Method and System for Automatically Detecting Noise-Causing Vehicle Based on Acoustic Beamforming Data Performed in Terminal

Abstract

The present invention relates to a method and system for automatically detecting noise-causing vehicles based on acoustic beamforming data performed at a terminal, wherein the method and system analyze acoustic beamforming data in which acoustic pressure levels for each grid are mapped to collected image data by linking an image camera and an acoustic camera, and automatically detect moving noise sources efficiently and precisely by synchronizing the viewpoint and storing and transmitting the data to a server only when a preset trigger condition is satisfied.

Description

Technology Field

[0001] The present invention relates to a method and system for automatically detecting noise-causing vehicles based on acoustic beamforming data performed at a terminal, wherein the method and system analyze acoustic beamforming data in which acoustic pressure levels for each grid are mapped to collected image data by linking an image camera and an acoustic camera, and automatically detect moving noise sources efficiently and precisely by synchronizing the viewpoint and storing and transmitting the data to a server only when a preset trigger condition is satisfied. Background Technology

[0002] With the recent explosive growth of the delivery platform market and the resulting increase in motorcycle traffic, noise-related complaints in urban areas are surging. According to statistics, complaints regarding motorcycle noise are increasing steeply every year, and noise pollution in residential areas caused by illegally modified motorcycles with loud exhaust sounds or those that frequently accelerate rapidly is emerging as a social issue.

[0003] However, the current noise enforcement system fails to keep up with the characteristics of these mobile noise sources. Current enforcement methods are limited to dispatching officials and police to the scene to measure exhaust noise from parked vehicles at close range or conducting ad-hoc inspections relying on manpower. Critics have pointed out that this not only causes manpower shortages but also undermines the effectiveness of enforcement because 24-hour constant monitoring is impossible. Furthermore, while current regulations establish standards for exhaust noise while stationary, there is a lack of clear standards to regulate "noise during acceleration," which is the source of actual suffering for residents, as well as automated enforcement equipment to support such measures.

[0004] Conventional noise meters currently in use have limitations in that they only measure the overall equivalent noise level (Leq) or peak noise of the installation area, and cannot identify specifically which vehicle among the numerous passing vehicles generated the noise. In other words, even if noise levels are measured, it is difficult to proceed with administrative sanctions, such as the imposition of fines, because the offending party cannot be identified.

[0005] Meanwhile, license plate recognition (LPR) technology applied to existing CCTVs for crime prevention or speed enforcement has primarily developed around four-wheeled vehicles. Consequently, it fails to properly reflect the characteristics of two-wheeled vehicles, which have license plates attached only to the rear, resulting in significantly lower recognition rates. Furthermore, there is a problem where recognition accuracy deteriorates even further under tough conditions, such as rain, low-light nighttime environments, or distorted license plates. Additionally, existing rule-based systems lack precise synchronization between the time of noise generation and the time of video recording, making it difficult to secure legal validity as evidence of noise violations.

[0006] Accordingly, in line with the trend of strengthened management by the Ministry of Environment, such as the amendment of the Noise and Vibration Control Act, there is a need to develop an intelligent noise-generating vehicle enforcement system capable of precisely tracking noise from moving vehicles without human intervention, visualizing noise sources, selectively triggering only violating vehicles, and automatically packaging clear evidence. Prior art literature

[0007] Korean Registered Patent KR 10-2863745 B1 “Noise Control System for Two-Wheeled Vehicles” (September 19, 2025) The problem to be solved

[0008] The present invention aims to provide a method and system for automatically detecting noise-causing vehicles based on acoustic beamforming data performed at a terminal, wherein the method and system analyze acoustic beamforming data mapped with acoustic pressure levels per grid to collected image data by linking an image camera and an acoustic camera, and automatically detect moving noise sources efficiently and precisely by synchronizing the time point and storing and transmitting the data to a server only when preset trigger conditions are satisfied. means of solving the problem

[0009] To solve the above problem, a method for automatically detecting a noise-causing vehicle based on acoustic beamforming data, performed in a terminal comprising one or more processors and one or more memories, comprises: a data receiving step of receiving acoustic beamforming data in which image data and acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of the multiple grid areas separated in the surveillance area from a video camera and an acoustic camera capturing the same surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on multiple acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated; and a data transmission step of transmitting detection result data including the acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the surveillance area and noise information generated by the noise-causing vehicle.

[0010] In one embodiment of the present invention, the acoustic beamforming data may correspond to data generated by mapping the sound pressure level (SPL) value measured in each of the corresponding grid areas separated in the monitoring area when a plurality of acoustic signals by a plurality of microphones embedded in the acoustic camera are beamformed with respect to the monitoring area.

[0011] In one embodiment of the present invention, the trigger condition may include a first trigger condition for determining whether the average value of the acoustic pressure level for the entire area included in the acoustic beamforming data is greater than a preset reference threshold value when a region of interest is not preset in a plurality of grid regions within the acoustic beamforming data.

