Micro embedded millimeter wave radar vision fusion system and product detection method

Through the micro embedded millimeter-wave radar vision fusion system, combined with the information of the image acquisition module and radar module, the problem that a single sensor cannot detect internal damage and material changes is solved, and the accuracy of product detection and production efficiency are improved. Meets the needs of modern high-speed production lines.

CN112346047BInactive Publication Date: 2024-11-12XUCHANG UNIV
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202011247534.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-11-10
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, a single sensor cannot effectively detect internal damage, material changes and multiple injuries of the product, resulting in high detection error rate and low production efficiency. Traditional manual detection has visual fatigue, which cannot meet the needs of modern high-speed production lines.

Method used

Using a micro embedded millimeter-wave radar vision fusion system, the product's visual information and spatial position information are collected through the image acquisition module and the radar module, and the product is fused. The complementary information of multiple sensors is used for product detection, and a single sensor is overcome. missed detection, missed detection and tracking failure.

Benefits of technology

It achieves the accuracy and production efficiency of product inspection, provides faster and more accurate inspection results, ensures product quality reliability and production line automation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112346047B_ABST
    Figure CN112346047B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of product detection, and provides a micro embedded millimeter wave radar visual fusion system and a product detection method, wherein the system specifically comprises: a fusion processor, an image acquisition module and a radar module respectively connected to the fusion processor; wherein the image acquisition module sends the collected product image information on the assembly line to the fusion processor; the radar module sends the collected product spatial position information on the assembly line to the fusion processor; the fusion processor fuses the received product image information and product spatial position information to obtain fusion information, and transmits the fusion information to a display device for display. The present invention fuses the multi-source information of the image information and the spatial position after time-space matching, so that the sensor data fusion can complement each other, improve the product detection efficiency on the assembly line, thereby making the assembly line product production faster and more accurate, and improving the production efficiency on the production line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of product production auxiliary technology, and in particular to a micro embedded millimeter wave radar vision fusion system and a product detection method. Background Art

[0002] With the continuous development of industrialization, the application of assembly lines is becoming more and more extensive, from single objects to multiple objects, from assembly lines to the integration of processing, transportation, inspection and storage. However, at present, production inspection is still mainly based on manual inspection, there is a certain misjudgment rate, and production efficiency is also seriously restricted. Therefore, how to liberate the constraints of the production line rate and further improve the efficiency of inspection, and the use of automated technology to replace manual inspection of products has a very important practical significance. In order to improve the reliability of inspection, automatic inspection equipment is used. On modern high-speed machines, traditional manual inspection cannot guarantee reliability due to visual fatigue and other reasons. Once damaged and defective products flow into the market, it will not only affect the brand and corporate image, but also bring unnecessary trouble and pain to customers. On modern lines, research has a realistic inspection system to replace the traditional manual inspection method, so that it can meet the requirements of production automation and product high quality, enhance the accuracy and high level of inspection, and provide a fundamental guarantee for the quality of production products.

[0003] Traditional inspection systems are mostly based on a single sensor. As the main sensor for industrial production, for example, a monocular camera sensor is used. The camera can realize environmental scene information. It is the application of machine vision in industrial production and the largest source of relevant environmental information for product production. It is unique in inspecting product appearance, color tone, packaging, etc. However, the monocular camera sensor, which is currently more commonly used, cannot provide detection of internal damage, material changes, multiple injuries, etc.

[0004] Or use millimeter wave radar sensor alone, its working frequency is selected in the 30~300GHz frequency domain (wavelength is 1~10mm, that is, millimeter wave band), its advantages are narrow beam, high angular resolution, wide frequency band, strong anti-interference ability, strong penetration, small size, light weight, long measurable distance, and all-day and all-weather working characteristics. Therefore, millimeter wave radar (especially 77GHz millimeter wave radar) has excellent advantages in target distance, exit velocity and radar intercept area. However, millimeter wave radar has poor recognition ability, cannot accurately identify the detailed features of production products, and does not have the ability to recognize sound and color changes.

