WO2020232669A1 - 打击检测方法、设备、可移动平台及计算机可读存储介质 - Google Patents

打击检测方法、设备、可移动平台及计算机可读存储介质 Download PDF

Info

Publication number
WO2020232669A1
WO2020232669A1 PCT/CN2019/087972 CN2019087972W WO2020232669A1 WO 2020232669 A1 WO2020232669 A1 WO 2020232669A1 CN 2019087972 W CN2019087972 W CN 2019087972W WO 2020232669 A1 WO2020232669 A1 WO 2020232669A1
Authority
WO
WIPO (PCT)
Prior art keywords
sound signal
preset
hit
detection device
algorithm
Prior art date
Application number
PCT/CN2019/087972
Other languages
English (en)
French (fr)
Inventor
张志鹏
林喜挺
李亮
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to CN201980012138.4A priority Critical patent/CN111699368A/zh
Priority to PCT/CN2019/087972 priority patent/WO2020232669A1/zh
Publication of WO2020232669A1 publication Critical patent/WO2020232669A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H11/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties
    • G01H11/06—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties by electric means
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
    • A63H17/00—Toy vehicles, e.g. with self-drive; ; Cranes, winches or the like; Accessories therefor
    • A63H17/26—Details; Accessories
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/16—Receiving elements for seismic signals; Arrangements or adaptations of receiving elements
    • G01V1/18—Receiving elements, e.g. seismometer, geophone or torque detectors, for localised single point measurements

