WO2019128263A1 - Vehicle honking detection method, device, apparatus, storage medium, and system - Google Patents

Abstract

A vehicle honking detection method, a device (104), an apparatus, a storage medium, and a system. The method comprises: determining that there is a honking vehicle inside a monitored region by means of audio signals collected by at least one first microphone (101) and at least one second microphone (102); determining a region of the honking vehicle according to signal energy of the audio signals collected by the at least one first microphone (101) and the at least one second microphone (102); and performing movement identification on an image corresponding to the region of the honking vehicle, and locating the honking vehicle when any one vehicle is identified as having a pre-determined movement.

Description

Method, device, device, storage medium and system for detecting vehicle whistle

This application claims the priority of the Chinese patent application filed on December 29, 2017, the Chinese National Intellectual Property Office, the application number is 201711478558.0, and the invention is entitled "Method, device and system for detecting vehicle whistle". Combined in this application.

Technical field

The present application relates to the field of security monitoring, and in particular, to a method, device, device, storage medium and system for detecting a whistle of a vehicle.

Background technique

With the rapid increase in the number of vehicles, vehicle congestion is becoming more and more obvious. Therefore, the driver usually whistle during the driving process to achieve the purpose of reminding the preceding car and urging driving. However, in order to maintain a normal living order, there are often areas on the road that prohibit whistling. These areas are often living areas or school areas. If there is a violation of the whistle, it will cause huge impact on people’s lives in these areas. Impact, therefore, there is a need for a method of detecting vehicle whistle to effectively monitor the behavior of violating whistle.

Summary of the invention

The present application provides a method, device, device, storage medium and system for detecting a whistle of a vehicle, which can solve the problem that the illegal whistle cannot be effectively supervised.

In one aspect, a method of detecting a whistle of a vehicle is provided, the method being applied to a computer device, the method comprising:

Determining the presence of a whistle vehicle in the controlled area by a sound signal collected by the at least one first microphone and the at least one second microphone; the first microphone is disposed along a lane in the controlled area, the second microphone edge The controlled area is disposed in a direction perpendicular to the lane;

Determining an area where the whistle vehicle is located according to signal energy of a sound signal collected by the at least one first microphone and the at least one second microphone;

The action corresponding to the image corresponding to the area where the whistle vehicle is located is recognized, and when it is recognized that there is a preset action in any of the vehicles, the whistle vehicle is positioned.

In a possible implementation manner, the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area comprises:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area comprises:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, when a spectrum of the target sound signal has a peak in a preset whistle sound spectrum range, determining that the whistle vehicle exists in the controlled area includes:

Transforming the target sound signal into a frequency domain to obtain a spectrum of the target sound signal;

Dividing the spectrum into two frequency bands, and performing peak search on the two frequency bands based on the first preset frequency and the second preset frequency;

When a peak occurs in the frequency spectrum within a preset range of the first preset frequency and the second preset frequency, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation, the determining, according to the signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone, the area where the whistle vehicle is located includes:

Determining a first sound signal having the largest signal energy and a second sound signal having the largest signal energy;

Determining an area in which the whistle vehicle is located based on a position of a source microphone of the first sound signal and a source microphone of the second sound signal.

In a possible implementation, determining, according to a location of the source microphone of the first sound signal and a source microphone of the second sound signal, an area where the whistle vehicle is located includes:

Determining a first extension line according to a location of a source microphone of the first sound signal;

Determining a second extension line according to a location of the source microphone of the second sound signal;

Determining an intersection of the first extension line and the second extension line in the controlled area;

The sub-area in which the intersection is located in the controlled area is used as the area where the whistle vehicle is located.

In a possible implementation manner, the image corresponding to the area where the whistle vehicle is located is motion-recognized, and when it is recognized that there is a preset action in any of the vehicles, positioning the whistle vehicle includes:

Obtaining a monitoring image of the controlled area captured by the camera;

Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles, the vehicle is determined to be a whistle vehicle.

In a possible implementation, after positioning the whistle vehicle, the method further includes:

Highlighting an area where the whistle vehicle is located on a monitored image of the controlled area; and/or,

The license plate number of the whistle vehicle is identified, and the identified license plate number is output.

In one aspect, an apparatus for detecting a whistle of a vehicle is provided, the apparatus comprising:

a vehicle determining module, configured to determine, by the sound signal collected by the at least one first microphone and the at least one second microphone, a whistle vehicle in the controlled area; the first microphone is disposed along a lane in the controlled area, The second microphone is disposed along the vertical direction of the lane in the controlled area;

a region determining module, configured to determine an area where the whistle vehicle is located according to signal energy of a sound signal collected by the at least one first microphone and the at least one second microphone;

The vehicle positioning module is configured to perform motion recognition on an image corresponding to the area where the whistle vehicle is located, and locate the whistle vehicle when it is recognized that there is a preset action in any of the vehicles.