[0005] Therefore, how to integrate multiple sensors and use complementary information to detect production products so that product production can be faster and more accurate is an issue that needs to be solved urgently. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a miniature embedded millimeter-wave radar vision fusion system and a product detection method, which use multiple sensors to overcome the defects of single sensor missed detection, false detection, tracking failure, state and system inaccuracy, etc. The image acquisition module collects the product visual information on the product assembly line and the data obtained after the radar module interacts with the object is solved, and the product spatial position information can be collected. Therefore, it has multi-source information of image information and spatial position at the same time, and uses complementary information to perform product detection on the assembly line, which makes product production faster and more accurate, thereby improving the production efficiency on the production line.

[0007] In a first aspect, the present invention provides a miniature embedded millimeter-wave radar vision fusion system, specifically comprising:

[0008] A fusion processor, an image acquisition module and a radar module respectively connected to the fusion processor;

[0009] The image acquisition module is used to acquire product image information on the production line in real time and send the acquired product image information to the fusion processor;

[0010] The radar module is used to collect spatial position information of products on the assembly line and send the collected spatial position information of the products to the fusion processor;

[0011] The fusion processor fuses the received product image information and the product spatial position information to obtain fusion information, and transmits the fusion information to a display device for display.

[0012] Preferably, the image acquisition module is connected to the fusion processor via CSI, and the radar module is connected to the fusion processor via USB.

[0013] Preferably, the image acquisition module is a laser camera.

[0014] Preferably, the laser camera comprises a camera, a camera housing, a PCB circuit board arranged in the camera housing, and the PCB circuit board is provided with a control MCU, an image acquisition circuit and a CSI output interface;

[0015] The camera is protruding and embedded in the mounting hole of the camera housing, the PCB circuit board includes an image acquisition circuit, the input end of the image acquisition circuit is connected to the camera, and the output end is connected to the data input end of the control MCU, and the data output end of the control MCU is connected to the CSI input interface of the fusion processor through the CSI output interface.

[0016] Preferably, the laser camera uses an image sensor of model SONY-IMX219PQ.

[0017] Preferably, the radar module adopts millimeter wave radar.

[0018] Preferably, the millimeter wave radar includes a radar housing, a high-frequency electronic scanning radar element, and a PCB circuit board arranged in the radar housing; the high-frequency electronic scanning radar element is protruding and embedded in the mounting hole of the radar housing; the millimeter wave sensor, radar data acquisition circuit, power management, temperature sensor and control IC, UART communication circuit and UART output interface of the control MCU and hardware accelerator are integrated on the PCB circuit board; the input end of the radar data acquisition circuit is connected to the high-frequency electronic scanning radar component, the output end of the radar data acquisition circuit is connected to the data input end of the control MCU, and the output end of the control MCU is connected to the USB input interface of the fusion processor through the UART communication circuit.

[0019] Preferably, the millimeter wave radar adopts a single-chip millimeter wave sensor of model AWR1642.

[0020] Preferably, the fusion processor adopts a micro embedded system.

[0021] In a second aspect, the present invention further provides a product detection method, which is applied to the above-mentioned micro embedded millimeter wave radar vision fusion system, and mainly includes the following steps:

[0022] Step 1: The radar module collects spatial position information of products on the assembly line, and sends the collected spatial position information of the products and the corresponding first time tag to the fusion processor;

[0023] Step 2: The image acquisition module acquires product image information on the production line, and sends the acquired product image information and the corresponding second time tag to the fusion processor;

[0024] Step 3: The fusion processor performs spatial correction on the product spatial position information and the product image information, and combines the first time tag and the second time tag for spatiotemporal matching and then fuses them to obtain fusion information;

[0025] Step 5: The fusion processor outputs the fusion information to a display device and displays it in the form of a video.

[0026] In the present invention, the visual information of products on the product assembly line is collected by the image acquisition module, and the data obtained after the radar module interacts with the object is solved, so that the spatial position information of the products on the assembly line can be collected. Therefore, multi-source information of image information and spatial position is simultaneously provided, and the multi-source data is fused after time-space matching, so that the sensor data fusion can complement each other and improve the product detection efficiency on the assembly line. The present invention uses multiple sensors to overcome the defects of missed detection, false detection, tracking failure, state and system inaccuracy caused by the use of a single sensor in the prior art, so that the production of assembly line products is faster and more accurate, thereby improving the production efficiency on the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] 1. Figure 1 A schematic diagram of the structure of a miniature embedded millimeter-wave radar vision fusion system provided by an embodiment of the present invention;

[0028] 2. Figure 2 A flowchart of a product detection method applied to a micro-embedded millimeter-wave radar vision fusion system provided in an embodiment of the present invention.