[0012] In one embodiment of the present invention, the trigger condition may include a second trigger condition that, when a region of interest is preset in a plurality of grid regions within the acoustic beamforming data, extracts the average value of the acoustic pressure level of the grid regions corresponding to the inside and outside of the region of interest, respectively, and determines whether the average value of the acoustic pressure level inside the region of interest is greater than a preset reference threshold, and at the same time, determines whether the average value of the acoustic pressure level inside the region of interest is greater than the average value of the acoustic pressure level outside the region of interest.

[0013] In one embodiment of the present invention, the data receiving step stores the received image data and the acoustic beamforming data in a temporary storage buffer while updating them in real time, and the data storage step can, when the trigger signal is generated, extract the image data and the acoustic beamforming data of a preset time interval stored in the temporary storage buffer and store the image data and the acoustic beamforming data by synchronizing their timing.

[0014] In one embodiment of the present invention, the data transmission step may include a data processing step of overlaying the acoustic beamforming data onto the image data to visually overlay the acoustic pressure level of each grid area on the image of the surveillance area, and generating detection result data that is displayed in different colors in stages distinguished according to the magnitude of the acoustic pressure level value on the image.

[0015] To solve the above problem, an automatic noise-causing vehicle detection system based on acoustic beamforming data, comprising a terminal including one or more processors and one or more memories, comprises: a data receiving step of receiving image data and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of the multiple grid areas separated in the surveillance area from a video camera and an acoustic camera capturing the same surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on multiple acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated; and a data transmission step of transmitting detection result data including the acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the surveillance area and noise information generated by the noise-causing vehicle. Effects of the invention

[0017] According to one embodiment of the present invention, by combining a video camera and an acoustic camera that capture the same surveillance area, visual object information and auditory noise source location information are simultaneously obtained, thereby enabling the accurate matching of noise sources moving on the road and securing highly reliable grounds for enforcement.

[0018] According to one embodiment of the present invention, by dividing the monitoring area into a plurality of grid areas and generating acoustic beamforming data in which acoustic pressure level (SPL) values ​​are mapped to each grid, it is possible to pinpoint the location of the vehicle causing the actual noise even in a situation where multiple vehicles are mixed within the screen, thereby achieving the effect of drastically reducing the false detection rate.

[0019] According to one embodiment of the present invention, in a general environment where no region of interest is set, triggering is performed based on the average acoustic pressure level of the entire area, thereby enabling the detection of abnormal noise occurrences in a wide area without missing them.

[0020] According to one embodiment of the present invention, when a region of interest is set, by applying a second trigger condition that compares and analyzes acoustic pressure levels inside and outside the region of interest, it is possible to effectively exclude false detections caused by ambient noise outside the region of interest, such as construction noise or vehicles in the opposite lane.

[0021] According to one embodiment of the present invention, by applying an adaptive trigger condition that bases the average noise level of the entire area on whether an area of ​​interest is set, or compares the difference in noise levels between the inside and outside of the area of ​​interest, it is possible to achieve flexible and precise detection even in various road environments and installation conditions.

[0022] According to one embodiment of the present invention, by updating data in a temporary buffer under normal circumstances and extracting and storing data from a certain section before and after only when a trigger signal occurs, it is possible to accurately capture the key section required for cracking down on noise-generating vehicles while simultaneously efficiently utilizing the data storage space.

[0023] According to one embodiment of the present invention, even in environments where visibility is reduced due to adverse weather conditions such as night or fog, by setting an image correction area based on the location of a noise source identified through acoustic data analysis and performing image quality improvement processing, it is possible to achieve the effect of identifying a noise-generating vehicle regardless of weather or lighting conditions.

[0024] According to one embodiment of the present invention, by applying a super-resolution algorithm that tracks the movement path of a noise source and reconstructs information from multiple frames based on this, it is possible to achieve the effect of restoring detailed information of a noise-generating vehicle even in low-resolution or blurry images. Brief explanation of the drawing

[0026] FIG. 1 illustrates the configuration of a terminal control unit that performs an automatic noise-causing vehicle detection method based on acoustic beamforming data according to an embodiment of the present invention. FIG. 2 illustrates the steps and process of performing an automatic noise-causing vehicle detection method based on acoustic beamforming data according to an embodiment of the present invention. FIG. 3 illustrates an example of the installation of an image camera and an acoustic camera in a data reception step according to an embodiment of the present invention, and an example of image data and acoustic beamforming data generated thereby. FIG. 4 illustrates an example of acoustic beamforming data generated by an acoustic camera according to one embodiment of the present invention. FIG. 5 illustrates an example of a first trigger condition for determining whether to generate a trigger signal based on the overall average value of acoustic beamforming data according to an embodiment of the present invention. FIG. 6 illustrates an example of a second trigger condition that determines whether a trigger signal is generated by comparing an average value inside a region of interest, an average value outside of it, and a reference threshold value according to an embodiment of the present invention. FIG. 7 illustrates the process of synchronizing the timestamps of image data and acoustic beamforming data through a temporary storage buffer in a data storage step according to an embodiment of the present invention. FIG. 8 illustrates detection result data generated by overlaying acoustic beamforming data onto image data according to one embodiment of the present invention. FIG. 9 illustrates a visibility enhancement processing step that performs image processing to improve visibility for a correction area set based on acoustic beamforming data according to an embodiment of the present invention. FIG. 10 illustrates a process of performing a visibility enhancement processing step and a super-resolution algorithm on a plurality of frames including a driving path of a noise-generating vehicle according to an embodiment of the present invention. FIG. 11 schematically illustrates the internal configuration of a computing device according to one embodiment of the present invention. Specific details for implementing the invention

