A real-time fusion millimeter wave imaging frame increase method and system

Abstract

The present invention provides a real-time fusion millimeter wave imaging frame increase method, which can solve the problems of poor real-time imaging and low acquisition frame rate of existing systems, resulting in poor continuity of video images and non-smooth display. The original single-frame millimeter wave imaging image of the target person under test entering the security inspection channel at the current moment, which is acquired by the millimeter wave security inspection imager; the direction of travel and the area where the target person under test is located in the security inspection channel are determined according to the current signal status of each photoelectric switch; the imaging target area is separated from the original single-frame millimeter wave imaging image at the current moment and transferred to a newly added background image to form an image to be analyzed; the imaging target area in the image to be analyzed is partitioned and the imaging offset direction of the target person under test at the next moment is predicted; the imaging target area is offset and the offset imaging target area is integrated with the background area in the original single-frame millimeter wave image to form a newly added image frame.

Description

Technical Field

[0001] The present invention relates to the field of security inspection technology, in particular to the field of channel-type millimeter wave imaging security inspection, and specifically to a real-time fusion millimeter wave imaging frame increment method and system. Background Art

[0002] At present, the channel-type millimeter-wave body security inspection system has been widely used in places with large crowds, such as public security checkpoints, subway stations, airports, railway stations, docks, ports, and high-speed rail lines, due to its advantages of zero radiation, no stop, non-contact, good privacy protection, high security efficiency, good imaging effect, and the ability to detect a wide variety of prohibited items.

[0003] The existing millimeter wave human body security inspection system usually includes millimeter wave image acquisition equipment installed on both sides of the security inspection channel. A set of photoelectric switches and a visible light camera are respectively installed at the entrance and exit of the security inspection channel. At the same time, two sets of photoelectric switches are sequentially installed in the security inspection channel. Figure 1 As shown, during security checks, the person being inspected enters the security inspection channel from the entrance and walks at a normal pace in the channel to the exit. During this process, the millimeter wave image acquisition devices on both sides of the security inspection channel continuously receive terahertz waves naturally emitted by the back and front of the person being inspected. When a person hides objects such as guns and knives in their clothing, there is a strong contrast between the terahertz wave radiation intensity at the location of the objects and other parts of the body. The system imaging device represents the difference in terahertz wave radiation intensity of various parts of the body in the form of grayscale images, which appear as grayscale differences in the image, thereby achieving non-contact detection of objects hidden under clothing. The visible light cameras installed at the entrance and exit are used to collect images at the entrance and exit to determine whether there are targets entering or leaving the security inspection channel, and can cooperate with the gates installed at the entrance and exit to control the number of people being measured in the security inspection channel to meet the maximum traffic volume requirements. When the people being measured walk in the security inspection channel, they will trigger a total of four groups of photoelectric switches installed at the entrance, security inspection channel and exit. The direction of travel and position of the people being measured in the security inspection channel are determined according to the order in which each group of photoelectric switches is triggered, so that the system imaging equipment can more accurately extract the imaging video and image of the people being measured, ensuring the accuracy and reliability of security inspection.

[0004] However, the existing channel-type millimeter-wave body security inspection system is affected by factors such as the limitations of the system imaging equipment and the long imaging time. It has problems with poor real-time performance of millimeter-wave images and low acquisition frame rate, which leads to poor continuity of millimeter-wave video images and choppy video display. Summary of the Invention

[0005] To address the above problems, the present invention provides a real-time fusion millimeter wave imaging frame increase method, which can solve the problems of poor real-time imaging and low acquisition frame rate in existing systems, resulting in poor video image continuity and unsmooth display.

[0006] A real-time fusion millimeter wave imaging frame increase method, the technical solution of which is as follows: millimeter wave image acquisition equipment is respectively set at both ends of the security inspection channel, an entrance photoelectric switch and an exit photoelectric switch are respectively set at the entrance and exit of the security inspection channel, a first process photoelectric switch and a second process photoelectric switch are arranged at intervals in the security inspection channel, and a visible light camera device is respectively installed on the inner side of the entrance and the inner side of the exit of the security inspection channel. The method includes the following steps:

[0007] Step S10, obtaining an original single-frame millimeter wave image of the front and / or back of the target person entering the security inspection channel at the current moment, captured by the millimeter wave security inspection imager;