[0029] Best Mode for Carrying Out the Invention

[0030] In order to enable those skilled in the art to more clearly understand the micro embedded millimeter wave radar vision fusion system and product detection method provided by the present invention, they will be described in detail below with reference to the accompanying drawings.

[0031] like Figure 1 As shown, an embodiment of the present invention provides a miniature embedded millimeter wave radar vision fusion system, which specifically includes:

[0032] A fusion processor, an image acquisition module and a radar module respectively connected to the fusion processor;

[0033] The image acquisition module is used to acquire product image information on the production line in real time and send the acquired product image information to the fusion processor;

[0034] The radar module is used to collect spatial position information of products on the assembly line and send the collected spatial position information of the products to the fusion processor;

[0035] The fusion processor fuses the received product image information and the product spatial position information to obtain fusion information, and transmits the fusion information to a display device for display.

[0036] Specifically, a miniature embedded millimeter-wave radar vision fusion system provided in an embodiment of the present invention is mainly used in a product detection system on a high-speed production line.

[0037] Among them, the image acquisition module can adopt a laser camera, the laser camera includes a camera, a camera housing, a PCB circuit board arranged in the camera housing, and the PCB circuit board is provided with a control MCU, an image acquisition circuit and a CSI output interface; the camera is protruding and embedded in the mounting hole of the camera housing, the PCB circuit board includes an image acquisition circuit, the input end of the image acquisition circuit is connected to the camera, and the output end is connected to the data input end of the control MCU, and the data output end of the control MCU is connected to the CSI input interface of the fusion processor through the CSI output interface.

[0038] Preferably, the image acquisition circuit is designed using a C674x DSP A / D converter, and the DSP core uses a secondary cache-based architecture. The level 1 program cache (L1P) is a 32KB direct-mapped cache, and the level 1 data cache (L1D) is a 32KB; 2-way, set-associative cache. The level 2 program cache (L2P) consists of 256KB of storage space, which is shared between program and data space. The level 2 program cache (L2P) can be configured as mapped memory, cache, or a combination of the two.

[0039] Specifically, the laser camera can be designed and implemented using an image sensor of model SONY-IMX219PQ.

[0040] The radar module can adopt a millimeter wave radar, which includes a radar shell, a high-frequency electronic scanning radar element and a PCB circuit board arranged in the radar shell. The high-frequency electronic scanning radar element is protruding and embedded in the mounting hole of the radar shell. The PCB circuit board is integrated with a millimeter wave sensor that controls the MCU and the hardware accelerator, a radar data acquisition circuit, a power management, a temperature sensor and a control IC, a UART communication circuit and a UART output interface. The input end of the radar data acquisition circuit is connected to the high-frequency electronic scanning radar component, the output end of the radar data acquisition circuit is connected to the data input end of the control MCU, and the output end of the control MCU is connected to the USB input interface of the fusion processor through the UART communication circuit.

[0041] Specifically, the millimeter-wave radar can adopt a single-chip millimeter-wave sensor model AWR1642, the transmission band is Texas Instruments' AWR1642, a 76GHz to 81GHz single-chip millimeter-wave sensor with an integrated MCU and hardware accelerator, its on-board antenna can be field tested, and it has a serial port interface based on XDS110 JTAG, which can be used for flash memory programming and UART-interface, which can be used for control, configuration and data visualization.

[0042] The specific implementation method may be:

[0043] The above-mentioned laser camera is installed above the high-speed production line, and is aligned with and completely covers the production line, so as to collect product image information on the production line; the laser camera has an image acquisition system that can independently acquire images, and the laser camera is connected to the fusion processor via CSI, and the collected product image information is sent to the fusion processor via CSI.