Definitions

  • the embodiments of the present invention relate to the field of sound detection, and in particular to a method, equipment, removable platform, and computer-readable storage medium for strike detection.
  • the accelerometer In order to detect whether the car is currently hit, the accelerometer is usually fixedly connected to the measured object of the car, and the accelerometer is used to detect whether the movable platform is currently hit. For example, when a certain magnitude of vibration is detected, it is considered as being hit. Blow.
  • the accelerometer has the problem of measuring over-range.
  • the accelerometer on the car is limited by the volume and the measurement range is limited, and the instantaneous acceleration generated when the car is hit may easily exceed the measurement limit and make it impossible to measure.
  • the embodiments of the present invention provide a strike detection method, equipment, a removable platform, and a computer-readable storage medium to solve the technical problem that the detection result of the existing strike detection algorithm is not accurate enough.
  • the first aspect of the embodiments of the present invention is to provide a blow detection method, which is applied to a blow detection device, the blow detection device is used to be fixedly installed inside the object to be measured, and the upper cover of the blow detection device is provided with an annular protrusion , The annular protrusion is used to form a cavity with the measured object; the method includes:
  • the sound signal is detected through a preset strike detection algorithm to determine whether the measured object is hit.
  • the second aspect of the embodiments of the present invention is to provide a strike detection device, which is used to be fixedly installed inside the object to be measured on a movable platform, and the upper cover of the strike detection device is provided with an annular protrusion, so The annular protrusion is used to form a cavity with the object to be measured; a microphone is also provided in the strike detection device, and the microphone is used to obtain sound signals.
  • the third aspect of the embodiments of the present invention is to provide a movable platform in which the object to be measured and the strike detection device as described in the second aspect are arranged.
  • the fourth aspect of the embodiments of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method described in the first aspect.
  • the strike detection method, equipment, movable platform, and computer-readable storage medium provided in this embodiment.
  • the strike detection device is arranged inside the object to be measured.
  • a ring of annular protrusions is provided on the upper cover of the strike detection device, so that it can interact with the victim.
  • a cavity is formed between the measured objects.
  • the shock detection device is also provided with a microphone, and the sound signal can be obtained through the microphone. Since the sound signal is obtained from the cavity, the quality of the sound signal can be improved, and the sensitivity of the sound signal capture can be improved. Further, the sound signal can be detected through a preset strike detection algorithm, and it is determined whether the detected object is currently being struck according to the detection result. Thereby, it can be accurately determined whether the object under test is currently hit, and the accuracy of hit detection can be improved.
  • FIG. 2 is a schematic flowchart of a strike detection method provided by Embodiment 2 of the present invention.
  • FIG. 3 is a schematic flowchart of a strike detection method provided by Embodiment 3 of the present invention.
  • FIG. 5 is a schematic flowchart of a strike detection method provided by Embodiment 5 of the present invention.
  • FIG. 6 is a schematic structural diagram of a strike detection device provided by Embodiment 6 of the present invention.
  • FIG. 7 is a schematic structural diagram of a strike detection device provided by Embodiment 7 of the present invention.
  • a component when a component is said to be “fixed to” another component, it can be directly on the other component or a central component may also exist. When a component is considered to be “connected” to another component, it can be directly connected to another component or there may be a centered component at the same time.
  • the present invention provides a strike detection method, equipment, removable platform and computer-readable storage medium. It should be noted that the strike detection method, equipment, removable platform, and computer-readable storage medium provided by the present invention can be applied to any strike detection scenario.
  • FIG. 1 is a schematic flow chart of the striking detection method provided in the first embodiment of the present invention.
  • the striking method provided in this embodiment can be applied to a striking detection device, which can be fixedly installed on the inner side of the object to be measured, and on the striking detection device
  • the cover is provided with an annular protrusion, which is used to form a cavity with the object to be measured; as shown in FIG. 1, the method includes:
  • Step 101 Acquire a sound signal through a microphone set in the strike detection device
  • Step 102 Detect the sound signal through a preset strike detection algorithm, and determine whether the measured object is hit.
  • the execution subject of this embodiment is a strike detection device.
  • the strike detection equipment provided in this embodiment is fixedly installed on the inside of the object under test, where the object under test can be a preset armor plate on a movable platform, or a housing of a movable platform, or any type that needs to be hit.
  • the detected hardware devices are not limited in the present invention.
  • the impact detection device is provided with an upper cover, a detection circuit board and a lower cover.
  • the upper cover is provided with a ring of annular protrusions. Therefore, the annular protrusions can form a cavity with the object to be measured, so that the When an object is hit or passes by an obstacle and generates vibration, the sound signal generated by the vibration can be transmitted through the cavity.
  • the movable platform Since the cavity is closed to the outside world, the diffusion of the sound signal can be reduced, the signal quality of the sound signal can be improved, and the sensitivity of vibration capture can be improved. Since in practical applications, there are many situations that will cause the movable platform to generate vibrations and sound signals. Taking the measured object as the armor plate on the movable platform, for example, it may be physically attacked on the armor plate during the game. It will cause the armor plate to vibrate and generate sound signals. In addition, the movable platform may pass obstacles during the movement, which will cause the movable platform to bump and generate sound signals. In a multi-machine combat game, you can perform operations such as scoring based on the blow received. At this time, the vibration of the armor plate caused by the obstacle may affect the game result.
  • the number of microphones can be multiple.
  • the microphone array can be used to collect the sound signal, and the difference of multiple microphones can be used to filter the noise to further improve the signal quality of the sound signal.
  • the blow detection device is arranged inside the object to be measured, and a ring of annular protrusions is provided on the upper cover of the blow detection device, thereby forming a cavity with the object to be measured.
  • the shock detection device is also provided with a microphone, and the sound signal can be obtained through the microphone. Since the sound signal is obtained from the cavity, the quality of the sound signal can be improved, and the sensitivity of the sound signal capture can be improved. Further, the sound signal can be detected through a preset strike detection algorithm, and it is determined whether the detected object is currently being struck according to the detection result. Thereby, it can be accurately determined whether the object under test is currently hit, and the accuracy of hit detection can be improved.
  • the acquiring a sound signal through a microphone provided in the strike detection device includes:
  • the object to be measured when the object to be measured is hit, the object to be measured is vibrated, thereby being able to generate a sound signal. Since the annular protrusion can form a cavity with the object to be measured, when the object to be measured is hit or passes by an obstacle and generates vibration, the sound signal generated by the vibration can be transmitted through the cavity. Since the cavity is closed to the outside world, the sound signal will not diffuse and the signal quality of the sound signal will be improved. Therefore, in order to improve the signal quality of the sound signal, the sound signal propagated in the cavity can be acquired through a microphone.
  • the strike detection method provided in this embodiment acquires the sound signal propagated in the cavity through a microphone, so that the quality of the sound signal can be improved, and the accuracy of the strike detection can be improved.
  • a sound-transmitting hole is also provided on the upper cover of the percussion detection device corresponding to the microphone. Therefore, when the object to be measured vibrates to generate a sound signal, the sound signal in the cavity can be transmitted to the microphone through the sound hole, so that the microphone can acquire the sound signal generated by the vibration when the object to be measured vibrates.
  • the number and size of the sound-permeable holes can be set according to actual application requirements, and the present invention is not limited here.
  • the strike detection method provided in this embodiment can improve the signal quality of the sound signal by setting a sound hole on the strike detection device at a position corresponding to the microphone, and collecting sound signals through the microphone when the object to be measured vibrates. Improve the accuracy of strike detection.
  • the detecting the sound signal by using a preset strike detection algorithm includes:
  • Step 203 Detect the target signal corresponding to the sound signal through a preset strike detection algorithm.
  • the microphone collects the sound signal
  • the sound signal needs to be converted into a voltage analog signal.
  • any signal conversion method can be used to realize the conversion of the sound signal, and the present invention is not limited herein. Since there are signals that are useless for strike detection in the collected sound signals, in order to improve the efficiency of strike detection analysis and improve the accuracy of strike detection analysis, it is necessary to filter the voltage analog signal through a preset filter to obtain the need for strike detection Target signal. Further, the target signal can be detected by a preset strike detection algorithm to obtain the detection result.
  • the strike detection method provided in this embodiment converts the sound signal into a voltage analog signal and filters the voltage analog to filter out signals that are useless for strike detection to obtain a target signal and perform strike detection on the target signal, thereby enabling further Improve the accuracy of strike detection.
  • signals that are useless for strike detection are high-frequency components. Therefore, the high-frequency components in the voltage analog signals can be filtered through a high-pass filter to obtain a target signal containing only low-frequency components. Since some low-frequency components are filtered through the high-pass filter, the detection efficiency of the remaining part of the signal is higher, and after the useless high-frequency components are removed, the detection result is more accurate.
  • the strike detection method provided in this embodiment uses a high-pass filter to filter out high-frequency components in the voltage analog signal to obtain a target signal, thereby improving the accuracy of strike detection.
  • the detecting the sound signal through a preset strike detection algorithm to determine whether the measured object has been hit includes:
  • the sound signal is detected through a preset recognition algorithm, and it is determined whether the measured object is hit.
  • the sound signal in order to detect whether the detected object has been hit, the sound signal may be detected through a preset recognition algorithm to obtain the detection result.
  • a recognition algorithm that can analyze the sound signal can be used for detection.
  • it can use a trained neural network model for detection, or a trained decision tree algorithm for detection.
  • the present invention is not limited here.
  • the recognition algorithm is a decision tree algorithm.
  • the identification algorithm is specifically a decision tree algorithm. In addition, it can also be any other identification algorithm, and the present invention is not limited here.
  • the strike detection method provided in this embodiment detects the sound signal through a preset recognition algorithm, so that it can accurately determine whether the detected object is hit.
  • Fig. 3 is a schematic flow chart of the strike detection method provided by the third embodiment of the present invention.
  • the sound signal is detected by the preset recognition algorithm, and the Whether the object under test has been hit, including:
  • Step 301 Acquire at least one feature information corresponding to the sound signal
  • Step 302 Determine whether each of the characteristic information meets a preset first condition through a preset recognition algorithm, and obtain a judgment result;
  • Step 303 Determine whether the measured object is hit according to the judgment result.
  • the sound signal in order to detect whether the detected object has been hit, the sound signal may be detected through a preset recognition algorithm to obtain the detection result.
  • the feature information includes at least one of the following: energy information, peak information, tail information, and attenuation information corresponding to the sound signal.
  • the feature information may also include any information describing the characteristics of the sound signal, and the present invention is not limited herein.
  • the recognition algorithm can be trained through preset conditions. Accordingly, after at least one feature information in the sound signal is acquired, for each feature information, the feature information can be identified by the recognition algorithm.
  • the recognition algorithm learns in advance that when the sound signal is hit, the energy information of the sound signal is in the first range, and the peak information is in the second range. If the information is in the third range, if the decision tree algorithm detects that the values corresponding to the three characteristic information of the sound signal are within the above ranges, it can output the information that the measured object has been hit, otherwise, it can be determined that the measured object has not been hit ,
  • the vibration may be caused by the movable platform passing through obstacles.
  • the strike detection device acquires at least one characteristic information of a sound signal and detects the characteristic information through a recognition algorithm, so as to accurately determine whether the object under test has been struck, and further improve the accuracy of strike detection .
  • the determining whether the measured object is hit according to the judgment result includes:
  • the sound signal is detected by the recognition algorithm, it can be determined whether the detected object is hit according to the detection result. Specifically, if each feature information satisfies the preset first condition, it can be determined that the object under test has been hit. Conversely, if any feature information does not meet the preset first condition, it can be determined that the object under test has not been hit. Blow.
  • the rule for determining whether the object to be measured is hit according to the judgment result can be adjusted according to the requirements in actual applications, and the present invention is not limited here. For example, the rule may be that if the ratio of the feature information satisfying the preset condition to the total feature information is greater than the preset threshold, it can be determined that the object under test has been hit, otherwise, it can be determined that the object under test has not been hit.
  • the strike detection method provided in this embodiment determines that the measured object is hit if all the characteristic information meets the preset first condition, and if any characteristic information does not meet the preset first condition, then the measured object is determined Without being hit, it can accurately determine whether the measured object is hit, which improves the accuracy of hit detection.
  • the detecting the sound signal through a preset strike detection algorithm to determine whether the measured object has been hit includes:
  • the sound signal is detected through a preset neural network algorithm, and it is determined whether the measured object is hit.
  • the preset attack detection algorithm may be a neural network algorithm. Specifically, after the sound signal is acquired, the sound signal can also be detected through a preset neural network algorithm to determine whether the measured object is hit.
  • the detecting the sound signal through a preset neural network algorithm to determine whether the measured object has been hit includes:
  • the sound signal is input into a preset neural network algorithm, and it is determined whether the measured object is hit according to the output result of the neural network algorithm.
  • the sound signal after the sound signal is acquired, the sound signal can be input to a preset neural network algorithm, the output result of the neural network algorithm is acquired, and whether the object under test is hit is determined according to the output result.
  • the strike detection method provided in this embodiment implements the detection of sound signals through a preset neural network algorithm, thereby improving the accuracy of strike detection.
  • Fig. 4 is a schematic flow chart of the strike detection method provided by the fourth embodiment of the present invention.
  • the sound signal is detected by a preset neural network algorithm, Before determining whether the measured object is hit, it also includes:
  • Step 401 Obtain a preset sound signal to be processed
  • Step 402 Mark the sound signal to be processed according to whether the sound signal to be processed is generated after being hit by the object under test to obtain data to be trained;
  • Step 403 Train a preset neural network algorithm to be trained by using the training data to obtain the preset neural network algorithm.