[0008] Step S20: obtaining the current signal status of each photoelectric switch, and determining the direction of travel and the area of the target person in the security inspection channel according to the current signal status of each photoelectric switch;

[0009] Step S30, separating the imaging target area and the background area from the original single-frame millimeter wave imaging image at the current moment, and transferring the separated imaging target area to the newly added background image to form an image to be analyzed;

[0010] Step S40, partitioning the imaging target area in the image to be analyzed according to a preset partition threshold feature and predicting the moving imaging offset direction of the target person at the next moment;

[0011] Step S50, offsetting the imaging target area according to the imaging offset direction of the target person at the next moment predicted in step S40, and integrating the offset imaging target area with the background area in the original single-frame millimeter wave image to form a new image frame;

[0012] Step S60: inserting the newly added image frame into the original single-frame millimeter-wave imaging image.

[0013] Furthermore, when any visible light camera device captures that a target person enters the security inspection channel, steps S10 to S40 are executed.

[0014] Furthermore, in step S20, the direction of travel of the person being measured in the security inspection channel is judged according to the signal state of the current photoelectric switch. Specifically, if the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in sequence, it is judged that the target person being measured is moving in the forward direction along the security inspection channel; if the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in reverse order, it is judged that the target person being measured is moving in the reverse direction along the security inspection channel.

[0015] Furthermore, the security inspection channel is defined as follows: the area between the entrance photoelectric switch and the first process photoelectric switch is the entrance section, the area between the first process photoelectric switch and the second process photoelectric switch is the imaging detection section, and the area between the second process photoelectric switch and the exit photoelectric switch is the exit section; in step S20, when it is determined that the target person is in a forward moving state, if only the entrance photoelectric switch is in a triggered state at the current moment, the target person is located in the entrance section; if both the entrance photoelectric switch and the first process photoelectric switch are in a triggered state at the current moment, the target person is located in the imaging detection section section; if the entrance photoelectric switch, the first process photoelectric switch and the second process photoelectric switch are all in the triggered state at the current moment, the target person under test is located in the exit section; when it is determined that the target person under test is moving in the reverse direction, if only the exit photoelectric switch is in the triggered state at the current moment, the target person under test is located in the exit section; if the exit photoelectric switch and the second process photoelectric switch are in the state of being triggered in sequence at the current moment, the target person under test is located in the imaging detection section; if the exit photoelectric switch, the second process photoelectric switch and the first process photoelectric switch are in the state of being triggered in sequence at the current moment, the target person under test is located in the entrance section.

[0016] Furthermore, in step S30, the imaging contour of the person being measured is separated from the original single-frame millimeter wave imaging image at the current moment according to the brightness characteristics and contour characteristics. The separated imaging contour of the person being measured forms the imaging target area, and the rest is the background area.

[0017] Furthermore, in step 40, the imaging target area in the image to be analyzed is partitioned as follows according to a preset partition threshold feature: the circumscribed rectangle of the imaging target area in the image to be analyzed is obtained so that the imaging target area is completely enclosed in the circumscribed rectangle, and the imaging target area enclosed in the circumscribed rectangle is divided into a head area, a torso area, and a leg area in a top-down order; a vertical bisector is made through the center point of the image to be analyzed so that the vertical bisector separates the imaging target area into left and right parts; the area size features S of the head area, torso area, and leg area of the imaging target area on the left and right sides of the vertical bisector are obtained, and the area size features on the left and right sides are compared; and according to the area feature size comparison result, it is determined whether the measured target person needs horizontal and vertical moving imaging offset processing at the next moment in the current position area.

[0018] Furthermore, the head area, the torso area, and the leg area are divided into areas in a ratio of 1:2:2 from top to bottom based on the height of the circumscribed rectangle.

[0019] Furthermore, the area feature sizes of the head area, torso area, and leg area of the imaging target area on the left and right sides of the vertical bisector are compared respectively; in the entrance section or the exit section, if the horizontal center point of the imaging target area is located in the set area of the image to be analyzed, or the absolute value of the area feature difference ΔS between the left and right parts of the head area and the leg area is greater than the preset threshold, then the target person under test needs to perform horizontal and vertical moving imaging offset processing at the next moment in the current position area; in the imaging detection section, if the absolute value of the area feature difference ΔS between the left and right parts of the head area and the torso area is less than the preset threshold, then the target person under test only performs vertical moving imaging offset processing at the next moment in the current position area.