[0044] The millimeter-wave radar is installed above the high-speed production line and below the laser camera; the millimeter-wave radar is connected to a 5V power supply system and is connected to the fusion processor via USB to collect spatial position information of products on the production line. The spatial position information of the products may specifically include spatial position, speed, acceleration and echo energy data (including radar reflection area) of the products; and the collected spatial position information of the products is transmitted to the fusion processor via USB.

[0045] Preferably, the above USB transmission adopts USB3.0.

[0046] Specifically, the fusion processor adopts a micro embedded system.

[0047] Specifically, it can be implemented using the fourth-generation Raspberry Pi design developed by the British Raspberry Pi Foundation, which has an ARMv8 series 1.5GHz, an image processing chip that can process H.265 and H.264, 4GB of memory, a 15-pin MIPI camera (CSI) interface, Micro-HDMI (2) with a maximum resolution of 4Kp60, 4 USB interfaces, a rated power of 15w (5V / 3A), and a weight of 45g.

[0048] Preferably, the fusion processor can be installed on the back of the display device, and is used to receive the product image information sent by the laser camera, and receive the product spatial position information sent by the millimeter-wave radar, and fuse the product image information and the product spatial position information. Finally, the fused information is transmitted to the display device via HDMI to display the product status on the assembly line in real time, provide monitoring of abnormal products and sound and light prompts, so that monitoring personnel can grasp the product status at any time to ensure the quality of the products, which is helpful for the management and inspection of production products, avoids problems such as missed detection, false detection and inaccuracy, and improves production efficiency.

[0049] It should be noted that the spatiotemporal matching and fusion algorithm involved in the embodiment of the present invention can be specifically implemented as follows: During the fusion process, data from multiple sensors are usually changed to the same spatiotemporal reference system. Sensor matching refers to the processing required for error-free conversion of multiple sensor data, which generally includes two aspects: time matching and space matching.

[0050] The so-called time matching is to synchronize the asynchronous measurement information of various sensors about the same target to the same time. Since the measurements of each sensor are independent of each other and the sampling periods are often different, the time when the data is provided to the fusion control processor is often different. The general practice of time matching is to unify the data of each sensor into a sensor data with a longer scanning period. Therefore, in the embodiment of the present invention, the millimeter wave data with a longer scanning period is used as the standard for time matching. By using the least squares criterion registration method, the optimal function matching of the time data is found by minimizing the sum of squares of the error, which can eliminate the asynchrony of the target state measurement caused by time deviation, and thus eliminate the influence of time deviation on multi-sensor data fusion.

[0051] The so-called spatial matching, also known as sensor registration, is to estimate and compensate for sensor deviations by measuring a common target in space with multiple sensors. For multiple different sensors, each sensor uses a different coordinate system, so before fusing the information between the sensors, it is necessary to convert the multiple different sensors into the same measurement coordinate system.

[0052] The embodiment of the present invention adopts an optical image and radar measurement fusion algorithm.

[0053] Specifically, the sensor used for target tracking provides measurement of the target object according to the sensor coordinate system or frame. In the embodiment of the present invention, the millimeter wave data reception is adopted, and the two-dimensional polar coordinate system is used to measure the distance and azimuth. The position (distance and azimuth) measurement in the polar coordinate system is converted to the Cartesian coordinate system, which can be expressed as:

[0054]

[0055] After completing the millimeter-wave radar coordinate conversion, the next consideration is the distance difference and observation angle between the two sensors. Here, it is assumed that the optical camera is looking straight ahead, while the millimeter-wave radar has an observation angle. After the two coordinate systems are translated and rotated, the coordinate relationship between the two coordinate systems can be determined. After determining the coordinate relationship, spatial matching is performed. Assuming that the sensor bias vector does not change over time and is independent of noise, the Kalman filter can be applied to estimate the sensor's bias vector. The Kalman filter is a highly efficient recursive filter that can estimate the state of a dynamic system from a series of incomplete and noisy measurements. The Kalman filter will generate an estimate of the unknown variable based on the values ​​of each measurement at different times, considering the joint distribution at each time, so it will be more accurate than the estimation method based on a single measurement.

