A millimeter wave vital signs detection system

Abstract

The application discloses a kind of millimeter wave living body detection systems, including detection main body, millimeter wave detection module and central control terminal;Detection main body is opened with detection passage;Multiple millimeter wave detection modules are installed in the inner wall of detection passage to scan target object in multiple spatial orientations;Millimeter wave detection module includes millimeter wave radio frequency front end and distributed computing unit;Millimeter wave radio frequency front end is used to emit millimeter wave signal and receive target reflection signal;Distributed computing unit under the local reference of radio frequency front end, to echo signal is carried out local phase stabilization processing and micro-motion characteristic analysis, and generates living body existence determination result before not through long distance digital transmission;Central control terminal comprehensively judges whether there is living body in the target to be detected.The application completes phase level signal processing near millimeter wave radio frequency front end, and combines multi-module spatial redundancy detection, effectively improves the detection stability and reliability of micro-motion living body target in logistics security check and the like scene.

Description

Technical Field

[0001] This invention relates to the field of millimeter-wave radar detection technology, specifically to a millimeter-wave liveness detection system suitable for continuous channel scenarios such as logistics security checks. Background Technology

[0002] With the rapid development of cross-border logistics and urban express delivery, incidents of smuggling live animals (such as exotic pets) during transportation are increasing, seriously threatening public safety, ecological balance, and the enforcement of relevant regulations. Existing detection methods, such as X-ray security checks, CT scans, and manual spot checks, suffer from low security, low efficiency, high false positive rates, or the inability to automate these methods.

[0003] Millimeter-wave radar, due to its excellent penetration capability and sensitivity to micro-motion, has potential advantages in the field of liveness detection. Some existing millimeter-wave detection devices exist, such as the invention patent application number 202310833214.6, which includes: a detection device body and a host computer; the detection device body includes: a shielded box and a security conveyor belt; the security conveyor belt is used to transport the target object through the shielded box; the shielded box houses a millimeter-wave radar device that emits millimeter-wave radar signals towards the target object, receives the reflected signals, and mixes them with the emitted millimeter-wave radar signals to generate a radar target echo; the signal is transmitted to the host computer via wired or wireless means, and the received radar target echo is processed to detect whether a live object exists in the target object. This detection device uses a shielded box, which effectively reduces interference from external electromagnetic signals to the millimeter-wave radar detection equipment, thus contributing to the efficient and accurate operation of the millimeter-wave radar detection equipment; it can accurately monitor whether there are live objects in luggage and express packages in security inspection scenarios, improving the security inspection efficiency of transit goods at airports and customs.

[0004] The aforementioned patent employs a centralized structure, where data collected by the radar front-end is transmitted via cable to a central processing unit or host computer for unified processing. In continuous channel scenarios such as logistics security checks, the micro-motion amplitude of live targets is relatively small. Under conditions of multiple radars or long-distance transmission, millimeter-wave echo signals are prone to phase reference inconsistencies, synchronization errors, and quantization noise during cross-module and cross-clock domain transmission, leading to irreversible distortion of the micro-motion phase characteristics, thereby affecting the stability and accuracy of liveness detection.

[0005] Therefore, existing centralized processing architectures are unable to simultaneously guarantee phase feature integrity and detection consistency under multi-view detection conditions, and there is an urgent need for a new system architecture that can achieve stable liveness detection under the constraints of millimeter-wave echo physical characteristics. Summary of the Invention

[0006] In view of this, the present invention provides a millimeter-wave liveness detection system, which solves the problem of unstable liveness detection caused by phase degradation under the existing centralized processing architecture by performing phase-level signal processing near the millimeter-wave radio frequency front end and combining spatial redundancy consistency determination of multiple detection modules.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A millimeter-wave liveness detection system includes a detection body, a millimeter-wave detection module, and a central control terminal; The detection body has a detection channel; multiple millimeter-wave detection modules are installed along the detection direction of the detection channel on its inner wall to scan the target object in multiple spatial orientations; each millimeter-wave detection module includes a millimeter-wave radio frequency front-end and a distributed computing unit; the millimeter-wave radio frequency front-end is used to transmit millimeter-wave signals and receive target reflection signals; the distributed computing unit, with the local oscillator reference of the millimeter-wave radio frequency front-end, performs local phase stabilization processing and micro-motion feature analysis on the millimeter-wave echo signal, and generates a binary detection signal to characterize the presence of a living body before cross-module digital transmission; the central control terminal is communicatively connected to the distributed computing unit to receive the binary detection signal, and the central control terminal comprehensively judges whether a living body exists in the detected target based on the consistency relationship of the detection results in multiple spatial orientations.

