An object detection method, apparatus and device

Abstract

The application provides an object detection method, device and equipment. The method comprises: acquiring a target X-ray intensity value of an object to be detected collected by an X-ray detector; querying an information table obtained to obtain a first mass thickness value of a first base material and a second mass thickness value of a second base material; determining second attribute information of a second unknown object based on the first mass thickness value and the second mass thickness value and first attribute information of a first unknown object; or determining fifth attribute information of the first unknown object and sixth attribute information of the second unknown object based on the first mass thickness value and the second mass thickness value and third attribute information of the first unknown object and fourth attribute information of the second unknown object. The technical solution of the application can improve detection accuracy.

Description

Technical Field

[0001] This application relates to the field of non-invasive detection, and more particularly to an object detection method, apparatus, and device. Background Technology

[0002] With the increasing demand for security inspections, security inspection equipment is becoming more and more prevalent, and this equipment typically employs X-ray technology. For example, security inspection equipment may include an X-ray generator and an X-ray detector, and the object to be inspected can be placed on a transmission device. During the movement of the transmission device, the X-ray generator emits X-rays towards the object to be inspected, and the X-ray detector receives the X-rays that pass through the object. Based on these X-rays, an image is created of the object; that is, the X-ray detector can acquire an X-ray image of the object. Then, based on the X-ray image, the internal structure of the object is analyzed to determine its type, also known as the category of the object being inspected.

[0003] However, when two objects are superimposed, i.e., when the object to be detected is the superposition of the first unknown object and the second unknown object, it is impossible to analyze the internal structure of the object to be detected based on the X-ray image, that is, it is impossible to detect the object to be detected, and there are problems such as detection errors. Summary of the Invention

[0004] This application provides an object detection method, the method comprising:

[0005] The target X-ray intensity value of the object to be detected is acquired by an X-ray detector; wherein the object to be detected is the superposition of a first unknown object and a second unknown object.

[0006] By querying the acquired information table using the target X-ray intensity value, the first mass thickness value of the first base material and the second mass thickness value of the second base material are obtained; wherein, the mass thickness value is the product of thickness and density; wherein, the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein, the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material;

[0007] Based on the first mass thickness value and the second mass thickness value, as well as the first attribute information of the first unknown object, the second attribute information of the second unknown object is determined.

[0008] Alternatively, based on the first mass thickness value and the second mass thickness value, as well as the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined.

[0009] This application provides an object detection device, the device comprising:

[0010] The acquisition module is used to acquire the target X-ray intensity value of the object to be detected collected by the X-ray detector; wherein, the object to be detected is the object resulting from the superposition of a first unknown object and a second unknown object;

[0011] The query module is used to query an acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material; wherein the mass thickness value is the product of thickness and density; wherein the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material;

[0012] The determining module is used to determine the second attribute information of the second unknown object based on the first mass thickness value and the second mass thickness value, as well as the first attribute information of the first unknown object;

[0013] Alternatively, based on the first mass thickness value and the second mass thickness value, as well as the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined.

[0014] This application provides an electronic device, including: a processor and a machine-readable storage medium, the machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute the machine-executable instructions to implement the object detection method of the example above in this application.

[0015] This application provides a computer program product, which includes a computer program that, when executed by a processor, implements the object detection method described above in this application.

[0016] This application provides a machine-readable storage medium storing machine-executable instructions that can be executed by a processor; wherein the processor is configured to execute the machine-executable instructions to implement the object detection method of the above example of this application when the machine-executable instructions are executed.

[0017] As can be seen from the above technical solutions, in this embodiment, the first mass thickness value of the first base material and the second mass thickness value of the second base material can be obtained by querying an information table based on the target X-ray intensity value of the object to be detected. Then, the attribute information of the first unknown object and the attribute information of the second unknown object can be determined based on the first mass thickness value and the second mass thickness value. In this way, the object to be detected can be detected based on the first mass thickness value of the first base material and the second mass thickness value of the second base material, improving detection accuracy and avoiding detection errors. When two objects are superimposed, the superimposed objects can also be identified and detected non-invasively based on X-rays, enabling the identification of material types (e.g., determining the type of unknown object) and the quantitative analysis of material components (e.g., determining the mass thickness value of the unknown object). Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an object detection method according to one embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating an object detection method according to one embodiment of this application;

[0020] Figure 3 This is a flowchart illustrating an object detection method according to one embodiment of this application;

[0021] Figure 4 This is a flowchart illustrating an object detection method according to one embodiment of this application;

[0022] Figure 5 This is a schematic diagram of the structure of an object detection device according to one embodiment of this application;

[0023] Figure 6 This is a hardware structure diagram of an electronic device according to one embodiment of this application. Detailed Implementation

[0024] This application proposes an object detection method, which can be applied to electronic devices. See [link to relevant documentation]. Figure 1 The diagram shown is a flowchart of the object detection method, which may include:

[0025] Step 101: Obtain the target X-ray intensity value of the object to be detected collected by the X-ray detector; wherein, the object to be detected is the superposition of the first unknown object and the second unknown object.

[0026] Step 102: Query the acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material; wherein, the mass thickness value is the product of thickness and density; wherein, the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein, the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material.

[0027] Step 103: Based on the first mass thickness value and the second mass thickness value, and the first attribute information of the first unknown object, determine the second attribute information of the second unknown object; or, based on the first mass thickness value and the second mass thickness value, and the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, determine the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object.

[0028] For example, the first attribute information may include, but is not limited to, a first type parameter of the first unknown object and the mass and thickness value of the first unknown object; the second attribute information may include, but is not limited to, a second type parameter of the second unknown object; or, the second attribute information may include, but is not limited to, a second type parameter of the second unknown object and the mass and thickness value of the second unknown object; wherein, the first type parameter is used to identify the type of the first unknown object; wherein, the second type parameter is used to identify the type of the second unknown object.

[0029] For example, the first unknown object and the second unknown object have overlapping and non-overlapping regions, and the target X-ray intensity value is the X-ray intensity value of the overlapping region. Before determining the second attribute information of the second unknown object based on the first mass thickness value and the second mass thickness value, as well as the first attribute information of the first unknown object, the X-ray intensity value of the non-overlapping region collected by the X-ray detector is obtained. The non-overlapping region is the region where the first unknown object itself is located. Based on the X-ray intensity value of the non-overlapping region, the first mass attenuation coefficient of the first base material and the second mass attenuation coefficient of the second base material, the first type parameter and the mass thickness value of the first unknown object are determined.

[0030] For example, the third attribute information may include the mass and thickness value of the first unknown object, the fourth attribute information may include the mass and thickness value of the second unknown object, the fifth attribute information may include the first type parameter of the first unknown object, and the sixth attribute information may include the second type parameter of the second unknown object.

[0031] Alternatively, the third attribute information may include the first type parameter of the first unknown object, the fourth attribute information may include the second type parameter of the second unknown object, the fifth attribute information may include the mass and thickness value of the first unknown object, and the sixth attribute information may include the mass and thickness value of the second unknown object.

[0032] Alternatively, the third attribute information may include a first type parameter of the first unknown object, the fourth attribute information may include the mass thickness value of the second unknown object, the fifth attribute information may include the mass thickness value of the first unknown object, and the sixth attribute information may include a second type parameter of the second unknown object. In the embodiments of this application, the mass thickness value refers to the product of thickness and density.

[0033] It is understood that in the embodiments of this application, attribute information is used to describe and distinguish different objects. Attribute information may include one or more of the object's type parameters, mass, thickness values, etc. In the above example, the third attribute information and the fifth attribute information of the first unknown object are used to indicate different attribute information of the first unknown object, and similarly, the fourth attribute information and the sixth attribute information of the second unknown object are used to indicate different attribute information of the second unknown object.

[0034] For example, the effective atomic number of the first unknown object can be determined based on the already determined type of the first unknown object; and the first type parameter of the first unknown object can be determined based on the effective atomic number of the first unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material.

[0035] The effective atomic number of the second unknown object can be determined based on the already determined type of the second unknown object; the second type parameter of the second unknown object can be determined based on the effective atomic number of the second unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material.

[0036] For example, based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the first type parameter, the effective atomic number of the first unknown object is determined, and the type of the first unknown object is determined based on the effective atomic number of the first unknown object; based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the second type parameter, the effective atomic number of the second unknown object is determined, and the type of the second unknown object is determined based on the effective atomic number of the second unknown object.