  • the neural network in order to detect the sound signal through the neural network algorithm, the neural network needs to be trained first. Specifically, the sound signal to be processed needs to be acquired first, for each sound signal to be processed, it is determined whether the sound signal to be processed is generated by a blow, and the sound signal to be processed is marked according to the result to obtain the data to be trained. Further, the pre-established neural network algorithm to be trained can be trained according to the data to be trained to obtain the neural network algorithm. Since the neural network algorithm is obtained through the training of the marked voice signal to be processed, the neural network algorithm can accurately detect whether the sound signal is generated by a blow.
  • the strike detection algorithm provided in this embodiment trains the preset neural network algorithm to be trained through the data to be trained, so that the trained neural network algorithm can be obtained, which provides a basis for strike detection.
  • FIG. 5 is a schematic flow chart of the strike detection method provided by the fifth embodiment of the present invention. Based on any of the above embodiments, as shown in FIG. 5, after the sound signal is acquired by the microphone provided in the strike detection device ,Also includes:
  • Step 501 Divide the sound signal into at least one sound signal segment according to a preset time interval.
  • the detecting the sound signal by using a preset attack detection algorithm to determine whether the detected object has been attacked includes:
  • Step 502 Detect the sound signal segment through a preset strike detection algorithm, and determine whether the measured object is hit.
  • the sound signal in order to improve the real-time performance of the game during the game battle, it is necessary to detect the sound signal in time.
  • the sound signal may be divided into at least one sound signal segment according to a preset time interval. For each sound signal segment, the sound signal segment is detected by a preset strike detection algorithm to determine whether the detected object is hit.
  • the processing efficiency is higher.
  • the strike detection algorithm provided in this embodiment divides the acquired sound signal to detect the segmented sound signal segment, which facilitates subsequent data processing and statistics, and can improve the efficiency of strike detection.
  • the detecting the sound signal passage through a preset strike detection algorithm to determine whether the measured object has been hit includes:
  • For each sound signal segment determine whether the sound signal segment includes a valid sound signal
  • the sound signal collected by the microphone may not be completely generated by the vibration of the measured object.
  • the vibration of a device rigidly connected to the measured object may also be collected by the microphone, which is far away from the measured object.
  • the background sound may also be collected. Therefore, in order to further improve the signal quality of the sound signal, it is necessary to filter the sound signal. Specifically, for each sound signal segment, it is determined whether the sound signal segment includes a valid sound signal, and if it is included, the sound signal segment can be detected to determine whether the measured object is hit. Conversely, if the sound segment does not include a valid sound signal, it means that the sound signal segment is caused by noise or vibration of other devices. At this time, in order to improve the accuracy of strike detection and reduce the processing pressure of the processor, the sound signal can be discarded paragraph.
  • the strike detection method provided in this embodiment processes the sound signal segments by determining whether valid sound signals are included in each sound signal segment, so as to improve the accuracy of the strike detection and reduce the calculation pressure of the processor.
  • detecting the sound signal segment by using a preset strike detection algorithm to determine whether the measured object has been struck includes:
  • the sound signal segment includes a valid sound signal, use the sound signal segment as an initial segment, and use the initial segment to the last sound signal segment in the sound signal as the sound signal to be detected;
  • the sound signal to be detected is detected by a preset attack detection algorithm, and it is determined whether the detected object is attacked.
  • the sound signal segment if it is detected that the sound signal segment includes a valid sound signal, it means that the sound signal segment is generated by the vibration of the object to be measured, and at this time, the sound signal segment can be hit detection.
  • the sound signal may be used as the initial paragraph, and the sound signal paragraph from the initial paragraph to the last sound signal in the sound signal may be used as the sound signal to be detected.
  • the sound signal to be detected is detected through a preset strike detection algorithm. Since the sound signal to be detected is composed of sound signal segments containing valid sound signals, performing strike detection on the sound signal to be detected can effectively improve the accuracy of strike detection.
  • the strike detection algorithm uses the sound signal paragraph as the initial paragraph if the sound signal segment includes a valid sound signal, and uses the initial paragraph to the last sound signal paragraph in the sound signal as the sound signal to be detected.
  • the strike detection algorithm detects the sound signal to be detected to determine whether the object under test is hit, which can effectively improve the accuracy of strike detection.
  • the determining whether a valid sound signal is included in the sound signal paragraph includes:
  • the sound signal paragraph includes a valid sound signal based on the paragraph characteristics of the sound signal paragraph.
  • the paragraph feature may specifically include features such as signal energy and zero-crossing rate.
  • it may also include other features that can determine whether the sound signal is valid, and the present invention is not limited herein. Specifically, it can be determined whether the signal energy and the zero-crossing rate corresponding to the sound signal segment meet the preset second condition, and if they are satisfied, it can be determined that the sound signal segment includes a valid sound signal. On the contrary, if it is not satisfied, it can be determined that the sound signal segment does not include a valid sound signal, and in this case, the sound signal segment can be discarded.
  • the strike detection algorithm determines whether the signal energy and the zero-crossing rate corresponding to the sound signal segment meet the preset second condition, so as to effectively determine whether the sound signal segment includes a valid sound signal. Detection accuracy provides the basis.
  • the method further includes:
  • the analyzed strike information can be sent to a control terminal that is communicatively connected to a movable platform provided with strike detection equipment and the object under test.
  • the control terminal communicates and connects with the movable platform through a preset connection mode, thereby enabling information interaction.
  • the control terminal determines that the measured object has been hit, it can broadcast the current battle state, and in addition, can perform operations such as scoring based on the hit information received.
  • the strike detection method provided in this embodiment sends strike information to the control terminal communicatively connected to the movable platform provided with the measured object if it is determined that the object under test has been strikes, so that the control terminal can check the current battle state based on the strike information. Broadcasting, so as to accurately know the battle information, improve the user's game experience.
  • Fig. 6 is a schematic structural diagram of a strike detection device according to the sixth embodiment of the present invention. As shown in Fig. 6, the strike detection device 1 is used to be fixedly installed inside the object under test on a movable platform, and includes:
  • annular protrusion 3 is provided on the exterior of the upper cover 1, and the annular protrusion 3 is used to form a cavity with the measured object;
  • the bottom shell 5 forms a closed cavity with the upper cover 2;
  • the detection circuit board 6 is arranged in the closed cavity
  • the microphone 4 is arranged on the side of the detection circuit board 6 facing the upper cover 2 for acquiring sound signals.
  • the strike detection device 1 provided in this embodiment is provided with an upper cover 2, a bottom case 5 and a detection circuit board 6.
  • an annular protrusion 3 is provided on the outside of the upper cover 2, and the annular protrusion 3 may be a closed circular, square, elongated or other shape.
  • the shock detection device 1 is set on the side of the measured object, the annular protrusion 3 can form a cavity with the measured object, so that when the measured object is shocked and vibrates, the sound signal generated by the vibration can pass through the cavity To spread. Since the cavity is closed to the outside world, the sound signal diffusion can be reduced, the signal quality of the sound signal can be improved, and the sensitivity of capturing percussion sounds can be improved.
  • the annular protrusion 3 may be composed of an elastic material such as silica gel, etc., so that the annular protrusion 3 can better fit the object to be measured to form a closed cavity.
  • the annular protrusion 3 is made of elastic material. This can eliminate some noises while improving the sensitivity of capturing percussive sounds.
  • the strike detection device provided in this embodiment is fixedly installed on the inside of the object to be measured on a movable platform.
  • the upper cover of the strike detection device is provided with a ring-shaped protrusion that is used to form a cavity with the object to be tested.
  • the body; the strike detection device is also provided with a microphone, the microphone is used to obtain sound signals, so as to accurately achieve the acquisition of sound signals, and provide a basis for improving the accuracy of strike detection.
  • the upper cover 2 of the strike detection device is further provided with a sound transmission hole 7 at a position corresponding to the microphone 4, and The sound signal can be transmitted to the microphone 4 through the sound hole 7.
  • a sound-transmitting hole is also provided on the upper cover of the percussion detection device corresponding to the microphone. Therefore, when the object to be measured vibrates to generate a sound signal, the sound signal in the cavity can be transmitted to the microphone through the sound hole, so that the microphone can acquire the sound signal generated by the vibration when the object to be measured vibrates.
  • the sound transmission hole is at least one
  • the sound transmission holes are arranged in a honeycomb shape.
  • the number of sound transmission holes may be at least one, and those skilled in the art can set the number and arrangement shape of the sound transmission holes according to actual application requirements, and the present invention is not limited herein.
  • the arrangement shape of the sound transmission holes can be set according to the shape of the microphone; for example, when the microphones are circular, they can be arranged in a honeycomb shape.
  • the sound-through hole is provided at the position corresponding to the microphone on the upper cover, so that the sound signal in the cavity can be directly transmitted to the microphone, so as to achieve better acquisition of the sound signal.
  • the accuracy of strike detection provides the basis.
  • the shock detection device 1 is further provided with at least one shock-absorbing ball 8.
  • the microphone 4 is arranged in the The center of the shock-absorbing ball 8; when the number of the shock-absorbing ball 8 is multiple, the shock-absorbing ball 8 is evenly arranged under the microphone 4.
  • a shock-absorbing ball 8 may also be provided in the striking detection device 1.
  • the number of shock-absorbing balls 8 may be at least one.
  • the microphone 4 may be small in size, only one shock-absorbing ball 8 may be provided. Accordingly, the microphone 4 may be arranged at the center of the shock-absorbing ball 8.
  • the number of shock-absorbing balls can be multiple, or when the microphone is large in volume, multiple shock-absorbing balls can be used to evenly support the microphone, and the multiple shock-absorbing balls can be evenly arranged under the microphone.
  • the shock-absorbing ball may be a silicone shock-absorbing ball.
  • the shock detection device provided in this embodiment can effectively remove the noise caused by the vibration of the lower cover or the connection of the lower cover by setting the shock-absorbing ball in the shock detection device, and further concentrate the source of the sound signal to obtain better Test results.
  • FIG. 7 is a schematic structural diagram of a strike detection device according to Embodiment 7 of the present invention. Based on any of the foregoing embodiments, as shown in FIG. 7, the strike detection device includes a memory 71 and a processor 72;
  • the memory 71 is used to store program code; the processor 72 calls the program code, and when the program code is executed, is used to perform the following operations:
  • the sound signal is detected through a preset strike detection algorithm to determine whether the measured object is hit.
  • the blow detection device is arranged inside the object to be measured, and a ring of annular protrusions is provided on the upper cover of the blow detection device, thereby forming a cavity with the object to be measured.
  • the shock detection device is also provided with a microphone, and the sound signal can be obtained through the microphone. Since the sound signal is obtained from the cavity, the quality of the sound signal can be improved, and the sensitivity of the sound signal capture can be improved. Further, the sound signal can be detected through a preset strike detection algorithm, and it is determined whether the detected object is currently being struck according to the detection result. Thereby, it can be accurately determined whether the object under test is currently hit, and the accuracy of hit detection can be improved.
  • the processor when the processor acquires a sound signal through a microphone provided in the strike detection device, it is configured to:
  • the processor when the processor acquires the sound signal propagating in the cavity through the microphone, it is configured to:
  • the sound signal propagated in the cavity is acquired through the microphone.
  • the processor acquires the sound signal through the microphone provided in the strike detection device, it is further used for:
  • the processor detects the sound signal through the preset strike detection algorithm, it is configured to:
  • the target signal corresponding to the sound signal is detected through a preset strike detection algorithm.
  • the filter is a high-pass filter.
  • the processor when the processor detects the sound signal through a preset strike detection algorithm to determine whether the measured object has been struck, it is configured to:
  • the sound signal is detected through a preset recognition algorithm to determine whether the measured object is hit.
  • the identification algorithm is a decision tree algorithm.
  • the processor detects the sound signal through a preset recognition algorithm to determine whether the measured object is hit, it is used to:
  • the characteristic information includes at least one of the following: energy information, peak information, tail information, and attenuation information corresponding to the sound signal.
  • the processor is configured to: when determining whether the measured object has been hit according to the judgment result:
  • the processor when the processor detects the sound signal through a preset strike detection algorithm to determine whether the measured object has been struck, it is configured to:
  • the sound signal is detected through a preset neural network algorithm, and it is determined whether the measured object is hit.
  • the processor detects the sound signal through a preset neural network algorithm to determine whether the measured object is hit, it is used to:
  • the sound signal is input into a preset neural network algorithm, and it is determined whether the measured object is hit according to the output result of the neural network algorithm.
  • the processor is further configured to: before detecting the sound signal through a preset neural network algorithm to determine whether the measured object is hit,
  • the preset neural network algorithm to be trained is trained through the data to be trained to obtain the preset neural network algorithm.
  • the processor acquires the sound signal through the microphone provided in the strike detection device, it is further used for:
  • the processor detects the sound signal through a preset strike detection algorithm to determine whether the measured object is hit, it is used to:
  • the sound signal segment is detected by a preset attack detection algorithm to determine whether the object under test is attacked.
  • the processor when the processor detects the sound signal segment through a preset strike detection algorithm to determine whether the measured object has been struck, it is used to:
  • For each sound signal segment determine whether the sound signal segment includes a valid sound signal
  • the processor is configured to detect the sound signal segment by using a preset strike detection algorithm to determine whether the object under test has been struck if it is :
  • the sound signal segment includes a valid sound signal, use the sound signal segment as an initial segment, and use the initial segment to the last sound signal segment in the sound signal as the sound signal to be detected;
  • the sound signal to be detected is detected by a preset attack detection algorithm, and it is determined whether the detected object is attacked.
  • the processor is configured to: when determining whether a valid sound signal is included in the sound signal paragraph:
  • the processor is further configured to:
  • Yet another embodiment of the present invention also provides a movable platform in which the object to be measured and the strike detection device according to any of the above embodiments are provided.
  • Another embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the strike detection device as described in any of the foregoing embodiments.
  • this embodiment also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the strike detection method described in the foregoing embodiment.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.
  • the above-mentioned integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium.
  • the above-mentioned software functional unit is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor execute the method described in the various embodiments of the present invention. Part of the steps.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Environmental & Geological Engineering (AREA)
  • Geology (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)

