Method and system for identifying dangerous goods at bottom of vehicle in airport flight area

Abstract

The invention discloses a method and system for identifying dangerous goods at the bottom of a vehicle in an airport flight area, and the method comprises the steps: obtaining the vehicle type of a to-be-detected vehicle, transmitting a detection wave to the bottom of the to-be-detected vehicle, and synchronously collecting a reflection sequence of the detection wave at the bottom of the to-be-detected vehicle in real time; performing differential processing on the reflection sequence to generate a maximum response deviation value, calculating an abnormal fusion response intensity value according to the maximum response deviation value, and identifying a plurality of areas at the bottom of the to-be-detected vehicle as abnormal areas according to the abnormal fusion response intensity value; and constructing a physical property response vector of each abnormal region, and searching a dangerous goods physical property response vector corresponding to the physical property response vector of the abnormal region in a dangerous goods database, thereby determining the dangerous goods category of the abnormal region.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of vehicle bottom dangerous goods identification, and more particularly relates to a method and system for identifying dangerous goods at the bottom of a vehicle in an airport flight zone. BACKGROUND

[0002] The airport flight zone is a key link in the civil aviation safety system as the area for core operation activities such as take-off and landing, taxiing, and parking of aircraft, and its safety guarantee work is directly related to the stable operation of the aviation transportation system and the safety of passengers' lives and property. In this highly controlled area, various types of ground service vehicles (such as towing vehicles, refueling vehicles, catering vehicles, baggage trailers, security patrol vehicles, etc.) bear heavy transportation and support tasks, with a large number, complex types, and frequent operation, especially during peak hours, with a huge flow of vehicles and tight scheduling. The bottom of these vehicles is extremely prone to become a hidden space for illegally carrying or hiding dangerous goods as they need to frequently pass through the apron, parking apron, maintenance area, and the periphery of the airport. If not timely discovered and effectively blocked, it is extremely likely that explosives, contraband, or dangerous chemicals will enter the flight zone, thereby threatening the safe operation of aircraft, causing flight interruptions, and even causing serious aviation safety accidents.

[0003] Under the background of continuous improvement of aviation safety levels, the civil aviation flight zone has higher requirements for security inspection systems: not only to achieve comprehensive, dead-angle-free coverage inspection of the vehicle bottom, but also to have real-time identification capability for new, complex, and disguised dangerous targets while ensuring high pass rate. Therefore, how to efficiently, accurately, and in real time, conduct safety inspection on vehicles passing through the flight zone, especially intelligent identification and abnormality investigation of the vehicle bottom and hidden structure areas, has become an important technical challenge currently faced by the civil aviation field. This requires a new type of intelligent security inspection system with high sensitivity, high automation, and high adaptability, which can break through the limitations of traditional image recognition, achieve accurate perception and intelligent analysis of the vehicle bottom structure and its disturbance response behavior, ensure the forward movement of the flight zone safety barrier, the formation of a closed loop of prevention and control, and the closed loop management of risk hidden dangers, so as to effectively guard the last line of defense of civil aviation operation safety.

[0004] Therefore, there is an urgent need for a technical solution that can improve the identification accuracy of dangerous goods at the bottom of vehicles in the airport flight zone and effectively reduce safety risks. SUMMARY

[0005] To solve the above technical problems, the present application provides a method for identifying dangerous goods at the bottom of a vehicle in an airport flight zone, comprising:

[0006] Obtaining the vehicle type of a vehicle to be detected, emitting a detection wave to the bottom of the vehicle to be detected, and synchronously collecting a reflection sequence of the detection wave of the bottom of the vehicle to be detected in real time;

[0007] performing differential processing on the reflection sequence to generate a maximum response deviation value, calculating an abnormal fusion response intensity value based on the maximum response deviation value, and identifying multiple areas on the bottom of the vehicle to be detected as abnormal areas based on the abnormal fusion response intensity values;

[0008] A physical property response vector of each abnormal area is constructed, and a dangerous goods physical property response vector corresponding to the physical property response vector of the abnormal area is searched in a dangerous goods database, thereby determining the dangerous goods category of the abnormal area.

[0009] Furthermore, transmitting a detection wave to the bottom of the vehicle to be detected includes:

[0010] Obtain a set of dangerous goods material characteristics from the dangerous goods database, and a set of normal vehicle bottom material characteristics of the same vehicle type as the vehicle to be detected, perform spectral mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, find the frequency set that maximizes the response difference between the two, and emit detection waves according to the frequency set.