[0037] For example, the effective atomic number of the first unknown object and the first type parameter satisfy the following expression relationship: Z X1= a1Z1 + (1-a1)Z2; The effective atomic number of the second unknown object and the second type parameter satisfy the following expression relationship: Z X2 = b1Z1 + (1-b1)Z2; where Z X1 Z represents the effective atomic number of the first unknown object. X2 The effective atomic number of the second unknown object is represented by a1, the first type parameter is represented by b1, the second type parameter is represented by Z1, the first effective atomic number is represented by Z2, and the second effective atomic number is represented by Z2.

[0038] For example, the first mass thickness value, the second mass thickness value, the first type parameter of the first unknown object, the second type parameter of the second unknown object, the mass thickness value of the first unknown object, and the mass thickness value of the second unknown object satisfy the following expression relationship: t1=a1t X +b1t Y t2=(1-a1)t X +(1-b1)t Y Where t1 represents the first mass thickness value, t2 represents the second mass thickness value; a1 represents the first type parameter of the first unknown object, b1 represents the second type parameter of the second unknown object; t X t represents the mass and thickness of the first unknown object. Y This represents the mass and thickness value of the second unknown object.

[0039] As can be seen from the above technical solutions, in this embodiment, the first mass thickness value of the first base material and the second mass thickness value of the second base material can be obtained by querying an information table based on the target X-ray intensity value of the object to be detected. Then, the attribute information of the first unknown object and the attribute information of the second unknown object can be determined based on the first mass thickness value and the second mass thickness value. In this way, the object to be detected can be detected based on the first mass thickness value of the first base material and the second mass thickness value of the second base material, improving detection accuracy and avoiding detection errors. When two objects are superimposed, the superimposed objects can also be identified and detected non-invasively based on X-rays, enabling the identification of material types (e.g., determining the type of unknown object) and the quantitative analysis of material components (e.g., determining the mass thickness value of the unknown object).

[0040] The technical solutions described above in the embodiments of this application will be explained below in conjunction with specific application scenarios.

[0041] An X-ray machine is a device that generates X-rays (X-rays). It can also be called an X-ray generator. The X-ray generator emits X-rays towards the object to be inspected, and the X-ray detector receives the X-rays that pass through the object to be inspected. Based on the X-rays, the object to be inspected is imaged to obtain an X-ray image of the object to be inspected.

[0042] X-ray machines can include single-energy X-ray machines and multi-energy X-ray machines (such as dual-energy X-ray machines). Single-energy X-ray machines acquire X-ray images of objects by using X-rays of a single energy. For example, an X-ray generator emits X-rays of a single energy to the object being examined, an X-ray detector receives the X-rays of a single energy, and the object is imaged based on the X-rays to obtain an X-ray image of the object being examined.

[0043] Furthermore, dual-energy X-ray machines acquire X-ray images of objects by using two different energies of X-rays, thus enabling more accurate differentiation of different substances. For example, an X-ray generator emits two different energies of X-rays towards the object, an X-ray detector receives these two energies, and the object is imaged based on these two energies to obtain an X-ray image of the object.

[0044] For a single-energy X-ray machine, when the X-ray generator emits X-rays to the object to be tested, the intensity change of the X-rays passing through a single object to be tested follows the Beer-Lamber law, as shown in formula (1).

[0045] I(E)=I0(E)exp(-μ(E)t) Formula (1)

[0046] E represents the incident X-ray energy, that is, the energy of the X-rays emitted by the X-ray generator. I0(E) is the initial X-ray intensity value, that is, the X-ray intensity value when the X-ray generator emits X-rays. This initial X-ray intensity value corresponds to the incident X-ray energy E and is a known value. I(E) is the target X-ray intensity value observed by the X-ray detector, that is, the X-ray intensity value when the X-ray detector receives X-rays passing through the object to be detected. This target X-ray intensity value corresponds to the incident X-ray energy E and is a known value.

[0047] μ(E) represents the mass attenuation coefficient of the object to be detected. This mass attenuation coefficient corresponds to the incident X-ray energy E and is an unknown value. That is, it is necessary to determine the mass attenuation coefficient corresponding to the incident X-ray energy E.

[0048] t represents the mass thickness value of the object to be detected. The mass thickness value is an unknown value, meaning it needs to be determined. For example, the mass thickness value could be the thickness of the object to be detected multiplied by its density.

[0049] The exp function is used to represent an exponential function with the natural constant e as the base.

[0050] In formula (1), the mass attenuation coefficient and mass thickness value are related to the type of the object to be detected, and the type of the object can be determined based on the mass attenuation coefficient and mass thickness value. However, since both the mass attenuation coefficient and mass thickness value are unknown, they cannot be determined based on formula (1), and therefore the type of the object to be detected cannot be determined. In summary, single-energy X-ray machines lack type discrimination capabilities, and the information observed by the X-ray detector cannot simultaneously solve for the mass attenuation coefficient and mass thickness value.

[0051] For dual-energy X-ray machines, the X-ray generator emits two types of X-rays of different energies towards the object being detected. For example, two X-ray generators can produce two different energies of X-rays, or one X-ray generator can operate at two different voltages to produce two different energies of X-rays. Based on the differences in the absorption rates of different materials for X-rays of different energies, the X-ray detector can receive both types of X-rays, thereby converting the received X-rays of different energies into an X-ray image. Based on this, when two different energies of X-rays pass through a single object being detected, see formulas (2) and (3).

[0052] I(E1)=I0(E1)exp(-μ(E1)t) Formula (2)

[0053] I(E2)=I0(E2)exp(-μ(E2)t) Formula (3)

[0054] E1 represents the first incident X-ray energy, E2 represents the second incident X-ray energy, I0(E1) represents the initial X-ray intensity value of the first incident X-ray energy, I0(E2) represents the initial X-ray intensity value of the second incident X-ray energy, I(E1) represents the target X-ray intensity value corresponding to the first incident X-ray energy observed by the X-ray detector, and I(E2) represents the target X-ray intensity value corresponding to the second incident X-ray energy observed by the X-ray detector. Furthermore, μ(E) and t represent the mass attenuation coefficient and mass thickness value of the object to be detected. Clearly, when the mass attenuation coefficient and mass thickness value are unknown, they can be determined using formulas (2) and (3). Considering that the mass attenuation coefficient and mass thickness value are related to the effective atomic number and electron density of the substance, they can be used to distinguish different substances. Therefore, the type of object to be detected can be determined based on the mass attenuation coefficient and mass thickness value.

[0055] In summary, dual-energy X-ray machines have the ability to distinguish between different types of materials. The information observed by the X-ray detector can be used to simultaneously solve for the mass attenuation coefficient and the mass thickness value, thereby enabling more accurate differentiation between different materials.

[0056] However, when two objects are superimposed, i.e., the object to be detected is the superposition of the first unknown object and the second unknown object, there are 4 unknown parameters, namely the mass attenuation coefficient and mass thickness value of the first unknown object, the mass attenuation coefficient and mass thickness value of the second unknown object. The mass attenuation coefficient and mass thickness value of the first unknown object and the second unknown object cannot be determined by formula (2) and formula (3), so the type of the first unknown object and the type of the second unknown object cannot be determined.

[0057] In response to the above findings, this embodiment proposes an object detection method that can identify and detect superimposed objects using X-rays in a non-invasive manner when two objects are superimposed, enabling material type identification (determining the type of unknown objects) and quantitative analysis of material composition (determining the mass and thickness values ​​of unknown objects).

[0058] To achieve the identification and detection of superimposed objects, this embodiment can select two materials with known effective atomic numbers, referred to as the first base material and the second base material. For example, the effective atomic number of an element is consistent with the nuclear charge of its atomic nucleus, and the effective atomic number of a compound can be estimated using the following empirical formula: c i Z represents the number of atoms of the element in the compound. i This is the effective atomic number of the element, where n can be an empirical value, generally between 2 and 4.

[0059] Assuming that the effective atomic number of all unknown objects is no greater than A, and that the effective atomic number of all unknown objects is no less than B, where B is less than A, then when selecting the first and second base materials, the effective atomic number of the first base material must be less than B, and the effective atomic number of the second base material must be greater than A. In this way, the effective atomic number of the unknown objects falls within the range of the effective atomic numbers of the first and second base materials; that is, the effective atomic number of the unknown objects can fall within the range of effective atomic numbers from A to B.