In a possible implementation manner, the vehicle determining module is configured to:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, the vehicle determining module is configured to:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, the area determining module includes:

a sound signal determining unit, configured to determine a first sound signal with the largest signal energy and a second sound signal with the largest signal energy;

And an area determining unit, configured to determine an area where the whistle vehicle is located according to a source microphone of the first sound signal and a source microphone of the second sound signal.

In a possible implementation, the vehicle positioning module is configured to:

Obtaining a monitoring image of the controlled area captured by the camera;

Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles, the vehicle is determined to be a whistle vehicle.

In a possible implementation, the device further includes: a reminding module, configured to:

Highlighting an area where the whistle vehicle is located on a monitored image of the controlled area; and/or,

The license plate number of the whistle vehicle is identified, and the identified license plate number is output.

In one aspect, a system for detecting a whistle of a vehicle is provided, the system comprising:

At least one first microphone disposed along a lane within the controlled area;

Having at least one second microphone disposed in a direction perpendicular to the lane in the controlled area;

a camera for monitoring the controlled area;

A device for detecting a whistle of a vehicle provided in the above implementation.

In one aspect, a computer apparatus is provided comprising a memory, a processor, and computer executable instructions stored on the memory and executable on the processor, wherein the processor is implemented when the computer executable instructions are executed A method of detecting a whistle of a vehicle in any of the above aspects.

In one aspect, a computer readable storage medium is provided having stored thereon instructions that are executed by a processor to perform the method of detecting a whistle of a vehicle of any of the above aspects.

The technical solution provided by the embodiment of the present application may include the following beneficial effects: the method of the present application provides a solution for detecting and locating a car whistle by installing a certain number of microphones in the whistle-free area, once When the vehicle violates the whistle, the approximate area of the vehicle can be detected, and then the monitoring image captured by the camera can be used to confirm the whistle motion recognition twice to prevent false alarms and greatly improve the detection accuracy.

The above general description and the following detailed description are intended to be illustrative and not restrictive.

DRAWINGS

The drawings herein are incorporated in and constitute a part of the specification,

1 is a schematic structural diagram of a system for detecting a whistle of a vehicle according to an embodiment of the present application;

2 is a flowchart of a method for detecting a whistle of a vehicle according to an embodiment of the present application;

3 is a schematic flow chart of a method for detecting a whistle of a vehicle according to an embodiment of the present application;

4 is a block diagram of an apparatus for detecting a whistle of a vehicle according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a computer device 500 according to an embodiment of the present application.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. The following description refers to the same or similar elements in the different figures unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with aspects of the present application as detailed in the appended claims.

Before the detailed description of the embodiments of the present application, a system for detecting a whistle of a vehicle according to an embodiment of the present application is briefly introduced. Referring to FIG. 1, the system includes:

At least one first microphone 101 disposed along a lane in the controlled area; at least one second microphone 102 disposed in a direction perpendicular to the lane in the controlled area; a camera 103 for monitoring the controlled area And a device 104 for detecting a whistle of the vehicle, for determining, based on the sound signals collected by the at least one first microphone 101 and the at least one second microphone 102, where the whistle vehicle is located in the controlled area An area, and an action recognition of an image corresponding to the area where the whistle vehicle is located to determine the whistle vehicle. In order to enable the above microphone to efficiently collect sounds in the controlled area, the orientation of each microphone can be set to face the controlled area. For example, for the first microphone, the orientation of the first microphone may be horizontal to the lane within the controlled area, and for the second microphone, the orientation of the second microphone may be perpendicular to the lane within the controlled area.

In order to realize the detection of an area, a plurality of microphones may be set in the controlled area to detect the sound signal in the controlled area. In order to realize the positioning of the whistle vehicle, the controlled area may be set when the microphone is set. The lane is provided with at least one first microphone. If there are multiple lanes in the controlled area, it can be set at the outer edge of a lane at the edge of the area. In order to determine a more accurate area through the horizontal and vertical sound signals, At least one second microphone may be disposed along the vertical direction of the lane of the controlled area, and if there are multiple lanes in the controlled area, it may be disposed at an intersection of each lane and the edge of the controlled area. The camera 103 may be an imaging device capable of monitoring the entire controlled area. Of course, the monitoring area may be larger than the controlled area to avoid a dead angle. Moreover, the camera 103 can be a camera system composed of a plurality of cameras, so that panoramic monitoring can be performed. The device 104 for detecting the whistle of the vehicle may be disposed on the monitoring device, where the monitoring device refers to any type of computer device that can monitor the area through the sound signal collected by the microphone and the image signal collected by the camera, and the monitoring device can It is located on the monitoring server or monitoring client. Of course, the monitoring device can also be the camera 103.