Abstract

一种打击检测方法、设备、可移动平台及计算机可读存储介质，该打击检测设备用于固定安装在被测物体内侧，打击检测设备的上盖设置有环形凸起，环形凸起用于与被测物体形成腔体；该方法包括：通过设置于打击检测设备内的麦克风获取声音信号（101）；通过预设的打击检测算法对声音信号进行检测，确定被测物体是否受到打击（102）。通过在打击检测设备上设置环形凸起，从而环形凸起能够与被测物体之间形成腔体，能够提高麦克风获取的声音信号的信号质量，进而能够提高打击检测精准度。

Description

打击检测方法、设备、可移动平台及计算机可读存储介质 技术领域
本发明实施例涉及声音检测领域，尤其涉及一种打击检测方法、设备、可移动平台及计算机可读存储介质。
背景技术
智能化小车可以与预设区域内的其他智能化小车进行多车对战。为了实现多个智能化小车的多车对战，可以控制小车发射弹药对其他小车进行攻击，相应地，还可以检测小车当前是否受到打击。
为了检测小车当前是否受到打击，通常都是将加速计与小车的被测物体进行固定连接，通过加速计对可移动平台当前是否受到打击进行检测，例如当检测到发生一定幅度的震动时认为受到打击。
但是，加速度计存在测量超量程的问题。一般小车上所配的加速度计受体积限制，测量范围有限，而小车受到打击时产生的瞬时加速度可能很容易超过测量限度而导致无法测量。
发明内容
本发明实施例提供一种打击检测方法、设备、可移动平台及计算机可读存储介质，以解决现有的打击检测算法检测结果不够精准的技术问题。
本发明实施例的第一方面是提供一种打击检测方法，应用于打击检测设备，所述打击检测设备用于固定安装在被测物体内侧，所述打击检测设备的上盖设置有环形凸起，所述环形凸起用于与所述被测物体形成腔体；所述方法包括：
通过设置于所述打击检测设备内的麦克风获取声音信号；
通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
本发明实施例的第二方面是提供一种打击检测设备，所述打击检测设备用于固定安装在可移动平台的被测物体内侧，所述打击检测设备的上盖 设置有环形凸起，所述环形凸起用于与所述被测物体形成腔体；所述打击检测设备内还设置有麦克风，所述麦克风用于获取声音信号。
本发明实施例的第三方面是提供一种可移动平台，所述可移动平台中设置有被测物体以及如第二方面所述的打击检测设备。
本发明实施例的第四方面是提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行以实现第一方面所述的方法。
本实施例提供的打击检测方法、设备、可移动平台及计算机可读存储介质，打击检测设备设置在被测物体内侧，通过在打击检测设备的上盖设置一圈环形凸起，从而能够与被测物体之间形成腔体。此外，打击检测设备中还设置有麦克风，进而能够通过该麦克风获取声音信号，由于声音信号是从腔体中获取的，从而能够提高声音信号的质量，且提高声音信号捕捉的灵敏度。进一步地，可以通过预设的打击检测算法对该声音信号进行检测，根据检测结果确定该被测物体当前是否受到打击。从而能够精准地确定被测物体当前是否受到打击，提高打击检测的精准度。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例一提供的打击检测方法的流程示意图；
图2为本发明实施例二提供的打击检测方法的流程示意图；
图3为本发明实施例三提供的打击检测方法的流程示意图；
图4为本发明实施例四提供的打击检测方法的流程示意图；
图5为本发明实施例五提供的打击检测方法的流程示意图；
图6为本发明实施例六提供的打击检测设备的结构示意图；
图7为本发明实施例七提供的打击检测设备的结构示意图。
附图标记：
1：打击检测设备；  2：上盖；  3：环形凸起；
4：麦克风；        5：底壳；  6：检测电路板；
7：透音孔          8：减震球。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
需要说明的是，当组件被称为“固定于”另一个组件，它可以直接在另一个组件上或者也可以存在居中的组件。当一个组件被认为是“连接”另一个组件，它可以是直接连接到另一个组件或者可能同时存在居中组件。
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。本文所使用的术语“及/或”包括一个或多个相关的所列项目的任意的和所有的组合。
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
为了解决现有的打击检测算法检测结果不够精准的技术问题，本发明提供了一种打击检测方法、设备、可移动平台及计算机可读存储介质。需要说明的是，本发明提供的打击检测方法、设备、可移动平台及计算机可读存储介质可以应用在任意一种打击检测的场景中。
图1为本发明实施例一提供的打击检测方法的流程示意图，本实施例提供的打击方法能够应用于打击检测设备，该打击检测设备可以固定安装在被测物体内侧，该打击检测设备的上盖设置有环形凸起，该环形凸起用于与被测物体形成腔体；如图1所述，所述方法包括：
步骤101、通过设置于所述打击检测设备内的麦克风获取声音信号；
步骤102、通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
本实施例的执行主体为打击检测设备。本实施例提供的打击检测设备 固定安装在被测物体的内侧，其中，该被测物体可以为可移动平台上预设的装甲板，也可以为可移动平台外壳，或者任意一种需要进行打击检测的硬件设备，本发明在此不做限制。进一步地，该打击检测设备设置有上盖、检测电路板以及下盖，该上盖设置有一圈环形凸起，因此，该环形凸起能够与被测物体之间形成腔体，从而当被测物体受到打击或路过障碍而产生震动时，震动产生的声音信号能够通过该腔体进行传播。由于该腔体对外界而言是封闭的，从而可以减少声音信号的扩散，提高声音信号的信号质量，进一步地，能够提高震动捕捉的灵敏度。由于在实际应用中，有多种情况都会使可移动平台产生振动以及声音信号，以被测物体为可移动平台上的装甲板举例来说，在游戏里对战过程中物理打击到装甲板上可能会引起装甲板振动，产生声音信号，此外，可移动平台在移动过程中可能会经过障碍，此时会使得可移动平台颠簸而产生声音信号。而在多机战斗游戏过程中，可以根据受到的打击进行计分等操作，此时，经过障碍导致的装甲板振动则可能会影响游戏结果。为了实现对被测物体当前是否受到打击的检测，首先需要通过打击检测设备中预设的麦克风对声音信号进行获取，获取到声音信号之后，可以通过预设的打击检测算法对该声音信号进行检测，以确定该被测物体是否收到打击。此外，通过在上盖设置一圈凸起，与被测物体形成腔体，提高被测物体震动检测的灵敏度，从而对被测物体的外形要求不高，异形的被测物体也能够纳入检测范围。
作为一种可以实施的方式，麦克风的数量可以为多个。可以采用麦克风阵列采集声音信号，并且利用多麦克风的差分进行滤噪，进一步地提高声音信号的信号质量。
本实施例提供的打击检测方法，打击检测设备设置在被测物体内侧，通过在打击检测设备的上盖设置一圈环形凸起，从而能够与被测物体之间形成腔体。此外，打击检测设备中还设置有麦克风，进而能够通过该麦克风获取声音信号，由于声音信号是从腔体中获取的，从而能够提高声音信号的质量，且提高声音信号捕捉的灵敏度。进一步地，可以通过预设的打击检测算法对该声音信号进行检测，根据检测结果确定该被测物体当前是否受到打击。从而能够精准地确定被测物体当前是否受到打击，提高打击检测的精准度。
进一步地，在上述实施例的基础上，所述通过设置于所述打击检测设备内的麦克风获取声音信号，包括：
通过所述麦克风获取所述腔体中传播的声音信号。
在本实施例中，当被测物体受到打击时，被测物体发生震动，进而能够生成声音信号。由于环形凸起能够与被测物体之间形成腔体，从而当被测物体受到打击或路过障碍而产生震动时，震动产生的声音信号能够通过该腔体进行传播。由于该腔体与外界是封闭的，从而会导致声音信号不扩散，提高声音信号的信号质量。因此，为了提高声音信号的信号质量，可以通过麦克风获取腔体中传播的声音信号。
本实施例提供的打击检测方法，通过麦克风获取腔体中传播的声音信号，从而能够提高声音信号的质量，进而能够提高打击检测的精准度。
进一步地，在上述任一实施例的基础上，所述打击检测设备的上盖与所述麦克风对应的位置还设置有透音孔，所述腔体中的声音信号可以通过所述透音孔传播至所述麦克风；
相应地，所述通过所述麦克风获取所述腔体中传播的声音信号，包括：
当所述被测物体发生震动时，通过所述麦克风获取所述腔体中传播的声音信号。
在本实施例中，为了使麦克风能够获取到腔体中传播的声音信号，该打击检测设备的上盖与该麦克风对应的位置上还设置有透音孔。从而在被测物体发生震动产生声音信号时，腔体中的声音信号可以通过该透音孔传播至麦克风，从而麦克风能够在被测物体发生震动时，对震动产生的声音信号进行获取。需要说明的是，该透音孔的数量和大小可以根据实际应用中的需求进行设置，本发明在此不做限制。
本实施例提供的打击检测方法，通过在打击检测设备上与麦克风对应的位置设置透音孔，并在被测物体震动时，通过麦克风采集声音信号，从而能够提高声音信号的信号质量，进而能够提高打击检测的精准度。
图2为本发明实施例二提供的打击检测方法的流程示意图，在上述任一实施例的基础上，如图2所示，所述通过设置于所述打击检测设备内的麦克风获取声音信号之后，还包括：
步骤201、将所述声音信号转换为电压模拟信号；
步骤202、通过预设的滤波器对所述电压模拟信号进行滤波，获得目标信号；
相应地，所述通过预设的打击检测算法对所述声音信号进行检测，包括：
步骤203、通过预设的打击检测算法对所述声音信号对应的目标信号进行检测。
在本实施例中，麦克风采集到声音信号之后，为了实现对声音信号的分析与检测，需要将声音信号转换为电压模拟信号。需要说明的是，可以采用任意一种信号转换方法实现对声音信号的转换，本发明在此不做限制。由于采集到的声音信号中存在对打击检测无用的信号，因此，为了提高打击检测分析效率以及提高打击检测分析精准度，需要通过预设的滤波器对电压模拟信号进行滤波，获得需要进行打击检测的目标信号。进一步地，可以通过预设的打击检测算法对该目标信号进行检测，获得检测结果。
本实施例提供的打击检测方法，通过将声音信号转换为电压模拟信号，并对电压模拟进行滤波，滤除对打击检测无用的信号，获得目标信号，对目标信号进行打击检测，从而能够进一步地提高打击检测的精准度。
进一步地，在上述任一实施例的基础上，所述滤波器为高通滤波器。
在本实施例中，电压模拟信号中，对打击检测无用的信号为高频分量，因此，可以通过高通滤波器对电压模拟信号中的高频分量进行过滤，得到只包含低频分量的目标信号。由于通过高通滤波器滤除了部分低频分量，从而对剩余的部分信号进行检测效率较高，且去除了无用的高频分量之后，检测结果较为精准。