[0011] Furthermore, performing differential processing on the reflection sequence to generate a maximum response deviation value includes:

[0012]

[0013] Where ΔR(x, y, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected i The maximum response deviation value when t is the sampling time, R ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the position (x, y) of the bottom of a normal vehicle of the same type as the vehicle to be detected i The response deviation value, R(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected at sampling time t i The response deviation value.

[0014] Furthermore, calculating the abnormal fusion response intensity value according to the maximum response deviation value includes:

[0015]

[0016] Where M(x, y) is the abnormal fusion response intensity value at the bottom position (x, y) of the vehicle to be detected, ω i is the frequency λ of the i-th detection wave i The weight of .

[0017] Furthermore, identifying the plurality of areas on the bottom of the vehicle to be detected as abnormal areas according to the abnormal fusion response strength values ​​includes: normalizing the abnormal fusion response strength values ​​M(x, y) to be within the interval [0, 1];

[0018] The abnormal fusion response strength value M(x, y) is compared with the preset response threshold, and the bottom position (x, y) of the vehicle to be detected corresponding to the abnormal fusion response strength value M(x, y) exceeding the response threshold is marked as an abnormal point;

[0019] For all outliers, aggregation analysis is performed according to the connection relationship of the eight neighborhoods until all outliers are merged into several non-overlapping outlier areas. Among them, if two outliers are spatially touching each other or only separated by one grid, the two outliers are classified into the same area and regarded as an outlier area.

[0020] Furthermore, constructing the physical property response vector of each abnormal region includes: thermal variation coefficient, dielectric response amplitude and frequency domain response peak position.

[0021] The present invention also provides a system for identifying dangerous goods under vehicles in an airport flight area, comprising:

[0022] An induction module is used to obtain the vehicle type of the vehicle to be detected, transmit a detection wave to the bottom of the vehicle to be detected, and synchronously collect a reflection sequence of the detection wave from the bottom of the vehicle to be detected in real time;

[0023] an abnormal region acquisition module, configured to perform differential processing on the reflection sequence to generate a maximum response deviation value, calculate an abnormal fusion response intensity value based on the maximum response deviation value, and identify multiple regions on the bottom of the vehicle to be detected as abnormal regions based on the abnormal fusion response intensity values;

[0024] The identification module is used to construct a physical property response vector of each abnormal area and search the hazardous goods database for a physical property response vector of the hazardous goods corresponding to the physical property response vector of the abnormal area, thereby determining the hazardous goods category of the abnormal area.

[0025] Furthermore, transmitting a detection wave to the bottom of the vehicle to be detected includes:

[0026] Obtain a set of dangerous goods material characteristics from the dangerous goods database, and a set of normal vehicle bottom material characteristics of the same vehicle type as the vehicle to be detected, perform spectral mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, find the frequency set that maximizes the response difference between the two, and emit detection waves according to the frequency set.

[0027] Furthermore, performing differential processing on the reflection sequence to generate a maximum response deviation value includes:

[0028]

[0029] wherein, ΔR(x, y, λ i ) is the maximum response deviation value at the position (x, y) of the bottom of the vehicle to be detected at the i i th probe wave frequency λ ref , t is the sampling time, R i (x, y, λ i ) is the response deviation value at the position (x, y) of the bottom of the normal vehicle of the same vehicle type as the vehicle to be detected at the i i th probe wave frequency λ i , R(x, y, t, λ i ) is the response deviation value at the position (x, y) of the bottom of the vehicle to be detected at the i i th probe wave frequency λ i at the sampling time t.

[0030] Further, calculating the abnormal fusion response intensity value according to the maximum response deviation value comprises:

[0031]

[0032] wherein, M(x, y) is the abnormal fusion response intensity value at the position (x, y) of the bottom of the vehicle to be detected, ω i is the weight of the i i th probe wave frequency λ i .

[0033] Overall, compared with the prior art, the above technical scheme conceived by the present application has the following beneficial effects:

[0034] 1. The technical scheme of the present application realizes a fundamental change from the traditional AI image recognition static, passive, and visual feature driven mode to a dynamic, active, and physical property driven mode;

[0035] 2. The technical scheme of the present application can actively stimulate the target area at the bottom of the vehicle to produce a differential response, thereby effectively identifying dangerous goods at the bottom of the vehicle;

[0036] 3. The technical scheme of the present application does not rely on large-scale artificial sample labeling, has good generalization ability, and significantly improves the identification accuracy of dangerous goods at the bottom of the vehicle.