FIG. 2 is a flowchart of a method for detecting a whistle of a vehicle according to an embodiment of the present application. Referring to FIG. 2, the method includes:

201. Determine, by the sound signal collected by the at least one first microphone and the at least one second microphone, that there is a whistle vehicle in the controlled area; the first microphone is disposed along a lane in the controlled area, and the second microphone edge The controlled area is disposed in a direction perpendicular to the lane.

In order to realize the detection of an area, a plurality of microphones may be set in the controlled area to detect the sound signal in the controlled area. In order to realize the positioning of the whistle vehicle, the controlled area may be set when the microphone is set. The lane is provided with at least one first microphone. If there are multiple lanes in the controlled area, it can be set at the outer edge of a lane at the edge of the area. In order to determine a more accurate area through the horizontal and vertical sound signals, At least one second microphone may be disposed along the vertical direction of the lane of the controlled area, and if there are multiple lanes in the controlled area, it may be disposed at an intersection of each lane and the edge of the controlled area.

202. Determine, according to signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone, an area where the whistle vehicle is located.

Since the position of the whistle vehicle can be determined according to the energy of the sound signal, the determination of the area where the whistle vehicle is located can be realized by the setting of a plurality of microphones.

203. Perform motion recognition on an image corresponding to the area where the whistle vehicle is located, and locate a whistle vehicle when it is recognized that there is a preset motion in any of the vehicles.

The method of the present application provides a scheme for detecting the sound of a car whistle and locating a corresponding vehicle. By installing a certain number of microphones in the whisper-free area, once the vehicle violently whistle, the approximate area of the vehicle can be detected. Then, the monitoring image captured by the camera is used to confirm the whistle motion recognition twice to prevent false alarms and greatly improve the detection accuracy.

FIG. 3 is a schematic flow chart of a method for detecting a whistle of a vehicle according to an embodiment of the present application. The method can be applied to the system provided in FIG. 1 to describe the device for detecting the whistle of the vehicle as an example of the monitoring device. The monitoring device refers to the sound signal that can be collected by the microphone and the image signal collected by the camera. Any type of computer device that is monitored. Referring to FIG. 3, the embodiment specifically includes:

301. The monitoring device acquires at least one first sound signal collected by at least one first microphone in the controlled area, and acquires at least one second sound signal collected by at least one second microphone in the controlled area.

The first microphone may be disposed along a lane in the controlled area, and the second microphone may be disposed along a vertical direction of the lane in the controlled area. For the controlled area, the microphone can be configured based on the area size and/or the shape of the area of the controlled area. For example, the controlled area is a rectangular area, and the microphone can be uniformly disposed at the edge of the controlled area to collect the environment. All the sound signals in the sound, including the wind, the voice and the car whistle. The sound signals collected by the at least one first microphone and the at least one second microphone may be output to a monitoring device for subsequent analysis by the monitoring device. Of course, such sound collection can be real-time acquisition, and subsequent analysis can also be real-time analysis based on real-time collected sound signals.

In order to increase the detection accuracy, the number of microphones in the controlled area can be appropriately increased. For example, the number of first microphones is increased, and of course, the number of first microphones and second microphones can also be increased to achieve higher detection accuracy.

302. The monitoring device determines a target sound signal, where the target sound signal is a signal with the highest signal energy of the at least one first sound signal and the at least one second sound signal.

Specifically, the monitoring device may perform energy calculation on each frame of the sound signal collected by each microphone. When the signal energy of the sound signal is less than a preset threshold, the sound signal is considered to be other noise and is not processed, when the sound signal is When the signal energy is greater than or equal to the preset threshold, the sound signal is involved in the subsequent processing. Here, considering that the general whistle sound is loud, the preset threshold can be set larger. The specific size can be set according to the noise level in the actual environment.

As an implementation manner, when determining whether to perform a subsequent detection process, it may further determine whether there is a sound signal whose signal energy is greater than a preset threshold, and if yes, perform the determining process in the step 302 to select a signal energy in which the signal energy is maximum. The microphone performs the next step.

As an implementation manner, when determining whether to perform a subsequent detection process, it is also determined whether the sound signal whose signal energy is greater than a preset threshold reaches a preset number. When a signal energy value exceeding a certain number of microphones is greater than a preset threshold, It is considered that the whistle sound is likely to be at this time. Therefore, when the sound signal whose signal energy is greater than the preset threshold exceeds the preset number, the determining process in step 302 is performed to select the microphone with the highest signal energy for the next step. Operation. Of course, it is also possible to directly determine whether there is a whistle vehicle in the controlled area by using the method of determining whether the preset number is reached, that is, after determining that the number of sound signals whose signal energy exceeds the preset threshold reaches a preset number , directly determine the whistle vehicle in the controlled area, and perform step 306 and subsequent steps to further locate the whistle vehicle.

Of course, if the detected ambient noise is greater than the preset noise, the pre-processing, such as noise reduction processing, low-pass filtering, etc., may be performed before the energy calculation to avoid the subsequent processing due to the large noise.