[0009] Preferably, the detection body is an inverted U-shaped metal shielding chamber, an arched electromagnetic shielding tunnel, or a modular assembly of split and connectable shielding modules.

[0010] Preferably, the detection body is made of metal and its inner wall is coated with a conductive coating to shield external electromagnetic interference and prevent millimeter wave leakage.

[0011] Preferably, the detection channel is an electric conveyor belt, a pneumatic pipeline conveying system, a gravity slide rail conveyor, or a pedestrian walkway.

[0012] Preferably, the distributed computing unit is used to complete phase feature extraction before the millimeter-wave echo signal is transmitted across modules, so as to avoid irreversible phase distortion caused by cross-module clock deviation and quantization noise.

[0013] Preferably, the distributed computing unit and the millimeter-wave radio frequency front-end are disposed on the same printed circuit board or packaged as the same module.

[0014] Preferably, the distributed computing unit and the millimeter-wave radio frequency front end are coupled through a high-speed interconnect bus or a board-to-board connector to form the millimeter-wave detection module.

[0015] Preferably, the central control terminal performs spatial redundancy consistency verification on the detection results obtained by multiple millimeter-wave detection modules in different spatial orientations. When the preset consistency conditions are met, it is determined that a living being exists.

[0016] Preferably, multiple millimeter-wave detection modules form a distributed architecture and communicate with the central control terminal through a unified data bus or local area network.

[0017] Preferably, the distributed architecture is a master-slave structure, wherein at least one of the millimeter-wave detection modules is designated as a master node; the remaining millimeter-wave detection modules are slave nodes; the master node is responsible for receiving the detection results from the slave nodes and communicating with the central control terminal. Alternatively, the distributed architecture may be a fair distributed structure, in which each millimeter-wave detection module has equivalent status and independently reports the detection results to the central control terminal or generates a collective decision through an internal negotiation protocol before reporting.

[0018] As can be seen from the above technical solution, compared with the prior art, this invention improves the stability of micro-motion liveness feature extraction by performing phase-level processing near the millimeter-wave radio frequency front-end, avoiding the irrecoverable phase distortion caused by cross-module synchronization errors in centralized processing architectures. By using multiple millimeter-wave detection modules to observe the same detection channel from different spatial orientations and making judgments based on spatial redundancy consistency, the detection failure problem caused by occlusion, attitude changes, or multipath effects under a single viewpoint is effectively overcome. By transmitting only detection results or low-dimensional features, the physical information degradation introduced by cross-module transmission of high-dimensional phase data is avoided, improving the system's engineering feasibility while ensuring detection reliability. Attached Figure Description To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 Schematic diagram of the detection system provided by the present invention Figure 1 ; Figure 2 Schematic diagram of the detection system provided by the present invention Figure 2 ; Figure 3 Schematic diagram of the millimeter-wave detection module structure provided by the present invention Figure 1 ; Figure 4 Schematic diagram of the millimeter-wave detection module structure provided by the present invention Figure 2 ; Figure 5 The master-slave distributed architecture workflow diagram provided by this invention; Figure 6 A flowchart illustrating the fair distributed architecture workflow provided by this invention.

[0020] Among them, 1-Detection body; 11-Detection channel; 2-Millimeter wave detection module; 21-Millimeter wave RF front end; 22-Distributed computing unit; 23-High-speed interconnect bus; 24-Board to board connector; 3-Central control terminal. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] See appendix Figure 1 According to an embodiment of the present invention, a millimeter-wave liveness detection system, wherein a distributed computing unit performs phase correlation processing under the local oscillator reference of the millimeter-wave radio frequency front end, thereby avoiding phase mismatch introduced by the echo signal during cross-module transmission, is suitable for non-contact liveness detection and security screening in places such as ports and logistics centers. The system includes a detection body 1, millimeter-wave detection modules 2, and a central control terminal 3. A detection channel 11 is provided inside the detection body 1, which is used to block environmental interference and guide the target object through. Multiple millimeter-wave detection modules 2 are installed on the inner wall of the detection channel 11 along the detection direction to scan the target object in multiple spatial orientations. Specifically, multiple millimeter-wave detection modules 2 are fixed to pre-set mechanical interfaces on the inner wall of the detection body 1 corresponding to the detection channel 11. The detection channels 11 are arranged vertically, horizontally, or facing each other to form a three-dimensional coverage of the target area. The millimeter-wave detection module 2 includes a millimeter-wave radio frequency front-end 21 and a distributed computing unit 22. The millimeter-wave radio frequency front-end 21 is used to transmit millimeter-wave signals and receive target reflection signals. Under the local oscillator reference of the millimeter-wave radio frequency front-end 21, the distributed computing unit 22 performs local phase stabilization processing and micro-motion feature analysis on the millimeter-wave echo signal, and generates a binary detection signal to characterize the presence of a living body before cross-module digital transmission. The central control terminal 3 is communicatively connected to the distributed computing unit 22 to receive the binary detection signal. Based on the consistency relationship of multiple spatial orientation detection results, the central control terminal 3 comprehensively judges whether there is a living body in the detected target, and performs alarm prompts or result display operations accordingly.