[0037] 4. The technical scheme of the present application has good generalization identification ability for unknown dangerous goods, material varieties, and disguised objects, and breaks through the limitations of the traditional AI recognition “training-test closed loop”. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is the method flowchart of embodiment 1 of the present application;

[0039] Figure 2 is the system structure diagram of embodiment 2 of the present application. DETAILED DESCRIPTION

[0040] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings of the specification and specific embodiments.

[0041] The method provided by the application can be implemented in a terminal environment, which can include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the embodiments below.

[0042] The processor can include one or more processing cores. The processor connects various parts in the entire terminal through various interfaces and lines, executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0043] The storage medium can include random access memory (RAM) and read-only memory (ROM). The storage medium can be used to store instructions, programs, codes, code sets or instructions.

[0044] The display screen is used to display the user interface of each application.

[0045] In addition, those skilled in the art can understand that the structure of the terminal described above does not constitute a limitation on the terminal, and the terminal can include more or fewer components, or combine certain components, or different component arrangements. For example, the terminal also includes radio frequency circuit, input unit, sensor, audio circuit, power supply and other components, which are not described here.

[0046] Embodiment 1

[0047] As shown in the figure, the embodiment provides a method for identifying dangerous goods at the bottom of a vehicle in an airport flight area, which includes: Figure 1

[0048] Step 101, obtaining the vehicle type (such as truck, tank truck, pickup truck, etc.) of the vehicle to be detected (the vehicle type is not limited in this embodiment, and the user can set the relevant vehicle type), emitting a detection wave to the bottom of the vehicle to be detected, and synchronously collecting the reflection sequence of the detection wave at the bottom of the vehicle to be detected in real time;

[0049] Specifically, emitting a detection wave to the bottom of the vehicle to be detected includes:

[0050] ​Obtain a hazardous material characteristic set from a hazardous material database, and obtain a normal vehicle bottom material characteristic set of the same vehicle type as the vehicle to be detected, perform spectral mapping on the hazardous material characteristic set and the normal vehicle bottom material characteristic set, find a frequency set that maximizes the difference between the responses of the two sets, and emit a probe wave according to the frequency set.

[0051] Step 102, differential processing is performed on the reflection sequence to generate a maximum response deviation value, and an abnormal fusion response intensity value is calculated according to the maximum response deviation value, and a plurality of regions of the bottom of the vehicle to be detected are identified as abnormal regions according to the abnormal fusion response intensity value;

[0052] Specifically, the differential processing of the reflection sequence to generate a maximum response deviation value includes:

[0053]

[0054] wherein, ΔR(x, y, λ i ) is the maximum response deviation value at the position (x, y) of the bottom of the vehicle to be detected at the i-th probe wave frequency λ i , t is the sampling time, R ref (x, y, λ i ) is the response deviation value at the position (x, y) of the bottom of the normal vehicle of the same vehicle type as the vehicle to be detected at the i-th probe wave frequency λ i , and R(x, y, t, λ i ) is the response deviation value at the position (x, y) of the bottom of the vehicle to be detected at the i-th probe wave frequency λ i at the sampling time t.

[0055] Specifically, calculating an abnormal fusion response intensity value according to the maximum response deviation value includes:

[0056]

[0057] wherein, M(x, y) is the abnormal fusion response intensity value at the position (x, y) of the bottom of the vehicle to be detected, ω i is the weight of the i-th probe wave frequency λ i .

[0058] Specifically, identifying a plurality of regions of the bottom of the vehicle to be detected as abnormal regions according to the abnormal fusion response intensity value includes: performing standardization processing on the abnormal fusion response intensity value M(x, y) to standardize it to the [0, 1] interval.

[0059] Comparing the abnormal fusion response intensity value M(x, y) with a preset response threshold, and marking the position (x, y) of the bottom of the vehicle to be detected corresponding to the abnormal fusion response intensity value M(x, y) that exceeds the response threshold as an abnormal point.

[0060] For all outliers, aggregation analysis is performed according to the connection relationship of the eight neighborhoods until all outliers are merged into several non-overlapping outlier areas. Among them, if two outliers are spatially touching each other or only separated by one grid, the two outliers are classified into the same area and regarded as an outlier area.