[0027] Hereinafter, various embodiments and / or aspects are disclosed with reference to the drawings. For illustrative purposes, numerous specific details are disclosed in the following description to aid in a general understanding of one or more aspects. However, it will also be recognized by those skilled in the art that these aspects may be practiced without such specific details. The following description and the accompanying drawings describe specific exemplary aspects of one or more aspects in detail. However, these aspects are exemplary, and some of the various methods in the principles of the various aspects may be used, and the description is intended to include all such aspects and their equivalents.

[0029] In addition, various aspects and features will be presented by a system that may include a number of devices, components and / or modules, etc. It should also be understood and recognized that various systems may include additional devices, components and / or modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in relation to the drawings.

[0030] Terms such as "examples," "examples," "aspects," and "examples" as used herein may not be interpreted as implying that any aspect or design described is superior or more advantageous than other aspects or designs. Terms used below, such as "part," "component," "module," "system," and "interface," generally refer to computer-related entities and may refer, for example, to hardware, a combination of hardware and software, or software.

[0031] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that the relevant feature and / or component is present, but not to exclude the presence or addition of one or more other features, components and / or groups thereof.

[0032] Additionally, terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0033] Furthermore, in the embodiments of the present invention, all terms used herein, including technical or scientific terms, unless otherwise defined, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in the embodiments of the present invention.

[0035] FIG. 1 illustrates the configuration of a terminal control unit that performs an automatic noise-causing vehicle detection method based on acoustic beamforming data according to an embodiment of the present invention.

[0036] An automatic noise-causing vehicle detection method based on acoustic beamforming data, performed in a terminal comprising one or more processors and one or more memories according to an embodiment of the present invention, comprises: a data receiving step of receiving acoustic beamforming data in which image data and acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the same surveillance area from a video camera and an acoustic camera capturing the same surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on a plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated; and a data transmission step of transmitting detection result data including the acoustic beamforming data and image data to an external server system; wherein the detection result data may include image information of a noise-causing vehicle identified in the surveillance area and noise information generated by the noise-causing vehicle.

[0038] As illustrated in FIG. 1, the automatic detection method for noise-generating vehicles according to one embodiment of the present invention can be performed on a terminal corresponding to a computing device comprising one or more processors and one or more memories. The terminal includes a terminal control unit (1), and the terminal control unit (1) is connected to transmit and receive data with an image camera (2), an acoustic camera (3), and a server system (4), and may include a data receiving unit (10), a trigger signal generating unit (11), a data storage unit (12), and a data transmitting unit (13).

[0039] The above video camera (2) can capture a surveillance area requiring noise control, such as a road, residential area, or construction site, generate real-time video data, and receive it from the terminal control unit (1).

[0040] The above acoustic camera (3) includes a microphone array in which a plurality of microphones are arranged, measures the location and magnitude (acoustic pressure level, SPL) of sound generation, tracks a noise source in space using beamforming, and generates acoustic beamforming data that can be visualized and receives it from the terminal control unit (1).

[0042] The data receiving unit (10) of the terminal control unit (1) receives image data and acoustic beamforming data from the image camera (2) and the acoustic camera (3), respectively, and the trigger signal generating unit (2) can analyze the acoustic beamforming data received by the data receiving unit (10) in real time to determine whether a preset trigger condition is satisfied.

[0043] If a trigger condition is satisfied and a trigger signal is generated by the trigger signal generation unit (11), the data storage unit (12) stores the image data and the acoustic beamforming data for a data storage interval set based on the time when the trigger signal is generated, and the image data and acoustic beamforming data stored at this time are transmitted to the data transmission unit (13) and can finally be transmitted to the server system (4) through the data transmission unit (13).

[0044] The above server system (4) can integrate and manage data collected from multiple terminals and provide a user interface so that an administrator can monitor it or use it as a basis for enforcement.

[0046] FIG. 2 illustrates the steps and process of performing an automatic noise-causing vehicle detection method based on acoustic beamforming data according to an embodiment of the present invention.

[0047] As illustrated in FIG. 2, the method for automatically detecting noise-causing vehicles based on acoustic beamforming data according to one embodiment of the present invention can be performed in a sequential flow of a data reception step (S10), a trigger signal generation step (S11), a data storage step (S12), and a data transmission step (S13).

[0049] In the data reception step (S10) above, the terminal control unit (1) can continuously receive real-time streaming data frame by frame from a video camera (2) and an acoustic camera (3) that are capturing the same surveillance area. From the video camera (2), video data including visual information according to the flow of time can be received, and from the acoustic camera (3), acoustic beamforming data that spatially visualizes the acoustic information of the surveillance area according to the flow of time can be received.

[0051] In the data reception step (S10) above, a time difference may occur between the collected image data and the acoustic beamforming data due to reasons such as the difference in sensor processing speed between the image camera (2) and the acoustic camera (3). While the image data received from the image camera (2) includes metadata containing timestamps indicating shooting time information for each frame, the frames of the acoustic beamforming data received from the acoustic camera (3) may not include such timestamp information, which may make it difficult to accurately match the time of the two data.