[0020] Furthermore, when the target person under measurement needs to perform horizontal moving imaging offset processing at the next moment in the current position area, it is predicted that the moving imaging of the target person under measurement at the next moment will move toward the side with a larger area feature of the head area and a smaller area feature of the leg area; when the target person under measurement needs to perform vertical moving imaging offset processing at the next moment in the current position area, if the original single-frame millimeter-wave imaging image at the current moment is a front view, it is predicted that the moving imaging of the target person under measurement at the next moment will move upward; if the original single-frame millimeter-wave imaging image at the current moment is a back view, it is predicted that the moving imaging of the target person under measurement at the next moment will move downward.

[0021] Furthermore, in step S50 , the imaging target area is offset, specifically, the entire imaging target area is offset by 1 to 2 pixels.

[0022] The present invention also provides a real-time integrated millimeter wave imaging frame increase system, which includes

[0023] The optical switch signal acquisition module is used to collect the trigger status of the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch;

[0024] An image processing module is used to separate and extract the imaging target area and the background area of the original single-frame millimeter wave imaging image of the target person entering the security inspection channel acquired by the millimeter wave image acquisition device, and synthesize the image to be analyzed;

[0025] An analysis and synthesis module is used to partition the imaging target area in the image to be analyzed according to the preset partition threshold characteristics, analyze and predict the moving imaging offset direction of the target person at the next moment, and synthesize the newly added image frames;

[0026] The processor is used to control the optical signal acquisition module, the image processing module, and the analysis and synthesis module to perform the above operations.

[0027] Furthermore, it also includes a visible light portrait acquisition module, which is electronically connected to the processor and is used to send the image of the target person entering the security inspection channel captured by the visible light camera device to the processor, so that the processor controls the light-on signal acquisition module, the image processing module, and the analysis and synthesis module to perform frame addition processing.

[0028] The present invention also provides a computer device, which includes a processor, a memory and a program; the program is stored in the memory, and the processor calls the program stored in the memory to execute the above-mentioned real-time fusion millimeter wave imaging frame increase method.

[0029] The present invention also provides a computer-readable storage medium, which is used to store a program, and the program is used to execute the above-mentioned real-time fusion millimeter wave imaging frame increase method.

[0030] The beneficial effect of the method of the present invention is that it judges the travel direction and position area of the target person to be measured in the security inspection channel by analyzing the triggering state of each photoelectric switch at the current moment, and predicts the travel imaging offset direction of the target person to be measured at the next moment by partitioning the imaging target area separated from the original single-frame millimeter wave imaging image according to the preset partition threshold feature, and accordingly offsets the original single-frame millimeter wave imaging image at the current moment as a whole to form a new image frame at the next moment, thereby realizing real-time fusion frame addition, greatly improving the continuity of the millimeter wave security inspection imaging video image and making the video image display smoother, thereby improving the accuracy of security inspection; at the same time, the method of the present invention is based on the existing channel-type millimeter wave security inspection imaging system, and does not require large-scale modification of the hardware system, which can effectively save the cost of system hardware upgrade and modification. At the same time, it only needs to perform analysis and calculation on the original single-frame millimeter wave imaging image to achieve reliable frame addition processing. The method is simple, the analysis and calculation amount is small, and it is not easy to cause excessive operating burden on the system hardware. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a schematic diagram of the layout of the existing channel-type millimeter wave security inspection imaging system;

[0032] Figure 2 Schematic diagram of partitioning of the imaging target area in the embodiment of the method of the present invention;

[0033] Figure 3 Schematic diagram of the process of the present invention;

[0034] Figure 4 A schematic diagram of the system structure of a real-time integrated millimeter wave imaging frame increment system of the present invention;

[0035] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention.

