A method, device and computer readable storage medium for identifying a modified vehicle

Abstract

Embodiments of the present application disclose a modified vehicle identification method, device and computer readable storage medium, the method comprising: obtaining a target video containing a sound with a sound decibel number greater than or equal to a preset decibel threshold; obtaining a first trend of a sound wave signal of the sound in the target video changing over time; obtaining a second trend of speed information of all vehicles in the target video changing over time; and determining a vehicle satisfying a preset judgment rule between the first trend and the second trend as a modified vehicle. Through the embodiment scheme, the modified vehicle identification is realized based on the current vehicle monitoring equipment at low cost, which is conducive to large-scale promotion and use.

Description

Technical Field

[0001] This application relates to vehicle monitoring technology, and more particularly to a method, apparatus and computer-readable storage medium for identifying modified vehicles. Background Technology

[0002] Illegal vehicle modification is a criminal offense. In addition to the potential safety hazards caused by altering vehicle parameters, modifications to the engine and exhaust system can also generate noise, commonly known as "street noise," which disrupts people's daily lives.

[0003] Currently, the identification of modified cars is still in the stage of human identification. One important method of identifying modified cars is based on sound recognition, such as identifying the special sounds produced after modifying the engine and exhaust system.

[0004] One existing sound localization method requires two or more sound acquisition devices to simultaneously collect sound information. Based on the different locations of the two microphones and the different times they receive sound feedback, the location range of the specific noise is determined. This is then combined with the vehicle positions captured in video to identify modified vehicles from traffic flow. However, this method relies on special cameras or specialized equipment with sound localization capabilities, and the backend server also needs video content analysis capabilities to determine the physical location of the vehicle to correlate with the sound source. The cost of camera modification or scene construction is high, hindering large-scale promotion and use. Summary of the Invention

[0005] This application provides a method, apparatus, and computer-readable storage medium for identifying modified vehicles, which can achieve the identification of modified vehicles at low cost based on current vehicle monitoring equipment, and is conducive to large-scale promotion and use.

[0006] This application provides a method for identifying modified vehicles, which may include:

[0007] Acquire target videos containing sound with a decibel level greater than or equal to a preset decibel threshold;

[0008] Obtain a first trend of the acoustic wave signal of the sound in the target video changing over time;

[0009] Obtain the second trend of the speed information of all vehicles in the target video changing over time;

[0010] Vehicles that satisfy the first trend and the second trend according to preset judgment rules are identified as modified vehicles.

[0011] In an exemplary embodiment of this application, the acoustic signal may include: an acoustic oscillation frequency; the first trend may include a trend of change in the acoustic oscillation frequency;

[0012] The velocity information may include acceleration; the second trend may include the acceleration change trend.

[0013] In an exemplary embodiment of this application, determining a vehicle whose first trend and second trend satisfy a preset judgment rule as a modified vehicle may include:

[0014] Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration are identified as modified vehicles.

[0015] In an exemplary embodiment of this application, determining that the time points of change of the acoustic wave oscillation frequency and the acceleration change trend are consistent may include:

[0016] Obtain the first moment when the acceleration begins to increase from zero;

[0017] Obtain the second moment when the sound wave oscillation frequency begins to increase;

[0018] Obtain the third moment when the acceleration increases to its maximum.

[0019] The fourth moment when the sound wave oscillation frequency increases to the maximum sound wave oscillation frequency is obtained;

[0020] When the first moment and the second moment coincide, and the third moment and the fourth moment coincide, it is determined that the time nodes of the change trends of the acoustic wave oscillation frequency and the acceleration change trends are consistent.

[0021] In an exemplary embodiment of this application, the acoustic signal may include: an acoustic oscillation frequency; the first trend includes a trend of change in the acoustic oscillation frequency;

[0022] The velocity information may include acceleration and velocity; the second trend includes the acceleration change trend and the velocity change trend.

[0023] In an exemplary embodiment of this application, determining a vehicle whose first trend and second trend satisfy a preset judgment rule as a modified vehicle may include:

[0024] Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration, and whose similarity between the acoustic oscillation frequency and the velocity changes is greater than or equal to a preset similarity threshold, are identified as modified vehicles.