[0052] To solve this, the terminal control unit (1) may additionally assign a synchronization timestamp to the video data and acoustic beamforming data frames separately from the timestamp information included in the video data. The video data and acoustic beamforming data can be synchronized frame by frame based on the synchronization timestamp and the timestamp included in the metadata of the video data. The specific process will be described later in the description of FIG. 7.

[0054] In the trigger signal generation step (S11), the received acoustic beamforming data can be analyzed to determine whether noise at a level requiring interruption has occurred in the current frame. Specifically, the acoustic pressure level for each grid within the acoustic beamforming data included in each frame can be monitored, and whether a preset trigger condition is satisfied can be checked.

[0055] If the condition is not satisfied (NO), the system can proceed to the data reception step (S10) for the next frame without a separate storage procedure and continue real-time monitoring. On the other hand, if the condition is satisfied (YES), that is, if a noise-causing vehicle is detected, a trigger signal is generated starting from the corresponding frame, and the process can proceed to the data storage step (S12).

[0056] In other words, the above noise-generating vehicle may include vehicles such as motorcycles and passenger cars that generate noise exceeding a standard level and satisfy a preset trigger condition.

[0058] In the above data storage step (S12), the image data and acoustic beamforming data can be stored during a data storage period, which is a preset interval from the time when the trigger signal is generated. At this time, the image data and acoustic beamforming data stored in the temporary storage buffer can be used for frame synchronization of the image data and acoustic beamforming data. The specific process for this will be described later in the description of FIG. 7.

[0060] In the data transmission step (S13), detection result data is generated based on the image data and acoustic beamforming data stored in the data storage step (S12), and can be transmitted to an external server system such as a control center or a cloud server.

[0061] Since the above detection result data is in a form where acoustic information showing the location and amount of noise generated is combined on a frame-by-frame basis along with video information, the server system receiving it can play or analyze it to immediately identify violating vehicles and check noise levels without any separate complex processes.

[0062] When transmission is complete, the terminal control unit (1) returns to the data reception step (S10) to monitor for the appearance of the next noise source.

[0064] FIG. 3 illustrates an example of the installation of an image camera and an acoustic camera in a data reception step according to an embodiment of the present invention, and an example of image data and acoustic beamforming data generated thereby.

[0066] As illustrated in the example in FIG. 3(a), the video camera (2) and the acoustic camera (3) can be installed side by side on a fixed structure such as a roadside street light or a traffic light support. At this time, the installation angles of the two cameras can be adjusted so that they are directed toward a specific section of the road, i.e., a pre-set surveillance area. By aligning the visual space captured by the video camera (2) with the auditory space where the acoustic camera (3) collects sound, a foundation can be established to accurately match visual information and auditory information during future data analysis.

[0068] As shown on the left side of FIG. 3(b), the video camera (2) can capture the surveillance area and generate video data on the right side of FIG. 3(b). The video data may contain visual image information including objects such as vehicles and motorcycles traveling on the road and the surrounding background. As described above, the video data may be generated in frame units, and each frame may include a timestamp for the time of capture held as metadata and a synchronization timestamp assigned by the terminal control unit (1).

[0069] Meanwhile, the acoustic camera (3) can collect all sounds occurring in the monitoring area through a number of built-in microphones and generate acoustic beamforming data on the right side of (b) of FIG. 3 by analyzing the location and magnitude of the sound using beamforming technology. The acoustic beamforming data may correspond to data obtained by dividing the monitoring area into virtual grids and mapping the magnitude of the noise measured in each grid area, i.e., the acoustic pressure level (SPL) value.

[0070] In the example of Figure 3 (b), the waves are depicted as spreading out in the form of contour lines from the center of the motorcycle, which is the location where the noise is generated. In actual data, this can be composed of a set of data in which the acoustic pressure level is higher towards the center of the noise-generating vehicle with high noise levels, and the acoustic pressure level is lower as it moves away from the center of the noise-generating vehicle.

[0072] According to one embodiment of the present invention, by combining a video camera and an acoustic camera that capture the same surveillance area, visual object information and auditory noise source location information are simultaneously obtained, thereby enabling the accurate matching of noise sources moving on the road and securing highly reliable grounds for enforcement.

[0074] FIG. 4 illustrates an example of acoustic beamforming data generated by an acoustic camera according to one embodiment of the present invention.

[0075] The acoustic beamforming data according to one embodiment of the present invention may correspond to data generated by mapping acoustic pressure level values ​​measured in each of the corresponding grid areas separated in the monitoring area when a plurality of acoustic signals by a plurality of microphones embedded in the acoustic camera are beamformed with respect to the monitoring area.

[0077] As illustrated in FIG. 4, the acoustic beamforming data may correspond to data that is converted to allow visual identification of the noise generation distribution within the monitoring area, rather than simply storing sound waveform information.