[0036] Figure markings: 10-processor, 20-security inspection channel, 20a-entrance section, 20b-imaging detection section, 20c-exit section, 21-security inspection channel entrance, 22-security inspection channel exit, 41-millimeter wave image acquisition device, 42-millimeter wave image acquisition device, 51-entrance photoelectric switch, 52-first process photoelectric switch, 53-second process photoelectric switch, 54-exit photoelectric switch, 61-visible light camera device, 62-visible light camera device, 71-head area, 72-torso area, 73-leg area. DETAILED DESCRIPTION

[0037] The present invention provides a real-time fusion millimeter wave imaging frame increase method, which sets millimeter wave image acquisition devices at both ends of the security inspection channel 20. Figure 1 , Figure 1 In the figure, 41 is a millimeter wave image acquisition device arranged at one side of the entrance 21 of the security inspection channel, 42 is a millimeter wave image acquisition device arranged at one side of the exit 22 of the security inspection channel, an entrance photoelectric switch 51 and an exit photoelectric switch 54 are respectively arranged at the entrance 21 and the exit 22 of the security inspection channel, a first process photoelectric switch 52 and a second process photoelectric switch 53 are arranged at intervals in the security inspection channel 20, and visible light cameras 61 and 62 are respectively installed on the inner side of the entrance 21 and the inner side of the exit 22 of the security inspection channel, which includes the following steps: Figure 3 ,:

[0038] Step S10 , obtaining original single-frame millimeter wave images of the front and / or back of the target person entering the security inspection channel 20 at the current moment, captured by the millimeter wave security inspection imagers 41 , 42 .

[0039] Step S20: obtaining the current signal status of each photoelectric switch, and determining the direction of travel of the target person in the security inspection channel and the area in the security inspection channel where the target person is located based on the current signal status of each photoelectric switch;

[0040] If the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in sequence, it is judged that the target person under test is moving in the forward direction along the security inspection channel; if the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in reverse order, it is judged that the target person under test is moving in the reverse direction along the security inspection channel; when the target person under test is moving in the forward direction in the security inspection channel, the millimeter wave image acquisition device 41 is used to capture the back imaging view of the target person under test, and the millimeter wave image acquisition device 42 is used to capture the front imaging view of the target person under test; if moving in the reverse direction, the opposite is true.

[0041] The security inspection channel is defined as follows: the area between the entrance photoelectric switch and the first process photoelectric switch is the entrance section 20a, the area between the first process photoelectric switch and the second process photoelectric switch is the imaging detection section 20b, and the area between the second process photoelectric switch and the exit photoelectric switch is the exit section 20c.

[0042] When it is determined that the target person is moving forward, if only the entrance photoelectric switch is in the triggered state at the current moment, the target person is located in the entrance section 20a; if the entrance photoelectric switch and the first process photoelectric switch are all in the triggered state at the current moment, the target person is located in the imaging detection section 20b; if the entrance photoelectric switch, the first process photoelectric switch, and the second process photoelectric switch are all in the triggered state at the current moment, the target person is located in the exit section 20c;

[0043] When it is determined that the target person being measured is in the reverse moving state, if at the current moment only the exit photoelectric switch is in the triggered state, the target person being measured is located in the exit section; if at the current moment the exit photoelectric switch and the second process photoelectric switch are in the state of being triggered in sequence, the target person being measured is located in the imaging detection section; if at the current moment the exit photoelectric switch, the second process photoelectric switch, and the first process photoelectric switch are in the state of being triggered in sequence, the target person being measured is located in the entrance section.

[0044] Step S30, separating the imaging target area and the background area from the original single-frame millimeter wave imaging image at the current moment, and transferring the separated imaging target area to the newly added background image to form an image to be analyzed;

[0045] Specifically, the imaging contour of the person being measured is separated from the original single-frame millimeter wave imaging image at the current moment according to the brightness characteristics and contour characteristics. The separated imaging contour of the person being measured forms the imaging target area, and the rest is the background area.

[0046] Step S40, partitioning the imaging target area in the image to be analyzed according to a preset partition threshold feature and predicting the moving imaging offset direction of the target person at the next moment;

[0047] Specifically, the bounding rectangle of the imaging target area in the image to be analyzed is obtained so that the imaging target area is completely enclosed in the bounding rectangle, and the imaging target area enclosed in the bounding rectangle is divided into a head area 71, a torso area 72, and a leg area 73 in a top-down order. Preferably, the head area, the torso area, and the leg area are divided in a ratio of 1:2:2 from top to bottom based on the height of the bounding rectangle. Figure 2 A vertical bisector 74 is drawn through the center point of the image to be analyzed, so that the vertical bisector divides the imaging target area into left and right parts. That is, the vertical bisector 74 divides the head area 71 into a left part 71a and a right part 71b of the head area, divides the torso area 72 into a left part 72a and a right part 72b of the torso area, and divides the leg area 73 into a left part 73a and a right part 73b of the leg area;

