Three-dimensional hit and miss localization system
By using multiple acoustic sensors and machine learning models in the LOMAH system to calculate hit and miss information of shots, the problem of measurement errors caused by direct sunlight on the temperature sensor is solved, improving the accuracy and ease of use of the system.
Patent Information
- Application Number
- CN202380045475.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-06-09
- Filing Date
- 2023-06-09
- Publication Date
- 2025-01-21
AI Technical Summary
When using temperature sensors, the existing LOMAH system has large ambient temperature measurement errors caused by direct sunlight, which affects the calculation of hits and misses, and increases system complexity and setting time.
By setting up a sensor array on the target platform of the LOMAH system, including at least four acoustic sensors, combined with a machine learning model, it calculates the impact and trajectory of the bullet, and directly outputs hit and miss information on the display, avoiding direct influence on the ambient temperature. Measurement.
Improves the accuracy and ease of use of the LOMAH system, reduces system complexity and setup time, and enables accurate determination of shot hits without the need to use ambient temperature in calculations.
Smart Images

Figure CN119343577A_ABST
Abstract
Description
Technical Field
[0001] The present application generally relates to a method for locating three-dimensional miss and hit locations of supersonic bullet shooting. Miss And Hit,LOMAH) system. Background Art
[0002] There are currently several LOMAH systems on the market for electronic hit scoring during shooter practice and improvement. Most LOMAH systems have a target platform that includes an array of acoustic sensors that detect shot information, i.e. the time it takes for the sound or shock wave to arrive at the different acoustic sensors in the sensor array. An electronic picture of the target board is then calculated and displayed using the arrival time differences or detection times of the different acoustic sensors. Using a LOMAH system can save shooters time during practice, as the shot results are displayed directly at the shooter's location, without the shooter having to walk up to the target to view hits and misses.
[0003] To improve the accuracy of the LOMAH system, the target platform is also equipped with a temperature sensor. As is well known in the art, the speed of sound in air varies with the air temperature, so it is important to know the ambient temperature when making calculations in order to obtain a correct hit and miss picture. However, there are also disadvantages in using a temperature sensor if it does not display the correct ambient temperature value. The temperature sensor is set on the target platform most of the time, and since the target platform is located in an open area, the target platform is often exposed to direct sunlight. In this case, the error in measuring the ambient temperature is usually large and has a significant impact on the calculation of hits and misses. One solution may be to place the temperature sensor in another more protected location to avoid direct sunlight. This makes the system more complicated and also increases the time required to set up the system. In addition, when the sun moves, it is usually necessary to move the temperature sensor as well.
[0004] Therefore, there is a need to further improve the accuracy of LOMAH systems while also improving the ease of use of such systems. Summary of the invention
[0005] The purpose of this application is to improve the accuracy of the LOMAH system without using temperature sensors, and to provide great flexibility in the configuration, arrangement and number of sensors in the target platform of the LOMAH system.
[0006] This is achieved by a three-dimensional LOMAH system for locating the shooting of a supersonic bullet, the system including a target platform, a processor and a memory disposed in the target platform, and a sensor array disposed on an upper surface of the target platform, the sensor array including at least four acoustic sensors arranged in two rows, the memory including instructions, which when executed by the processor, cause the three-dimensional LOMAH system to detect shooting information of a shot generated by a shooter and passing near the target platform using the acoustic sensor, record the detection time of each acoustic sensor, and create a time vector for each combination of two acoustic sensors based on the recorded detection time A set of time vectors is input into a target calculation module trained using a machine learning (ML) model, the model having been trained with a large amount of training data using random input data, the target calculation model being configured to create a set of time vectors for each combination of two sensors based on the random input data and associated with actual hits and misses of the shots in the training data, the target calculation module being configurable to use a set of training data including a starting point, velocity, impact angle, and hit coordinates of a supersonic bullet: calculating the impact and trajectory of the bullet based on the input time vector set, and outputting the impact and trajectory of the bullet on a display connected to the LOMAH system.