[0079] The above acoustic camera utilizes tens to hundreds of microphones arranged internally. When a noise-generating vehicle, such as a car or motorcycle, moves on the road and generates noise, an acoustic signal may reach each microphone with a minute time difference depending on the distance from the sound source. The processor of the acoustic camera can perform a beamforming algorithm to backtrack the direction and location where the sound originated by utilizing this information regarding time and phase differences.

[0080] In order to effectively convert these beamforming results into data, the entire monitoring area is divided into grid areas, and acoustic beamforming data can be generated by calculating and mapping the magnitude of the noise occurring at each corresponding location, i.e., the acoustic pressure level, for each grid area.

[0082] The illustrated example in Fig. 4 is an example of visualizing these mapping results in the form of a heatmap. In the drawing, the central part of the noise-generating vehicle has a darker color compared to the periphery, which is a set of grids with higher acoustic pressure level values ​​than the periphery, and in reality, it may correspond to the location where a vehicle is honking its horn or making exhaust sounds. On the other hand, the periphery of the noise-generating vehicle has a lighter color compared to the central part, which is a set of grids with lower acoustic pressure level values ​​than the central part, and may correspond to a relatively quiet background area.

[0084] According to one embodiment of the present invention, by dividing the monitoring area into a plurality of grid areas and generating acoustic beamforming data that maps acoustic pressure level values ​​to each grid, it is possible to pinpoint the location of the vehicle causing the actual noise even in a situation where multiple vehicles are mixed within the screen, thereby achieving the effect of drastically reducing the false detection rate.

[0086] FIG. 5 illustrates an example of a first trigger condition for determining whether to generate a trigger signal based on the overall average value of acoustic beamforming data according to an embodiment of the present invention.

[0087] According to one embodiment of the present invention, the trigger condition may include a first trigger condition for determining whether the average value of the acoustic pressure level for the entire area included in the acoustic beamforming data is greater than a preset reference threshold value when a region of interest is not preset in a plurality of grid regions within the acoustic beamforming data.

[0089] Figure 5 illustrates a trigger condition in a situation where there is no separately designated area of ​​interest within the monitoring area. This situation may correspond to cases where there is not much traffic, such as on quiet roads or during nighttime hours, so it is acceptable to monitor the entire screen without needing to limit specific lanes or areas.

[0090] In this way, if the region of interest is not set, the generation of a trigger signal is determined through the first trigger condition, and the first trigger condition can be satisfied if the average value of the total acoustic pressure level of the acoustic beamforming data exceeds a preset reference threshold without a preset region of interest.

[0092] In the above trigger signal generation step (S11), the terminal control unit (1) can calculate the overall average value of the acoustic pressure level values ​​of all grid areas included in the entire acoustic beamforming data.

[0093] As shown in Fig. 5(a), if a motorcycle traveling on the road generates noise, such as by making a loud exhaust sound or sounding a horn, the acoustic pressure level values ​​of multiple grid areas centered on the motorcycle may rise, and the average value of the acoustic pressure level values ​​may rise.

[0094] As shown in Fig. 5(b), when the average value of the acoustic pressure level of the entire grid area is compared with a preset reference threshold value and the overall average value exceeds the reference threshold value, the terminal control unit (1) can generate a trigger signal.

[0095] At this time, the above threshold value may be set by considering the environmental noise standards or legal regulatory limits of the relevant area.

[0097] According to one embodiment of the present invention, in a general environment where no region of interest is set, triggering is performed based on the average acoustic pressure level of the entire area, thereby enabling the detection of abnormal noise occurrences in a wide area without missing them.

[0099] FIG. 6 illustrates an example of a second trigger condition that determines whether a trigger signal is generated by comparing an average value inside a region of interest, an average value outside of it, and a reference threshold value according to an embodiment of the present invention.

[0100] According to one embodiment of the present invention, the trigger condition may include a second trigger condition that, when a region of interest is preset in a plurality of grid regions within the acoustic beamforming data, extracts the average value of the acoustic pressure level of the grid regions corresponding to the inside and outside of the region of interest, respectively, and determines whether the average value of the acoustic pressure level inside the region of interest is greater than a preset reference threshold, and at the same time, the average value of the acoustic pressure level inside the region of interest is greater than the average value of the acoustic pressure level outside the region of interest.

[0102] Figure 6 illustrates trigger conditions in a situation where a region of interest is designated to intensively monitor a specific lane or zone within a monitoring area. As shown in Figure 6(b), a specific grid group within the acoustic beamforming data can be designated as a region of interest, and the remaining grid groups can be separated from the region of interest.

[0103] When a region of interest is set in this manner, the generation of a trigger signal is determined through a second trigger condition, wherein the second trigger condition can be satisfied when the average value inside the region of interest exceeds a preset threshold and the average value inside the region of interest is greater than the average value outside the region of interest.

[0105] In the above trigger signal generation step (S11), the terminal control unit (1) can calculate the average value of acoustic pressure level values ​​of grids belonging to the region of interest in the acoustic beamforming data and the average value of acoustic pressure level values ​​of grids belonging to the region of interest, respectively.

[0107] Figure 6 (a) illustrates a situation in which a region of interest is set and video data and acoustic beamforming data are being collected for a motorcycle traveling on a road.