[0056] In summary, in the embodiment of the present invention, the visual information of the products on the product assembly line is collected by the image acquisition module, and the data obtained after the radar module interacts with the object is solved, so that the spatial position information of the products on the assembly line can be collected. Therefore, multi-source information of image information and spatial position is simultaneously provided. The multi-source data is fused after time-space matching, so that the sensor data fusion can complement each other and realize product detection on the assembly line. The present invention uses multiple sensors to overcome the defects of missed detection, false detection, tracking failure, state and system inaccuracy caused by the use of a single sensor in the prior art, so that the production of assembly line products is faster and more accurate, thereby improving the production efficiency on the production line.

[0057] At the same time, compared with the prior art, the micro embedded millimeter wave radar vision fusion system provided in the embodiment of the present invention has a light and thin overall structural design, a reasonable and stable structure, is easy to install and use, and has a low manufacturing cost.

[0058] On the one hand, the product image information on the assembly line collected by the image acquisition module through CSI transmission is high-speed, stable and clear with a clarity of up to 1080P. On the other hand, the product spatial position information collected by the millimeter-wave radar transmitted through USB3.0 is high-speed, complete and low-cost, which is conducive to promotion and application.

[0059] like Figure 2 As shown, an embodiment of the present invention further provides a product detection method, which is applied to the above-mentioned micro embedded millimeter wave radar vision fusion system, and specifically includes the following steps:

[0060] S1: The radar module collects spatial position information of products on the production line, and sends the collected spatial position information of the products and the corresponding first time tag to the fusion processor;

[0061] S2: The image acquisition module acquires product image information on the production line, and sends the acquired product image information and the corresponding second time tag to the fusion processor;

[0062] S3: the fusion processor performs spatial correction on the product spatial position information and the product image information, combines the first time tag and the second time tag for spatiotemporal matching, and then fuses them to obtain fusion information;

[0063] S4: The fusion processor outputs the fusion information to a display device and displays it in a video manner.

[0064] Specifically, after setting the radar module (such as the millimeter-wave radar module) according to the required radar parameters, the millimeter-wave radar starts to detect and obtain the two-dimensional data and time tags of the products on the assembly line in real time, that is, the spatial position information of the product, and the corresponding time tag, recorded as the first time tag, and obtain the real-time image of the product on the assembly line and the corresponding time tag in real time through the image acquisition module (such as an optical camera), that is, the product image information and the corresponding time tag, recorded as the second time tag. A two-dimensional polar coordinate system is used to measure distance and azimuth. The position (distance and azimuth) measurement in the polar coordinate system is converted to Cartesian coordinates, which can be expressed as:

[0065]

[0066] After completing the millimeter wave radar coordinate conversion, the distance difference and observation angle between the radar module and the image acquisition module are measured. The measured distance difference and observation angle are then transmitted to the fusion processor, which performs spatial correction on the product spatial position information and product image information, and combines the time tags (including the first time tag and the second time tag) for time-space matching, and finally fuses them to obtain fusion information.

[0067] The specific implementation methods of other schemes have been described in detail in the above embodiments and will not be repeated here.

[0068] The embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A miniature embedded millimeter wave radar vision fusion system, It is characterized in that include: A fusion processor, an image acquisition module and a radar module respectively connected to the fusion processor; The image acquisition module is installed above the high-speed production line and is aligned with and completely covers the production line, and is used to acquire product image information on the production line in real time and send the acquired product image information to the fusion processor; The radar module is installed above the high-speed production line and below the image acquisition module, and is used to collect spatial position information of products on the production line and send the collected spatial position information of the products to the fusion processor; The fusion processor time-matches the received product image information, synchronizes the asynchronous product image information of the same product to the same target time, and when the image acquisition module performs asynchronous scanning on the same product, uses the acquisition time corresponding to the millimeter wave data with a longer scanning period as the target time; and the fusion processor converts the received asynchronous product spatial position information of the same product into a two-dimensional polar coordinate system, measures the distance and azimuth, converts the distance and azimuth measurements in the two-dimensional polar coordinate system to the Cartesian coordinate system, and determines the two-dimensional polar coordinate system and the Cartesian coordinate system after coordinate translation and coordinate rotation. The coordinate relationship between the polar coordinate system and the Cartesian coordinate system is spatially matched; if the sensor deviation vector does not change with time and is independent of noise, the Kalman filter is used to estimate the sensor deviation vector; the Kalman filter generates an estimate of the unknown variable based on the values ​​of each measurement quantity at different times and considers the joint distribution at each time; the fusion processor fuses the product image information after time matching and the product spatial position information after spatial matching using an optical image and radar measurement fusion algorithm to obtain fusion information, and transmits the fusion information to the display device for display; wherein the fusion processor is installed on the back of the display device.