303. The monitoring device transforms the target sound signal into a frequency domain to obtain a spectrum of the target sound signal.

The monitoring device can perform a Fourier transform on the target sound signal to convert the target sound signal from the time domain to the frequency domain to obtain its spectrum.

304. The monitoring device divides the spectrum into two frequency bands, and performs peak search on the two frequency bands based on the first preset frequency and the second preset frequency.

The first preset frequency is 3.2 kHz and the second preset frequency is 4.1 kHz. In theory, the whistle spectrum of the most common two-tone electric horn has a value of only 3.2 kHz and 4.1 kHz and a large value, so even in a noisy real environment, at these two frequencies Peaks appear, so for fast peak search, the spectrum can be divided into two frequency bands. For example, with 3.6 kHz as the segmentation frequency, the spectrum is divided into two frequency bands of 0-3.6 kHz and 3.6 kHz. If a peak value is found to have a particularly high peak at 3.2 kHz and 4.1 kHz in the spectrum, it is considered that there is a whistling sound. Of course, the frequency of the segmentation may also be any frequency between 3.2 kHz and 4.1 kHz, which is not limited in this embodiment of the present application. For other car horn sounds, generally only the frequency of a certain frequency point is relatively large. Therefore, the above method can also be used to set a plurality of preset frequencies based on the horn sound spectrum of the car horn sound. Therefore, a peak search is performed in the spectrum of the first sound signal and the second sound signal, and if a peak appears at the plurality of preset frequencies, it is considered that there is a whistle sound at this time. The value of the specific preset frequency may be determined based on an actual test, which is not limited in this embodiment of the present application.

In the peak search, the frequency sweep method may be used, that is, the two frequency bands of the spectrum are respectively swept, and the scanned spectrum size is compared, if the peaks appear in 3.2 kHz in the two frequency bands respectively. Near 4.1.kHz, it is considered to be a whistle. Of course, the peak search can also be performed in other ways, such as the manner in which the peak is searched by curve fitting or the manner in which the threshold is set.

Of course, in the case of performing the peak search, the above-mentioned spectrum segmentation may be used for searching, and the segmentation may be performed without searching. This embodiment of the present application does not limit this.

305. When a peak occurs in the preset range of the first preset frequency and the second preset frequency, the monitoring device determines that there is a whistle vehicle in the controlled area.

The above steps 303 to 305 are to determine that a spectrum of the target sound signal has a peak in the preset whistle sound spectrum range, and then determine a possible implementation manner of the whistle vehicle in the controlled area, by acquiring the target sound signal. After the spectrum, based on the law that the whistle sound spectrum peaks at two preset frequencies, it is determined that the presence of the whistle vehicle can ensure the accuracy of the determination result.

The above steps 301 to 305 are to determine a possible implementation of the whistle vehicle in the controlled area by the sound signals collected by the at least one first microphone and the at least one second microphone. The presence of the whistle vehicle is determined by the law of the peak of the highest energy sound signal and the whistle sound spectrum, so that the determination result is accurate and reliable. Through the above process, it can be determined that the whistle vehicle does exist in the controlled area, and then the whistle vehicle can be positioned in the next step.

306. The monitoring device determines a first sound signal with the largest signal energy and a second sound signal with the largest signal energy.

When the signal energy is large, the closer the distance between the sound source and the microphone is, so that the first sound signal with the largest signal energy can be determined from the at least one first sound signal, and the signal is determined from the at least one second sound signal. The second most powerful sound signal.

307. The monitoring device determines, according to a location of the source microphone of the first sound signal and a source microphone of the second sound signal, an area where the whistle vehicle is located.

When it is judged that there is a whistling sound at this time, in order to confirm the area where the whistle vehicle is located at this time, the entire road surface can be divided into several areas by using a microphone, for example, as indicated by a broken line in FIG. 1, the direction along the lane and the direction perpendicular to the lane are selected. The two microphones with the highest energy, the two microphones extend the intersection of the dotted lines to determine the center point of the area. That is, when determining the area where the whistle vehicle is located based on the source microphone, the following process may be adopted: determining a first extension line according to a position of the source microphone of the first sound signal; and a source microphone according to the second sound signal Position determining a second extension line; determining an intersection of the first extension line and the second extension line in the controlled area; the sub-area where the intersection is located in the controlled area is the area where the whistle vehicle is located.

The above steps 306 to 307 are a possible implementation manner of determining the area where the whistle vehicle is located based on the signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone. The source of the whistle vehicle is determined by the source microphone based on the highest energy sound signal. Since the signal energy can reflect the distance between the sound source and the microphone, the signal energy is larger, indicating that the closer the sound source is to the microphone, The method determines the accuracy and reliability of the area where the whistle vehicle is located.