[0025] In an exemplary embodiment of this application, obtaining the similarity between the trend of change in the acoustic wave oscillation frequency and the trend of change in velocity may include:

[0026] Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity;

[0027] During the period of change of the sound wave oscillation frequency, the slopes of the first curve and the second curve are compared in each time slice with a preset duration;

[0028] Obtain the number of first time slices in which the slopes of the first curve and the second curve are both positive or both are negative within the same time slice;

[0029] The proportion of the number of the first time slices to the total number of time slices within the change period is calculated as the similarity between the first curve and the second curve.

[0030] In an exemplary embodiment of this application, obtaining the similarity between the trend of change in the acoustic wave oscillation frequency and the trend of change in velocity may include:

[0031] Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity;

[0032] During the first time period when the sound wave oscillation frequency changes and the second time period when the sound wave oscillation frequency stops changing, the slopes of the first curve and the second curve are compared in each time slice with a preset duration.

[0033] The number of second time slices in the first time period in which the slopes of the first curve and the second curve are both positive or both are negative is obtained, and the sum of the number of third time slices in the second time period in which the second curve continues to maintain a positive or negative value;

[0034] The ratio of the sum of the number of the second time slices and the number of the third time slices to the total number of time slices in the first and second time periods is used as the similarity between the first curve and the second curve.

[0035] This application also provides a modified vehicle identification device, which may include a processor and a computer-readable storage medium. The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the modified vehicle identification method is implemented.

[0036] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the modified vehicle identification method.

[0037] Compared with related technologies, the embodiments of this application may include: acquiring a target video containing sound with a decibel level greater than or equal to a preset decibel threshold; acquiring a first trend of the sound wave signal of the sound in the target video changing over time; acquiring a second trend of the speed information of all vehicles in the target video changing over time; and identifying vehicles whose first trend and second trend satisfy a preset judgment rule as modified vehicles. This embodiment achieves low-cost identification of modified vehicles based on current vehicle monitoring equipment, facilitating large-scale promotion and use.

[0038] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the solutions described in the description and the accompanying drawings. Attached Figure Description

[0039] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0040] Figure 1 This is a flowchart of the modified vehicle identification method according to an embodiment of this application;

[0041] Figure 2 This is a schematic diagram illustrating the relationship between the oscillation frequency and time of a pitch-increasing oscillation according to an embodiment of this application.

[0042] Figure 3 This is a schematic diagram illustrating the relationship between the vehicle's speed and acceleration and time during an acceleration process according to an embodiment of this application.

[0043] Figure 4 This is a schematic diagram illustrating the changes in frequency, velocity, and acceleration in an embodiment of this application;

[0044] Figure 5 This is a schematic diagram illustrating the identification of modified vehicles based on the consistency of time points in the changing trends of sound wave oscillation frequency and acceleration, according to an embodiment of this application.

[0045] Figure 6 This is a schematic diagram illustrating the identification of modified vehicles based on speed curves and oscillation frequency curves according to an embodiment of this application.

[0046] Figure 7 This is a block diagram of the modified vehicle identification device according to an embodiment of this application. Detailed Implementation

[0047] This application describes several embodiments, but these descriptions are exemplary and not restrictive, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0048] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive scheme as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive schemes to form another unique inventive scheme as defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.

[0049] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0050] This application provides a method for identifying modified vehicles, such as... Figure 1 As shown, it may include steps S101-S104:

[0051] S101. Obtain the target video containing sound with a decibel level greater than or equal to a preset decibel threshold.

[0052] In an exemplary embodiment of this application, acquiring the target video with a sound decibel level greater than or equal to a preset decibel threshold may include:

[0053] When the microphone on the speed camera picks up a sound with a decibel level greater than or equal to a preset decibel threshold, it sends a noise alarm to the backend analysis server.

[0054] The command instructs the backend analysis server to extract the video recorded within the duration of the noise, and use it as the target video.

[0055] In an exemplary embodiment of this application, when the microphone on the speed camera detects noise with a decibel level higher than a certain value (such as the aforementioned decibel threshold, which can be defined according to different application scenarios and is not limited to a specific value), a noise alarm can be generated and sent to the backend analysis server. The backend analysis server will extract the video recorded during the duration of the noise and use it as the target video for subsequent retrospective evidence collection.