[0060] For example, when the unknown object is a substance near an organic compound, the first base material could be acrylic (PMMA), and the second base material could be aluminum (Al). Of course, acrylic is just one example of the first base material, and aluminum is just one example of the second base material; there are no restrictions on this.

[0061] For example, after selecting the first base material and the second base material, since two materials with known effective atomic numbers are selected, the effective atomic numbers of the first base material (hereinafter referred to as the first effective atomic number) and the second base material (hereinafter referred to as the second effective atomic number) can be obtained. Furthermore, the mass decay curves of the first base material and the second base material are obtained theoretically or experimentally. There are no restrictions on the method of obtaining these mass decay curves; as long as the mass decay curves are obtained, it is acceptable.

[0062] Based on the mass decay curve of the first base material, the mass decay curve can be looked up by the incident X-ray energy E to obtain the mass decay coefficient μ(E) corresponding to the incident X-ray energy E. This mass decay coefficient is the mass decay coefficient of the first base material, and will be referred to as the first mass decay coefficient thereafter.

[0063] Based on the mass decay curve of the second base material, the mass decay curve can be looked up by the incident X-ray energy E to obtain the mass decay coefficient μ(E) corresponding to the incident X-ray energy E. This mass decay coefficient is the mass decay coefficient of the second base material, and will be referred to as the second mass decay coefficient thereafter.

[0064] In summary, the first effective atomic number of the first base material, the second effective atomic number of the second base material, the first mass decay coefficient of the first base material, and the second mass decay coefficient of the second base material are obtained.

[0065] For example, after selecting the first and second base materials, an information table can be maintained. This information table can include the correspondence between the sample X-ray intensity values, the mass thickness values ​​of the first and second base materials. For instance, the process of obtaining the information table may include:

[0066] An X-ray generator emits X-rays onto the sample material, and an X-ray detector acquires the sample X-ray intensity values ​​of the sample material. The sample material can be a composite of a first substrate material and a second substrate material, and the mass and thickness values ​​of both the first and second substrate materials are known. Based on this, the correspondence between the sample X-ray intensity values, the mass and thickness values ​​of the first and second substrate materials can be recorded in an information table.

[0067] See Table 1 for an example of this information table. For instance, a sample material is obtained by superimposing a first base material with a mass thickness value of d11 and a second base material with a mass thickness value of d21. The sample X-ray intensity value c1 of this sample material is recorded in the information table. Similarly, a sample material is obtained by superimposing a first base material with a mass thickness value of d12 and a second base material with a mass thickness value of d22. The sample X-ray intensity value c2 of this sample material is also recorded in the information table, and so on, until the information table is maintained.

[0068] Table 1

[0069] Sample X-ray intensity value c1 Mass thickness value d11 Mass thickness value d21 Sample X-ray intensity value c2 Mass thickness value d12 Mass thickness value d22 Sample X-ray intensity value c3 Mass thickness value d13 Mass thickness value d23 Sample X-ray intensity value c4 Mass thickness value d14 Mass thickness value d24 … … …

[0070] In one possible implementation, the sample X-ray intensity value may include K sample sub-intensity values, where K can be a positive integer. For example, for a single-energy X-ray machine, the X-ray generator emits X-rays of one energy to the sample material, and the sample X-ray intensity value includes one sample sub-intensity value. For a dual-energy X-ray machine, the X-ray generator emits X-rays of two energies to the sample material, and the sample X-ray intensity value includes two sample sub-intensity values, as shown in Table 2, which is an example of an information table. For a three-energy X-ray machine, the X-ray generator emits X-rays of three energies to the sample material, and the sample X-ray intensity value includes three sample sub-intensity values, and so on. For ease of description, the information table shown in Table 2 will be used as an example below.

[0071] Table 2

[0072] Sample sub-intensity values ​​c11, c12 Mass thickness value d11 Mass thickness value d21 Sample sub-intensity values ​​c21, c22 Mass thickness value d12 Mass thickness value d22 Sample sub-intensity values ​​c31, c32 Mass thickness value d13 Mass thickness value d23 Sample sub-intensity values ​​c41, c42 Mass thickness value d14 Mass thickness value d24 … … …

[0073] For example, after selecting the first and second base materials, for a dual-energy X-ray machine, when two X-rays of different energies pass through a single object to be detected, the object to be detected is referred to as the unknown object X, and the mass attenuation coefficient of the unknown object X is μ. X Therefore, if the effective atomic number of the unknown object X falls within the range of the effective atomic numbers of the first and second base materials, the mass attenuation coefficient μ1 of the first base material and the second mass attenuation coefficient μ2 of the second base material can be used to approximate the mass attenuation coefficient of the unknown object X as μ. X That is, μ X = a1μ1 + a2μ2. In the above formula, the first mass attenuation coefficient μ1, the second mass attenuation coefficient μ2, and the mass attenuation coefficient μ... X All correspond to the incident X-ray energy E.

[0074] In the above formula, the sum of a1 and a2 can be a fixed value, such as 1. Therefore, the above formula can also be equivalent to: μ X= a1μ1+(1-a1)μ2. a1 represents the base material decomposition coefficient, that is, the base material decomposition coefficient when the unknown object X is decomposed into the first base material and the second base material. The base material decomposition coefficient a1 can also be called the type parameter of the unknown object X, which is used to determine the type of the unknown object X.

[0075] Based on this, when two X-rays of different energies pass through a single object to be detected, formulas (2) and (3) can be transformed, that is, the mass attenuation coefficient μ of the unknown object X can be transformed. X Replace it with the above formula, i.e., μ X =a1μ1+(1-a1)μ2, see formulas (4) and (5).

[0076] I(E1)=I0(E1)exp[-(a1μ1(E1)+(1-a1)μ2(E1))t] Formula (4)

[0077] I(E2)=I0(E2)exp[-(a1μ1(E2)+(1-a1)μ2(E2))t] Formula (5)

[0078] E1 represents the first incident X-ray energy, E2 represents the second incident X-ray energy, I0(E1) represents the initial X-ray intensity value of the first incident X-ray energy, I0(E2) represents the initial X-ray intensity value of the second incident X-ray energy, I(E1) represents the target X-ray intensity value corresponding to the first incident X-ray energy, and I(E2) represents the target X-ray intensity value corresponding to the second incident X-ray energy. μ1(E1) represents the first mass attenuation coefficient μ1 of the first substrate material corresponding to the first incident X-ray energy, μ1(E2) represents the first mass attenuation coefficient μ1 of the first substrate material corresponding to the second incident X-ray energy, μ2(E1) represents the second mass attenuation coefficient μ2 of the second substrate material corresponding to the first incident X-ray energy, and μ2(E2) represents the second mass attenuation coefficient μ2 of the second substrate material corresponding to the second incident X-ray energy. Clearly, both the first mass attenuation coefficient μ1 and the second mass attenuation coefficient μ2 can be known values.

[0079] The type parameter a1 of the unknown object X represents the decomposition coefficient of the base material, and t represents the mass thickness value of the unknown object X. When the type parameter a1 and the mass thickness value are unknown, the type parameter a1 and the mass thickness value can be determined by formulas (4) and (5), and the type parameter a1 can be used to distinguish different substances.

[0080] In one possible implementation, formula (4) can be transformed to obtain formula (6) in integral form, and formula (5) can be transformed to obtain formula (7) in integral form.

[0081]

[0082] For example, when two unknown objects are superimposed, these two unknown objects are referred to as the first unknown object X and the second unknown object Y, and the superimposed object is referred to as the object to be detected. That is, the object to be detected is the object superimposed by the first unknown object X and the second unknown object Y. The effective atomic number of the first unknown object X is unknown, but it is within the range of the effective atomic numbers of the first base material and the second base material. The effective atomic number of the second unknown object Y is also unknown, but it is within the range of the effective atomic numbers of the first base material and the second base material. In subsequent embodiments, the effective atomic numbers of the first unknown object X and the second unknown object Y can be determined, and then the type of the unknown object can be analyzed.

[0083] For single-energy X-ray machines and multi-energy X-ray machines (such as dual-energy X-ray machines), when the X-ray generator emits X-rays to the object to be detected, the intensity change of the X-rays passing through the object to be detected (i.e., the first unknown object X and the second unknown object Y) follows the Beer-Lambert law, as shown in formula (8).