[0048] Obtain the area size features of the head region, torso region, and leg region of the imaging target area on the left and right sides of the vertical bisector and calculate the area feature difference ΔS between the left and right sides of each region;

[0049] The area feature of the left part 71a of the head region is recorded as S 71a The area characteristic of the right part 71b of the head region is S 71b , then the area characteristic difference ΔS between the left and right parts of the head area 71 =S71a -S 71b ;

[0050] The area feature of the left part 72a of the trunk region is recorded as S 72a The area characteristic of the right part 72b of the trunk region is recorded as S 72b , then the area characteristic difference ΔS between the left and right parts of the trunk area 72 =S 72a -S 72b ;

[0051] The area characteristic of the left part 73a of the leg region is recorded as S 73a The area characteristic of the right side portion 73b of the leg region is recorded as S 73b , then the area characteristic difference ΔS between the left and right parts of the leg area 73 =S 73a -S 73b ;

[0052] In the entrance and exit sections, if the horizontal center of the target person is within the specified position area, or the absolute value of the area characteristic difference ΔS between the left and right parts of the head and leg areas is greater than the preset threshold δ, then the target person will need to undergo horizontal and vertical moving imaging offset processing at the next moment in the current position area. In the imaging detection section, if the area characteristic difference ΔS between the left and right parts of the head and torso areas is less than the preset threshold δ, then the target person will only undergo vertical moving imaging offset processing at the next moment in the current position area.

[0053] When the target person under measurement needs to perform horizontal moving imaging offset processing at the next moment in the current position area, it is predicted that the moving imaging of the target person under measurement at the next moment will move toward the side with a larger area feature of the head area and a smaller area feature of the leg area; when the target person under measurement needs to perform vertical moving imaging offset processing at the next moment in the current position area, if the original single-frame millimeter-wave imaging image at the current moment is a front view, it is predicted that the moving imaging of the target person under measurement at the next moment will move upward; if the original single-frame millimeter-wave imaging image at the current moment is a back view, it is predicted that the moving imaging of the target person under measurement at the next moment will move downward.

[0054] In step S50, the imaging target area is offset according to the imaging offset direction of the target person at the next moment predicted in step S40. Specifically, the imaging target area is offset as a whole by 1 to 2 pixels; and the offset imaging target area is integrated with the background area in the original single-frame millimeter wave image to form a new image frame.

[0055] Step S60: inserting the newly added image frame into the original single-frame millimeter-wave imaging image.

[0056] As a preferred technical solution of the method of the present invention, when any visible light camera device 61 or 62 captures that the target person to be measured enters the security inspection channel, steps S10 to S40 are executed; that is, only when the visible light camera device 61 arranged at the entrance side of the security inspection channel or the visible light camera device 62 arranged at the exit side of the security inspection channel detects that the target person to be measured enters the security inspection channel, the frame addition processing of the inventive method is performed, otherwise the frame addition processing is not performed to reduce the system workload.

[0057] The present invention also provides a real-time integrated millimeter wave imaging frame increase system. Figure 4 , which includes

[0058] The light-on signal acquisition module is electrically connected to the processor and is used to collect the triggering status of the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch;

[0059] An image processing module is electronically connected to the processor and is used to separate and extract the imaging target area and the background area of the original single-frame millimeter wave imaging image of the target person entering the security inspection channel captured by the millimeter wave image acquisition device, and synthesize the image to be analyzed;

[0060] An analysis and synthesis module, electronically connected to the processor, is used to partition the imaging target area in the image to be analyzed according to the preset partition threshold characteristics, analyze and predict the moving imaging offset direction of the target person at the next moment, and synthesize the newly added image frames;

[0061] The processor is used to control the optical signal acquisition module, the image processing module, and the analysis and synthesis module to perform the above operations.

[0062] A further preferred technical solution of the system of the present invention also includes a visible light portrait acquisition module, which is electronically connected to the processor and is used to send the image of the target person entering the security inspection channel captured by the visible light camera device to the processor, so that the processor controls the light-on signal acquisition module, the image processing module, and the analysis and synthesis module to perform frame addition processing.

