Ball drop point positioning method based on distributed optical fiber sensing technology

Distributed optical fiber sensing technology with patch-type sensors and neural networks addresses precision and cost challenges in ball landing point positioning, achieving accurate and cost-effective real-time ball location in sports fields.

CN119056038APending Publication Date: 2024-12-03HARBIN ENG UNIV

Patent Information

Application Number
CN202411369938.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing ball landing point positioning technologies, such as the 'Hawkeye' system and time difference-based methods, face challenges in achieving precise and cost-effective positioning for multiple targets and high-frequency scenarios in sports like table tennis and tennis, due to issues like lens distortion, light diffraction, and inconsistent sensor distances.

Method used

A method utilizing distributed optical fiber sensing technology to detect and analyze vibration characteristics, employing patch-type optical fiber sensors, Fourier transforms, and neural networks to identify the ball landing point by analyzing frequency and amplitude differences.

Benefits of technology

Accurately locates the ball landing point with 1mm×1mm precision and 0.05s response time, providing real-time positioning and reducing costs compared to existing systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119056038A_ABST
    Figure CN119056038A_ABST
Patent Text Reader

Abstract

The invention provides a ball drop point positioning method based on a distributed optical fiber sensing technology. According to the method, sensing optical fibers are arranged below a playground, when a ball falls on the playground, generated vibration signals are detected by the sensing optical fibers, after the signals are demodulated through an optical fiber demodulator, specific frequencies, specific amplitude forms and the like of the vibration signals at different positions are used as characteristics, and the positions where vibration is generated are determined through calculation and analysis; therefore, ball drop point positioning is realized. Based on the characteristics of high sensitivity, low cost and the like of distributed optical fiber sensing, the falling point of a ball on a playground is accurately positioned by utilizing the technology, and the method and the system have obvious help for judging whether the falling point position of the ball is out of the limit in a game and carrying out auxiliary training and analyzing techniques and tactics for athletes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of distributed optical fiber sensing and ball landing point positioning, and in particular to a ball landing point positioning method based on distributed optical fiber sensing technology. Background Art

[0002] With the rapid development of science and technology, more and more smart devices and technologies have entered people's lives. In the field of sports, there are also cases of applying technologies such as artificial intelligence or deep learning. For example, the concept of "smart sports field" has emerged. Some smart sports fields can monitor the number of people on the sports field and monitor the body temperature of people by arranging cameras, infrared and other sensors; some smart sports fields can use motors to realize the layout of different competition venues and use intelligent power management to achieve energy saving. Most of the existing smart sports field technologies ignore the focus on the sport itself, that is, the landing point of the ball on the sports field and the position of the players in ball sports, such as the footsteps of the players in badminton games, or the landing point of the ball on the table in table tennis games. These data are of great significance to professional games and athletes. They can identify the landing point of the ball, determine whether the ball is out of bounds, or help coaches analyze the skills and tactics of players through statistical data.

[0003] The most mature technology for ball tracking and landing point positioning is the "Hawkeye" system in tennis (for example, Li Wenlong. Research on the application of Hawkeye technology in high-level tennis competitions [D]. Shanxi: Shanxi University, 2009. DOI: 10.7666 / d.Y2682072.), also known as the "instant response system", which consists of a high-speed camera, a computer and a screen. The "Hawkeye" uses a computer to divide the three-dimensional space of the stadium into measurement units calculated in millimeters, and uses a high-speed camera to capture the basic data of the flight trajectory of the tennis ball from different angles at the same time; then, through computer calculation, these data are generated into a three-dimensional image; finally, using instant imaging technology, the movement route and landing point of the tennis ball are clearly presented on a large screen. However, there are some problems with the "Hawkeye" system, such as the influence of lens distortion or point diffusion, the influence of light diffraction, etc., which cause certain errors. At the same time, a set of "Hawkeye" system is worth 400,000 US dollars, which is expensive. It needs to be redeveloped to be applied to different ball sports such as table tennis and tennis, which will bring about a large cost.

[0004] In addition to using cameras, other mainstream landing point positioning technologies mainly use positioning methods based on time difference. For example, by arranging a number of acoustic vibration sensors, the distance from each vibration sensor to the point to be measured is inconsistent, which makes the time for the vibration signal to reach the vibration sensor have a certain difference. The landing point is located by analyzing the time when each vibration sensor receives the vibration signal. Since the sensor that receives the signal is located at the edge of the venue, it takes a certain amount of time to receive the signal. Therefore, this landing point positioning method is difficult to achieve positioning in the case of multiple targets and high frequency. By using distributed fiber optic sensing, by detecting and analyzing the specific frequency and amplitude of vibration, the precise positioning of the landing point of various ball sports such as table tennis and tennis can be achieved. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the prior art and propose a method for locating the ball landing point based on distributed optical fiber sensing technology. The present invention arranges sensing optical fibers under the sports field to detect and analyze the different vibration characteristics caused by the ball hitting different points on the field and falling at different positions, such as the frequency and amplitude of the vibration, so as to achieve accurate positioning of the ball landing point.