[0084]

[0085] In the above formula, E k Let represent the energy of the k-th incident X-ray. For a single-energy X-ray machine, the value of k ranges from 1; for a dual-energy X-ray machine, the value of k ranges from 1 to 2, and so on. I0(E) represents the initial X-ray intensity value of the k-th incident X-ray energy. k ) represents the target X-ray intensity value corresponding to the k-th incident X-ray energy observed by the X-ray detector. X (E) represents the mass attenuation coefficient of the first unknown object X corresponding to the k-th incident X-ray energy, hereinafter denoted as μ. X , t X μ represents the mass and thickness of the first unknown object X. Y (E) represents the mass attenuation coefficient of the second unknown object Y corresponding to the k-th incident X-ray energy, hereinafter denoted as μ. Y , t Y This represents the mass and thickness value of the second unknown object Y.

[0086] Regarding the mass decay coefficient μ X It can be approximated using the first mass attenuation coefficient μ1 of the first base material and the second mass attenuation coefficient μ2 of the second base material, such as μ X = a1μ1 + a2μ2, where a1 represents the first type parameter of the first unknown object X, and a2 = 1 - a1. This relates to the mass decay coefficient μ. YIt can be approximated using the first mass attenuation coefficient μ1 of the first base material and the second mass attenuation coefficient μ2 of the second base material, such as μ Y =b1μ1+b2μ2, where b1 represents the second type parameter of the second unknown object Y, and b2 = 1-b1.

[0087] Based on this, formula (8) can be transformed to change the mass attenuation coefficient μ of the first unknown object X. X Replace it with the above formula, i.e., μ X =a1μ1+a2μ2, where μ is the mass attenuation coefficient of the second unknown object Y. Y Replace it with the above formula, i.e., μ Y =b1μ1+b2μ2, thus obtaining formula (9). Based on formula (9), formula (9) can be transformed to obtain formula (10).

[0088]

[0089] For example, when an X-ray generator emits X-rays to a sample material (composed of a first substrate material and a second substrate material) for a single-energy X-ray machine or a multi-energy X-ray machine (such as a dual-energy X-ray machine), the following formula (11) can be obtained by referring to formula (8) when the X-ray passes through the sample material.

[0090]

[0091] In formula (11), μ1 represents the first mass attenuation coefficient of the first base material, t1 represents the mass thickness value of the first base material (denoted as the first mass thickness value), μ2 represents the second mass attenuation coefficient of the second base material, and t2 represents the mass thickness value of the second base material (denoted as the second mass thickness value).

[0092] Combining formulas (10) and (11), we can derive formula (12). Furthermore, considering that a2 = 1 - a1 and b2 = 1 - b1, formula (12) can also be transformed into formula (13).

[0093] t1=a1t X +b1t Y t2=a2t X +b2t Y Formula (12)

[0094] t1=a1t X +b1t Y t2=(1-a1)t X +(1-b1)t Y Formula (13)

[0095] As can be seen from formula (13), when the first mass thickness value t1 and the second mass thickness value t2 are known, there are 4 variables (a1, b1, t2). X ,t Y ), a1 represents the first type parameter of the first unknown object X, t X Let b1 represent the mass and thickness of the first unknown object X, b1 represent the second type parameter of the second unknown object Y, and t represent the second type parameter of the first unknown object Y. Y Let t1 represent the mass and thickness value of the second unknown object Y. Based on the two known variables, and combining the first mass and thickness value t1 with the second mass and thickness value t2, the remaining two variables can be solved, thus completing the object detection.

[0096] Based on the above technical concept, this application proposes an object detection method. Based on a first mass thickness value and a second mass thickness value, if the first attribute information of a first unknown object is known, the second attribute information of a second unknown object can be determined. In this example, the first attribute information may include a first type parameter and the mass thickness value of the first unknown object, and the second attribute information may include a second type parameter of the second unknown object, or the second attribute information may include both the second type parameter and the mass thickness value of the second unknown object. Therefore, if the first type parameter a1 and the mass thickness value t of the first unknown object X are known... X Then we can solve for the second type parameter b1 of the second unknown object Y and the mass and thickness t of the second unknown object Y. Y Alternatively, if the first type parameter a1 of the first unknown object X and the mass and thickness value t of the first unknown object X are known... X Then, the second type parameter b1 of the second unknown object Y can be solved. In this example, the second type parameter b1 of the second unknown object Y and the mass and thickness value t of the second unknown object Y are solved. Y For example. Based on this, see... Figure 2 The diagram shown is a flowchart of the object detection method, which may include:

[0097] Step 201: Obtain the target X-ray intensity value of the object to be detected collected by the X-ray detector. The object to be detected is the superposition of the first unknown object X and the second unknown object Y.

[0098] For example, an X-ray generator emits X-rays towards an object to be detected, and an X-ray detector collects the X-ray intensity value of the X-rays that pass through the object to be detected, which is the target X-ray intensity value.

[0099] Step 202: Query the acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material. The mass thickness value can be the product of thickness and density. For example, the first mass thickness value can be the product of the thickness and density of the first base material, and the second mass thickness value can be the product of the thickness and density of the second base material.

[0100] For example, in the case of a single-energy X-ray machine, when obtaining the information table, the sample X-ray intensity value includes a sample sub-intensity value, and the target X-ray intensity value includes a target sub-intensity value.

[0101] Based on this, for each sample X-ray intensity value in the information table, the target loss value for that sample X-ray intensity value is calculated based on the difference between the target X-ray intensity value and the sample X-ray intensity value, as shown in Table 1. The target loss value for sample X-ray intensity value c1 is the absolute value of the difference between the target X-ray intensity value and the sample X-ray intensity value c1. Based on the sample X-ray intensity value corresponding to the minimum target loss value, the first mass thickness value of the first base material and the second mass thickness value of the second base material are retrieved from the information table.

[0102] For example, if the minimum target loss value corresponds to the sample X-ray intensity value c3, then the mass thickness value d13 corresponding to the sample X-ray intensity value c3 is used as the first mass thickness value of the first base material, and the mass thickness value d23 corresponding to the sample X-ray intensity value c3 is used as the second mass thickness value of the second base material.

[0103] For example, in the case of a multi-energy X-ray machine, when acquiring the information table, the sample X-ray intensity value may include K sample sub-intensity values, and the target X-ray intensity value may include K target sub-intensity values ​​that correspond one-to-one with the K sample sub-intensity values, where K can be a positive integer greater than 1. For instance, taking a dual-energy X-ray machine as an example, the sample X-ray intensity value may include 2 sample sub-intensity values, and the target X-ray intensity value may include 2 target sub-intensity values ​​that correspond one-to-one with the 2 sample sub-intensity values.

[0104] Based on this, for each sample X-ray intensity value in the information table, the target loss value for that sample X-ray intensity value is calculated using K target sub-intensity values ​​and K sample sub-intensity values ​​of the target X-ray intensity value. For example, the target loss value Loss for that sample X-ray intensity value can be denoted as: Loss(f1(t1,t2),f2(t1,t2)…,f k (t1,t2); I 1,obs ,I 2,obs ,…,I k,obsf1(t1,t2) represents the intensity value of the first sample sub-sample, f2(t1,t2) represents the intensity value of the second sample sub-sample, ..., f k (t1,t2) represents the intensity value of the Kth sample sub-value, I 1,obs I represents the intensity value of the first target sub-target corresponding to f1(t1,t2). 2,obs Indicates the intensity value of the second target sub-target, ..., I k,obs This represents the intensity value of the Kth target sub-target.

[0105] When calculating the target loss value, the absolute value of the difference between the target sub-intensity value and the sample sub-intensity value can be calculated, and then the average of the absolute values ​​of all differences can be used as the target loss value. For example, calculating I... 1,obs The absolute value of the difference between f1(t1,t2) and I 2,obs The absolute value of the difference between f2(t1,t2) and f2(t1,t2), ..., I k,obs with f k The absolute value of the difference between (t1, t2) is used, and then the average of the absolute values ​​of all the differences is taken as the target loss value.

[0106] Alternatively, when calculating the target loss value, the least squares method can be used to determine the target loss value, i.e., Loss = ∑ i [f i (t1,t2)-I i,obs ] 2 In the above formula, the values ​​of i range from 1 to k.