[0061] Step 103 : constructing a physical property response vector for each abnormal area, and searching a dangerous goods database for a physical property response vector corresponding to the physical property response vector for the abnormal area, thereby determining the dangerous goods category of the abnormal area.

[0062] Specifically, constructing the physical property response vector of each abnormal region includes: thermal variation coefficient, dielectric response amplitude and frequency domain response peak position.

[0063] Preferably, the thermal variation coefficient represents the degree of thermal response of the abnormal area after being stimulated by a detection wave (such as infrared irradiation or heat source scanning), reflecting its properties such as heat capacity, thermal conductivity, and thermal hysteresis. This embodiment illustrates how to obtain the thermal variation coefficient through the following example, as follows:

[0064] Get all thermal infrared reflectivity R at the abnormal area position (x, y) within a certain time period T (x, y, t) and substitute it into the following formula:

[0065]

[0066] Among them, R T (x, y, t) is the thermal infrared reflectivity at the abnormal area position (x, y) at time t, C T is the thermal variation coefficient, if C T The larger the value, the more violently the abnormal area reacts to temperature changes, and the abnormal area is volatile and flammable. i′ | is the number of all locations in the i′th abnormal area, where all locations refer to location points.

[0067] Preferably, the dielectric response amplitude represents the degree of reflection enhancement after the abnormal area is excited by the detection wave (such as millimeter wave, microwave). This embodiment uses the following example to illustrate how to obtain the dielectric response amplitude, which is as follows:

[0068]

[0069] Among them, C E is the dielectric response amplitude. The larger it is, the more it indicates that the abnormal area contains materials with strong conductivity and high polarizability structure, such as liquid conductive media, battery components, and metal-doped substances. E (x, y, λ e) is the abnormal area position (x, y) in the dielectric response sensitive band λ e The actual reflectivity under e For the dielectric response sensitive band (such as 30GHz to 300GHz), R E-ref (x, y, λ e ) is the position (x, y) in the dielectric response sensitive band λ e The reference reflectivity under the abnormal area (i.e., the reflectivity when the bottom of the vehicle corresponding to the abnormal area is normal).

[0070] Preferably, the frequency domain response peak position is used to reflect the characteristic wavelength position of the most significant absorption or reflection in the abnormal area. This embodiment uses the following example to illustrate how to obtain the frequency domain response peak position, as follows:

[0071] ΔR′(x,y,λ i )=|R′(x,y,t,λ i )-R′ ref (x,y,λ i )|

[0072] Where ΔR′(x, y, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) i The reflectivity change when R′(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) at time t i The actual reflectivity, R′ ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) i The reference reflectivity when the abnormal area is normal (i.e., the reflectivity when the bottom of the vehicle corresponding to the abnormal area is normal).

[0073]

[0074] Among them, C λ is the peak position of the frequency domain response, ΔR′(λ i ) is the frequency λ of the i-th detection wave i The average value of the reflectivity change at all locations in the abnormal area.

[0075] If C λ If it is between 1.2μm and 1.4μm, there is water-containing organic matter in the abnormal area;

[0076] If C λ If the particle size is between 9μm and 11μm, nitro powder exists in the abnormal area.

[0077] Example 2

[0078] As Figure 2 shown, the embodiment proposes an airport flight area vehicle bottom dangerous goods identification system, comprising:

[0079] An induction module is configured to acquire a vehicle type of a vehicle to be detected (such as a truck, a tank truck, a pickup truck, etc., the vehicle type is not limited in the embodiment, and the user can set the related vehicle type by himself), emit a detection wave to the bottom of the vehicle to be detected, and synchronously collect a reflection sequence of the detection wave at the bottom of the vehicle to be detected in real time.

[0080] Specifically, emitting the detection wave to the bottom of the vehicle to be detected comprises:

[0081] Acquiring a dangerous goods material characteristic set from a dangerous goods database, and acquiring a normal vehicle bottom material characteristic set of the same vehicle type as the vehicle to be detected, performing frequency spectrum mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, finding a frequency set that maximizes the response difference between the two sets, and emitting the detection wave according to the frequency set.

[0082] An abnormal area acquisition module is configured to perform differential processing on the reflection sequence, generate a maximum response deviation value, calculate an abnormal fusion response intensity value according to the maximum response deviation value, and identify a plurality of areas at the bottom of the vehicle to be detected as abnormal areas according to the abnormal fusion response intensity value.