本实施例提供的打击检测方法，通过采用高通滤波器对电压模拟信号中的高频分量进行滤除，获得目标信号，从而能够提高打击检测的精度。
进一步地，在上述任一实施例的基础上，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
在本实施例中，为了实现对被测物体是否受到打击进行检测，可以通过预设的识别算法对声音信号进行检测，获得检测结果。需要说明的是， 可以采用任意一种能够实现对声音信号进行分析的识别算法进行检测，举例来说，其可以采用训练好的神经网络模型进行检测，也可以通过训练后的决策树算法进行检测，本发明在此不做限制。
具体地，在上述任一实施例的基础上，所述识别算法为决策树算法。
该识别算法具体以为决策树算法，此外，也可以为其他任意一种识别算法，本发明在此不做限制。
本实施例提供的打击检测方法，通过预设的识别算法对声音信号进行检测，从而能够精准地确定被测物体是否受到打击。
图3为本发明实施例三提供的打击检测方法的流程示意图，在上述任一实施例的基础上，如图3所示，所述通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
步骤301、获取所述声音信号对应的至少一个特征信息；
步骤302、通过预设的识别算法判断各所述特征信息是否符合预设的第一条件，获得判断结果；
步骤303、根据所述判断结果确定所述被测物体是否受到打击。
在本实施例中，为了实现对被测物体是否受到打击进行检测，可以通过预设的识别算法对声音信号进行检测，获得检测结果。具体地，首先可以获取声音信号对应的至少一个特征信息，其中，该特征信息包括如下至少一种：所述声音信号对应的能量信息、峰值信息、尾音信息、衰减程度信息。此外，该特征信息还可以包括任意一种描述声音信号特性的信息，本发明在此不做限制。为了实现对声音信号的检测，首先可以通过预设的条件对识别算法进行训练，相应地，获取到声音信号中的至少一个特征信息之后，针对每一个特征信息，可以通过识别算法将该特征信息与预设的条件进行比较，以确定该特征信息的值符合预设的第一条件，并根据判断结果确定被测物体是否受到打击。以实际应用举例来说，若当前特征信息为能量信息、峰值信息以及尾音信息，识别算法预先学习到受到打击时，声音信号的能量信息在第一范围内，峰值信息在第二范围内，尾音信息在第三范围内，若决策树算法检测到声音信号三个特征信息对应的值分别在上述范围内，则可以输出被测物体受到打击的信息，反之，则可以判定被测物体未受到打击，震动可能是由于可移动平台经过障碍产生的。
本实施例提供的打击检测装置，通过获取声音信号的至少一个特征信息，并通过识别算法对该特征信息进行检测，从而能够准确地判定被测物体是否受到打击，进一步地提高打击检测的精准度。
进一步地，在上述任一实施例的基础上，所述根据所述判断结果确定所述被测物体是否受到打击，包括：
若每一特征信息均满足预设的第一条件，则判定所述被测物体受到打击；
若任一特征信息不满足所述预设的第一条件，则判定所述被测物体未受到打击。
在本实施例中，通过识别算法对声音信号进行检测之后，可以根据检测结果确定被测物体是否受到打击。具体地，若每一特征信息均满足预设的第一条件，则可以判定被测物体受到打击，反之，若任一特征信息不满足预设的第一条件，则可以判定被测物体未受到打击。需要说明的是，可以根据实际应用中的需求对根据判断结果确定被测物体是否受到打击的规则进行调整，本发明在此不做限制。举例来说，该规则可以为若满足预设条件的特征信息占全部特征信息的比例大于预设的阈值，则可以判定被测物体受到打击，反之，则可以判定被测物体未受到打击。
本实施例提供的打击检测方法，通过若全部特征信息均满足预设的第一条件，则判定被测物体受到打击，若任一特征信息不满足预设的第一条件，则判定被测物体未受到打击，可以精准地对被测物体是否受到打击进行判定，提高了打击检测的精准度。
进一步地，在上述任一实施例的基础上，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
在本实施例中，预设的打击检测算法可以为神经网络算法。具体地，在获取到声音信号之后，还可以通过预设的神经网络算法对该声音信号进行检测，确定被测物体是否受到打击。
具体地，在上述任一实施例的基础上，所述通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
将所述声音信号输入至预设的神经网络算法中，根据所述神经网络算法的输出结果确定所述被测物体是否受到打击。
在本实施例中，获取到声音信号之后，可以将该声音信号输入至预设的神经网络算法中，获取该神经网络算法的输出结果，根据该输出结果确定被测物体是否受到打击。
本实施例提供的打击检测方法，通过预设的神经网络算法实现对声音信号的检测，从而能够提高打击检测的精准度。
图4为本发明实施例四提供的打击检测方法的流程示意图，在上述任一实施例的基础上，如图4所示，所述通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击之前，还包括：
步骤401、获取预设的待处理声音信号；
步骤402、根据所述待处理声音信号是否为被测物体打击后产生的，对所述待处理声音信号进行标注，获得待训练数据；
步骤403、通过所述待训练数据对预设的待训练神经网络算法进行训练，获得所述预设的神经网络算法。
在本实施例中，为了通过神经网络算法对声音信号进行检测，首先需要训练获得神经网络。具体地，首先需要获取待处理声音信号，针对每一待处理声音信号，确定该待处理声音信号是否为打击产生的，并根据该结果对待处理声音信号进行标注，获得待训练数据。进一步地，可以根据待训练数据对预先建立的待训练神经网络算法进行训练，获得神经网络算法。由于该神经网络算法是通过标注后的待处理声音信号训练获得的，因此，该神经网络算法能够对声音信号是否为受打击产生的进行符合需求的准确的检测。
本实施例提供的打击检测算法，通过待训练数据对预设的待训练神经网络算法进行训练，从而能够获得训练后的神经网络算法，为打击检测提供了基础。
图5为本发明实施例五提供的打击检测方法的流程示意图，在上述任一实施例的基础上，如图5所示，所述通过设置于所述打击检测设备内的麦克风获取声音信号之后，还包括：
步骤501、按照预设的时间间隔将所述声音信号分割为至少一段声音 信号段落；
相应地，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
步骤502、通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击。
在本实施例中，在游戏对战过程中，为了提高游戏的实时性，需要及时对声音信号进行检测。具体地，可以按照预设的时间间隔将该声音信号分割为至少一段声音信号段落。针对每一声音信号段落，通过预设的打击检测算法对该声音信号段落进行检测，以确定被测物体是否受到打击。此外，将声音信号进行分割后处理，由于每一段声音信号数据量较小，因此，处理效率较高。
本实施例提供的打击检测算法，通过将获取到的声音信号进行分割，对分割后的声音信号段落进行检测，便于后续数据处理和统计，并且能够提高打击检测的效率。
进一步地，在上述任一实施例的基础上，所述通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击，包括：
针对各声音信号段落，确定所述声音信号段落中是否包括有效声音信号；
若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击；
若否，则舍弃所述声音信号段落。
在实际应用过程中，麦克风采集到的声音信号可能不完全是被测物体震动产生的，举例来说，与被测物体刚性连接的装置的震动也可能被麦克风采集到，距离被测物体较远的背景音也可能被采集到，因此，为了进一步地提高声音信号的信号质量，还需要对声音信号进行筛选。具体地，针对每一声音信号段落，确定该声音信号段落中是否包括有效声音信号，若包括，则可以对该声音信号段落进行检测，以确定被测物体是否受到打击。反之，若该声音段落中不包括有效声音信号，则表征该声音信号段落是由噪声或其他装置震动导致的，此时，为了提高打击检测精准度以及降低处理器处理压力，可以舍弃该声音信号段落。
本实施例提供的打击检测方法，通过确定各声音信号段落中是否包括有效声音信号对声音信号段落进行处理，从而能够在提高打击检测精准度的基础上，降低处理器计算压力。
进一步地，在上述任一实施例的基础上，所述若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击，包括：
若所述声音信号段落包括有效声音信号，则将所述声音信号段落作为初始段落，将所述初始段落至所述声音信号中最后一个声音信号段落作为待检测声音信号；
通过预设的打击检测算法对所述待检测声音信号进行检测，确定所述被测物体是否受到打击。
在本实施例中，若检测到声音信号段落中包括有效声音信号，则表征该声音信号段落是由被测物体震动产生的，此时可以对该声音信号段落进行打击检测。具体地，可以将该声音信号作为初始段落，并将初始段落至声音信号中的最后一个声音信号段落作为待检测声音信号。通过预设的打击检测算法对该待检测声音信号进行检测。由于待检测声音信号是由包含有效声音信号的声音信号段落组成，因此，对待检测声音信号进行打击检测能够有效提高打击检测的精准度。
本实施例提供的打击检测算法，通过若声音信号段落包括有效声音信号，则将声音信号段落作为初始段落，将初始段落至声音信号中最后一个声音信号段落作为待检测声音信号，通过预设的打击检测算法对待检测声音信号进行检测，确定被测物体是否受到打击，从而能够有效提高打击检测的精准度。
具体地，在上述任一实施例的基础上，所述确定所述声音信号段落中是否包括有效声音信号，包括：
判断所述声音信号段落对应的信号能量以及过零率是否满足预设的第二条件；
若是，则判定所述声音信号段落中包括有效声音信号；
若否，则判定所述声音信号段落中不包括有效声音信号。
在本实施例中，具体可以通过声音信号段落的段落特征确定该声音信 号段落中是否包括有效声音信号。该段落特征具体可以包括信号能量以及过零率等特征，此外，还可以包括其他能够判断声音信号是否有效的特征，本发明在此不做限制。具体地，可以判断声音信号段落对应的信号能量以及过零率是否满足预设的第二条件，若满足，可以判定该声音信号段落中包括有效声音信号。反之，若不满足，则可以判定声音信号段落中不包括有效声音信号，此时，可以将该声音信号段落进行舍弃。
本实施例提供的打击检测算法，通过判断声音信号段落对应的信号能量以及过零率是否满足预设的第二条件，从而能够有效地确定该声音信号段落中是否包括有效声音信号，为提高打击检测精准度提供了基础。
进一步地，在上述任一实施例的基础上，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击之后，还包括：