[0107] Of course, the above are just two examples. There are no restrictions on how the target loss value is determined. The target loss value can be determined based on the difference between the target sub-intensity value and the corresponding sample sub-intensity value.

[0108] Based on the sample X-ray intensity value corresponding to the minimum target loss value, the first mass thickness value of the first base material and the second mass thickness value of the second base material can be retrieved from the information table. For example, referring to Table 2, if the minimum target loss value corresponds to sample sub-intensity values ​​c31 and c32, then the mass thickness value d13 corresponding to sample sub-intensity values ​​c31 and c32 is taken as the first mass thickness value of the first base material, and the mass thickness value d23 corresponding to sample sub-intensity values ​​c31 and c32 is taken as the second mass thickness value of the second base material.

[0109] Step 203: Obtain the first type parameter and mass thickness value of the first unknown object.

[0110] In one possible implementation, the first type parameter a1 and the mass thickness value t of the first unknown object X can be obtained by direct measurement. X .

[0111] For example, the first unknown object can be a bottle, pallet, or container of a fixed shape, and the second unknown object can be a liquid inside a bottle (the type of liquid needs to be detected), an object on a pallet (the type of object needs to be detected), or an object inside a container (the type of object needs to be detected).

[0112] For a first unknown object such as a bottle, pallet, or container of a fixed shape, where the material of the first unknown object is uniform (i.e., the type of the first unknown object is known) and the thickness of the first unknown object is fixed (i.e., the mass and thickness value t of the first unknown object is known),... X Therefore, the type, thickness, and density of the first unknown object can be measured beforehand. There are no restrictions on the measurement method; as long as information such as type, thickness, and density is obtained, the first type parameter a1 and the mass-thickness value t can be derived. X .

[0113] For example, based on the thickness and density of the first unknown object, the mass-thickness value t of the first unknown object can be determined. X Mass thickness value t X It can be thickness multiplied by density. Based on the type of the first unknown object, since the type (i.e., material type) corresponds to the effective atomic number, the effective atomic number of the first unknown object can be determined. Based on the effective atomic number of the first unknown object, the first type parameter a1 can be determined using the following formula: Z X1 = a1Z1 + (1 - a1)Z2. Z X1 Z1 can represent the first effective atomic number of the first base material, and Z2 can represent the second effective atomic number of the second base material.

[0114] In one possible implementation, the first type parameter a1 and the mass thickness value t of the first unknown object X can be obtained indirectly through measurement. X .

[0115] For example, when a first unknown object and a second unknown object are superimposed, there are superimposed and non-superimposed regions. The non-superimposed region is the area of ​​the first unknown object. The range of the first unknown object is larger than the range of the second unknown object. The second unknown object is within the range of the first unknown object, but the second unknown object is not present in some areas of the first unknown object (i.e., the non-superimposed region).

[0116] For example, when an unknown liquid is superimposed on an object A (object A is a flat, single-type object, such as a notebook), there is a significant difference between the effective atomic number of the liquid in the superimposed region and the actual effective atomic number of the liquid. Directly using the effective atomic number of the liquid in the superimposed region to determine the liquid type will lead to an increase in the false alarm rate.

[0117] In this scenario, object A can be larger than the liquid region. Therefore, object A can be considered the first unknown object, and the unknown liquid the second unknown object. There are overlapping and non-overlapping regions between object A and the unknown liquid. The non-overlapping region is the area containing only object A, while the overlapping region contains both object A and the unknown liquid. The overlapping and non-overlapping regions can be determined through pre-measurement, manual selection, or intelligent selection based on machine learning or deep learning.

[0118] In the above application scenario, since the first unknown object and the second unknown object have overlapping and non-overlapping regions, the X-ray intensity values ​​of the overlapping region and the non-overlapping region collected by the X-ray detector can be obtained. In step 201, the target X-ray intensity value is the X-ray intensity value of the overlapping region. Based on the X-ray intensity value of the non-overlapping region, the first type parameter a1 of the first unknown object X and the mass thickness value t of the first unknown object X can be obtained. X .

[0119] First, the first mass attenuation coefficient μ1 of the first base material and the second mass attenuation coefficient μ2 of the second base material are known. Therefore, the first mass attenuation coefficient μ1 and the second mass attenuation coefficient μ2 can be obtained.

[0120] Then, based on the X-ray intensity values ​​of the non-overlapping region (i.e., the X-ray intensity values ​​for the first unknown object, independent of the second unknown object), the first mass attenuation coefficient μ1, and the second mass attenuation coefficient μ2, the first type parameter a1 and the mass thickness value t of the first unknown object X can be determined. X .

[0121] For example, as shown in formulas (4) and (5), or formulas (6) and (7), I0(E1) and I0(E2) can represent the initial X-ray intensity values, and I(E1) and I(E2) can represent the X-ray intensity values ​​of the non-overlapping region (i.e., the X-ray intensity values ​​corresponding to the first and second incident X-ray energies). All of these parameters are known values. In addition, μ1(E1) and μ1(E2) can represent the first mass attenuation coefficient corresponding to the incident X-ray energy, and μ2(E1) and μ2(E2) can represent the second mass attenuation coefficient corresponding to the incident X-ray energy. Both of these mass attenuation coefficients are known values.

[0122] In summary, it can be seen that only the first type parameter a1 and the mass thickness value t... X Since there are two unknown values, the first type parameter a1 and the mass thickness value t can be solved using formulas (4) and (5). X Alternatively, the first type parameter a1 and the mass thickness value t can be solved using formulas (6) and (7). X .

[0123] Step 204: Based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the first type parameter of the first unknown object, and the mass thickness value of the first unknown object, determine the second type parameter of the second unknown object and the mass thickness value of the second unknown object. Alternatively, based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the first type parameter of the first unknown object, and the mass thickness value of the first unknown object, determine the second type parameter of the second unknown object.

[0124] For example, based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the first type parameter of the first unknown object, and the mass thickness value of the first unknown object, formula (13) can be used to determine the second type parameter of the second unknown object and the mass thickness value of the second unknown object.

[0125] In formula (13), t1 represents the first mass thickness value, t2 represents the second mass thickness value, a1 represents the first type parameter of the first unknown object, and t X This represents the mass and thickness value of the first unknown object. Clearly, the above four parameters are known parameters. Furthermore, b1 represents the second type of parameter of the second unknown object, t... Y The mass and thickness of the second unknown object are represented by the above two parameters, which are unknown parameters. Based on the above four known parameters, the two unknown parameters are solved by formula (13) to obtain the second type parameter b1 and the mass and thickness value t. Y .

[0126] Step 205: Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the first type parameter of the first unknown object, determine the effective atomic number of the first unknown object, and determine the type of the first unknown object based on the effective atomic number of the first unknown object, thus completing the detection of the first unknown object. Step 205 is optional. If the type of the first unknown object is known (see step 203, where the type of the first unknown object is measured in advance), then the type of the first unknown object is not determined based on step 205. Only if the type of the first unknown object is unknown is the type of the first unknown object determined based on step 205.

[0127] Step 206: Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the second type parameter of the second unknown object, determine the effective atomic number of the second unknown object, and determine the type of the second unknown object based on the effective atomic number of the second unknown object, thus completing the detection of the second unknown object.

[0128] For example, the first effective atomic number Z1 of the first base material and the second effective atomic number Z2 of the second base material are known, so the first effective atomic number Z1 and the second effective atomic number Z2 can be obtained.

[0129] Based on the first effective atomic number Z1, the second effective atomic number Z2, and the first type parameter a1, the effective atomic number Z of the first unknown object X can be determined using the following formula. X1 Z X1 = a1Z1 + (1 - a1)Z2. The effective atomic number Z of the first unknown object X is obtained. X1 Subsequently, since there is a correspondence between the effective atomic number and the material type, the effective atomic number Z of the first unknown object X can be used as a basis for calculation. X1 Determine the type of the first unknown object.

[0130] Based on the first effective atomic number Z1, the second effective atomic number Z2, and the second type parameter b1, the effective atomic number Z of the second unknown object Y can be determined using the following formula. X2 Z X2 =b1Z1+(1-b1)Z2. The effective atomic number Z of the second unknown object Y is obtained. X2 Subsequently, since there is a correspondence between the effective atomic number and the material type, the effective atomic number Z of the second unknown object Y can be used as a basis for calculation. X2 Determine the type of the second unknown object.