[0063] In an embodiment of the present invention, a computer device is further provided, comprising: a processor, a memory, and a program;

[0064] The program is stored in the memory, and the processor calls the program stored in the memory to execute the above-mentioned real-time fusion millimeter wave imaging frame increase method.

[0065] The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements an interception strategy derivation method for credit anti-fraud. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0066] The memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM). The memory is used to store programs, and the processor executes the programs after receiving execution instructions.

[0067] The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. The processor can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0068] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0069] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium is used to store a program, and the program is used to execute the above-mentioned real-time fusion millimeter wave imaging frame increase method.

[0070] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, computer devices, or computer program products. Thus, embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] The above detailed description of the specific implementation of the present invention is only a preferred embodiment of the present invention and should not be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent.

Claims

1. A real-time fusion millimeter wave imaging frame increment method, comprising: millimeter wave image acquisition devices disposed at both ends of a security inspection channel; an entrance photoelectric switch and an exit photoelectric switch disposed at the entrance and exit of the security inspection channel, respectively; a first process photoelectric switch and a second process photoelectric switch disposed at intervals within the security inspection channel; and a visible light camera mounted on the inner side of the entrance and exit of the security inspection channel, characterized in that: It includes the following steps, Step S10, obtaining an original single-frame millimeter wave image of the front and / or back of the target person entering the security inspection channel at the current moment, captured by the millimeter wave security inspection imager; Step S20: obtaining the current signal status of each photoelectric switch, and determining the direction of travel and the area of the target person in the security inspection channel according to the current signal status of each photoelectric switch; Step S30, separating the imaging target area and the background area from the original single-frame millimeter wave imaging image at the current moment, and transferring the separated imaging target area to the newly added background image to form an image to be analyzed; Step S40, partitioning the imaging target area in the image to be analyzed according to a preset partition threshold feature and predicting the moving imaging offset direction of the target person at the next moment; Step S50, offsetting the imaging target area according to the imaging offset direction of the target person at the next moment predicted in step S40, and integrating the offset imaging target area with the background area in the original single-frame millimeter wave image to form a new image frame; Step S60: inserting the newly added image frame into the original single-frame millimeter-wave imaging image.

2. The real-time fusion millimeter wave imaging frame increment method according to claim 1, characterized in that: When any visible light camera device captures that a target person enters the security inspection channel, steps S10 to S60 are executed.

3. The real-time fusion millimeter wave imaging frame increment method according to claim 1, characterized in that: In step S20, the direction of movement of the person being measured in the security inspection channel is determined based on the signal state of the current photoelectric switch. Specifically, if the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in sequence, it is determined that the target person being measured is moving in the forward direction of the security inspection channel; if the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch are triggered in reverse order, it is determined that the target person being measured is moving in the reverse direction of the security inspection channel.

4. The real-time fusion millimeter wave imaging frame increment method according to claim 3, characterized in that: The security inspection channel is defined as follows: the area between the entrance photoelectric switch and the first process photoelectric switch is the entrance section, the area between the first process photoelectric switch and the second process photoelectric switch is the imaging detection section, and the area between the second process photoelectric switch and the exit photoelectric switch is the exit section. In step S20, when it is determined that the target person is moving in the forward direction, if only the entrance photoelectric switch is in the triggered state at the current moment, the target person is located in the entrance section; if both the entrance photoelectric switch and the first process photoelectric switch are in the triggered state at the current moment, the target person is located in the imaging detection section; if both the entrance photoelectric switch, the first process photoelectric switch, and the second process photoelectric switch are in the triggered state at the current moment, the target person is located in the exit section. When it is determined that the target person being measured is in the reverse moving state, if at the current moment only the exit photoelectric switch is in the triggered state, the target person being measured is located in the exit section; if at the current moment the exit photoelectric switch and the second process photoelectric switch are in the state of being triggered in sequence, the target person being measured is located in the imaging detection section; if at the current moment the exit photoelectric switch, the second process photoelectric switch, and the first process photoelectric switch are in the state of being triggered in sequence, the target person being measured is located in the entrance section.

5. The real-time fusion millimeter wave imaging frame increment method according to claim 1, characterized in that: In step S30, the imaging contour of the person being measured is separated from the original single-frame millimeter wave imaging image at the current moment according to the brightness characteristics and contour characteristics. The separated imaging contour of the person being measured forms the imaging target area, and the rest is the background area.