[0007] Although a variety of configurations, arrangements, and different numbers of sensors are described above, many other configurations, arrangements, and numbers of sensors are possible. One advantage of the present application is that the target computing platform can be configured in a variety of different ways because the calculations performed on the time vectors created for each two acoustic sensor combinations to determine the impact and trajectory of the fired bullets are based on the same configuration and settings used when training the LOMAH system. Therefore, this provides a great deal of flexibility in designing the LOMAH system because the configuration, arrangement, and number of sensors can be easily adapted to the specific purpose to be performed by the LOMAH system.
[0008] In a preferred embodiment of the three-dimensional LOMAH system, the target calculation module can be configured to calculate the hit or miss, the speed of the supersonic bullet, and the impact angle in the x direction and the impact angle in the y direction in a three-dimensional space defined in a standard right-handed Cartesian coordinate system based on the created time vector set.
[0009] In another preferred embodiment of the three-dimensional LOMAH system, the target calculation module can also be configured to calculate the ambient temperature by incorporating the shooter's position and the ambient temperature into the random input data.
[0010] In yet another preferred embodiment of the three-dimensional LOMAH system, the target calculation module may be configured to calculate the impact angle within a range of ±30 degrees in the x-direction and the impact angle within a range of ±15 degrees in the y-direction.
[0011] In another exemplary embodiment of a three-dimensional LOMAH system, the sensor array includes at least six sensors arranged in two rows.
[0012] In another exemplary embodiment of a three-dimensional LOMAH system, the sensor array includes eight sensors arranged in three rows, namely, a first row, a second row, and a middle row arranged between the first row and the second row, the middle row including two sensors.
[0013] In another exemplary embodiment of the three-dimensional LOMAH system, the two sensors in the middle row are arranged to be offset by a certain distance in the horizontal direction relative to the sensors in the first row and the second row. Preferably, the distance between the two sensors in the middle row is half of the distance between the sensors in the first row and the second row.
[0014] In an exemplary embodiment of a three-dimensional LOMAH system, each sensor in the sensor array is arranged at an angle in the range of 30-70 degrees relative to the horizontal extension of the target platform. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The present application will now be described by way of example and with reference to the accompanying drawings, in which: Figure 1 A perspective view of the LOMAH system target platform is shown. Figure 2 A side view of a portion of the front of the target platform is shown, indicating the angle (α) at which the acoustic sensor extends relative to the horizontal of the target platform. Figure 3 A schematic block diagram of an embodiment of a LOMAH system including a target platform and a display is shown. DETAILED DESCRIPTION
[0016] The present application is described in detail below.
[0017] Now go to Figure 1 , one embodiment of a target platform 30 of a LOMAH system 100 will be described. The LOMAH system 100 in this embodiment is a three-dimensional LOMAH system, i.e., it is not only able to detect shots in the x and y planes, but can also calculate the angle at which the shot hit the target. Figure 1 In , the three-dimensional space is defined in a standard right-handed Cartesian coordinate system. Another advantage of the LOMAH system according to the present application is that it is also able to calculate the ambient temperature without a temperature sensor, as will be explained later.
[0018] The target platform 30 is provided with a target computing module 40, which includes a processor 2 and a memory 4. Figure 3As shown. A sensor array is also provided on the upper surface of the target platform 30, and the sensor array includes a plurality of acoustic sensors 6, 8, 10, 12, 14, 16, 18, 20. The number of acoustic sensors is at least four, namely, acoustic sensors 6, 8, 10, 12, wherein the acoustic sensors 6, 8, 10, 12 are arranged in two rows. Different configurations and the number and number of rows of acoustic sensors will be further discussed below.
[0019] The memory 4 includes instructions that, when executed by the processor 2, cause the three-dimensional LOMAH system 100 to detect shooting information emitted by the shooter and passing near the target platform 30 through the acoustic sensors 6, 8, 10, and 12. When the sound or shock wave reaches above a certain threshold, the detection of the acoustic sensors 6, 8, 10, and 12 is triggered. Those skilled in the art should be able to determine the threshold level based on the surrounding environment and the settings of the LOMAH system 100 (such as the type of shooting, etc.). The target calculation module 40 records the detection time of each acoustic sensor 6, 8, 10, and 12. Then, the target calculation module 40 uses the detection time to create a time vector set for each combination of two acoustic sensors 6-8; 6-10; 6-12; 8-10; 8-12; 10-12. The time vector set is input to the target calculation module 40 to calculate the impact and trajectory of the bullet based on the input time vector set.