若确定所述被测物体受到打击，则向与设置有所述被测物体的可移动平台通信连接的控制终端发送打击信息，以使所述控制终端根据所述打击信息对当前对战状态进行播报。
在本实施例中，对声音信号进行打击检测确定被测物体是否受到打击之后，可以将分析后的打击信息发送至与设置有打击检测设备以及被测物体的可移动平台通信连接的控制终端，以使控制终端对该打击信息进行处理，其中控制终端通过预设的连接方式与可移动平台通信连接，进而能够进行信息交互。具体地，控制终端在接收到打击信息之后，若确定被测物体受到打击，则可以对当前对战状态进行播报，此外，还可以根据受到的打击信息进行计分等操作。
本实施例提供的打击检测方法，通过若确定被测物体受到打击，则向与设置有被测物体的可移动平台通信连接的控制终端发送打击信息，以使控制终端根据打击信息对当前对战状态进行播报，从而能够精准地对对战信息进行获知，提高用户的游戏体验。
图6为本发明实施例六提供的打击检测设备的结构示意图，如图6所示，所述打击检测设备1用于固定安装在可移动平台的被测物体内侧，包括：
上盖1，所述上盖1外部设置有环形凸起3，所述环形凸起3用于与 所述被测物体形成腔体；
底壳5，与所述上盖2形成闭合内腔；
检测电路板6，设置于所述闭合内腔中；以及
麦克风4，设置于所述检测电路板6朝向所述上盖2的一侧，用于获取声音信号。
如图6所示，本实施例提供的打击检测设备1设置有上盖2、底壳5以及检测电路板6。其中，上盖2外部设置有环形凸起3，环形凸起3可以为闭合式的圆形、方形、长条形或其他形状。当打击检测设备1设置在被测物体一侧时，该环形凸起3能够与被测物体形成腔体，从而当被测物体受到打击而产生震动时，震动产生的声音信号能够通过该腔体进行传播。由于该腔体与外界是封闭的，从而可以减少声音信号扩散，提高声音信号的信号质量，进一步地，能够提高打击声音捕捉的灵敏度。此外，为了实现对声音信号的获取，打击检测设备1中还设置有麦克风4。在一些实施方式中，环形凸起3可以为弹性材料如硅胶等构成，从而可以使得环形凸起3可以更好地贴合被测物体来形成封闭的腔体。
其中，该环形凸起3为弹性材料。从而能够在提高打击声音捕捉的灵敏度的同时，消除部分噪音。
本实施例提供的打击检测设备，通过固定安装在可移动平台的被测物体内侧，所述打击检测设备的上盖设置有环形凸起，所述环形凸起用于与所述被测物体形成腔体；所述打击检测设备内还设置有麦克风，所述麦克风用于获取声音信号，从而能够精准地实现对声音信号的获取，为提高打击检测的精准度提供了基础。
进一步地，在上述任一实施例的基础上，如图6所示，所述打击检测设备的上盖2与所述麦克风4对应的位置还设置有透音孔7，所述腔体中的声音信号可以通过所述透音孔7传播至所述麦克风4。
在本实施例中，为了使麦克风能够获取到腔体中传播的声音信号，该打击检测设备的上盖与该麦克风对应的位置上还设置有透音孔。从而在被测物体发生震动产生声音信号时，腔体中的声音信号可以通过该透音孔传播至麦克风，从而麦克风能够在被测物体发生震动时，对震动产生的声音信号进行获取。
进一步地，在上述任一实施例的基础上，如图6所示，所述透音孔为至少一个；
其中，当所述透音孔为多个时，所述透音孔呈蜂窝状排布。
在本实施例中，透音孔的数量可以为至少一个，本领域技术人员可以根据实际应用中的需求对透音孔的数量以及排布形状进行设置，本发明在此不做限制。具体地，当透音孔的数量为多个时，透音孔的排布形状可以根据麦克风的形状进行设置；例如当麦克风为圆形时，其可以成蜂窝状排布。
本实施例提供的打击检测设备，通过在上盖与麦克风对应的位置设置透音孔，从而能够使腔体中的声音信号直接传播至麦克风，实现了更好地对声音信号的获取，为提高打击检测精准度提供了基础。
进一步地，在上述任一实施例的基础上，所述打击检测设备1还设置有至少一个减震球8，当所述减震球8的数量为一个时，所述麦克风4设置在所述减震球8中心；当所述减震球8的数量为多个时，所述减震球8均匀设置在所述麦克风4下方。
在本实施例中，为了实现对噪声的滤除，打击检测设备1中还可以设置有减震球8。具体地，减震球8的数量可以为至少一个，当麦克风4体积较小时，可以只设置一个减震球8，相应地，可以将麦克风4设置在减震球8的中心位置。可选地，减震球的数量可以为多个，或者当麦克风体积较大时，可以采用多个减震球均匀支撑麦克风，多个减震球可以均匀设置在麦克风的下方。需要说明的是，可以采用任意材质或数量的减震球，本发明在此不做限制。举例来说，该减震球可以为硅胶减震球。
本实施例提供的打击检测设备，通过在打击检测设备中设置减震球，从而能够有效地去除因下盖或连接下盖的震动产生的噪音，进一步地集中声音信号的来源以获得更好的检测结果。
图7为本发明实施例七提供的打击检测设备的结构示意图，在上述任一实施例的基础上，如图7所示，所述打击检测设备包括：存储器71、处理器72；
所述存储器71用于存储程序代码；所述处理器72，调用所述程序代码，当程序代码被执行时，用于执行以下操作：
通过设置于所述打击检测设备内的麦克风获取声音信号；
通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
本实施例提供的打击检测设备，打击检测设备设置在被测物体内侧，通过在打击检测设备的上盖设置一圈环形凸起，从而能够与被测物体之间形成腔体。此外，打击检测设备中还设置有麦克风，进而能够通过该麦克风获取声音信号，由于声音信号是从腔体中获取的，从而能够提高声音信号的质量，且提高声音信号捕捉的灵敏度。进一步地，可以通过预设的打击检测算法对该声音信号进行检测，根据检测结果确定该被测物体当前是否受到打击。从而能够精准地确定被测物体当前是否受到打击，提高打击检测的精准度。
进一步地，在上述任一实施例的基础上，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号时，用于：
通过所述麦克风获取所述腔体中传播的声音信号。
进一步地，在上述任一实施例的基础上，所述处理器在通过所述麦克风获取所述腔体中传播的声音信号时，用于：
当所述被测物体发生震动时，通过所述麦克风获取所述腔体中传播的声音信号。
进一步地，在上述任一实施例的基础上，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号之后，还用于：
将所述声音信号转换为电压模拟信号；
通过预设的滤波器对所述电压模拟信号进行滤波，获得目标信号；
相应地，所述处理器在通过预设的打击检测算法对所述声音信号进行检测时，用于：
通过预设的打击检测算法对所述声音信号对应的目标信号进行检测。
进一步地，在上述任一实施例的基础上，所述滤波器为高通滤波器。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是 否受到打击。
进一步地，在上述任一实施例的基础上，所述识别算法为决策树算法。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
获取所述声音信号对应的至少一个特征信息；
通过预设的识别算法判断各所述特征信息是否符合预设的条件，获得判断结果；
根据所述判断结果确定所述被测物体是否受到打击。
进一步地，在上述任一实施例的基础上，所述特征信息包括如下至少一种：所述声音信号对应的能量信息、峰值信息、尾音信息、衰减程度信息。
进一步地，在上述任一实施例的基础上，所述处理器在根据所述判断结果确定所述被测物体是否受到打击时，用于：
若每一特征信息均满足预设的条件，则判定所述被测物体受到打击；
若任一特征信息不满足所述预设的条件，则判定所述被测物体未受到打击。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
将所述声音信号输入至预设的神经网络算法中，根据所述神经网络算法的输出结果确定所述被测物体是否受到打击。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击之前，还用于：
获取预设的待处理声音信号；
根据所述待处理声音信号是否为被测物体打击后产生的，对所述待处理声音信号进行标注，获得待训练数据；
通过所述待训练数据对预设的待训练神经网络算法进行训练，获得所述预设的神经网络算法。
进一步地，在上述任一实施例的基础上，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号之后，还用于：
按照预设的时间间隔将所述声音信号分割为至少一段声音信号段落；
相应地，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击时，用于：
针对各声音信号段落，确定所述声音信号段落中是否包括有效声音信号；
若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击；
若否，则舍弃所述声音信号段落。
进一步地，在上述任一实施例的基础上，所述处理器在若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击时，用于：
若所述声音信号段落包括有效声音信号，则将所述声音信号段落作为初始段落，将所述初始段落至所述声音信号中最后一个声音信号段落作为待检测声音信号；
通过预设的打击检测算法对所述待检测声音信号进行检测，确定所述被测物体是否受到打击。
进一步地，在上述任一实施例的基础上，所述处理器在确定所述声音信号段落中是否包括有效声音信号时，用于：
判断所述声音信号段落对应的信号能量以及过零率是否满足预设的条件；
若是，则判定所述声音信号段落中包括有效声音信号；
若否，则判定所述声音信号段落中不包括有效声音信号。
进一步地，在上述任一实施例的基础上，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击之后，还用于：
若确定所述被测物体受到打击，则向与设置有所述被测物体的可移动平台通信连接的控制终端发送打击信息，以使所述控制终端根据所述打击信息对当前对战状态进行播报。
本发明又一实施例还提供了一种可移动平台，所述可移动平台中设置有被测物体以及如上述任一实施例所述的打击检测设备。
本发明又一实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行以实现如上述任一实施例所述的打击检测设备。
另外，本实施例还提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行以实现上述实施例所述的打击检测方法。
在本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元 中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (43)