[0006] The present invention is implemented by the following technical solutions. The present invention proposes a ball landing point positioning method based on distributed optical fiber sensing technology, and the method is specifically:

[0007] Step 1: Select the fiber type and deploy the fiber optic sensor under the actual sports field to be monitored;

[0008] Step 2: After the fiber optic sensor is laid out, the fiber optic sensor and the fiber optic demodulator are connected. The fiber optic demodulator is connected to a computer used for simulation experiments and location positioning. Test data is collected for the actual field environment. The collected signals are: the vibration signal of the ground when the ball falls on the ground, or when a person walks on the ground, or the vibration signal of the table;

[0009] Step 3: Perform Fourier transform on the collected vibration signal to obtain the independent modal components of each order that constitute the vibration mixed mode. The independent modal components of each order obtained through different landing point data are used as features for identifying the landing point of the ball.

[0010] Step 4: Design a neural network structure for the vibration mixed modal signal. Input the original vibration signal and the modal signal into the network at the same time. The network operates on the vibration signal and the modal signal separately, and finally concatenates the results of the two together as the input of the last layer.

[0011] Step 5: Input the data demodulated by the fiber optic demodulator into the computer for calculation and analysis to determine the location where the vibration occurs, thereby locating the landing point of the ball.

[0012] Furthermore, the selected optical fiber type is patch-type optical fiber sensors, and the number of the patch-type optical fiber sensors is 42.

[0013] Furthermore, data from 42 patch-type fiber optic sensors were collected, and the data length of each fiber optic sensor was 120 points. These data were combined into a single-channel image format of 1*42*120, and used as an input to the network. After Fourier transform of each patch-type fiber optic sensor data, another set of 1*42*120 data was obtained as another input to the network. After 4 residual connection layers and a global average pooling layer, 256*2*2 deep features were extracted for each input, and then the deep features were flattened to 1*1024. The features of the two inputs were concatenated into 1*2048 as the input of the final fully connected layer. The output of the fully connected layer is 42, corresponding to the number of divided areas.

[0014] Furthermore, when the ball falls on different points on the sports field, it will stimulate different vibration frequencies and different amplitude forms on the field. By analyzing the differences in vibration information at different points, the landing point can be located.

[0015] Furthermore, the optical fiber demodulator includes a laser, an erbium-doped fiber amplifier EDFA, an acousto-optic modulator AOM, a circulator, a signal generator AWG, a photodetector PD and a data acquisition card; the continuous light emitted by the laser is amplified by the EDFA, modulated into pulse light by the AOM, and enters the sensing optical fiber after passing through the optical circulator. The back Rayleigh scattered light generated by the pulse light propagating in the optical fiber enters the circulator again, and after passing through another EDFA, the generated electrical signal is sent to the photodetector PD. After the PD receives the generated electrical signal, the data acquisition card converts the analog electrical signal into a digital signal and processes it through a computer.

[0016] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the ball landing point positioning method based on distributed optical fiber sensing technology are implemented.

[0017] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of a ball landing point positioning method based on distributed optical fiber sensing technology.

[0018] The advantages of the ball landing point positioning method based on distributed optical fiber sensors described in the present invention are:

[0019] The present invention utilizes the high sensitivity and low cost of distributed fiber optic sensing to achieve accurate positioning of the landing points of various balls on the sports field. From the simulation results, it is concluded that the positioning area accuracy can reach 1mm×1mm. At the same time, the response time to the landing point of the ball is 0.05s, and real-time landing point display can be completed. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0021] Figure 1 This is an overall schematic diagram of the smart sports field based on distributed fiber optic sensing technology.

[0022] Figure 2 This is the structural principle diagram of the optical fiber demodulator.

[0023] Figure 3 Schematic diagram for vibration detection and positioning.