2. According to the miniature embedded millimeter wave radar vision fusion system of claim 1, It is characterized in that The image acquisition module is connected to the fusion processor via CSI, and the radar module is connected to the fusion processor via USB.

3. The micro embedded millimeter wave radar vision fusion system according to claim 2, It is characterized in that The image acquisition module is a laser camera.

4. According to claim 3, the micro embedded millimeter wave radar vision fusion system, It is characterized in that The laser camera comprises a camera, a camera housing, a PCB circuit board arranged in the camera housing, and the PCB circuit board is provided with a control MCU, an image acquisition circuit and a CSI output interface; The camera is protruding and embedded in the mounting hole of the camera housing, the PCB circuit board includes an image acquisition circuit, the input end of the image acquisition circuit is connected to the camera, and the output end is connected to the data input end of the control MCU, and the data output end of the control MCU is connected to the CSI input interface of the fusion processor through the CSI output interface.

5. According to claim 4, the micro embedded millimeter wave radar vision fusion system, It is characterized in that The laser camera uses an image sensor model SONY-IMX219PQ.

6. The micro embedded millimeter wave radar vision fusion system according to claim 2, It is characterized in that The radar module adopts millimeter wave radar.

7. The micro embedded millimeter wave radar vision fusion system according to claim 6, It is characterized in that The millimeter wave radar includes a radar housing, a high-frequency electronic scanning radar element, and a PCB circuit board arranged in the radar housing. The high-frequency electronic scanning radar element is protruding and embedded in the mounting hole of the radar housing. The millimeter wave sensor, radar data acquisition circuit, power management, temperature sensor and control IC, UART communication circuit and UART output interface of the control MCU and hardware accelerator are integrated on the PCB circuit board. The input end of the radar data acquisition circuit is connected to the high-frequency electronic scanning radar element, the output end of the radar data acquisition circuit is connected to the data input end of the control MCU, and the output end of the control MCU is connected to the USB input interface of the fusion processor through the UART communication circuit.

8. The micro embedded millimeter wave radar vision fusion system according to claim 7, It is characterized in that The millimeter wave radar adopts a single-chip millimeter wave sensor of model AWR1642.

9. The miniature embedded millimeter wave radar vision fusion system according to any one of claims 1 to 8, It is characterized in that The fusion processor adopts a micro embedded system.

10. A product testing method, It is characterized in that The micro embedded millimeter wave radar vision fusion system as claimed in any one of claims 1 to 9 specifically comprises the following steps: Step 1: The radar module collects spatial position information of products on the assembly line, and sends the collected spatial position information of the products and the corresponding first time tag to the fusion processor; Step 2: The image acquisition module acquires product image information on the production line, and sends the acquired product image information and the corresponding second time tag to the fusion processor; Step 3: The fusion processor performs spatial correction on the product spatial position information and the product image information, and combines the first time tag and the second time tag for spatiotemporal matching and then fuses them to obtain fusion information; Step 5: The fusion processor outputs the fusion information to a display device and displays it in the form of a video.

Citation Information

Patent Citations

  • Embedded vision detecting system

    CN101393010A

  • Unmanned ship perception fusion algorithm based on deep learning

    CN110414396A

  • Multi-sensor fusion method based on DS-GNN algorithm

    CN110726990A

  • Commercial vehicle safe driving auxiliary system based on vision and millimeter wave radar fusion

    CN111098786A

  • Multi-sensor multi-target cooperative detection information fusion method and system

    CN111860589A