[0131] For example, in a security inspection scenario, the above object detection method can be applied to security inspection equipment, and this method is used to detect the type of unknown object (i.e., the category of unknown object). The type of unknown object can be elements such as carbon, iron, hydrogen, nitrogen, and oxygen, or it can be electronic products, liquids, corrosive substances, metals, batteries, radioactive objects, ceramics, cosmetics, etc. Of course, the above are just examples of types of unknown objects and are not intended to limit the scope.

[0132] Based on the above technical concept, this application proposes an object detection method. Based on a first mass thickness value and a second mass thickness value, if the third attribute information of a first unknown object and the fourth attribute information of the second unknown object are known, then the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined. In this example, the third attribute information includes the mass thickness value of the first unknown object, the fourth attribute information includes the mass thickness value of the second unknown object, the fifth attribute information includes the first type parameter of the first unknown object, and the sixth attribute information includes the second type parameter of the second unknown object. Based on this, if the mass thickness value t of the first unknown object X is known... X The mass and thickness value t of the second unknown object Y Y Then, the first type parameter a1 of the first unknown object X and the second type parameter b1 of the second unknown object Y can be solved. Based on this, see... Figure 3 The diagram shown is a flowchart of the object detection method, which may include:

[0133] Step 301: Obtain the target X-ray intensity value of the object to be detected collected by the X-ray detector. The object to be detected is the superposition of the first unknown object X and the second unknown object Y.

[0134] Step 302: Query the acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material.

[0135] Step 303: Obtain the mass and thickness values ​​of the first unknown object and the second unknown object.

[0136] In one possible implementation, the mass and thickness value t of the first unknown object X can be obtained by direct measurement. X The mass and thickness value t of the second unknown object Y Y For example, if the first unknown object is of a fixed shape, its thickness and density can be measured beforehand. The density can be obtained from the weight / volume ratio; the measurement method is not limited as long as the thickness and density are known. Based on the thickness and density of the first unknown object, its mass-thickness value t is determined. X Mass thickness value t X It can be thickness multiplied by density. The second unknown object is an object of fixed shape. Its thickness and density are measured beforehand, and based on these measurements, the mass-thickness value t of the second unknown object is determined. Y Mass thickness value t Y It can be thickness multiplied by density.

[0137] In one possible implementation, the mass and thickness value t of the first unknown object X can be obtained through indirect measurement. X The mass and thickness value t of the second unknown object Y Y For example, an image of the object to be detected can be acquired, and the mass and thickness value t of the first unknown object X can be analyzed based on this image. X The mass and thickness value t of the second unknown object Y Y Alternatively, an image of the object to be detected can be acquired and input into a machine learning model to obtain the mass and thickness value t of the first unknown object X. X The mass and thickness value t of the second unknown object Y Y Of course, the above is just an example, and there are no restrictions on this indirect measurement method, as long as the mass and thickness value t of the first unknown object X can be obtained. X The mass and thickness value t of the second unknown object Y Y That's all.

[0138] In one possible implementation, the mass and thickness value t of the first unknown object X can be obtained through indirect measurement. X The mass and thickness value t of the second unknown object Y Y For example, in fat percentage testing, it's difficult to obtain materials consisting solely of lean and fatty meat. A flattened, uniformly layered piece of lean meat (which may contain fat) and a flattened, uniformly layered piece of fatty meat (which may contain lean meat) are stacked together. The resulting object to be tested should be as square as possible. During the stacking process, constrained phantoms or similar methods can be used, but the thickness of these phantoms should be as thin as possible to be negligible. Based on this process, an object to be tested containing both lean and fatty meat is obtained.

[0139] First, the total weight of the object to be tested (i.e., the superimposed object of lean and fat meat) can be obtained through weighing. Then, the base area of ​​the object can be obtained through measurement. Based on the total weight and base area of ​​the object, the mass thickness can be calculated. The mass thickness of the object is the mass thickness value t of the first unknown object X (e.g., lean meat). X The mass and thickness value t of the second unknown object Y (such as fat) Y The sum of these factors. For example, mass thickness * base area = thickness * base area * density, mass thickness * base area = volume * density = weight, therefore, mass thickness = weight / base area. Clearly, the total weight of the object being tested divided by its base area gives the mass thickness of the object being tested.

[0140] Then, during the fat percentage test, for the object consisting of lean and fatty meat (i.e., the object to be tested), the fat percentage can be obtained. For example, the fat percentage can be obtained using methods such as Soxhlet extraction or near-infrared spectroscopy. There are no restrictions on the specific method used, as long as the fat percentage can be obtained. Since the fat percentage represents the ratio between the mass of the fatty meat and the total mass of the object to be tested, when the second unknown object Y represents the fatty meat, the fat percentage can be t. Y / (t X +t Y ).

[0141] In summary, we can obtain t. X +t Y The values ​​of (i.e., the mass and thickness of the object to be detected) and t Y / (t X +t Y The value of ) (i.e., the fat percentage of the object to be tested) can be used to solve for the mass and thickness value t of the first unknown object X. X The mass and thickness value t of the second unknown object Y Y .

[0142] Step 304: Based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the mass thickness value of the first unknown object, and the mass thickness value of the second unknown object, determine the first type parameter of the first unknown object and the second type parameter of the second unknown object.

[0143] For example, formula (13) can be used to determine the first type parameter of the first unknown object and the second type parameter of the second unknown object. In formula (13), t1 represents the first mass thickness value, t2 represents the second mass thickness value, and t X t represents the mass and thickness of the first unknown object. Y The mass and thickness of the second unknown object are represented. Clearly, the above four parameters are known parameters. Furthermore, a1 represents the first type parameter of the first unknown object, and b1 represents the second type parameter of the second unknown object; these two parameters are unknown parameters. Based on the above four known parameters, the two unknown parameters are solved using formula (13), thus obtaining a1 and b1.

[0144] Step 305: Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the first type parameter of the first unknown object, determine the effective atomic number of the first unknown object, and determine the type of the first unknown object based on the effective atomic number of the first unknown object, thus completing the detection of the first unknown object.

[0145] Step 306: Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the second type parameter of the second unknown object, determine the effective atomic number of the second unknown object, and determine the type of the second unknown object based on the effective atomic number of the second unknown object, thus completing the detection of the second unknown object.

[0146] Based on the above technical concept, this application proposes an object detection method. Based on a first mass thickness value and a second mass thickness value, if the third attribute information of a first unknown object and the fourth attribute information of the second unknown object are known, then the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined. In this example, the third attribute information includes a first type parameter of the first unknown object, the fourth attribute information includes a second type parameter of the second unknown object, the fifth attribute information includes the mass thickness value of the first unknown object, and the sixth attribute information includes the mass thickness value of the second unknown object. Therefore, if the first type parameter a1 of the first unknown object X and the second type parameter b1 of the second unknown object Y are known, the mass thickness value t of the first unknown object X can be calculated. X The mass and thickness value t of the second unknown object Y Y Based on this, see [link / reference]. Figure 4 The diagram shown is a flowchart of the object detection method, which may include:

[0147] Step 401: Obtain the target X-ray intensity value of the object to be detected collected by the X-ray detector. The object to be detected is the superposition of the first unknown object X and the second unknown object Y.

[0148] Step 402: Query the acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material.

[0149] Step 403: Determine the first type parameter (denoted as first type parameter a1) of the first unknown object X and the second type parameter (denoted as second type parameter b1) of the second unknown object Y.

[0150] In one possible implementation, when the first unknown object X and the second unknown object Y are superimposed, the first unknown object has a single material (i.e., its type is known). Therefore, its type can be determined by pre-measurement, and this measurement method is not limited. Alternatively, the type of the first unknown object can be pre-configured. Similarly, the second unknown object has a single material (i.e., its type is known). Therefore, its type can be determined by pre-measurement, or its type can be pre-configured.

[0151] For example, in scenarios where the relative content of two substances that cannot be mixed uniformly is determined, such as in food testing where it is necessary to determine information such as the size of bones and the proportion of meat in meat, meat and bones can be approximated as a single substance. That is, meat is the first unknown substance, and bone is the second unknown substance. Obviously, the type of the first unknown substance and the type of the second unknown substance can be determined by the sample.