[0020] The target calculation module 40 has been trained using a machine learning (ML) model that has been trained with a large amount of training data. For any given configuration of sensors on the target platform 30, the target calculation model 40 is trained using random input data including ambient temperature and shooter position. Based on the input data, the target calculation module 40 creates a time vector set for each combination of two sensors, and then associates it with the actual hits and misses in the training data. The final result is that the target calculation module 40 can determine the hit or miss in three-dimensional space based on the created time vector set, that is, the hit or miss in the x, y and z directions of the standard right-handed Cartesian coordinate system. Since the hit is determined in three-dimensional space, the speed of the bullet can also be calculated. In addition, the target calculation module 40 can also determine the impact angle θ in the x direction and the impact angle Φ in the y direction in combination with the ambient temperature. Therefore, by using the target calculation module of the present application, the hit of the shooting can be determined very accurately without using the ambient temperature when performing the calculation.
[0021] It should be understood that the detection area of the LOMAH system 100 may change, and the ability to detect rough misses may also change, depending on the number of sensors and their configuration. In general, the ability to detect rough misses increases with the number of sensors and the field of view of the sensors. For a typical target calculation module 40 according to the present application, the outputs are the x, y, and z coordinates in three-dimensional space above the target platform, the impact angle Θ in the x direction within the ±30 degree field of view, the impact angle Φ in the y direction within the ±15 degree field of view, and the ambient temperature. By increasing the amount of training data, the field of view of the impact angle can of course also be increased (if necessary).
[0022] As mentioned above, the number of acoustic sensors 6, 8, 10, 12 may vary and may be configured in different ways. Figure 1 In the illustrated embodiment, the sensor array includes eight sensors 6, 8, 10, 12, 14, 16, 18, 20, which are arranged in three rows, namely a first row, a second row, and an intermediate row arranged between the first row and the second row. The first row and the second row include three acoustic sensors 6, 18, 10 and 8, 16, 12, respectively, and the intermediate row includes two sensors 14, 20. In a preferred embodiment, the two sensors 14, 20 in the intermediate row can be arranged to be offset in the horizontal direction relative to the sensors in the first row and the second row. The two sensors 14, 20 in the intermediate row can be arranged to be offset in the horizontal direction by a distance that is half the distance between the sensors 6, 8, 10, 12, 16, 18 in the first row and the second row.
[0023] In another embodiment, Figure 3 As shown, there are four acoustic sensors 6, 8, 10, 12 arranged in two rows, with the first row including acoustic sensors 6, 10 and the second row including acoustic sensors 8, 12. In an alternative embodiment, the sensor array includes six sensors 6, 8, 10, 12, 16, 18 arranged in two rows, with the first row including acoustic sensors 6, 18, 10 and the second row including acoustic sensors 8, 16, 12. Acoustic sensors 16, 18 are shown in dashed lines because they are optional.
[0024] Now go to Figure 2 , the placement and orientation of each acoustic sensor will be discussed further, Figure 2The acoustic sensor 16 is taken as an example. Each acoustic sensor 6, 8, 10, 12, 14, 16, 18, 20 in the sensor array can be arranged at an angle α in the range of 0-90 degrees relative to the horizontal extension of the target platform 30. However, the acoustic sensors 6, 8, 10, 12, 14, 16, 18, 20 in the sensor array are preferably arranged in the range of 30-70 degrees. For all acoustic sensors 6, 8, 10, 12, 14, 16, 18, 20, different acoustic sensors can have the same angle α, but it can also vary according to the embodiment. The advantage of having a certain angle α with the horizontal extension direction of the target platform 30 is that rainwater slides off the acoustic sensor more easily. Another advantage is that when the acoustic sensors are arranged at a certain angle, the target area can be increased.