308. The monitoring device acquires a monitoring image of the controlled area captured by the camera.

After determining the area where the whistle vehicle is located, in order to avoid misjudgment, the video monitor can be combined to further determine the whistle vehicle. The process of acquiring the monitoring image may be to acquire a multi-frame monitoring image within a preset time period before the current time point to identify whether a vehicle is whistling. Of course, the acquired monitoring image may also be a multi-frame monitoring image in a period of time before and after the current time point.

309. The monitoring device determines an image corresponding to the area in the monitoring image.

Based on the area determined in step 307, the monitoring device may determine an image corresponding to the area where the whistle vehicle is located in the acquired monitoring image. Of course, the monitoring device may extract the multi-frame image corresponding to the area from the multi-frame monitoring image. .

310. Perform motion recognition on the image based on an action feature of a preset action, and determine the vehicle as the whistle vehicle when the action feature is included in an image of any of the images.

For a whistle car, the driver will make some specific actions to make a whistle. For example, the preset action may be at least one tapping action on the steering wheel, if the action of the preset action is recognized in the image. The feature indicates that the action corresponds to the vehicle performing a whistling operation, and therefore, the detected granularity can be implemented on the vehicle. It is worth noting that when it is identified in the image that the vehicle including the action feature is greater than one, each vehicle in the image that identifies the action feature is identified as a whistle vehicle.

The above steps 308 to 310 are to identify the action corresponding to the image of the area where the whistle vehicle is located. When it is recognized that there is a preset action in any vehicle, a possible implementation manner of positioning the whistle vehicle is determined by determining the whistle. After the vehicle is in the area, the surveillance image captured by the camera is used to confirm the whistle motion recognition twice, thereby positioning the whistle vehicle, which can prevent false alarms and greatly improve the detection accuracy. The steps 308 to 310 may be performed by the monitoring device to obtain a monitoring image and perform motion recognition on the image of the area where the whistle vehicle is located, or may be an image corresponding to the area where the whistle vehicle is located by the camera of the controlled area. Perform motion recognition to locate the whistle vehicle when it is recognized that there is a preset motion in any of the vehicles. Optionally, after the positioning process, the whistle event may also be prompted. Specifically, at least one of the following reminding modes may be adopted:

A reminder mode, the monitoring device highlights the area where the whistle vehicle is located on the monitored image of the controlled area.

In order to prompt the monitoring personnel, the monitoring personnel can be notified by means of highlighting that the vehicle currently has a whistle, and the highlighting can be to circle the area with a color prompt box, so that the monitoring personnel are watching After the color prompt box, the license plate number of the vehicle can be obtained through visual observation. Further, since the monitoring image is real-time, the monitoring device can also track the position of the vehicle for the purpose of accurate prompting, and highlight the vehicle according to the movement of the vehicle to achieve the purpose of real-time prompting.

Another reminder method is to identify the license plate number of the whistle vehicle and output the identified license plate number.

In order to improve the monitoring efficiency and reduce the manual intervention, the license plate number of the determined whistle vehicle can be directly identified to obtain the vehicle number, and the vehicle number can be recorded, and the vehicle can be deducted based on the record to achieve the warning. the goal of.

The method of the present application provides a scheme for detecting the sound of a car whistle and locating a corresponding vehicle. By installing a certain number of microphones in the whisper-free area, once the vehicle violently whistle, the approximate area of the vehicle can be detected. Then, the monitoring image captured by the camera is used to confirm the whistle motion recognition twice to prevent false alarms and greatly improve the detection accuracy. Further, by determining the region where the whistle vehicle is located by using the magnitude of the signal energy, the recognition range at the time of secondary confirmation can be greatly reduced, and the detection accuracy is improved. Further, in the peak search process, the spectrum is segmented, thereby achieving the purpose of fast search.

FIG. 4 is a block diagram of an apparatus for detecting a whistle of a vehicle according to an embodiment of the present application. Referring to Figure 4, the apparatus includes a vehicle determination module 401, an area determination module 402, and a vehicle positioning module 403.

The vehicle determining module 401 is configured to determine, by using a sound signal collected by the at least one first microphone and the at least one second microphone, that there is a whistle vehicle in the controlled area; the at least one first microphone is located in the controlled area a lane setting, wherein the at least one second microphone is disposed along a vertical direction of the lane in the controlled area;

The area determining module 402 is configured to determine, according to signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone, an area where the whistle vehicle is located;

The vehicle positioning module 403 is configured to perform motion recognition on an image corresponding to the area where the whistle vehicle is located, and locate the whistle vehicle when it is recognized that there is a preset action in any of the vehicles.

In one possible implementation, the vehicle determination module 401 is configured to:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.