[0024] Explanation of the marks in the figure: 1 is the sideline of the sports field, 2 is the inside of the sports field, 3 is the laid sensor optical fiber, 4 is the optical fiber demodulator for demodulating the vibration signal, 5 is the computer for simulation experiments and landing point positioning, 6 is the laser, 7 is the erbium-doped fiber amplifier (EDFA), 8 is the acousto-optic modulator (AOM), 9 is the optical circulator, 10 is the signal generator (AWG), 11 is the photodetector (PD), and 12 is the data acquisition card. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Combination Figure 1-Figure 3 The present invention proposes a ball landing point positioning method based on distributed optical fiber sensing technology, which can detect the location of the ball landing point on various sports fields in real time. The method is specifically as follows:

[0027] Step 1: Select the fiber type and deploy the fiber sensor at a suitable depth or location below the actual sports field to be monitored;

[0028] Step 2: After the fiber optic sensor is laid out, the fiber optic sensor and the fiber optic demodulator are connected. The fiber optic demodulator is connected to a computer used for simulation experiments and location positioning. Test data is collected for the actual field environment. The collected signals are: the vibration signal of the ground when the ball falls on the ground, or when a person walks on the ground, or the vibration signal of the table;

[0029] Step 3: Perform Fourier transform on the collected vibration signal to obtain the independent modal components of each order that constitute the vibration mixed mode. The independent modal components of each order obtained through different landing point data are used as features for identifying the landing point of the ball.

[0030] Step 4: Design a neural network structure for the vibration mixed modal signal. Input the original vibration signal and the modal signal into the network at the same time. The network operates on the vibration signal and the modal signal separately, and finally concatenates the results of the two together as the input of the last layer.

[0031] Step 5: Input the data demodulated by the fiber optic demodulator into the computer for calculation and analysis to determine the location where the vibration occurs, thereby locating the landing point of the ball.

[0032] The optical fiber demodulator comprises a laser, an erbium-doped fiber amplifier EDFA, an acousto-optic modulator AOM, a circulator, a signal generator AWG, a photodetector PD and a data acquisition card; the continuous light emitted by the laser is amplified by the EDFA, modulated into pulse light by the AOM, and enters the sensing optical fiber after passing through the optical circulator; the back Rayleigh scattered light generated by the pulse light propagating in the optical fiber enters the circulator again, and after passing through another EDFA, the generated electrical signal is sent to the photodetector PD; after the PD receives the generated electrical signal, the data acquisition card converts the analog electrical signal into a digital signal and processes it through a computer.

[0033] When laying optical fibers, the position and quantity of the optical fibers should be adjusted according to the actual conditions of the venue; for example, the density of the optical fibers can be increased near the sidelines of the venue, and the shape of the optical fibers can be adjusted to achieve accurate judgment of the ball out of bounds. The optical fiber type selected by the present invention is a patch-type optical fiber sensor, and the number is 42.

[0034] Data from 42 patch-type fiber optic sensors were collected. The data length of each fiber optic sensor was 120 points. These data were combined into a single-channel image format of 1*42*120 and used as an input to the network. After Fourier transforming the data of each patch-type fiber optic sensor, another set of 1*42*120 data was obtained as another input to the network. After 4 residual connection layers and a global average pooling layer, 256*2*2 deep features were extracted for each input, and then the deep features were flattened to 1*1024. The features of the two inputs were spliced ​​into 1*2048 as the input of the final fully connected layer. The output of the fully connected layer is 42, corresponding to the number of divided areas. See Table 1 for details.

[0035] Table 1

[0036] Layer Singlebranchnet Parallelnet 1 Conv1(1,64,3) Conv1(1,64,3) 2 Conv2(64,128,3) Conv2(64,128,3) 3 Conv2(128,256,3) Conv2(128,256,3) 4 MaxPool2d(2,2) MaxPool2d(2,2) 5 Flatten Flatten 6 Linear(2048,42) Linear(2048,42)

[0037] When the ball falls on different points on the sports field, it will stimulate different vibration frequencies and different amplitude forms on the field. By analyzing the differences in vibration information at different points, the landing point can be located. Since the size, material, and constraints of the field will affect the vibration of the field and thus affect the analysis of vibration information at different landing points, the positioning system needs to be tested and calibrated in a field environment according to the actual conditions of different fields.

[0038] The sensing optical fiber is laid out in the actual monitored sports field. If necessary, the coupling degree between the sensing unit and the signal should be enhanced by patch structure or dense winding, so as to achieve the effect of increasing sensitivity. In the actual laying process, attention should also be paid to arranging the sensing optical fiber on both sides of the sideline 1 of the court to improve the spatial resolution at the sideline and use the ball to knock on the field. Connect the sensing optical fiber 3 and the optical fiber demodulator 4, turn on the laser 6, the continuous light emitted by the laser 6 is amplified by the EDFA 7, modulated into pulse light by the AOM 8, and enters the sensing optical fiber after passing through the optical circulator 9. The back Rayleigh scattered light generated by the pulse light propagating in the optical fiber enters the circulator 9 again, and after passing through another EDFA, the generated electrical signal is sent to the photodetector PD11. After receiving the generated optical signal, PD11 converts it into an electrical signal. The data acquisition card 12 converts the analog electrical signal into a digital signal and processes it through the computer 5. The signal generator AWG10 is connected to the AOM 8 and the data acquisition card 12 to directly transmit the generated electrical signal to the acousto-optic modulator and the data acquisition card.