[0056] In an exemplary embodiment of this application, the method may further include:

[0057] After receiving the noise alarm, the backend analysis server is instructed to use a deep learning algorithm to filter the sounds that generated the noise alarm and exclude one or more preset sounds from the sounds.

[0058] In an exemplary embodiment of this application, the backend server can use a deep learning algorithm to filter the sounds that generate alarms. For example, it can learn from samples to pre-collect various common high-decibel sounds as preset sounds, such as car horns, shouts, and broadcasts. By inputting the audio data from the target video into the preset deep learning model, interfering noises such as car horns can be eliminated, thereby improving the accuracy of noise recognition for modified vehicles.

[0059] S102. Obtain the first trend of the sound wave signal of the sound in the target video changing over time.

[0060] In an exemplary embodiment of this application, sound information can be converted into an audio digital signal. Analyzing the digital signal can yield sound wave signals, such as sound wave oscillation frequency, sound wave amplitude, and sound wave duration. The obtained sound wave signal can be continuously tracked and recorded to obtain the trend of the sound wave signal changing over time, i.e., a first trend.

[0061] In an exemplary embodiment of this application, the solution can primarily analyze the oscillation frequency of the sound wave signal, i.e., the "pitch". The higher the oscillation frequency of the sound wave signal, the higher the pitch; conversely, the lower the oscillation frequency, the lower the pitch. Here, the trend of the oscillation frequency of the collected sound (potentially modified car noise) over time can be recorded as this first trend.

[0062] In exemplary embodiments of this application, as Figure 2 The figure shown is a schematic diagram illustrating the trend of oscillation frequency with increasing pitch over time.

[0063] S103. Obtain the second trend of the speed information of all vehicles in the target video changing over time.

[0064] In an exemplary embodiment of this application, there may be multiple vehicles in the target video collected in the aforementioned scheme. At this time, it is not yet possible to determine which vehicle the noise from the modified vehicle comes from. Therefore, the speed information of the vehicle can be further obtained to prepare for subsequent judgment.

[0065] In an exemplary embodiment of this application, the vehicle speed information can be obtained from an existing speed camera (which may include, but is not limited to, radar speed measurement, video speed measurement, etc.), and the speed camera can measure the speed information of the vehicle appearing in the target video.

[0066] In an exemplary embodiment of this application, the speed information may include speed and acceleration. After acquiring the speed of each vehicle, the corresponding acceleration can be acquired based on the change of the speed over a certain period of time.

[0067] In an exemplary embodiment of this application, the trend of velocity and / or acceleration over time can be used as a second trend. For example... Figure 3 The figure shows a schematic diagram illustrating the relationship between a vehicle's speed and acceleration and time during an acceleration process.

[0068] S104. Vehicles that satisfy the first trend and the second trend according to the preset judgment rules are identified as modified vehicles.

[0069] In the exemplary embodiments of this application, generally speaking, when a vehicle is traveling at a constant speed, the power generated by the engine drives the wheels to rotate. The traction force generated by the friction between the tires and the ground is the same as the various resistances of the vehicle's movement, the vehicle acceleration is 0, and the speed remains constant. Under constant road conditions, the engine speed is a constant value, and the exhaust volume and cycle of the engine are also relatively fixed. At this time, the frequency and amplitude of air vibrations are the same when compared in each exhaust cycle, that is, the generated noise tone is also periodically the same.

[0070] In an exemplary embodiment of this application, when the driver presses the accelerator, the engine speed increases. At the instant of acceleration, the vehicle accelerates because the driving force exceeds the resistance forces, causing the acceleration to jump from zero. The vehicle speed increases accordingly until the driving force and resistance forces cancel each other out again, the acceleration returns to zero, and the speed returns to a constant level. Simultaneously, the increased accelerator speed and exhaust volume lead to faster airflow within the exhaust system, potentially generating more standing waves. This increases the air oscillation frequency, resulting in a higher pitch. To human hearing, the noise appears denser and sharper; to digital signals, the sound wave oscillation frequency is also increased. Therefore, for modified vehicles, the speed and noise generated by different engine speeds exhibit a similar trend with time. The specific relationship is described below.

[0071] In an exemplary embodiment of this application, the moment when the engine speed (i.e., the vehicle speed) increases can be decomposed into an infinitesimally small time interval. At the instant t1 when the engine speed increases, it is as follows: Figure 4 The diagram shows the changes in frequency, velocity, and acceleration.

