

5. The method of claim 1, wherein, The construction of the initial spatial distribution information of the surface contour of the target object according to the distance information of the plurality of reflection points comprises: The first spatial distribution information of the surface contour of the target object is constructed according to the distance information of the plurality of reflection points; the first spatial distribution information is represented by using a cylindrical coordinate system; The coordinate conversion processing is performed on the first spatial distribution information to obtain the second spatial distribution information of the surface contour of the target object; the second spatial distribution information is represented by using a three-dimensional rectangular coordinate system; According to a preset condition, the reflection points in the second spatial distribution information are conditionally filtered to obtain third spatial distribution information; the reflection points in the second spatial distribution information are contour points of the surface of the target object; the preset condition is that the coordinate value of the reflection point in the height dimension is in a height value range, the coordinate value of the reflection point in the width dimension is in a width value range, and the coordinate value of the reflection point in the thickness dimension is in a thickness value range; wherein, the height value range and the width value range are preset distance ranges; the thickness value range is determined by the depth of a standing area of the target object in the security inspection system; The interpolation processing is performed on the third spatial distribution information to obtain the initial spatial distribution information.

6. The method of claim 1, wherein, The determination of the target amplitude value of the target position point in the target spatial distribution information according to the echo signal obtained by detecting the target object by using the millimeter wave scanning array comprises: The plurality of candidate amplitude values corresponding to the target position point in the target spatial distribution information are determined according to the echo signal obtained by detecting the target object by using the millimeter wave scanning array; the plurality of candidate amplitude values are amplitude values corresponding to spatial scanning points having the same two-dimensional coordinates as the target position point in the vertical direction of the scanning plane; Determine a target amplitude value of a target position point of the target position based on the plurality of candidate amplitude values.

7. A security image acquisition apparatus, characterized by comprising: A processor applied to a security inspection system, the security inspection system further comprising: a millimeter wave scanning array and a ranging sensor, the ranging sensor being configured to measure a distance between a target object and the millimeter wave scanning array; the apparatus comprising: a construction module configured to construct target spatial distribution information of a surface profile of the target object based on distance information of a plurality of reflection points obtained by the ranging sensor detecting the target object, wherein the plurality of reflection points include points on the surface of the target object, and the distance information of the reflection points reflects distances between the reflection points and the millimeter wave scanning array; a determination module configured to determine a target amplitude value of a target position point in the target spatial distribution information based on echo signals obtained by the millimeter wave scanning array detecting the target object, wherein the target position point is a point in a two-dimensional plane parallel to a scanning plane of the millimeter wave scanning array, and the target amplitude value is used to represent a scattering intensity of the target position point to electromagnetic waves emitted by the millimeter wave scanning array; the determination module is further configured to determine a two-dimensional image of the target object based on the target spatial distribution information and the target amplitude value; the construction module is specifically configured to construct initial spatial distribution information of the surface profile of the target object based on the distance information of the plurality of reflection points, determine an expansion value of at least one coordinate dimension of a three-dimensional rectangular coordinate system of the initial spatial distribution information, wherein the expansion value is used to represent a number of expanded spatial steps, the spatial step represents a distance between adjacent two spatial position points, transform the reflection points in the initial spatial distribution information according to the expansion value based on coordinate information of the reflection points in the initial spatial distribution information, to obtain expansion points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system, and obtain the target spatial distribution information based on the reflection points in the initial spatial distribution information and the expansion points of the initial spatial distribution information in the at least one coordinate dimension of the three-dimensional rectangular coordinate system; the construction module is specifically configured to determine the expansion value of the at least one coordinate dimension of the three-dimensional rectangular coordinate system of the initial spatial distribution information based on preset values corresponding to different coordinate dimensions, or, in a case where the at least one coordinate dimension includes a distance dimension, determine the expansion value of the distance dimension of the initial spatial distribution information based on a measurement deviation between the millimeter wave scanning array and the ranging sensor and / or a clothing thickness of the target object, wherein the distance dimension is a dimension of a thickness direction of the target object.

8. A security system, characterized by comprise: one or more processors; one or more memories; a millimeter wave scanning array configured to scan and detect a target object; a ranging sensor configured to measure a distance between the target object and the millimeter wave scanning array; The one or more memories are configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors are configured to implement the security check image acquisition method according to any one of claims 1 to 6 when executing the computer instructions.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and when the computer execution instructions run on the computer, the computer is caused to execute the security check image acquisition method according to any one of claims 1 to 6.

Images