Further, in a possible implementation manner, the vehicle determining module 401 is configured to:

Transforming the target sound signal into a frequency domain to obtain a spectrum of the target sound signal;

Dividing the spectrum into two frequency bands, and performing peak search on the two frequency bands based on the first preset frequency and the second preset frequency;

When a peak occurs in the frequency spectrum within a preset range of the first preset frequency and the second preset frequency, it is determined that there is a whistle vehicle in the controlled area.

In one possible implementation, the vehicle determination module 401 is configured to:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation, the area determining module 402 includes:

a sound signal determining unit, configured to determine a first sound signal with the largest signal energy and a second sound signal with the largest signal energy;

And an area determining unit, configured to determine an area where the whistle vehicle is located according to a source microphone of the first sound signal and a source microphone of the second sound signal.

In a possible implementation, the area determining unit is used to:

Determining a first extension line according to a location of a source microphone of the first sound signal;

Determining a second extension line according to a location of the source microphone of the second sound signal;

Determining an intersection of the first extension line and the second extension line in the controlled area;

The sub-area in which the intersection is located in the controlled area is used as the area where the whistle vehicle is located.

In a possible implementation, the vehicle positioning module 403 is configured to:

Obtaining a monitoring image of the controlled area captured by the camera;

Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles, the vehicle is determined to be a whistle vehicle.

In a possible implementation, the device further includes a reminder module, configured to:

Highlighting the area where the whistle vehicle is located on the monitored image of the controlled area; and/or,

The license plate number of the whistle vehicle is identified, and the identified license plate number is output.

With regard to the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment relating to the method, and will not be explained in detail herein.

FIG. 5 is a schematic structural diagram of a computer device 500 according to an embodiment of the present disclosure. The computer device 500 includes a memory 501, a processor 502, and computer executable instructions stored on the memory 501 and executable on the processor 502. The processor 502, when executing the computer executable instructions, implements the following method of detecting a whistle of a vehicle:

Determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that there is a whistle vehicle in the controlled area, the first microphone is disposed along a lane in the controlled area, and the second microphone is controlled along the second microphone Set in the area perpendicular to the lane;

Determining an area where the whistle vehicle is located according to signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone;

The motion recognition is performed on the image corresponding to the area where the whistle vehicle is located, and when the preset motion is recognized in any of the vehicles, the whistle vehicle is positioned.

In a possible implementation manner, determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area includes:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area includes:

Obtaining at least one first sound signal collected by the at least one first microphone;

Obtaining at least one second sound signal collected by the at least one second microphone;

Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold exceeds a preset number;

If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation manner, when a spectrum of the target sound signal has a peak in a preset whistle sound spectrum range, determining that the whistle vehicle exists in the controlled area includes:

Transforming the target sound signal into a frequency domain to obtain a spectrum of the target sound signal;

Dividing the spectrum into two frequency bands, and performing peak search on the two frequency bands based on the first preset frequency and the second preset frequency;

When the frequency spectrum shows a peak within the preset range of the first preset frequency and the second preset frequency, it is determined that there is a whistle vehicle in the controlled area.

In a possible implementation, the determining, according to the signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone, the area where the whistle vehicle is located includes:

Determining a first sound signal having the largest signal energy and a second sound signal having the largest signal energy;

The area in which the whistle vehicle is located is determined based on the position of the source microphone of the first sound signal and the source microphone of the second sound signal.

In a possible implementation, the determining, according to the location of the source microphone of the first sound signal and the source microphone of the second sound signal, the area where the whistle vehicle is located includes:

Determining a first extension line according to a location of the source microphone of the first sound signal;

Determining a second extension line according to a location of the source microphone of the second sound signal;

Determining an intersection of the first extension line and the second extension line in the controlled area;

The sub-area in which the intersection is located in the controlled area is used as the area where the whistle vehicle is located.

In a possible implementation manner, the image corresponding to the area where the whistle vehicle is located is motion-recognized, and when it is recognized that there is a preset action in any of the vehicles, the positioning whistle vehicle includes:

Obtaining a monitoring image of the controlled area captured by the camera;

In the monitoring image, determining an image corresponding to the area where the whistle vehicle is located;

The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles in the image, the vehicle is determined to be a whistle vehicle.

In one possible implementation, after locating the whistle vehicle, the processor is further configured to:

Highlighting the area where the whistle vehicle is located on the monitored image of the controlled area; and/or,

The license plate number of the whistle vehicle is identified, and the recognized license plate number is output.

The embodiment of the present application further provides a computer readable storage medium, when the instructions in the computer readable storage medium are executed by a processor of a device for detecting a whistle of a vehicle, so that the device for detecting the whistle of the vehicle can perform the above detection The method of the vehicle whistling.

Other embodiments of the present application will be readily apparent to those skilled in the <RTIgt; The present application is intended to cover any variations, uses, or adaptations of the application, which are in accordance with the general principles of the application and include common general knowledge or common technical means in the art that are not disclosed in the disclosure. . The specification and examples are to be regarded as illustrative only,

It is to be understood that the invention is not limited to the details of the details and The scope of the present application is limited only by the accompanying claims.