[0108] If, as in Fig. 6 (a), the motorcycle is traveling inside the region of interest but the average value inside the region of interest is not greater than a preset threshold value, or even if the average value inside the region of interest is large, the average value outside the region of interest is also measured to be high due to noise generated outside the region of interest, the trigger may not be generated.

[0109] As illustrated in FIG. 6(b), when the average value of the acoustic pressure level value inside the area of ​​interest exceeds a preset threshold value and the average value of the acoustic pressure level value inside the area of ​​interest is greater than the average value of the acoustic pressure level value outside the area of ​​interest, the terminal control unit (1) can generate a trigger signal.

[0110] Similar to the first trigger condition above, the reference threshold can be set by considering the environmental noise standards or legal regulatory limits of the relevant area.

[0112] According to one embodiment of the present invention, when a region of interest is set, by applying a second trigger condition that compares and analyzes acoustic pressure levels inside and outside the region of interest, it is possible to effectively exclude false detections caused by ambient noise outside the region of interest, such as construction noise or vehicles in the opposite lane.

[0113] In addition, according to one embodiment of the present invention, by applying an adaptive trigger condition that bases the average noise level of the entire area on whether an area of ​​interest is set, or compares the difference in noise levels between the inside and outside of the area of ​​interest, it is possible to achieve flexible and precise detection even in various road environments and installation conditions.

[0115] FIG. 7 illustrates the process of storing data and synchronizing timestamps of image data and acoustic beamforming data in a data storage step according to an embodiment of the present invention.

[0116] According to one embodiment of the present invention, the data reception step stores the received image data and the acoustic beamforming data in a temporary storage buffer while updating them in real time, and the data storage step can, when the trigger signal is generated, extract the image data and the acoustic beamforming data of a preset time interval stored in the temporary storage buffer and store the image data and the acoustic beamforming data by synchronizing their timing.

[0118] Specifically, according to one embodiment of the present invention, the data receiving step (S10) assigns a synchronization timestamp to the image data and acoustic beamforming data stored in the temporary storage buffer, and the data storage step (S12) can synchronize the timing of the image data and acoustic beamforming data based on the synchronization timestamp.

[0120] FIG. 7(a) illustrates a flow in which data is stored and updated in a temporary storage buffer, and then a trigger signal is generated, and the data is stored according to the data storage step (S12). At this time, the data storage step (S12) may store the data after performing a data correction and synchronization process as shown in FIG. 7(b).

[0121] The above terminal control unit (1) updates and stores the image data and acoustic beamforming data received through the data reception step (S10) in a temporary storage buffer for a preset time, and can synchronize the frames of the image data and acoustic beamforming data when a trigger signal is generated through the data stored in the temporary storage buffer.

[0122] In addition, the data stored in the temporary storage buffer can be stored together with the image data and acoustic beamforming data corresponding to the data storage section in the data storage step (S12) as data for identifying the situation before and after the generation of the trigger signal, and then transmitted to the data transmission step (S13).

[0124] As described above in the description of Fig. 2, the video camera and the acoustic camera may have different hardware characteristics and processing speeds, so even if the terminal control unit (1) receives frames at the same time, there may be a slight difference in the actual time of shooting and measurement.

[0125] Additionally, the above video data includes a timestamp, which is shooting time information, as metadata, but the acoustic beamforming data may not include a timestamp. To resolve this, the terminal control unit (1) additionally assigns a synchronization timestamp to each data in the data reception step (S10), and can correct the time difference between the video data and the acoustic beamforming data through the synchronization timestamp.

[0126] Specifically, the terminal control unit (1) can calculate the difference between the timestamp included as metadata in the video data frame and the synchronization timestamp assigned by the terminal control unit (1) at the time of reception, thereby calculating the frame time difference between the currently received data. Then, based on this calculated time difference information, it can be corrected so that the time of the acoustic beamforming data frame matches the time of the video data.

[0127] For example, as shown in FIG. 7(b), the timestamps included as metadata for the image data are sequentially 29.9 seconds, 30.0 seconds, and 30.1 seconds, and the synchronization timestamps of the image data are sequentially 30.0 seconds, 30.1 seconds, and 30.2 seconds. The terminal control unit (1) calculates a time difference of 0.1 seconds between the timestamps and the synchronization timestamps and, based on this, matches the acoustic beamforming data with the image data containing the synchronization timestamp that is 0.1 seconds longer, thereby correcting the image data and acoustic beamforming data to include information at the same time.

[0129] Meanwhile, in the example of FIG. 7 (a), the temporary storage buffer is updated at a preset time unit of 10 seconds, and a trigger signal is generated at T1, which is slightly past 30 seconds. Accordingly, the terminal control unit (1) can store video data and acoustic beamforming data for a preset data storage interval based on time T1 in the data storage step (S12).

[0130] The image data and acoustic beamforming data stored at this time may correspond to data that corrects the time difference between the image data and the acoustic beamforming data based on the timestamp and the synchronization timestamp.

[0132] In the above data storage step (S12), data from a past point in time to the point in time when the trigger occurred, which was already stored in the temporary storage buffer, can be additionally stored as data intended to identify the situation before and after the time when the trigger signal was generated. In the example of FIG. 7 (a), the data stored in the temporary storage buffer from 30 seconds to time T1 may be applicable.