[0083] Specifically, performing differential processing on the reflection sequence to generate the maximum response deviation value comprises:

[0084]

[0085] Wherein, ΔR(x, y, λ i ) is the maximum response deviation value at the position (x, y) of the bottom of the vehicle to be detected at the i-th detection wave frequency λ i , t is the sampling time, R ref (x, y, λ i ) is the response deviation value of the position (x, y) of the normal vehicle bottom of the same vehicle type as the vehicle to be detected at the i-th detection wave frequency λ i , and R(x, y, t, λ i ) is the response deviation value of the position (x, y) of the bottom of the vehicle to be detected at the i-th detection wave frequency λ i at the sampling time t.

[0086] Specifically, calculating the abnormal fusion response intensity value according to the maximum response deviation value comprises:

[0087]

[0088] wherein M(x, y) is the abnormal fusion response intensity value at the position (x, y) of the bottom of the vehicle to be detected, ω i is the weight of the i-th probe wave frequency λ i .

[0089] Specifically, identifying a plurality of regions of the bottom of the vehicle to be detected as abnormal regions according to the abnormal fusion response intensity value comprises: normalizing the abnormal fusion response intensity value M(x, y) to the interval [0, 1];

[0090] Comparing the abnormal fusion response intensity value M(x, y) with a preset response threshold, and marking the position (x, y) of the bottom of the vehicle to be detected corresponding to the abnormal fusion response intensity value M(x, y) exceeding the response threshold as an abnormal point;

[0091] According to the connection relationship of the eight-neighborhood, performing aggregation analysis on all abnormal points until all abnormal points are merged into a plurality of non-overlapping abnormal regions, wherein if two abnormal points contact each other or are separated by only one grid in space, the two abnormal points are classified into the same region and serve as an abnormal region.

[0092] The identification module is configured to construct a physical property response vector of each of the abnormal regions, and search for a dangerous goods physical property response vector corresponding to the physical property response vector of the abnormal region in a dangerous goods database, so as to determine the dangerous goods category of the abnormal region.

[0093] Specifically, constructing the physical property response vector of each of the abnormal regions comprises: a thermal variation coefficient, a dielectric response amplitude, and a frequency domain response peak position.

[0094] Preferably, the thermal variation coefficient represents the thermal reaction degree of the abnormal region after being excited by a probe wave (such as infrared irradiation or heat source scanning), and reflects the thermal capacity, thermal conductivity, thermal hysteresis, and other properties. The embodiment illustrates how to obtain the thermal variation coefficient through the following examples, as follows:

[0095] Obtaining all thermal infrared reflectivities R T (x, y, t) at the position (x, y) of the abnormal region within a certain period of time, and substituting them into the following formula:

[0096]

[0097] wherein R T (x, y, t) is the thermal infrared reflectivity at the position (x, y) of the abnormal region at time t, C T is the thermal variation coefficient, and the greater the value of C T , the more it indicates that the abnormal region reacts violently to temperature changes, and thus it is concluded that the abnormal region is volatile and flammable, |A i′| is the number of all locations in the i′th abnormal area, where all locations refer to location points.

[0098] Preferably, the dielectric response amplitude represents the degree of reflection enhancement after the abnormal area is excited by the detection wave (such as millimeter wave, microwave). This embodiment uses the following example to illustrate how to obtain the dielectric response amplitude, which is as follows:

[0099]

[0100] Among them, C E is the dielectric response amplitude. The larger it is, the more it indicates that the abnormal area contains materials with strong conductivity and high polarizability structure, such as liquid conductive media, battery components, and metal-doped substances. E (x, y, λ e ) is the abnormal area position (x, y) in the dielectric response sensitive band λ e The actual reflectivity under e For the dielectric response sensitive band (such as 30GHz to 300GHz), R E-ref (x, y, λ e ) is the position (x, y) in the dielectric response sensitive band λ e The reference reflectivity under the abnormal area (i.e., the reflectivity when the bottom of the vehicle corresponding to the abnormal area is normal).

[0101] Preferably, the frequency domain response peak position is used to reflect the characteristic wavelength position of the most significant absorption or reflection in the abnormal area. This embodiment uses the following example to illustrate how to obtain the frequency domain response peak position, as follows:

[0102] ΔR′(x,y,λ i )=|R′(x,y,t,λ i )-R′ ref (x,y,λ i )|

[0103] Where ΔR′(x, y, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) i The reflectivity change when R′(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) at time t i The actual reflectivity, R′ ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the abnormal area position (x, y) i The reference reflectivity when the abnormal area is normal (i.e., the reflectivity when the bottom of the vehicle corresponding to the abnormal area is normal).