6. The real-time fusion millimeter wave imaging frame increment method according to claim 5, characterized in that: In step S40, the imaging target area in the image to be analyzed is partitioned as follows according to the preset partition threshold feature: the circumscribed rectangle of the imaging target area in the image to be analyzed is obtained so that the imaging target area is completely enclosed in the circumscribed rectangle, and the imaging target area enclosed in the circumscribed rectangle is divided into a head area, a torso area, and a leg area in a top-down order; a vertical bisector is made through the center point of the image to be analyzed so that the vertical bisector divides the imaging target area into left and right parts; the area size features S of the head area, torso area, and leg area of the imaging target area on the left and right sides of the vertical bisector are obtained, and the area size features on the left and right sides are compared; and based on the area feature size comparison results, it is determined whether the measured target person needs horizontal and vertical moving imaging offset processing at the next moment in the current position area.

7. The real-time fusion millimeter wave imaging frame increment method according to claim 6, characterized in that: The head area, the torso area, and the leg area are divided into areas in a ratio of 1:2:2 from top to bottom based on the height of the circumscribed rectangle.

8. The real-time fusion millimeter wave imaging frame increment method according to claim 6, characterized in that: The area feature sizes of the head area, torso area, and leg area of the imaging target area on the left and right sides of the vertical bisector are compared respectively. In the entrance section or the exit section, if the horizontal center point of the imaging target area is located in the set area of the image to be analyzed, or the absolute value of the area feature difference ΔS between the left and right parts of the head area and the leg area is greater than the preset threshold, then the measured target person needs to perform horizontal and vertical moving imaging offset processing at the next moment in the current position area; in the imaging detection section, if the absolute value of the area feature difference ΔS between the left and right parts of the head area and the torso area is less than the preset threshold, then the measured target person only needs to perform vertical moving imaging offset processing at the next moment in the current position area.

9. The real-time fusion millimeter wave imaging frame increment method according to claim 8, characterized in that: When the measured target person needs to perform horizontal moving imaging offset processing at the next moment in the current position area, it is predicted that the moving imaging of the measured target person at the next moment will move to the side with a larger head area feature and a smaller leg area feature; When the target person under test needs to undergo vertical moving imaging offset processing at the next moment in the current position area, if the original single-frame millimeter-wave imaging image at the current moment is a front view, it is predicted that the moving imaging of the target person under test at the next moment will move upward; if the original single-frame millimeter-wave imaging image at the current moment is a back view, it is predicted that the moving imaging of the target person under test at the next moment will move downward.

10. The real-time fusion millimeter wave imaging frame increment method according to claim 9, characterized in that: In step S50 , the imaging target area is offset, specifically, the entire imaging target area is offset by 1 to 2 pixels.

11. A real-time integrated millimeter wave imaging frame-increasing system, characterized by: It includes The optical switch signal acquisition module is used to collect the trigger status of the entrance photoelectric switch, the first process photoelectric switch, the second process photoelectric switch, and the exit photoelectric switch; An image processing module is used to separate and extract the imaging target area and the background area of the original single-frame millimeter wave imaging image of the target person entering the security inspection channel acquired by the millimeter wave image acquisition device, and synthesize the image to be analyzed; An analysis and synthesis module is used to partition the imaging target area in the image to be analyzed according to the preset partition threshold characteristics, analyze and predict the moving imaging offset direction of the target person at the next moment, and synthesize the newly added image frames; The processor is used to control the optical signal acquisition module, the image processing module, and the analysis and synthesis module to perform the above operations.

12. The real-time integrated millimeter wave imaging frame increment system according to claim 11, characterized in that: It also includes a visible light portrait acquisition module, which is electronically connected to the processor and is used to send the image of the target person entering the security inspection channel captured by the visible light camera device to the processor, so that the processor controls the light-on signal acquisition module, image processing module, and analysis and synthesis module to perform frame addition processing.

13. A computer device, characterized in that: It includes a processor, a memory and a program; the program is stored in the memory, and the processor calls the program stored in the memory to execute the real-time fusion millimeter wave imaging frame increase method according to claims 1 to 10.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a program, and the program is used to execute the real-time fusion millimeter wave imaging frame increase method according to claims 1 to 10.

Images