[0023] In this embodiment, the distributed computing unit 22 is used to extract phase features before the millimeter-wave echo signal is transmitted across modules, so as to avoid irreversible phase distortion caused by cross-module clock deviation and quantization noise.

[0024] To further optimize the above technical solution and facilitate the replacement of millimeter-wave detection modules, multiple millimeter-wave detection modules 2 are installed on the mechanical interface on the inner wall of the detection body 1 using mechanical clips, screws or magnetic attraction, and distributed in suitable detection positions such as the sides or top of the corresponding detection channel 11 to ensure full coverage of the detection target.

[0025] To further optimize the above technical solutions, such as Figure 3 As shown, the distributed computing unit 22 and the millimeter-wave radio frequency front-end 21 are disposed on the same printed circuit board or packaged as the same module; the distributed computing unit 22 and the millimeter-wave radio frequency front-end 21 are coupled through a high-speed interconnect bus 23 to form a millimeter-wave detection module 2.

[0026] In other specific embodiments, such as Figure 4 As shown, the distributed computing unit 22 and the millimeter-wave radio frequency front-end 21 are disposed on the same printed circuit board or packaged as the same module. The distributed computing unit 22 and the millimeter-wave radio frequency front-end 21 are coupled through a board-to-board connector 24 to form a millimeter-wave detection module 2.

[0027] In this embodiment, multiple millimeter-wave detection modules 2 form a distributed architecture and are connected to the central control terminal 3 through a unified data bus or local area network.

[0028] To further optimize the above technical solutions, such as Figure 5 As shown, the distributed architecture is a master-slave structure, in which at least one millimeter-wave detection module 2 is designated as the master node; the remaining millimeter-wave detection modules 2 are slave nodes; the master node is responsible for receiving the detection results from the slave nodes and communicating with the central control terminal 3. In this configuration, the detection system only needs to report data to the master node or directly to the central control terminal 3, making it suitable for centralized collaborative detection scenarios where tasks are uniformly scheduled and resources are controlled.

[0029] The master-slave architecture operates as follows: the millimeter-wave RF front-end 21 transmits continuous frequency-modulated millimeter-wave signals to the target object within the detection channel 11 and receives the echo signals reflected from the object's surface. The millimeter-wave RF front-end 21 integrates a mixer to mix the local oscillator signal with the received echo signal to generate an intermediate frequency (IF) signal. This IF signal contains information about the distance, velocity, and minor motions between the target object and the radar.

[0030] Subsequently, the distributed computing unit 22 performs a series of preprocessing and feature extraction operations on the intermediate frequency signal, and uses a locally built-in algorithm (such as an analysis method based on the variation law of micro-motion characteristics) to process the target reflected wave, automatically determine whether it is a living object, and output a binary result signal of "present" or "absent". In this way, it is ensured that the phase correlation features are processed within the millimeter-wave detection module, avoiding phase reference mismatch introduced by cross-module transmission.

[0031] Among multiple millimeter-wave detection modules 2, millimeter-wave detection module A is designated as the master module, which has the ability to communicate with the central control terminal 3. The master module establishes internal communication links (such as SPI bus, UART link, or WiFi Mesh) with slave modules B, C, etc., through wired or wireless networks to obtain their detection data or issue detection tasks.

[0032] After the main module preprocesses, merges, and filters the received multi-channel data, it transmits the integrated information to the terminal system through a data link (such as Gigabit Ethernet) established with the central control terminal 3. This is suitable for centralized task scheduling in low-bandwidth, high-latency environments.