[0104]

[0105] wherein C λ is the position of the peak of the frequency domain response, ΔR'(λ i ) is the average of the reflectivity change of all positions in the abnormal region at the i-th probe wave frequency λ i .

[0106] If C λ is in 1.2 μm-1.4 μm, the abnormal region contains water-containing organic matter;

[0107] If C λ is in 9 μm-11 μm, the abnormal region contains nitro-based powder.

[0108] Embodiment 3

[0109] The embodiment of the present application also provides a storage medium which stores a plurality of instructions for implementing the method for identifying dangerous goods at the bottom of a vehicle in an airport flight zone.

[0110] Optionally, in the embodiment, the storage medium can be located in any one of computer terminals in a computer terminal group in a computer network, or in any one of mobile terminals in a mobile terminal group.

[0111] Optionally, in the embodiment, the storage medium is configured to store program codes for executing the following method steps: step 101, acquiring a vehicle type of a vehicle to be detected, emitting a probe wave to the bottom of the vehicle to be detected, and synchronously collecting a reflection sequence of the probe wave at the bottom of the vehicle to be detected in real time;

[0112] Specifically, emitting the probe wave to the bottom of the vehicle to be detected comprises:

[0113] acquiring a dangerous goods material characteristic set from a dangerous goods database, and acquiring a normal vehicle bottom material characteristic set of the same vehicle type as the vehicle to be detected, performing frequency spectrum mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, finding a frequency set which maximizes the response difference between the two sets, and emitting the probe wave according to the frequency set.

[0114] Step 102, performing differential processing on the reflection sequence to generate a maximum response deviation value, calculating an abnormal fusion response intensity value according to the maximum response deviation value, and identifying a plurality of regions at the bottom of the vehicle to be detected as abnormal regions according to the abnormal fusion response intensity value;

[0115] Specifically, performing differential processing on the reflection sequence to generate a maximum response deviation value comprises:

[0116]

[0117] Where ΔR(x, y, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected i The maximum response deviation value when t is the sampling time, R ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the position (x, y) of the bottom of a normal vehicle of the same type as the vehicle to be detected i The response deviation value, R(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected at sampling time t i The response deviation value.

[0118] Specifically, calculating the abnormal fusion response intensity value according to the maximum response deviation value includes:

[0119]

[0120] Where M(x, y) is the abnormal fusion response intensity value at the bottom position (x, y) of the vehicle to be detected, ω i is the frequency λ of the i-th detection wave i The weight of .

[0121] Specifically, identifying the plurality of areas on the bottom of the vehicle to be detected as abnormal areas according to the abnormal fusion response strength value includes: normalizing the abnormal fusion response strength value M(x, y) to be within the interval [0, 1];

[0122] The abnormal fusion response strength value M(x, y) is compared with the preset response threshold, and the bottom position (x, y) of the vehicle to be detected corresponding to the abnormal fusion response strength value M(x, y) exceeding the response threshold is marked as an abnormal point;

[0123] For all outliers, aggregation analysis is performed according to the connection relationship of the eight neighborhoods until all outliers are merged into several non-overlapping outlier areas. Among them, if two outliers are spatially touching each other or only separated by one grid, the two outliers are classified into the same area and regarded as an outlier area.

[0124] Step 103 : constructing a physical property response vector for each abnormal area, and searching a dangerous goods database for a physical property response vector corresponding to the physical property response vector for the abnormal area, thereby determining the dangerous goods category of the abnormal area.

[0125] Specifically, constructing the physical property response vector of each abnormal region includes: thermal variation coefficient, dielectric response amplitude and frequency domain response peak position.

[0126] Example 4

[0127] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the method for identifying dangerous goods under vehicles in an airport flight area.

[0128] Specifically, the electronic device of this embodiment may be a computer terminal, which may include: one or more processors, and a storage medium.