[0039] The present invention proposes a method for realizing two-dimensional plane positioning of the ball landing point by using distributed optical fiber sensors. By laying out sensing optical fibers under the sports field, when the ball falls on the sports field, the vibration signal generated is detected by the sensing optical fibers. After the signal is demodulated by an optical fiber demodulator, the specific frequency and specific amplitude form of the vibration signal at different positions are used as features, and the position where the vibration is generated is determined through calculation and analysis, thereby realizing the positioning of the ball landing point. Based on the high sensitivity and low cost of distributed optical fiber sensing, the present invention uses this technology to realize the precise positioning of the ball landing point on the sports field, which is significantly helpful for judging whether the ball landing point is out of bounds in the game and for assisting athletes in training and analyzing skills and tactics.

[0040] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the ball landing point positioning method based on distributed optical fiber sensing technology are implemented.

[0041] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of a ball landing point positioning method based on distributed optical fiber sensing technology.

[0042] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). It should be noted that the memory of the method described in the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0043] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0044] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0045] It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The 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. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0046] The above is a detailed introduction to the ball landing point positioning method based on distributed optical fiber sensing technology proposed in the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A ball landing point positioning method based on distributed optical fiber sensing technology, characterized in that: The method is specifically as follows: Step 1: Select the fiber type and deploy the fiber optic sensor under the actual sports field to be monitored; Step 2: After the fiber optic sensor is laid out, the fiber optic sensor and the fiber optic demodulator are connected. The fiber optic demodulator is connected to a computer used for simulation experiments and location positioning. Test data is collected for the actual field environment. The collected signals are: the vibration signal of the ground when the ball falls on the ground, or when a person walks on the ground, or the vibration signal of the table; Step 3: Perform Fourier transform on the collected vibration signal to obtain the independent modal components of each order that constitute the vibration mixed mode. The independent modal components of each order obtained through different landing point data are used as features for identifying the landing point of the ball. Step 4: Design a neural network structure for the vibration mixed modal signal. Input the original vibration signal and the modal signal into the network at the same time. The network operates on the vibration signal and the modal signal separately, and finally concatenates the results of the two together as the input of the last layer. Step 5: Input the data demodulated by the fiber optic demodulator into the computer for calculation and analysis to determine the location where the vibration occurs, thereby locating the landing point of the ball.

2. The method according to claim 1, characterized in that The selected optical fiber type is patch type optical fiber sensor, the number of which is 42.

3. The method according to claim 2, characterized in that Data from 42 patch-type fiber optic sensors were collected, and the data length of each fiber optic sensor was 120 points. These data were combined into a single-channel image format of 1*42*120, and used as an input to the network. After Fourier transform of each patch-type fiber optic sensor data, another set of 1*42*120 data was obtained as another input to the network. After 4 residual connection layers and a global average pooling layer, 256*2*2 deep features were extracted for each input, and then the deep features were flattened to 1*1024. The features of the two inputs were spliced ​​together into 1*2048 as the input of the final fully connected layer. The output of the fully connected layer is 42, corresponding to the number of divided areas.

4. The method according to claim 1, characterized in that: When the ball falls on different points on the sports field, it will stimulate different vibration frequencies and different amplitude forms on the field. By analyzing the differences in vibration information at different points, the landing point can be located.

5. The method according to claim 1, characterized in that The optical fiber demodulator comprises a laser, an erbium-doped fiber amplifier EDFA, an acousto-optic modulator AOM, a circulator, a signal generator AWG, a photodetector PD and a data acquisition card; the continuous light emitted by the laser is amplified by the EDFA, modulated into pulse light by the AOM, and enters the sensing optical fiber after passing through the optical circulator; the back Rayleigh scattered light generated by the pulse light propagating in the optical fiber enters the circulator again, and after passing through another EDFA, the generated electrical signal is sent to the photodetector PD; after the PD receives the generated electrical signal, the data acquisition card converts the analog electrical signal into a digital signal and processes it through a computer.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Ping-pong player training analysis system

    CN112587902A

  • Induction type interactive positioning system and ball instrument

    CN116672692A

  • A detector system

    GB202018662D0

  • Method of determining coordinates of the place of falling of ammunition

    RU2730420C1

  • Improvements in fibre optic distributed acoustic sensing

    WO2024182833A1

Cited By

  • Multi-cascade distributed optical fiber vibration sensing accelerometer and acceleration parameter measuring method

    CN121026306A