[0033] In a master-slave architecture, the central control terminal 3 can be integrated into the detection subject 1, which directly interacts with the user. The slave modules do not need to communicate directly with the central control terminal 3, reducing system communication complexity and resource consumption. Simultaneously, the master module can adjust the slave module's working state and sampling strategy according to the detection scenario, improving system real-time performance and resource allocation efficiency.

[0034] like Figure 6 As shown, the distributed architecture can also be a fair distributed structure, in which each millimeter-wave detection module 2 has equal status and independently reports its detection results to the central control terminal 3, or generates a collective decision through an internal negotiation protocol before reporting. In this form, multiple millimeter-wave detection modules 2 are logically equal and communicate independently with the central control terminal 3. The central control terminal 3 uses polling, competition arbitration, or time window-based scheduling strategies to achieve real-time synchronization of module status and data, which is suitable for application scenarios such as task load balancing and self-organizing network detection.

[0035] The fair distributed architecture operates as follows: the millimeter-wave radio frequency front-end 21 transmits a continuous frequency-modulated millimeter-wave signal (chirp signal) to the target object within the detection channel 11, and receives the echo signal reflected from the object's surface. The millimeter-wave radio frequency front-end 21 integrates a mixer to mix the local oscillator signal with the received echo signal to generate an intermediate frequency (IF) signal. This IF signal contains information about the distance, velocity, and minor motions between the target object and the radar.

[0036] Subsequently, the distributed computing unit 22 performs a series of preprocessing and feature extraction operations on the intermediate frequency signal, and uses a locally built-in algorithm (such as an analysis method based on the variation law of micro-motion characteristics) to process the target reflected wave, automatically determine whether it is a living object, and output a binary result signal of "present" or "absent". In this way, it is ensured that the phase correlation features are processed within the millimeter-wave detection module, avoiding phase reference mismatch introduced by cross-module transmission.

[0037] In the fair distributed architecture, all millimeter-wave detection modules 2 are independently connected to the central control terminal 3. Each module has edge computing processing and communication capabilities. The central control terminal 3 does not rely on information from any single module, but receives and analyzes data from all modules.

[0038] The central control terminal 3 obtains detection data from modules A, B, and C in turn through a polling mechanism or a time window scheduling strategy, and can allocate processing priorities based on data timeliness and confidence level. In this approach, each module has greater task autonomy, the overall system is more robust, and it is suitable for complex dynamic scenarios that require real-time monitoring and concurrent multi-task detection.

[0039] The fair distributed architecture also supports mutual awareness between modules. That is, when the system is abnormal or a module fails, the other modules can automatically report their status and adjust their own detection parameters, thereby improving the overall robustness and fault tolerance of the system.

[0040] In this embodiment, the central control terminal 3 can be deployed outside the detection body 1 or embedded within it. It establishes a communication connection with all millimeter-wave detection modules via wired or wireless means and receives detection signals from all millimeter-wave detection modules. After receiving the detection results from each millimeter-wave detection module 2, the central control terminal 3 can not only use it for feedback methods such as audible and visual alarms, data recording, and image annotation, but also further link with the downstream sorting system to achieve automated processing.

[0041] To further optimize the above technical solution, the central control terminal 3 establishes a communication link with one or more millimeter-wave detection modules 2 through at least one wired or wireless communication method to adapt to different physical deployments and real-time requirements.

[0042] In this embodiment, the central control terminal 3 performs spatial redundancy consistency verification on the detection results obtained by multiple millimeter-wave detection modules 2 in different spatial orientations. When the preset consistency conditions are met, it is determined that there is a living body.

[0043] To further optimize the above technical solution, the detection body 1 is an inverted U-shaped metal shielding chamber, an arched electromagnetic shielding tunnel, or a modular assembly of split and splicable shielding modules. It is made of metal materials and its inner wall is coated with a conductive coating to shield external electromagnetic interference and prevent millimeter wave leakage.

[0044] In order to further optimize the above technical solution and improve the shielding effect of the detection body, the inner wall of the detection body 1 is coated or covered with a wave-absorbing material.

[0045] To further optimize the above technical solution, the detection channel 11 can be an electric conveyor belt, a pneumatic pipeline conveying system, a gravity slide rail conveyor, or a pedestrian walkway.