[0129] The storage medium can be used to store software programs and modules, such as the method for identifying dangerous goods under vehicles in an airport flight zone in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, thereby realizing the above-mentioned method for identifying dangerous goods under vehicles in an airport flight zone. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely located relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0130] The processor can call the information and application stored in the storage medium through the transmission system to execute the following method steps: Step 101, obtaining the vehicle type of the vehicle to be detected, transmitting a detection wave to the bottom of the vehicle to be detected, and synchronously collecting the reflection sequence of the detection wave from the bottom of the vehicle to be detected in real time;

[0131] Specifically, transmitting a detection wave to the bottom of the vehicle to be detected includes:

[0132] Obtain a set of dangerous goods material characteristics from the dangerous goods database, and a set of normal vehicle bottom material characteristics of the same vehicle type as the vehicle to be detected, perform spectral mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, find the frequency set that maximizes the response difference between the two, and emit detection waves according to the frequency set.

[0133] Step 102: performing differential processing on the reflection sequence to generate a maximum response deviation value, calculating an abnormal fusion response intensity value based on the maximum response deviation value, and identifying multiple areas on the bottom of the vehicle to be detected as abnormal areas based on the abnormal fusion response intensity values;

[0134] Specifically, performing differential processing on the reflection sequence to generate a maximum response deviation value includes:

[0135]

[0136] Where ΔR(x, y, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected i The maximum response deviation value when t is the sampling time, R ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the position (x, y) of the bottom of a normal vehicle of the same type as the vehicle to be detected i The response deviation value, R(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected at sampling time t i The response deviation value.

[0137] Specifically, calculating the abnormal fusion response intensity value according to the maximum response deviation value includes:

[0138]

[0139] Where M(x, y) is the abnormal fusion response intensity value at the bottom position (x, y) of the vehicle to be detected, ω i is the frequency λ of the i-th detection wave i The weight of .

[0140] Specifically, identifying the plurality of areas on the bottom of the vehicle to be detected as abnormal areas according to the abnormal fusion response strength value includes: normalizing the abnormal fusion response strength value M(x, y) to be within the interval [0, 1];

[0141] The abnormal fusion response strength value M(x, y) is compared with the preset response threshold, and the bottom position (x, y) of the vehicle to be detected corresponding to the abnormal fusion response strength value M(x, y) exceeding the response threshold is marked as an abnormal point;

[0142] For all outliers, aggregation analysis is performed according to the connection relationship of the eight neighborhoods until all outliers are merged into several non-overlapping outlier areas. Among them, if two outliers are spatially touching each other or only separated by one grid, the two outliers are classified into the same area and regarded as an outlier area.

[0143] Step 103 : constructing a physical property response vector for each abnormal area, and searching a dangerous goods database for a physical property response vector corresponding to the physical property response vector for the abnormal area, thereby determining the dangerous goods category of the abnormal area.

[0144] Specifically, constructing the physical property response vector of each abnormal region includes: thermal variation coefficient, dielectric response amplitude and frequency domain response peak position.

[0145] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0146] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0147] In the several embodiments of the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the embodiments described above are only schematic. For example, the division of units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0148] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0149] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0150] The integrated unit, if realized in the form of software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the essential part or all or part of the technical solutions which make contributions to the prior art can be embodied in the form of software product, and the computer software product is stored in a storage medium, including a plurality of instructions for making a computer equipment (which can be a personal computer, a server or a network equipment, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic or optical disk and various program code storage media.

[0151] Obviously, the above embodiments are merely example for clearly illustrating but not limitation to the embodiments. Based on the above description, other different forms of changes or variations can be made by those skilled in the art. Here, all the embodiments need not and can not be enumerated. The obvious changes or variations derived from the above description are still within the protection scope of the present application.

Claims

1. A method for identifying dangerous goods under vehicles in an airport flight area, characterized in that: include: Obtaining the vehicle type of the vehicle to be detected, transmitting a detection wave to the bottom of the vehicle to be detected, and synchronously collecting a reflection sequence of the detection wave from the bottom of the vehicle to be detected in real time; performing differential processing on the reflection sequence to generate a maximum response deviation value, calculating an abnormal fusion response intensity value based on the maximum response deviation value, and identifying multiple areas on the bottom of the vehicle to be detected as abnormal areas based on the abnormal fusion response intensity values; A physical property response vector of each abnormal area is constructed, and a dangerous goods physical property response vector corresponding to the physical property response vector of the abnormal area is searched in a dangerous goods database, thereby determining the dangerous goods category of the abnormal area.

2. The method for identifying dangerous goods under vehicles in an airport flight zone according to claim 1, characterized in that: Transmitting a detection wave toward the bottom of the vehicle to be detected includes: Obtain a set of dangerous goods material characteristics from the dangerous goods database, and a set of normal vehicle bottom material characteristics of the same vehicle type as the vehicle to be detected, perform spectral mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, find the frequency set that maximizes the response difference between the two, and emit detection waves according to the frequency set.