  1. 一种打击检测方法，应用于打击检测设备，其特征在于，所述打击检测设备用于固定安装在被测物体内侧，所述打击检测设备的上盖设置有环形凸起，所述环形凸起用于与所述被测物体形成腔体；所述方法包括：
    通过设置于所述打击检测设备内的麦克风获取声音信号；
    通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  2. 根据权利要求1所述的方法，其特征在于，所述通过设置于所述打击检测设备内的麦克风获取声音信号，包括：
    通过所述麦克风获取所述腔体中传播的声音信号。
  3. 根据权利要求2所述的方法，其特征在于，所述打击检测设备的上盖与所述麦克风对应的位置还设置有透音孔，所述腔体中的声音信号可以通过所述透音孔传播至所述麦克风；
    相应地，所述通过所述麦克风获取所述腔体中传播的声音信号，包括：
    当所述被测物体发生震动时，通过所述麦克风获取所述腔体中传播的声音信号。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述通过设置于所述打击检测设备内的麦克风获取声音信号之后，还包括：
    将所述声音信号转换为电压模拟信号；
    通过预设的滤波器对所述电压模拟信号进行滤波，获得目标信号；
    相应地，所述通过预设的打击检测算法对所述声音信号进行检测，包括：
    通过预设的打击检测算法对所述声音信号对应的目标信号进行检测。
  5. 根据权利要求4所述的方法，其特征在于，所述滤波器为高通滤波器。
  6. 根据权利要求1-3、5任一项所述的方法，其特征在于，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
    通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  7. 根据权利要求6所述的方法，其特征在于，所述识别算法为决策树算法。
  8. 根据权利要求7所述的方法，其特征在于，所述通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
    获取所述声音信号对应的至少一个特征信息；
    通过预设的识别算法判断各所述特征信息是否符合预设的第一条件，获得判断结果；
    根据所述判断结果确定所述被测物体是否受到打击。
  9. 根据权利要求8所述的方法，其特征在于，所述特征信息包括如下至少一种：所述声音信号对应的能量信息、峰值信息、尾音信息、衰减程度信息。
  10. 根据权利要求8所述的方法，其特征在于，所述根据所述判断结果确定所述被测物体是否受到打击，包括：
    若每一特征信息均满足预设的第一条件，则判定所述被测物体受到打击；
    若任一特征信息不满足所述预设的第一条件，则判定所述被测物体未受到打击。
  11. 根据权利要求1-3、5任一项所述的方法，其特征在于，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
    通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  12. 根据权利要求11所述的方法，其特征在于，所述通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
    将所述声音信号输入至预设的神经网络算法中，根据所述神经网络算法的输出结果确定所述被测物体是否受到打击。
  13. 根据权利要求11所述的方法，其特征在于，所述通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击之前，还包括：
    获取预设的待处理声音信号；
    根据所述待处理声音信号是否为被测物体打击后产生的，对所述待处理声音信号进行标注，获得待训练数据；
    通过所述待训练数据对预设的待训练神经网络算法进行训练，获得所述预设的神经网络算法。
  14. 根据权利要求1-3、5、7-10、12-13任一项所述的方法，其特征在于，所述通过设置于所述打击检测设备内的麦克风获取声音信号之后，还包括：
    按照预设的时间间隔将所述声音信号分割为至少一段声音信号段落；
    相应地，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击，包括：
    通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击。
  15. 根据权利要求14所述的方法，其特征在于，所述通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击，包括：
    针对各声音信号段落，确定所述声音信号段落中是否包括有效声音信号；
    若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击；
    若否，则舍弃所述声音信号段落。
  16. 根据权利要求15所述的方法，其特征在于，所述若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击，包括：
    若所述声音信号段落包括有效声音信号，则将所述声音信号段落作为初始段落，将所述初始段落至所述声音信号中最后一个声音信号段落作为待检测声音信号；
    通过预设的打击检测算法对所述待检测声音信号进行检测，确定所述被测物体是否受到打击。
  17. 根据权利要求15所述的方法，其特征在于，所述确定所述声音 信号段落中是否包括有效声音信号，包括：
    判断所述声音信号段落对应的信号能量以及过零率是否满足预设的第二条件；
    若是，则判定所述声音信号段落中包括有效声音信号；
    若否，则判定所述声音信号段落中不包括有效声音信号。
  18. 根据权利要求1-3、5、7-10、12-13、15-17任一项所述的方法，其特征在于，所述通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击之后，还包括：
    若确定所述被测物体受到打击，则向与设置有所述被测物体的可移动平台通信连接的控制终端发送打击信息，以使所述控制终端根据所述打击信息对当前对战状态进行播报。
  19. 一种打击检测设备，其特征在于，所述打击检测设备用于固定安装在可移动平台的被测物体内侧，包括：
    上盖，所述上盖外部设置有环形凸起，所述环形凸起用于与所述被测物体形成腔体；
    底壳，与所述上盖形成闭合内腔；
    检测电路板，设置于所述闭合内腔中；以及
    麦克风，设置于所述检测电路板朝向所述上盖的一侧，用于获取声音信号。
  20. 根据权利要求19所述的方法，其特征在于，所述环形凸起为弹性材料。
  21. 根据权利要求19所述的打击检测设备，其特征在于，所述打击检测设备的上盖与所述麦克风对应的位置还设置有透音孔，所述腔体中的声音信号可以通过所述透音孔传播至所述麦克风。
  22. 根据权利要求21所述的打击检测设备，其特征在于，所述透音孔为至少一个；
    其中，当所述透音孔为多个时，所述透音孔呈蜂窝状排布。
  23. 根据权利要求19所述的打击检测设备，其特征在于，所述打击检测设备还设置有至少一个减震球，当所述减震球的数量为一个时，所述麦克风设置在所述减震球中心；当所述减震球的数量为多个时，所述减震 球均匀设置在所述麦克风下方。
  24. 根据权利要求19-23任一项所述的打击检测设备，其特征在于，所述打击检测设备还包括：存储器、处理器；
    所述存储器用于存储程序代码；所述处理器，调用所述程序代码，当程序代码被执行时，用于执行以下操作：
    通过设置于所述打击检测设备内的麦克风获取声音信号；
    通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  25. 根据权利要求24所述的打击检测设备，其特征在于，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号时，用于：
    通过所述麦克风获取所述腔体中传播的声音信号。
  26. 根据权利要求25所述的打击检测设备，其特征在于，所述处理器在通过所述麦克风获取所述腔体中传播的声音信号时，用于：
    当所述被测物体发生震动时，通过所述麦克风获取所述腔体中传播的声音信号。
  27. 根据权利要求25-26任一项所述的打击检测设备，其特征在于，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号之后，还用于：
    将所述声音信号转换为电压模拟信号；
    通过预设的滤波器对所述电压模拟信号进行滤波，获得目标信号；
    相应地，所述处理器在通过预设的打击检测算法对所述声音信号进行检测时，用于：
    通过预设的打击检测算法对所述声音信号对应的目标信号进行检测。
  28. 根据权利要求27所述的打击检测设备，其特征在于，所述滤波器为高通滤波器。
  29. 根据权利要求25-26、28任一项所述的打击检测设备，其特征在于，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
    通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  30. 根据权利要求29所述的打击检测设备，其特征在于，所述识别算法为决策树算法。
  31. 根据权利要求30所述的打击检测设备，其特征在于，所述处理器在通过预设的识别算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
    获取所述声音信号对应的至少一个特征信息；
    通过预设的识别算法判断各所述特征信息是否符合预设的第一条件，获得判断结果；
    根据所述判断结果确定所述被测物体是否受到打击。
  32. 根据权利要求31所述的打击检测设备，其特征在于，所述特征信息包括如下至少一种：所述声音信号对应的能量信息、峰值信息、尾音信息、衰减程度信息。
  33. 根据权利要求31所述的打击检测设备，其特征在于，所述处理器在根据所述判断结果确定所述被测物体是否受到打击时，用于：
    若每一特征信息均满足预设的第一条件，则判定所述被测物体受到打击；
    若任一特征信息不满足所述预设的第一条件，则判定所述被测物体未受到打击。
  34. 根据权利要求25-26、28任一项所述的打击检测设备，其特征在于，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
    通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击。
  35. 根据权利要求34所述的打击检测设备，其特征在于，所述处理器在通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
    将所述声音信号输入至预设的神经网络算法中，根据所述神经网络算法的输出结果确定所述被测物体是否受到打击。
  36. 根据权利要求34所述的打击检测设备，其特征在于，所述处理器在通过预设的神经网络算法对所述声音信号进行检测，确定所述被测物 体是否受到打击之前，还用于：
    获取预设的待处理声音信号；
    根据所述待处理声音信号是否为被测物体打击后产生的，对所述待处理声音信号进行标注，获得待训练数据；
    通过所述待训练数据对预设的待训练神经网络算法进行训练，获得所述预设的神经网络算法。
  37. 根据权利要求25-26、28、30-33、35-36任一项所述的打击检测设备，其特征在于，所述处理器在通过设置于所述打击检测设备内的麦克风获取声音信号之后，还用于：
    按照预设的时间间隔将所述声音信号分割为至少一段声音信号段落；
    相应地，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击时，用于：
    通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击。
  38. 根据权利要求37所述的打击检测设备，其特征在于，所述处理器在通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击时，用于：
    针对各声音信号段落，确定所述声音信号段落中是否包括有效声音信号；
    若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击；
    若否，则舍弃所述声音信号段落。
  39. 根据权利要求38所述的打击检测设备，其特征在于，所述处理器在若是，则通过预设的打击检测算法对所述声音信号段落进行检测，确定所述被测物体是否受到打击时，用于：
    若所述声音信号段落包括有效声音信号，则将所述声音信号段落作为初始段落，将所述初始段落至所述声音信号中最后一个声音信号段落作为待检测声音信号；
    通过预设的打击检测算法对所述待检测声音信号进行检测，确定所述被测物体是否受到打击。
  40. 根据权利要求38所述的打击检测设备，其特征在于，所述处理器在确定所述声音信号段落中是否包括有效声音信号时，用于：
    判断所述声音信号段落对应的信号能量以及过零率是否满足预设的第二条件；
    若是，则判定所述声音信号段落中包括有效声音信号；
    若否，则判定所述声音信号段落中不包括有效声音信号。
  41. 根据权利要求25-26、28、30-33、35-36、38-40任一项所述的打击检测设备，其特征在于，所述处理器在通过预设的打击检测算法对所述声音信号进行检测，确定所述被测物体是否受到打击之后，还用于：
    若确定所述被测物体受到打击，则向与设置有所述被测物体的可移动平台通信连接的控制终端发送打击信息，以使所述控制终端根据所述打击信息对当前对战状态进行播报。
  42. 一种可移动平台，其特征在于，所述可移动平台中设置有被测物体以及如权利要求19-41任一项所述的打击检测设备。
  43. 一种计算机可读存储介质，其特征在于，其上存储有计算机程序，所述计算机程序被处理器执行以实现如权利要求1-18任一项所述的打击检测方法。
PCT/CN2019/087972 2019-05-22 2019-05-22 打击检测方法、设备、可移动平台及计算机可读存储介质 WO2020232669A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980012138.4A CN111699368A (zh) 2019-05-22 2019-05-22 打击检测方法、设备、可移动平台及计算机可读存储介质
PCT/CN2019/087972 WO2020232669A1 (zh) 2019-05-22 2019-05-22 打击检测方法、设备、可移动平台及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/087972 WO2020232669A1 (zh) 2019-05-22 2019-05-22 打击检测方法、设备、可移动平台及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2020232669A1 true WO2020232669A1 (zh) 2020-11-26