[0152] In summary, the types of the first unknown object and the second unknown object can be determined. The types of the first unknown object and the second unknown object can be pre-configured or obtained using a certain algorithm. There are no restrictions on the method of determining the types of the first unknown object and the second unknown object.

[0153] Since there is a correspondence between type and effective atomic number, the effective atomic number of the first unknown object can be determined based on its known type, and the effective atomic number of the second unknown object can be determined based on its known type. For example, based on the effective atomic number Z of the first unknown object... X1 The first effective atomic number Z1 of the first base material and the second effective atomic number Z2 of the second base material can determine the first type parameter of the first unknown object. For example, the first type parameter a1 of the first unknown object can be determined using the following formula: Z X1 = a1Z1 + (1 - a1)Z2. Based on the effective atomic number Z of the second unknown object. X2 The first effective atomic number Z1 of the first base material and the second effective atomic number Z2 of the second base material can be used to determine the second type parameter of the second unknown object. For example, the second type parameter b1 of the second unknown object can be determined using the following formula: Z X2 =b1Z1+(1-b1)Z2.

[0154] In one possible implementation, steps 301-304 can also be used to determine the first type parameter a1 of the first unknown object and the second type parameter b1 of the second unknown object.

[0155] For example, consider multiple objects to be detected, each composed of a first unknown object and a second unknown object superimposed on each other. That is, the first type parameter a1 is the same for different objects to be detected, and the second type parameter b1 is also the same for different objects to be detected. However, the mass and thickness values ​​of the first unknown object and the second unknown object differ among different objects to be detected.

[0156] In this application scenario, for the first object to be detected, steps 301-304 can be used to determine the first type parameter a1 and the second type parameter b1. For the second object to be detected and subsequent objects to be detected, the first type parameter a1 and the second type parameter b1 of the first object to be detected are used directly, and the first type parameter a1 and the second type parameter b1 of the objects to be detected are not determined again.

[0157] Step 404: Based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the first type parameter of the first unknown object, and the second type parameter of the second unknown object, determine the mass thickness value of the first unknown object and the mass thickness value of the second unknown object.

[0158] For example, formula (13) can be used to determine the mass thickness values ​​of the first unknown object and the second unknown object. In formula (13), t1 represents the first mass thickness value, t2 represents the second mass thickness value, a1 represents the first type parameter of the first unknown object, and b1 represents the second type parameter of the second unknown object. Obviously, the above four parameters are known parameters. In addition, t X t represents the mass and thickness of the first unknown object. Y The mass and thickness of the second unknown object are represented by the above two parameters, which are unknown parameters. Based on the above four known parameters, the two unknown parameters are solved by formula (13) to obtain t. X and t Y .

[0159] For example, after obtaining the mass and thickness value t of the first unknown object... X The mass and thickness value t of the second unknown object Y Then, based on the mass thickness value t X and mass thickness value t Y Perform relevant analysis. For example, if fat and lean meat are unevenly stacked together, obtain the mass thickness value t of the fat. X and the thickness value of lean meat t Y After that, through (t) X +t Y Determine the total weight of the object to be detected, and use t X / (t X +t Y Determine the fat percentage of the object to be tested by t Y / (t X +t Y To determine the lean meat percentage of the object being tested, and thus to grade the food.

[0160] Based on the above technical concept, this application proposes an object detection method. Based on a first mass thickness value and a second mass thickness value, if the third attribute information of a first unknown object and the fourth attribute information of the second unknown object are known, then the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined. In this example, the third attribute information may include a first type parameter of the first unknown object, the fourth attribute information may include the mass thickness value of the second unknown object, the fifth attribute information may include the mass thickness value of the first unknown object, and the sixth attribute information may include a second type parameter of the second unknown object. Based on this, if the first type parameter a1 of the first unknown object X and the mass thickness value t of the second unknown object Y are known... Y Then the mass and thickness t of the first unknown object X can be solved. X And the second type parameter b1 of the second unknown object Y. Based on this, the object detection method may include:

[0161] Obtain the target X-ray intensity value of the object to be detected collected by the X-ray detector. The object to be detected is the superposition of the first unknown object X and the second unknown object Y.

[0162] By querying the information table obtained by the target X-ray intensity value, the first mass thickness value of the first base material and the second mass thickness value of the second base material are obtained.

[0163] Determine the first type parameter a1 of the first unknown object X and the mass and thickness value t of the second unknown object Y. Y Regarding how to determine the first type parameter a1 of the first unknown object X and the mass and thickness value t of the second unknown object Y. Y In this embodiment, no restrictions are imposed; as long as the above two parameters can be obtained, it is acceptable.

[0164] Based on the first mass thickness value of the first base material, the second mass thickness value of the second base material, the first type parameter a1 of the first unknown object X, and the mass thickness value t of the second unknown object Y. Y Determine the mass and thickness value t of the first unknown object X. X And the second type parameter b1 of the second unknown object Y. For example, the mass thickness value t of the first unknown object X can be determined using formula (13). X And the second type parameter b1 of the second unknown object Y.

[0165] As can be seen from the above technical solutions, in the embodiments of this application, the detection of the object to be detected can be achieved based on the first mass thickness value of the first base material and the second mass thickness value of the second base material, improving detection accuracy and avoiding detection errors. When two objects are superimposed, the superimposed objects can also be identified and detected non-invasively based on X-rays, realizing the identification of material type (i.e., determining the type of unknown object) and the quantitative analysis of material composition (i.e., determining the mass thickness value of unknown object). The use of dual-energy X-ray imaging technology for material identification, including material type identification and quantitative analysis of material composition, provides a method for material identification when objects are superimposed under X-rays, which has good effects on material classification, discrimination, and quantitative calculation.

[0166] Based on the same concept as the method described above, this application proposes an object detection device, see [link to relevant documentation]. Figure 5 The diagram shown is a structural schematic of the object detection device, which may include:

[0167] The acquisition module 51 is used to acquire the target X-ray intensity value of the object to be detected collected by the X-ray detector; wherein, the object to be detected is the object resulting from the superposition of the first unknown object and the second unknown object;

[0168] The query module 52 is used to query an acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material; wherein the mass thickness value is the product of thickness and density; wherein the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material;

[0169] The determining module 53 is used to determine the second attribute information of the second unknown object based on the first mass thickness value, the second mass thickness value, and the first attribute information of the first unknown object;

[0170] Alternatively, based on the first mass thickness value and the second mass thickness value, as well as the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined.

[0171] For example, the first attribute information includes a first type parameter of the first unknown object and the mass thickness value of the first unknown object, and the second attribute information includes a second type parameter of the second unknown object, or the second attribute information includes a second type parameter of the second unknown object and the mass thickness value of the second unknown object; wherein, the first type parameter is used to identify the type of the first unknown object; and the second type parameter is used to identify the type of the second unknown object.

[0172] For example, the first unknown object and the second unknown object have overlapping and non-overlapping regions, and the target X-ray intensity value is the X-ray intensity value of the overlapping region; the acquisition module 51 is further configured to acquire the X-ray intensity value of the non-overlapping region collected by the X-ray detector; wherein, the non-overlapping region is the region where the first unknown object itself is located; the determination module 53 is further configured to determine the first type parameter of the first unknown object and the mass thickness value of the first unknown object based on the X-ray intensity value of the non-overlapping region, the acquired first mass attenuation coefficient of the first base material and the acquired second mass attenuation coefficient of the second base material.

[0173] For example, the third attribute information includes the mass thickness value of the first unknown object, the fourth attribute information includes the mass thickness value of the second unknown object, the fifth attribute information includes a first type parameter of the first unknown object, and the sixth attribute information includes a second type parameter of the second unknown object; or, the third attribute information includes the first type parameter of the first unknown object, the fourth attribute information includes the second type parameter of the second unknown object, the fifth attribute information includes the mass thickness value of the first unknown object, and the sixth attribute information includes the mass thickness value of the second unknown object; or, the third attribute information includes the first type parameter of the first unknown object, the fourth attribute information includes the mass thickness value of the second unknown object, the fifth attribute information includes the mass thickness value of the first unknown object, and the sixth attribute information includes the second type parameter of the second unknown object.