[0072] In exemplary embodiments of this application, as Figure 4 As shown, at time t1, the engine speed increases, the engine exhaust increases, and the air vibration causes the sound wave oscillation frequency to increase, resulting in increased propulsion and speed. This continues until time t2, when the propulsion and various resistances are equal, and the speed returns to uniformity. Acceleration experiences a jump at the instant the engine speed increases and immediately decays, returning to 0 at time t2.

[0073] In an exemplary embodiment of this application, by Figure 4 It can be seen that when a vehicle accelerates, the engine speed increases, and the relationship between the sound oscillation frequency and the vehicle's speed and acceleration is as follows:

[0074] ①At the instant the sound oscillation frequency increases, the acceleration value jumps upward and then approaches 0 after this moment;

[0075] ②The trend of increasing sound oscillation frequency is similar to the trend of increasing vehicle speed, but the speed increase is delayed.

[0076] In the exemplary embodiments of this application, similarly, when the vehicle decelerates, the engine speed decreases, and the relationship between the sound oscillation frequency and the vehicle's speed and acceleration is as follows:

[0077] ① At the instant when the frequency of sound oscillation decreases, the acceleration value jumps downward (for example, from 0 to a negative value), and then approaches 0 after this moment;

[0078] ②The decreasing trend of sound oscillation frequency is similar to the decreasing trend of vehicle speed, but the decrease in speed is delayed.

[0079] In an exemplary embodiment of this application, based on the relationship between the sound oscillation frequency and the vehicle speed and acceleration as described above, it can be known that the trend of the collected noise oscillation frequency changing with time (i.e., the first trend) can be compared with the trend of the speed / acceleration of all vehicles changing with time within the corresponding time period (i.e., the second trend), and vehicles whose first trend and second trend satisfy a preset judgment rule are identified as modified vehicles.

[0080] In an exemplary embodiment of this application, specifically, vehicles that have the same acceleration change time node and noise oscillation frequency change time node, and whose speed change trend curve and oscillation frequency change trend curve are similar, can be identified as modified vehicles.

[0081] In the exemplary embodiments of this application, due to differences in the modification effects and engine performance of modified vehicles, there may be some error in judging the similarity between the speed change trend curve and the oscillation frequency change trend curve. Therefore, it is preferable to use the relationship between the changing trends of oscillation frequency and acceleration as the standard for identifying modified vehicles. Alternatively, the relationship between the changing trends of oscillation frequency and acceleration, along with the similarity between the speed change trend curve and the oscillation frequency change trend curve, can be used together as the judgment standard for identifying modified vehicles. The two schemes are described below.

[0082] Option 1

[0083] In an exemplary embodiment of this application, the acoustic signal may include: an acoustic oscillation frequency; the first trend may include a trend of change in the acoustic oscillation frequency;

[0084] The velocity information may include acceleration; the second trend may include the acceleration change trend.

[0085] In an exemplary embodiment of this application, determining a vehicle whose first trend and second trend satisfy a preset judgment rule as a modified vehicle may include:

[0086] Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration are identified as modified vehicles.

[0087] In an exemplary embodiment of this application, since the acceleration and noise are not from the same vehicle, it is difficult for the frequency change time point in the sound wave oscillation frequency change trend and the acceleration change time point in the acceleration change trend to be consistent. Therefore, if it can be determined that the frequency change time point in the sound wave oscillation frequency change trend of the acquired noise is consistent with the acceleration change time point in the acceleration change trend of a certain vehicle, then it is highly likely that the noise is emitted by the current vehicle, and thus it can be determined that the vehicle is a modified vehicle.

[0088] In an exemplary embodiment of this application, determining that the time points of change of the acoustic wave oscillation frequency and the acceleration change trend are consistent may include:

[0089] Obtain the first moment when the acceleration increases from zero;

[0090] The second moment when the sound wave oscillation frequency begins to increase is obtained;

[0091] The third moment when the acceleration increases to the maximum acceleration is obtained; the third moment refers to the moment when the acceleration increases to an acceleration value, which will begin to decrease in a preset period of time after that moment; the acceleration value is the maximum acceleration;

[0092] The fourth moment when the sound wave oscillation frequency increases to the maximum sound wave oscillation frequency is obtained; the fourth moment refers to the moment when the sound wave oscillation frequency increases to a sound wave oscillation frequency value, which will be maintained for a subsequent preset period of time; the sound wave oscillation frequency value is the maximum sound wave oscillation frequency.