3. The method for identifying dangerous goods under vehicles in an airport flight zone according to claim 1, characterized in that: Performing differential processing on the reflection sequence to generate a maximum response deviation value includes: Where ΔR(x, y, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected i The maximum response deviation value when t is the sampling time, R ref (x, y, λ i ) is the frequency λ of the i-th detection wave at the position (x, y) of the bottom of a normal vehicle of the same type as the vehicle to be detected i The response deviation value, R(x,y,t,λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected at sampling time t i The response deviation value.

4. The method for identifying dangerous goods under vehicles in an airport flight zone according to claim 3, characterized in that: Calculating the abnormal fusion response intensity value according to the maximum response deviation value includes: Where M(x, y) is the abnormal fusion response intensity value at the bottom position (x, y) of the vehicle to be detected, ω i is the frequency λ of the i-th detection wave i The weight of .

5. The method for identifying dangerous goods under vehicles in an airport flight zone according to claim 4, characterized in that: Identifying the plurality of areas on the bottom of the vehicle to be detected as abnormal areas according to the abnormal fusion response strength values ​​includes: normalizing the abnormal fusion response strength values ​​M(x, y) to be within the interval [0, 1]; The abnormal fusion response strength value M(x, y) is compared with the preset response threshold, and the bottom position (x, y) of the vehicle to be detected corresponding to the abnormal fusion response strength value M(x, y) exceeding the response threshold is marked as an abnormal point; For all outliers, aggregation analysis is performed according to the connection relationship of the eight neighborhoods until all outliers are merged into several non-overlapping outlier areas. Among them, if two outliers are spatially touching each other or only separated by one grid, the two outliers are classified into the same area and regarded as an outlier area.

6. The method for identifying dangerous goods under vehicles in an airport flight zone according to claim 1, characterized in that: The physical property response vector of each abnormal region is constructed, including: thermal variation coefficient, dielectric response amplitude and frequency domain response peak position.

7. A system for identifying dangerous goods under vehicles in an airport flight area, characterized by: include: An induction module is used to obtain the vehicle type of the vehicle to be detected, transmit a detection wave to the bottom of the vehicle to be detected, and synchronously collect a reflection sequence of the detection wave from the bottom of the vehicle to be detected in real time; an abnormal region acquisition module, configured to perform differential processing on the reflection sequence to generate a maximum response deviation value, calculate an abnormal fusion response intensity value based on the maximum response deviation value, and identify multiple regions on the bottom of the vehicle to be detected as abnormal regions based on the abnormal fusion response intensity values; The identification module is used to construct a physical property response vector of each abnormal area and search the hazardous goods database for a physical property response vector of the hazardous goods corresponding to the physical property response vector of the abnormal area, thereby determining the hazardous goods category of the abnormal area.

8. The system for identifying dangerous goods under vehicles in an airport flight zone according to claim 7, characterized in that: Transmitting a detection wave toward the bottom of the vehicle to be detected includes: Obtain a set of dangerous goods material characteristics from the dangerous goods database, and a set of normal vehicle bottom material characteristics of the same vehicle type as the vehicle to be detected, perform spectral mapping on the dangerous goods material characteristic set and the normal vehicle bottom material characteristic set, find the frequency set that maximizes the response difference between the two, and emit detection waves according to the frequency set.

9. The system for identifying dangerous goods under vehicles in an airport flight zone according to claim 7, characterized in that: Performing differential processing on the reflection sequence to generate a maximum response deviation value includes: Among them, ΔR(x,y,λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected i The maximum response deviation value when t is the sampling time, R ref (x,y,λ i ) is the frequency λ of the i-th detection wave at the position (x, y) of the bottom of a normal vehicle of the same type as the vehicle to be detected i The response deviation value, R(x, y, t, λ i ) is the frequency λ of the i-th detection wave at the bottom position (x, y) of the vehicle to be detected at sampling time t i The response deviation value.

10. The system for identifying dangerous goods under vehicles in an airport flight zone according to claim 9, characterized in that: Calculating the abnormal fusion response intensity value according to the maximum response deviation value includes: Where M(x, y) is the abnormal fusion response intensity value at the bottom position (x, y) of the vehicle to be detected, ω i is the frequency λ of the i-th detection wave i The weight of .

Images