[0174] For example, the determining module 53 is further configured to determine the effective atomic number of the first unknown object based on the determined type of the first unknown object; and to determine a first type parameter of the first unknown object based on the effective atomic number of the first unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material. Furthermore, the determining module 53 is also configured to determine the effective atomic number of the second unknown object based on the determined type of the second unknown object; and to determine a second type parameter of the second unknown object based on the effective atomic number of the second unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material.

[0175] For example, the determining module 53 is further configured to determine the effective atomic number of the first unknown object based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the first type parameter, and to determine the type of the first unknown object based on the effective atomic number of the first unknown object; and to determine the effective atomic number of the second unknown object based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the second type parameter, and to determine the type of the second unknown object based on the effective atomic number of the second unknown object.

[0176] For example, the effective atomic number of the first unknown object and the first type parameter satisfy the following expression relationship: Z X1 = a1Z1 + (1-a1)Z2; The effective atomic number of the second unknown object and the second type parameter satisfy the following expression relationship: Z X2 =b1Z1+(1-b1)Z2;

[0177] Among them, Z X1 Z is used to represent the effective atomic number of the first unknown object. X2 The effective atomic number is used to represent the second unknown object, where a1 represents the first type parameter, b1 represents the second type parameter, Z1 represents the first effective atomic number, and Z2 represents the second effective atomic number.

[0178] For example, the first mass thickness value, the second mass thickness value, the first type parameter of the first unknown object, the second type parameter of the second unknown object, the mass thickness value of the first unknown object, and the mass thickness value of the second unknown object satisfy the following expression relationship:

[0179] t1=a1t X +b1t Y t2=(1-a1)t X +(1-b1)t Y;

[0180] Where t1 represents the first mass thickness value, t2 represents the second mass thickness value; a1 represents the first type parameter of the first unknown object, b1 represents the second type parameter of the second unknown object; t X t represents the mass and thickness of the first unknown object. Y This represents the mass and thickness value of the second unknown object.

[0181] Based on the same application concept as the above method, this application proposes an electronic device, see [link to application]. Figure 6 As shown, the electronic device includes a processor 61 and a machine-readable storage medium 62, the machine-readable storage medium 62 storing machine-executable instructions that can be executed by the processor 61; the processor 61 is used to execute the machine-executable instructions to implement the object detection method disclosed in the above example of this application.

[0182] Based on the same concept as the above method, this application also provides a machine-readable storage medium storing a plurality of computer instructions, which, when executed by a processor, can implement the object detection method disclosed in the above examples of this application.

[0183] The aforementioned machine-readable storage medium can be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, etc. For example, machine-readable storage media can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0184] Based on the same concept as the methods described above, this application also provides a computer program product, which may include a computer program. When executed by a processor, the computer program implements the object detection method disclosed in the examples above.

[0185] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0186] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An object detection method, characterized in that, The method includes: The target X-ray intensity value of the object to be detected is acquired by an X-ray detector; wherein the object to be detected is the superposition of a first unknown object and a second unknown object. By querying the acquired information table using the target X-ray intensity value, the first mass thickness value of the first base material and the second mass thickness value of the second base material are obtained; wherein, the mass thickness value is the product of thickness and density; wherein, the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein, the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material; Based on the first mass thickness value and the second mass thickness value, as well as the first attribute information of the first unknown object, the second attribute information of the second unknown object is determined. Alternatively, based on the first mass thickness value and the second mass thickness value, as well as the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined.

2. The method according to claim 1, characterized in that, The first attribute information includes a first type parameter of the first unknown object and the mass and thickness value of the first unknown object; the second attribute information includes a second type parameter of the second unknown object, or the second attribute information includes a second type parameter of the second unknown object and the mass and thickness value of the second unknown object. The first type parameter is used to identify the type of the first unknown object; The second type parameter is used to identify the type of the second unknown object.

3. The method according to claim 2, characterized in that, The first unknown object and the second unknown object have overlapping and non-overlapping regions, and the target X-ray intensity value is the X-ray intensity value of the overlapping region; before determining the second attribute information of the second unknown object based on the first mass thickness value, the second mass thickness value, and the first attribute information of the first unknown object, the method further includes: The X-ray intensity value of the non-overlapping region collected by the X-ray detector is obtained; wherein, the non-overlapping region is the region where the first unknown object itself is located; Based on the X-ray intensity value of the non-overlapping region, the first mass attenuation coefficient of the first base material and the second mass attenuation coefficient of the second base material, the first type parameter and the mass thickness value of the first unknown object are determined.

4. The method according to claim 1, characterized in that, The third attribute information includes the mass and thickness value of the first unknown object, the fourth attribute information includes the mass and thickness value of the second unknown object, the fifth attribute information includes the first type parameter of the first unknown object, and the sixth attribute information includes the second type parameter of the second unknown object. Alternatively, the third attribute information may include a first type parameter of the first unknown object, the fourth attribute information may include a mass thickness value of the second unknown object, the fifth attribute information may include a mass thickness value of the first unknown object, and the sixth attribute information may include a second type parameter of the second unknown object.

5. The method according to claim 1, characterized in that, The third attribute information includes a first type parameter of the first unknown object, the fourth attribute information includes a second type parameter of the second unknown object, the fifth attribute information includes the mass and thickness value of the first unknown object, and the sixth attribute information includes the mass and thickness value of the second unknown object.

6. The method according to claim 5, characterized in that, The method further includes: The effective atomic number of the first unknown object is determined based on the determined type of the first unknown object; the first type parameter of the first unknown object is determined based on the effective atomic number of the first unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material. The effective atomic number of the second unknown object is determined based on the already determined type of the second unknown object; the second type parameter of the second unknown object is determined based on the effective atomic number of the second unknown object, the first effective atomic number of the first base material, and the second effective atomic number of the second base material.

7. The method according to claim 4, characterized in that, The method further includes: Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the first type parameter, the effective atomic number of the first unknown object is determined, and the type of the first unknown object is determined based on the effective atomic number of the first unknown object. Based on the first effective atomic number of the first base material, the second effective atomic number of the second base material, and the second type parameter, the effective atomic number of the second unknown object is determined, and the type of the second unknown object is determined based on the effective atomic number of the second unknown object.

8. The method according to claim 6 or 7, characterized in that, The effective atomic number of the first unknown object and the first type parameter satisfy the following expression relationship: The effective atomic number of the second unknown object and the second type parameter satisfy the following expression relationship: ; in, Used to represent the effective atomic number of the first unknown object. Used to represent the effective atomic number of the second unknown object. This represents the first type of parameter. This indicates the second type of parameter. Indicates the first effective atomic number. This indicates the second effective atomic number.

9. The method according to claim 2 or 4, characterized in that, The first mass thickness value, the second mass thickness value, the first type parameter of the first unknown object, the second type parameter of the second unknown object, and the mass thickness value of the first unknown object and the mass thickness value of the second unknown object satisfy the following expression relationship: ， ； in, This represents the first mass thickness value. This represents the second mass thickness value; The first type parameter represents the first unknown object. The second type parameter represents the second unknown object; This represents the mass and thickness value of the first unknown object. This represents the mass and thickness value of the second unknown object.

10. An object detection device, characterized in that, The device includes: The acquisition module is used to acquire the target X-ray intensity value of the object to be detected collected by the X-ray detector; wherein, the object to be detected is the object resulting from the superposition of a first unknown object and a second unknown object; The query module is used to query an acquired information table using the target X-ray intensity value to obtain the first mass thickness value of the first base material and the second mass thickness value of the second base material; wherein the mass thickness value is the product of thickness and density; wherein the information table includes the correspondence between the sample X-ray intensity value, the mass thickness value of the first base material, and the mass thickness value of the second base material; wherein the first base material and the second base material are materials with known effective atomic numbers, and the effective atomic numbers of the first unknown object and the second unknown object are within the range of the effective atomic numbers of the first base material and the second base material; The determining module is used to determine the second attribute information of the second unknown object based on the first mass thickness value and the second mass thickness value, as well as the first attribute information of the first unknown object; Alternatively, based on the first mass thickness value and the second mass thickness value, as well as the third attribute information of the first unknown object and the fourth attribute information of the second unknown object, the fifth attribute information of the first unknown object and the sixth attribute information of the second unknown object are determined.

11. An electronic device, characterized in that, include: A processor and a machine-readable storage medium, the machine-readable storage medium storing machine-executable instructions that can be executed by the processor; The processor is configured to execute machine-executable instructions to implement the method of any one of claims 1-9.

Images