[0093] When the first moment and the second moment coincide, and the third moment and the fourth moment coincide, it is determined that the time nodes of the change trends of the acoustic wave oscillation frequency and the acceleration change trends are consistent.

[0094] In exemplary embodiments of this application, as Figure 5 As shown, at time t2 (i.e., the first and second time points), the oscillation frequency of the noise is ( Figure 5 (As shown by the solid line) begins to increase, acceleration ( Figure 5 As shown by the dashed line, there is a sudden transition from 0. From time t2 to t3, the oscillation frequency of the noise gradually increases, and the acceleration also gradually increases. At time t3 (i.e., the third and fourth time points), the oscillation frequency of the noise remains unchanged, while the acceleration returns to 0. The time points of the changes in the sound wave oscillation frequency and the acceleration are consistent.

[0095] Option 2

[0096] In an exemplary embodiment of this application, the acoustic signal may include: an acoustic oscillation frequency; the first trend includes a trend of change in the acoustic oscillation frequency;

[0097] The velocity information may include acceleration and velocity; the second trend includes the acceleration change trend and the velocity change trend.

[0098] In an exemplary embodiment of this application, determining a vehicle whose first trend and second trend satisfy a preset judgment rule as a modified vehicle may include:

[0099] Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration, and whose similarity between the acoustic oscillation frequency and the velocity changes is greater than or equal to a preset similarity threshold, are identified as modified vehicles.

[0100] In the exemplary embodiments of this application, the similarity threshold can be defined according to different application scenarios, and is not limited in detail here.

[0101] In the exemplary embodiments of this application, since there is no necessary functional relationship between speed change and sound wave change in numerical terms, but there is an implicit correlation in trend, the embodiments of this application only compare the changing trends of speed and sound waves, and do not compare specific numerical values.

[0102] In an exemplary embodiment of this application, based on the identification of modified vehicles according to the time nodes of the change trends of sound wave oscillation frequency and acceleration, the similarity judgment of the change trends of sound wave oscillation frequency and speed can be added, which can further improve the identification accuracy.

[0103] In an exemplary embodiment of this application, in order to ensure the feasibility of Scheme 2, it is necessary to accurately determine the similarity between the changing trends of the sound wave oscillation frequency and the changing trends of the velocity. Specifically, the following scheme can be used to determine this.

[0104] In an exemplary embodiment of this application, obtaining the similarity between the trend of change in the acoustic wave oscillation frequency and the trend of change in velocity may include:

[0105] Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity;

[0106] During the period of change of the sound wave oscillation frequency, the slopes of the first curve and the second curve are compared in each time slice with a preset duration;

[0107] Obtain the number of first time slices in which the slopes of the first curve and the second curve are both positive or both are negative within the same time slice;

[0108] The proportion of the number of the first time slices to the total number of time slices within the change period is calculated as the similarity between the first curve and the second curve.

[0109] In an exemplary embodiment of this application, the preset duration can be defined according to different application scenarios, and no specific value is limited. For example, it can be 1 second, that is, it can be set to take 1 second as a time slice and obtain the curve (first curve and second curve) within 1 second for comparison.

[0110] In an exemplary embodiment of this application, during the period of oscillation frequency change, the slopes of the first curve and the second curve in each time slice can be compared. If the slopes of the first curve and the second curve are both positive or both negative in the same time slice, then the first curve and the second curve in that time slice can be considered to be the same.

[0111] In an exemplary embodiment of this application, according to this scheme, time slices in all time slices within the period of change of sound wave oscillation frequency that have the same first curve and second curve can be found, the proportion of these time slices to all time slices can be calculated, and the calculated ratio can be used as the similarity between the first curve and the second curve.

[0112] In an exemplary embodiment of this application, the following scheme can also be used to obtain the similarity between the trend of change of the acoustic wave oscillation frequency and the trend of change of the velocity.