[0133] In other words, the above data storage step stores data that corrects the frame time difference between image data and acoustic beamforming data, and the data may include image data and acoustic beamforming data stored in a temporary storage buffer, as well as image data and acoustic beamforming data corresponding to a preset data storage interval.

[0134] In other words, video data and acoustic beamforming data at the same point in time can be synchronized and stored.

[0136] According to one embodiment of the present invention, by updating data in a temporary buffer under normal circumstances and extracting and storing data from a certain section before and after only when a trigger signal occurs, it is possible to accurately capture the key section required for cracking down on noise-generating vehicles while simultaneously efficiently utilizing the data storage space.

[0138] FIG. 8 illustrates detection result data generated by overlaying acoustic beamforming data onto image data according to one embodiment of the present invention.

[0139] The data transmission step according to one embodiment of the present invention may include a data processing step of overlaying the acoustic beamforming data onto the image data, so that the acoustic pressure level of each corresponding grid area is visually overlaid on the image of the surveillance area, and the detection result data is displayed in different colors in stages distinguished according to the magnitude of the acoustic pressure level value on the image.

[0141] FIG. 8 illustrates the process of generating detection result data in the data transmission step (S13). As illustrated in FIG. 8, the data transmission step (S13) includes a data processing step for generating detection result data, and in the data processing step, the terminal control unit (1) can generate detection result data including a plurality of frames by overlaying acoustic beamforming data at a synchronized time point on top of the image data corresponding to the data storage section stored in the data storage step, frame by frame.

[0142] The detection result data may have the acoustic pressure levels per grid of the acoustic beamforming data visually overlaid on an image capturing a surveillance area included in the video data. At this time, the acoustic pressure levels are divided into stages according to their magnitude, and grid areas corresponding to the same stage are marked with the same color. Consequently, as shown at the bottom of FIG. 8, the detection result data may correspond to data in which the acoustic pressure levels are displayed in different colors on the image according to their magnitude.

[0144] The visualization method included in the above detection result data enables enforcement officers to immediately identify noise-causing vehicles that actually generate noise, even in complex road images where numerous vehicles are mixed together. For example, when two motorcycles are driving side by side, it is not possible to tell which motorcycle is making a loud exhaust sound from the video alone, but if you look at the detection result data of the present invention, a dark marking appears only on the side of the motorcycle where the noise is concentrated, thus helping to make a clear distinction.

[0146] FIG. 9 illustrates a visibility enhancement processing step that performs image processing to improve visibility for a correction area set based on acoustic beamforming data according to an embodiment of the present invention.

[0147] According to one embodiment of the present invention, the data storage step may further include a visibility enhancement processing step in which, when the current external environment corresponds to a bad weather environment including one or more of night, fog, and rain where the noise-causing vehicle is expected not to be easily identified in the image data, a correction area including a preset range centered on the noise-causing vehicle within the image data stored in the data storage section is set based on the position coordinates of the noise-causing vehicle corresponding to a grid area where the acoustic pressure level identified in the acoustic beamforming data stored in the data storage section exceeds a preset standard, and a visibility enhancement processing including one or more of dehazing and contrast enhancement is performed on the correction area.

[0149] A terminal implementing the present invention can determine whether the current situation is an adverse weather environment, including night, fog, or rain, through external environmental sensors or image analysis. If such an adverse weather environment is present, the image quality of the video data may be reduced, making it difficult to identify noise-generating vehicles. Therefore, image quality improvement must be performed to identify noise-generating vehicles; however, instead of performing uniform image quality improvement on the entire video, the present invention can selectively improve image quality only in locations where there is a high probability of noise-generating vehicles existing, based on acoustic beamforming data.

[0150] That is, in the above visibility enhancement step, location coordinates where a noise-causing vehicle is predicted to exist are derived according to a preset standard that defines a location where a noise-causing vehicle is likely to exist, such as the location with the highest acoustic pressure level on the acoustic beamforming data stored in the above data storage step, and a correction area including a preset range in the image data stored in the above data storage step can be set based on the said location coordinates. Image quality improvement through visibility enhancement processing is performed only on the said correction area included in the said image data to derive image data with improved quality compared to before the visibility enhancement processing is performed, and this can be transmitted to the data transmission step.

[0151] In summary, when the above visibility enhancement processing step is performed, the above data transmission step can receive the image data and acoustic beamforming data stored in the temporary storage buffer received from the above data storage step, the image data and acoustic beamforming data corresponding to the preset data storage interval, and the image data with improved image quality obtained by performing the above visibility enhancement processing step.

[0153] The top of FIG. 9 illustrates video data of a motorcycle driving in a situation where visibility is obscured by thick fog, stored in the data storage step, and corresponding acoustic beamforming data. Since the external environment shown in the video data corresponds to an adverse weather environment, the visibility enhancement processing step can be performed.

[0154] First, based on preset criteria in the acoustic beamforming data, location coordinates where a noise-causing vehicle is likely to be located can be derived, and a correction area including a preset range based on said location coordinates can be set.