Claims (24)

1. A method of detecting a whistle of a vehicle, the method being applied to a computer device, the method comprising:

   Determining the presence of a whistle vehicle in the controlled area by the sound signal collected by the at least one first microphone and the at least one second microphone, the first microphone being disposed along a lane in the controlled area, the second microphone edge The controlled area is disposed in a direction perpendicular to the lane;

   Determining an area where the whistle vehicle is located according to signal energy of a sound signal collected by the at least one first microphone and the at least one second microphone;

   Performing motion recognition on an image corresponding to the area where the whistle vehicle is located, and positioning the whistle vehicle when it is recognized that there is a preset action in any of the vehicles.
2. The method according to claim 1, wherein the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area comprises:

   Obtaining at least one first sound signal collected by the at least one first microphone;

   Obtaining at least one second sound signal collected by the at least one second microphone;

   Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

   When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.
3. The method of claim 1, wherein the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, the presence of the whistle vehicle in the controlled area comprises:

   Obtaining at least one first sound signal collected by the at least one first microphone;

   Obtaining at least one second sound signal collected by the at least one second microphone;

   Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

   If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.
4. The method according to claim 2, wherein when the spectrum of the target sound signal has a peak in a predetermined whistle sound spectrum range, determining that the whistle vehicle exists in the controlled area comprises:

   Transforming the target sound signal into a frequency domain to obtain a spectrum of the target sound signal;

   Dividing the spectrum into two frequency bands, and performing peak search on the two frequency bands based on the first preset frequency and the second preset frequency;

   When a peak occurs in the frequency spectrum within a preset range of the first preset frequency and the second preset frequency, it is determined that there is a whistle vehicle in the controlled area.
5. The method according to claim 2 or 3, wherein the signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone determines the location of the whistle vehicle The area includes:

   Determining a first sound signal having the largest signal energy and a second sound signal having the largest signal energy;

   Determining an area in which the whistle vehicle is located based on a position of a source microphone of the first sound signal and a source microphone of the second sound signal.
6. The method according to claim 5, wherein the determining, according to the location of the source microphone of the first sound signal and the source microphone of the second sound signal, the area in which the whistle vehicle is located comprises:

   Determining a first extension line according to a location of a source microphone of the first sound signal;

   Determining a second extension line according to a location of the source microphone of the second sound signal;

   Determining an intersection of the first extension line and the second extension line in the controlled area;

   The sub-area in which the intersection is located in the controlled area is used as the area where the whistle vehicle is located.
7. The method according to claim 1, wherein the image corresponding to the area where the whistle vehicle is located is motion-recognized, and when it is recognized that there is a preset action in any of the vehicles, the positioning of the whistle vehicle includes:

   Obtaining a monitoring image of the controlled area captured by the camera;

   Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

   The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles, the vehicle is determined to be a whistle vehicle.
8. The method of claim 1 wherein after the location of the whistle vehicle, the method further comprises:

   Highlighting an area where the whistle vehicle is located on a monitored image of the controlled area; and/or,

   The license plate number of the whistle vehicle is identified, and the identified license plate number is output.
9. A device for detecting a whistle of a vehicle, characterized in that the device comprises:

   a vehicle determining module, configured to determine, by the sound signal collected by the at least one first microphone and the at least one second microphone, a whistle vehicle in the controlled area; the first microphone is disposed along a lane in the controlled area, The second microphone is disposed along the vertical direction of the lane in the controlled area;

   a region determining module, configured to determine an area where the whistle vehicle is located according to signal energy of a sound signal collected by the at least one first microphone and the at least one second microphone;

   The vehicle positioning module is configured to perform motion recognition on an image corresponding to the area where the whistle vehicle is located, and locate the whistle vehicle when it is recognized that there is a preset action in any of the vehicles.
10. The apparatus according to claim 9, wherein said vehicle determination module is configured to:

    Obtaining at least one first sound signal collected by the at least one first microphone;

    Obtaining at least one second sound signal collected by the at least one second microphone;

    Determining a target sound signal, wherein the target sound signal is a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

    When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.
11. The apparatus according to claim 9, wherein said vehicle determination module is configured to:

    Obtaining at least one first sound signal collected by the at least one first microphone;

    Obtaining at least one second sound signal collected by the at least one second microphone;

    Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

    If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.
12. The device according to claim 10 or 11, wherein the area determining module comprises:

    a sound signal determining unit, configured to determine a first sound signal with the largest signal energy and a second sound signal with the largest signal energy;

    And an area determining unit, configured to determine an area where the whistle vehicle is located according to a source microphone of the first sound signal and a source microphone of the second sound signal.
13. The apparatus according to claim 9, wherein said vehicle positioning module is configured to:

    Obtaining a monitoring image of the controlled area captured by the camera;

    Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

    The motion recognition of the image is performed based on the motion feature of the preset motion, and when the motion feature is included in the image of any of the vehicles, the vehicle is determined to be a whistle vehicle.
14. The device according to claim 9, wherein the device further comprises a reminding module, configured to:

    Highlighting an area where the whistle vehicle is located on a monitored image of the controlled area; and/or,

    The license plate number of the whistle vehicle is identified, and the identified license plate number is output.
15. A computer device comprising a memory, a processor, and computer executable instructions stored on the memory and executable on the processor, wherein the processor is configured to execute the computer executable instructions The following method:

    Determining the presence of a whistle vehicle in the controlled area by the sound signal collected by the at least one first microphone and the at least one second microphone, the first microphone being disposed along a lane in the controlled area, the second microphone edge The controlled area is disposed in a direction perpendicular to the lane;

    Determining an area where the whistle vehicle is located according to signal energy of a sound signal collected by the at least one first microphone and the at least one second microphone;

    Performing motion recognition on an image corresponding to the area where the whistle vehicle is located, and positioning the whistle vehicle when it is recognized that there is a preset action in any of the vehicles.
16. The computer device according to claim 15, wherein the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area comprises:

    Obtaining at least one first sound signal collected by the at least one first microphone;

    Obtaining at least one second sound signal collected by the at least one second microphone;

    Determining a target sound signal, the target sound signal being a signal having the highest signal energy of the at least one first sound signal and the at least one second sound signal;

    When the spectrum of the target sound signal peaks in the preset whistle sound spectrum range, it is determined that there is a whistle vehicle in the controlled area.
17. The computer device according to claim 15, wherein the determining, by the sound signal collected by the at least one first microphone and the at least one second microphone, that the whistle vehicle exists in the controlled area comprises:

    Obtaining at least one first sound signal collected by the at least one first microphone;

    Obtaining at least one second sound signal collected by the at least one second microphone;

    Determining whether the number of sound signals of the at least one first sound signal and the at least one second sound signal exceeding a preset threshold reaches a preset number;

    If the preset number is reached, it is determined that there is a whistle vehicle in the controlled area.
18. The computer device according to claim 16, wherein when the spectrum of the target sound signal has a peak in a predetermined whistle sound spectrum range, determining that the whistle vehicle exists in the controlled area comprises:

    Transforming the target sound signal into a frequency domain to obtain a spectrum of the target sound signal;

    Dividing the spectrum into two frequency bands, and performing peak search on the two frequency bands based on the first preset frequency and the second preset frequency;

    When a peak occurs in the frequency spectrum within a preset range of the first preset frequency and the second preset frequency, it is determined that there is a whistle vehicle in the controlled area.
19. The computer device according to claim 16 or 17, wherein the signal energy of the sound signal collected by the at least one first microphone and the at least one second microphone determines that the whistle vehicle is located The areas include:

    Determining a first sound signal having the largest signal energy and a second sound signal having the largest signal energy;

    Determining an area in which the whistle vehicle is located based on a position of a source microphone of the first sound signal and a source microphone of the second sound signal.
20. The computer device according to claim 19, wherein the determining, according to the location of the source microphone of the first sound signal and the source microphone of the second sound signal, the area in which the whistle vehicle is located comprises:

    Determining a first extension line according to a location of a source microphone of the first sound signal;

    Determining a second extension line according to a location of the source microphone of the second sound signal;

    Determining an intersection of the first extension line and the second extension line in the controlled area;

    The sub-area in which the intersection is located in the controlled area is used as the area where the whistle vehicle is located.
21. The computer device according to claim 15, wherein the image corresponding to the area where the whistle vehicle is located is motion-recognized, and when it is recognized that there is a preset action in any of the vehicles, the positioning of the whistle vehicle includes :

    Obtaining a monitoring image of the controlled area captured by the camera;

    Determining, in the monitoring image, an image corresponding to an area where the whistle vehicle is located;

    The image is motion-recognized based on the action feature of the preset action, and when the action feature is included in the image of any of the images, the vehicle is determined to be a whistle vehicle.
22. The computer apparatus according to claim 15, wherein said processor is further configured to: after positioning the whistle vehicle:

    Highlighting an area where the whistle vehicle is located on a monitored image of the controlled area; and/or,

    The license plate number of the whistle vehicle is identified, and the identified license plate number is output.
23. A computer readable storage medium, wherein the computer readable storage medium stores instructions, the instructions being executed by a processor to perform the method of detecting a whistle of a vehicle according to any one of claims 1-8 .
24. A system for detecting a whistle of a vehicle, characterized in that the system comprises:

    At least one first microphone disposed along a lane within the controlled area;

    Having at least one second microphone disposed in a direction perpendicular to the lane in the controlled area;

    a camera for monitoring the controlled area;

    A computer device as claimed in any one of claims 15 to 22.

Images