[0113] In an exemplary embodiment of this application, obtaining the similarity between the trend of change in the acoustic wave oscillation frequency and the trend of change in velocity may include:

[0114] Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity;

[0115] During the first time period when the sound wave oscillation frequency changes and the second time period when the sound wave oscillation frequency stops changing, the slopes of the first curve and the second curve are compared in each time slice with a preset duration.

[0116] The number of second time slices in the first time period in which the slopes of the first curve and the second curve are both positive or both are negative is obtained, and the sum of the number of third time slices in the second time period in which the second curve continues to maintain a positive or negative value;

[0117] The ratio of the sum of the number of the second time slices and the number of the third time slices to the total number of time slices is calculated as the similarity between the first curve and the second curve.

[0118] In an exemplary embodiment of this application, the solution includes a certain period after the oscillation frequency stops changing within the similarity judgment period. Within this period, if the velocity curve (i.e., the second curve) continues to maintain a positive or negative value within a time slice, the first and second curves can be considered identical. Based on this idea, the similarity judgment period is extended, which can improve the accuracy of similarity calculation.

[0119] In exemplary embodiments of this application, two specific embodiments of the proposed solutions are given below.

[0120] In exemplary embodiments of this application, as Figure 5 As shown in the figure, the curve of the oscillation frequency change trend of the noise of a modified car is as follows: Figure 5 As shown by the dashed line in the figure, the curve depicting the acceleration trend of a certain vehicle is as follows: Figure 5 As shown by the solid line, at time t2, the noise oscillation frequency increases, and the acceleration undergoes a sudden jump from 0. From time t2 to t3, the noise oscillation frequency gradually increases, and the acceleration also gradually increases. At time t3, the noise oscillation frequency remains unchanged, while the acceleration returns to 0. This conforms to the rule mentioned earlier that the time points of the changes in sound wave oscillation frequency and acceleration are consistent. Therefore, the vehicle can be considered a modified vehicle.

[0121] In exemplary embodiments of this application, as Figure 6 As shown, similarly Figure 5 Taking a vehicle as an example, the oscillation frequency variation curve of this vehicle (i.e., the first curve) is as follows: Figure 6 As shown by the dashed line in the image, the vehicle's speed curve (i.e., the second curve) is as follows: Figure 6 As shown by the solid line, the number of time units allowed for speed to continue changing is the same as the number of time units allowed for frequency to change. The speed curve and the oscillation frequency curve have the same trend from time 0 to t4 and from time t5 to t6. The speed curve and the oscillation frequency curve have different trends from time t4 to t5. The similarity between the current speed curve and the oscillation frequency curve is calculated to be 83%. If the pre-set similarity threshold is 70%, then the vehicle can be considered a modified vehicle.

[0122] In an exemplary embodiment of this application, in a traffic flow with multiple vehicles, the probability that each vehicle simultaneously accelerates and decelerates at every moment in the video is low. Therefore, through the solution of this embodiment, in a traffic flow with multiple vehicles, the noise of the modified vehicle can be linked to the vehicle in the captured video by analyzing the frequency change of noise and the acceleration and speed change of the vehicle, thereby realizing the identification of the modified vehicle.

[0123] In the exemplary embodiments of this application, the above describes a method for identifying modified vehicles in the backend of traffic flow with multiple interfering targets based on audio and video content analysis, as proposed in this application. It utilizes existing, widely deployed speed cameras to measure changes in vehicle speed and acceleration; and determines the sound of the modified vehicle and its sound characteristic changes based on audio and video acquisition. By analyzing the changing trends in two dimensions (sound information and speed information), the vehicle and noise are linked, thereby achieving the identification of modified vehicles.

[0124] In the exemplary embodiments of this application, the solutions of the embodiments of this application have at least the following advantages:

[0125] 1. No need to use professional sound source localization cameras or devices, nor is it necessary for the backend server to have the video content analysis capability to analyze the vehicle position in the video. In the context of the large-scale application of speed cameras, noise and vehicles can be correlated simply by processing the data fed back by the speed camera at the backend. Modified vehicles can be identified at low cost, achieving the technical effect of low construction cost, high recognition efficiency, and strong applicability.

[0126] 2. Existing methods for identifying modified vehicles mostly rely on public reports and manual enforcement. The modified vehicle identification method proposed in this application solves the problem of difficulty in identifying modified vehicles using existing technologies.