[0025] Although a variety of configurations, arrangements, and different numbers of sensors are described above, many other configurations, arrangements, and numbers of sensors are possible. One advantage of the present application is that the target computing platform 40 can be configured in a variety of different ways because, for each two acoustic sensor combinations, the calculations performed on the created time vectors to determine the impact and trajectory of the fired bullets are based on the same configuration and settings used when the LOMAH system was trained. Therefore, this provides a great deal of flexibility in designing the LOMAH system because the configuration, arrangement, and number of sensors can be easily adapted to the specific purpose to be performed by the LOMAH system.
Claims
1. A three-dimensional miss and hit location (LOMAH) system (100) for locating shots from supersonic bullets, the three-dimensional miss and hit location (LOMAH) system (100) comprising a target platform (30), the target platform (30) being provided with a processor (2) and a memory (4), and a sensor array being provided on an upper surface of the target platform (30), the sensor array comprising at least four acoustic sensors (6, 8, 10, 12) arranged in two rows, the memory (4) comprising instructions, which, when executed by the processor (2), cause the three-dimensional miss and hit location system (100) to: - detecting, by means of the acoustic sensors (6, 8, 10, 12), shooting information of shots generated by a shooter and passing near the target platform (30), - record the detection time of each acoustic sensor (6, 8, 10, 12), - creating a set of time vectors for each combination of two acoustic sensors (6-8; 6-10; 6-12; 8-10; 8-12; 10-12) based on the recorded detection times, and - inputting the time vector set into a target calculation module (40), the target calculation module (40) being trained using a machine learning model (ML), the machine learning model having been trained with a large amount of training data using random input data, the target calculation model (40) being configured to create the time vector set for each combination of two acoustic sensors and to associate actual hits and misses of shots in the training data based on the random input data, the target calculation module (40) being configurable to: using a training data set including the starting point, velocity, impact angle and hit coordinates of the supersonic bullet: - calculating the impact and trajectory of the bullet based on the input set of time vectors, and - Outputting the bullet impact and trajectory on a display (50) connected to the three-dimensional miss and hit location system (100).
2. The three-dimensional miss and hit location system (100) according to claim 1, wherein: The target calculation module (40) may be configured to calculate a hit or miss, a speed of the supersonic bullet, an impact angle (θ) in the x direction, and an impact angle (Φ) in the y direction in a three-dimensional space defined in a standard right-handed Cartesian coordinate system based on the created time vector set.
3. The three-dimensional miss and hit location system (100) according to claim 1 or 2, wherein: The target calculation module (40) may also be configured to calculate the ambient temperature by incorporating the shooter's position and the ambient temperature into the random input data.
4. The three-dimensional miss and hit locating system (100) according to any one of claims 1 to 3, wherein: The target calculation module (40) may be configured to calculate an impact angle (θ) within a range of ±30 degrees in the x-direction and an impact angle (Φ) within a range of ±15 degrees in the y-direction.
5. The three-dimensional miss and hit location system (100) according to any one of claims 1 to 4, wherein: The sensor array includes at least six acoustic sensors (6, 8, 10, 12, 16, 18), and the at least six acoustic sensors (6, 8, 10, 12, 16, 18) are arranged in two rows.
6. The three-dimensional miss and hit location system (100) according to any one of claims 1 to 5, wherein: The sensor array includes eight acoustic sensors (6, 8, 10, 12, 14, 16, 18, 20), and the eight acoustic sensors (6, 8, 10, 12, 14, 16, 18, 20) are arranged in three rows, namely a first row, a second row and a middle row, the middle row is arranged between the first row and the second row, and the middle row includes two acoustic sensors (14, 20).
7. The three-dimensional miss and hit location system (100) according to claim 6, wherein: The two acoustic sensors (14, 20) of the middle row are arranged to be offset in the horizontal direction relative to the acoustic sensors of the first and second rows.
8. The three-dimensional miss and hit location system (100) according to claim 7, wherein: The two acoustic sensors (14, 20) of the middle row are arranged to be offset in the horizontal direction by a distance which is half the distance of the acoustic sensors (6, 8, 10, 12, 16, 18) in the first and second rows.
9. The three-dimensional miss and hit location system (100) according to any one of claims 1 to 8, wherein: Each of the acoustic sensors (6, 8, 10, 12, 14, 16, 18, 20) in the sensor array is arranged to extend at an angle (α) in the range of 30 to 70 degrees relative to the horizontal of the target platform (30).