[0046] like Figure 1 As shown, the detection body is a closed structure, and its inner cavity is a detection channel. The detection channel is an electrically driven belt used to transport the package or item to be detected to the detection area. Figure 2 As shown, the detection channel is a pedestrian channel, suitable for pedestrian detection.

[0047] During actual inspection, when the detection result indicates "live body present," the central control terminal 3 can send a "package removal" control command to the downstream conveyor control system or intelligent sorting device via industrial communication interfaces (such as IO signals, RS485, CAN bus, EtherCAT). Upon receiving this control signal, the downstream equipment can drive the corresponding actuators (such as pneumatic push rods, swing arms, electric slide rails, etc.) to remove the package from the main conveyor path or guide it to a separate manual re-inspection channel, thereby achieving automatic isolation of suspicious packages. The system can also adjust detection sensitivity, reporting thresholds, and abnormal package identification methods through the parameter configuration interface to adapt to different scenario requirements.

[0048] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0049] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A millimeter-wave liveness detection system, characterized in that, It includes the detection body (1), the millimeter wave detection module (2) and the central control terminal (3); The detection body (1) has a detection channel (11) inside; there are multiple millimeter wave detection modules (2), and multiple millimeter wave detection modules (2) are installed on the inner wall of the detection channel (11) along the detection direction to scan the target object in multiple spatial orientations; the millimeter wave detection module (2) includes a millimeter wave radio frequency front end (21) and a distributed computing unit (22); the millimeter wave radio frequency front end (21) is used to transmit millimeter wave signals and receive target reflection signals; the distributed computing unit (22) performs local phase stabilization processing and micro-motion feature analysis on the millimeter wave echo signal under the local oscillator reference of the millimeter wave radio frequency front end (21), and generates a binary detection signal to characterize whether there is a living body before cross-module digital transmission; the central control terminal (3) is communicatively connected to the distributed computing unit (22) to receive the binary detection signal, and the central control terminal (3) comprehensively judges whether there is a living body in the detected target based on the consistency relationship of the detection results in multiple spatial orientations.

2. The millimeter-wave liveness detection system according to claim 1, characterized in that, The detection body (1) is an inverted U-shaped metal shielding chamber, an arched electromagnetic shielding tunnel, or a modular assembly of split-type shielding modules.

3. The millimeter-wave liveness detection system according to claim 2, characterized in that, The detection body (1) is made of metal material and its inner wall is coated with a conductive coating to shield external electromagnetic interference and prevent millimeter wave leakage.

4. The millimeter-wave liveness detection system according to claim 1, characterized in that, The detection channel (11) is an electric conveyor belt, a pneumatic pipeline conveying system, a gravity slide rail conveyor, or a pedestrian walkway.

5. The millimeter-wave liveness detection system according to claim 1, characterized in that, The distributed computing unit (22) is used to extract phase features before the millimeter-wave echo signal is transmitted across modules, so as to avoid irreversible phase distortion caused by cross-module clock deviation and quantization noise.

6. The millimeter-wave liveness detection system according to claim 1, characterized in that, The distributed computing unit (22) and the millimeter-wave radio frequency front-end (21) are located on the same printed circuit board or packaged as the same module.

7. The millimeter-wave liveness detection system according to claim 6, characterized in that, The distributed computing unit (22) and the millimeter-wave radio frequency front end (21) are coupled through a high-speed interconnect bus (23) or a board-to-board connector (24) to form the millimeter-wave detection module (2).

8. The millimeter-wave liveness detection system according to claim 1, characterized in that, The central control terminal (3) performs spatial redundancy consistency verification on the detection results obtained by multiple millimeter wave detection modules (2) in different spatial orientations. When the preset consistency conditions are met, it is determined that there is a living body.

9. A millimeter-wave liveness detection system according to claim 1, characterized in that, Multiple millimeter-wave detection modules (2) form a distributed architecture and communicate with the central control terminal (3) through a unified data bus or local area network.

10. A millimeter-wave liveness detection system according to claim 9, characterized in that, The distributed architecture is a master-slave structure, wherein at least one of the millimeter-wave detection modules (2) is designated as the master node; the remaining millimeter-wave detection modules (2) are slave nodes; the master node is responsible for receiving the detection results of the slave nodes and communicating with the central control terminal (3); Alternatively, the distributed architecture may be a fair distributed structure, in which each millimeter-wave detection module (2) has an equivalent status and independently reports the detection results to the central control terminal (3) or generates a collective decision through an internal negotiation protocol before reporting.

Images