[0127] This application also provides a modified vehicle identification device 1, such as... Figure 7 As shown, it may include a processor 11 and a computer-readable storage medium 12, wherein the computer-readable storage medium 12 stores instructions that, when executed by the processor 11, implement the modified vehicle identification method.

[0128] In the exemplary embodiments of this application, any of the embodiments in the foregoing method embodiments are applicable to the embodiments of the modified vehicle identification device, and will not be described in detail here.

[0129] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the modified vehicle identification method.

[0130] In the exemplary embodiments of this application, any of the embodiments in the foregoing method embodiments are applicable to the computer-readable storage medium embodiments, and will not be described in detail here.

[0131] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for identifying modified vehicles, characterized in that, The method includes: Acquire target videos containing sound with a decibel level greater than or equal to a preset decibel threshold; A first trend of the change of the sound wave signal of the sound in the target video over time is obtained; the sound wave signal includes: sound wave oscillation frequency; the first trend includes the change trend of the sound wave oscillation frequency; Obtain the second trend of the speed information of all vehicles in the target video changing over time; Vehicles that satisfy the first trend and the second trend according to preset judgment rules are identified as modified vehicles.

2. The modified vehicle identification method according to claim 1, characterized in that, The velocity information includes acceleration; the second trend includes the acceleration change trend.

3. The modified vehicle identification method according to claim 2, characterized in that, The step of identifying vehicles whose first trend and second trend satisfy a preset judgment rule as modified vehicles includes: Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration are identified as modified vehicles.

4. The modified vehicle identification method according to claim 3, characterized in that, Determining that the time points of the changes in the acoustic wave oscillation frequency and the acceleration change are consistent includes: Obtain the first moment when the acceleration begins to increase from zero; Obtain the second moment when the sound wave oscillation frequency begins to increase; Obtain the third moment when the acceleration increases to its maximum. The fourth moment when the sound wave oscillation frequency increases to the maximum sound wave oscillation frequency is obtained; When the first moment and the second moment coincide, and the third moment and the fourth moment coincide, it is determined that the time nodes of the change trends of the acoustic wave oscillation frequency and the acceleration change trends are consistent.

5. The modified vehicle identification method according to claim 1, characterized in that, The velocity information includes acceleration and velocity; the second trend includes the acceleration change trend and the velocity change trend.

6. The modified vehicle identification method according to claim 5, characterized in that, The step of identifying vehicles whose first trend and second trend satisfy a preset judgment rule as modified vehicles includes: Vehicles whose time points coincide with the changes in the acoustic oscillation frequency and the acceleration, and whose similarity between the acoustic oscillation frequency and the velocity changes is greater than or equal to a preset similarity threshold, are identified as modified vehicles.

7. The modified vehicle identification method according to claim 6, characterized in that, Obtaining the similarity between the trend of change in the sound wave oscillation frequency and the trend of change in the velocity includes: Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity; During the period of change of the sound wave oscillation frequency, the slopes of the first curve and the second curve are compared in each time slice with a preset duration; Obtain the number of first time slices in which the slopes of the first curve and the second curve are both positive or both are negative within the same time slice; The proportion of the number of the first time slices to the total number of time slices within the change period is calculated as the similarity between the first curve and the second curve.

8. The modified vehicle identification method according to claim 6, characterized in that, Obtaining the similarity between the trend of change in the sound wave oscillation frequency and the trend of change in the velocity includes: Obtain the first curve corresponding to the change trend of the sound wave oscillation frequency, and the second curve corresponding to the change trend of the velocity; During the first time period when the sound wave oscillation frequency changes and the second time period when the sound wave oscillation frequency stops changing, the slopes of the first curve and the second curve are compared in each time slice with a preset duration. The number of second time slices in the first time period in which the slopes of the first curve and the second curve are both positive or both are negative is obtained, and the sum of the number of third time slices in the second time period in which the second curve continues to maintain a positive or negative value; The ratio of the sum of the number of the second time slices and the number of the third time slices to the total number of time slices in the first and second time periods is used as the similarity between the first curve and the second curve.

9. A modified vehicle identification device, characterized in that, The device includes a processor and a computer-readable storage medium storing instructions that, when executed by the processor, implement the modified vehicle identification method as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the modified vehicle identification method as described in any one of claims 1-8.

Images