Family

ID=72476434

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/087972 WO2020232669A1 (zh) 2019-05-22 2019-05-22 打击检测方法、设备、可移动平台及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN111699368A (zh)
WO (1) WO2020232669A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201181416Y (zh) * 2008-04-10 2009-01-14 杭州亿脑智能科技有限公司 一种机器玩具的电路控制系统
JP2011169697A (ja) * 2010-02-17 2011-09-01 Asahi Kasei Corp 振動センサ、携帯情報端末
CN205759674U (zh) * 2016-05-31 2016-12-07 深圳市大疆创新科技有限公司 检测外部撞击物的检测系统以及遥控竞赛战车
CN106326698A (zh) * 2016-08-11 2017-01-11 上海青橙实业有限公司 终端的工作状态设置方法和终端
CN108513241A (zh) * 2018-06-29 2018-09-07 歌尔股份有限公司 振动传感器和音频设备
CN108764304A (zh) * 2018-05-11 2018-11-06 Oppo广东移动通信有限公司 场景识别方法、装置、存储介质及电子设备
CN208369851U (zh) * 2018-06-29 2019-01-11 深圳市大疆创新科技有限公司 驻极体麦克风、声振检测装置及竞赛遥控车
CN109753191A (zh) * 2017-11-03 2019-05-14 迪尔阿扣基金两合公司 一种声学触控系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2718928Y (zh) * 2004-07-28 2005-08-17 深圳市豪恩电声科技有限公司 驻极体电容式传声器连接器
KR100838239B1 (ko) * 2007-04-17 2008-06-17 (주)에스엠인스트루먼트 음질 표시 장치, 음질 표시 방법, 음질 표시 프로그램을 기록한 컴퓨터로 읽을 수 있는 매체
JP2012014003A (ja) * 2010-07-01 2012-01-19 Roland Corp 打楽器用打撃検出装置
CN101976564A (zh) * 2010-10-15 2011-02-16 中国林业科学研究院森林生态环境与保护研究所 昆虫声音识别方法
CN105810213A (zh) * 2014-12-30 2016-07-27 浙江大华技术股份有限公司 一种典型异常声音检测方法及装置
CN107223205A (zh) * 2016-05-31 2017-09-29 深圳市大疆创新科技有限公司 检测外部撞击物的检测系统、方法以及可移动物体
CN107545890A (zh) * 2017-08-31 2018-01-05 桂林电子科技大学 一种声音事件识别方法
CN109379650B (zh) * 2018-10-18 2020-04-14 深圳康佳电子科技有限公司 一种麦克风减震结构及麦克风设备
CN109758140A (zh) * 2019-01-09 2019-05-17 平安科技（深圳）有限公司 一种心率检测方法和装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201181416Y (zh) * 2008-04-10 2009-01-14 杭州亿脑智能科技有限公司 一种机器玩具的电路控制系统
JP2011169697A (ja) * 2010-02-17 2011-09-01 Asahi Kasei Corp 振動センサ、携帯情報端末
CN205759674U (zh) * 2016-05-31 2016-12-07 深圳市大疆创新科技有限公司 检测外部撞击物的检测系统以及遥控竞赛战车
CN106326698A (zh) * 2016-08-11 2017-01-11 上海青橙实业有限公司 终端的工作状态设置方法和终端
CN109753191A (zh) * 2017-11-03 2019-05-14 迪尔阿扣基金两合公司 一种声学触控系统
CN108764304A (zh) * 2018-05-11 2018-11-06 Oppo广东移动通信有限公司 场景识别方法、装置、存储介质及电子设备
CN108513241A (zh) * 2018-06-29 2018-09-07 歌尔股份有限公司 振动传感器和音频设备
CN208369851U (zh) * 2018-06-29 2019-01-11 深圳市大疆创新科技有限公司 驻极体麦克风、声振检测装置及竞赛遥控车

Also Published As

Publication number Publication date
CN111699368A (zh) 2020-09-22

Similar Documents

Publication Publication Date Title
CN108735219B (zh) 一种声音识别控制方法及装置
EP0121395B1 (en) Improvements in or relating to the testing of structures by impact
WO2021113879A3 (en) Acoustic signal based analysis of batteries
US10497277B2 (en) Feedback provision method, system, and analysis device
WO2019230687A1 (ja) 打音検査端末、打音検査システムおよび打音検査データ登録方法
CN109104683A (zh) 一种双麦克风相位测量校正的方法及校正系统
US20170182405A1 (en) Classifying collision events using inertial and audio data
WO2020232669A1 (zh) 打击检测方法、设备、可移动平台及计算机可读存储介质
JP3922061B2 (ja) 音質評価装置及び音質評価方法
CN104936096A (zh) 骨导声音传播装置和方法
CN102435676B (zh) 一种通过声音检测非晶合金产品合格性的方法
JP6273751B2 (ja) ドラム
US20200380955A1 (en) Detection of speech
WO2020087372A1 (zh) 撞击物识别方法、系统及存储介质
CN108665906B (zh) 一种赛事裁判哨声采集识别系统和方法
CN113115148A (zh) 一种耳机及入耳检测方法、装置
CN114640940B (zh) 一种自动化智能tws蓝牙耳机测试系统
CN106710602B (zh) 一种声学混响时间估计方法和装置
CN104575450B (zh) 钢琴琴键下沉负荷的测量方法
CN110352334B (zh) 打击检测方法、打击检测装置及装甲小车
CN106267762A (zh) 一种乒乓球击打次数的测定方法
CN109804252B (zh) 信号处理装置和信号处理方法
JPH11142231A (ja) 騒音分析装置
KR20200072242A (ko) 모바일 기기와 다채널 마이크 장치를 이용한 위험상황 판단 방법 및 장치
CN113631942A (zh) 声源跟踪控制方法和控制装置、声源跟踪系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19930103

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19930103

Country of ref document: EP

Kind code of ref document: A1