[0155] As illustrated in the middle of FIG. 9, the correction area can be applied to the image data, and visibility enhancement processing including dehazing for fog removal, sharpening to make blurry boundaries distinct, or a contrast enhancement algorithm for illuminance correction can be performed.

[0156] For example, image data including the correction area can be input into a deep learning-based inference model to generate virtual image data in which fog has been removed from the image data (preferably the correction area), and the inference model may be a deep learning-based inference model trained to generate an image with fog removed when receiving image data that captures an area where fog exists.

[0158] Finally, as shown at the bottom of FIG. 9, image data including a correction area containing a noise-generating vehicle with improved image quality compared to before the visibility enhancement processing can be transmitted to the data transmission stage.

[0160] According to one embodiment of the present invention, in order to prevent excessive computational load from being used when performing a processing process for improving visibility of the entire image data, the processing process for improving visibility can be performed only on a correction area corresponding to a part of the image data (preferably a correction area where a noise-causing vehicle is likely to be located based on acoustic beamforming data).

[0161] According to one embodiment of the present invention, even in environments where visibility is reduced due to adverse weather conditions such as night or fog, by setting an image correction area based on the location of a noise source identified through acoustic data analysis and performing image quality improvement processing, it is possible to achieve the effect of identifying a noise-generating vehicle regardless of weather or lighting conditions.

[0163] FIG. 10 illustrates a process of performing a visibility enhancement processing step and a super-resolution algorithm on a plurality of frames including a driving path of a noise-generating vehicle according to an embodiment of the present invention.

[0164] According to one embodiment of the present invention, the data storage step may further include a step of applying a super-resolution algorithm that, when the current external environment corresponds to an adverse weather environment including one or more of night, fog, and rain where it is expected that the noise-causing vehicle will not be easily identified in the image data, tracks a grid area in which the acoustic pressure level exceeds a preset standard in the acoustic beamforming data acquired frame by frame in the data storage section to derive the driving path of the noise-causing vehicle, performs the visibility enhancement processing step on a detailed area corresponding to the driving path in the image data to derive a plurality of correction areas, and aligns the correction areas between a plurality of consecutive frames to accumulate and reconstruct pixel information.

[0166] The present invention can utilize information from a series of frames to solve the problem where it is difficult to clearly identify the shape or features of a motorcycle, which is a noise-generating vehicle, using only a single image frame due to insufficient illumination or rain reflection during nighttime or rainy weather.

[0167] Specifically, based on acoustic beamforming data from consecutive frames within a data storage section, changes in the location of a noise source over time can be tracked, and the driving path of the noise source can be derived by connecting these frames. Similar to the visibility enhancement processing step described above, acoustic beamforming data containing the derived driving path can be mapped to corresponding image data to extract the correction area centered on the location where the noise-causing vehicle was present in each frame, and visibility enhancement processing can be performed on each of the multiple correction areas. Finally, a super-resolution algorithm can be executed to reconstruct a high-resolution image by aligning the multiple correction area images after the visibility enhancement processing is completed and superimposing and accumulating the pixel information of each image.

[0169] The top of FIG. 10 illustrates acoustic beamforming data frames according to a continuous flow of time. In each frame, there may be a high-noise grid area that has a darker color than the surrounding area where the noise-causing vehicle is presumed to be located. The terminal control unit (1) can derive a driving path, which is the movement trajectory of the noise-causing vehicle, by sequentially connecting the coordinate changes of the high-noise grid area.

[0170] Even if the subject is blurry and difficult to track in the video, reliable path tracking is possible because the center point of the noise moves clearly in the acoustic beamforming data.

[0172] The middle section of FIG. 10 illustrates correction area images extracted at each point in time by mapping the derived driving path information to the image data. The terminal control unit (1) can extract correction areas centered on the location where the noise source existed in the image data of each frame, and perform visibility enhancement processing such as dehazing and contrast enhancement on a plurality of correction areas. That is, a visibility enhancement processing step can be performed on the image data based on the driving path information.

[0174] The bottom of FIG. 10 illustrates the result of performing super-resolution processing using a plurality of extracted correction area images. A plurality of consecutive frames capturing a noise-causing vehicle may contain slightly different pixel information. The terminal control unit (1) can align the plurality of correction area images that have undergone visibility enhancement processing and overlap and accumulate the pixel information of each image. Through this, information that was missing or buried in noise in a single image can be reconstructed, thereby performing a super-resolution algorithm that generates a high-resolution image in which the shape of the noise-causing vehicle is clearly restored.

[0176] According to one embodiment of the present invention, by applying a super-resolution algorithm that tracks the movement path of a noise source and reconstructs information from multiple frames based thereon, it is possible to achieve the effect of restoring detailed information of a noise-generating vehicle even in low-resolution or blurry images.

[0178] FIG. 11 schematically illustrates the internal configuration of a computing device according to an embodiment of the present invention.

[0179] The terminal illustrated in FIG. 1 described above may include the components of the computing device (11000) illustrated in FIG. 11.

[0180] As illustrated in FIG. 11, the computing device (11000) may include at least one processor (11100), memory (11200), peripheral interface (11300), input / output subsystem (I / O subsystem) (11400), power circuit (11500), and communication circuit (11600). In this case, the computing device (11000) may correspond to the terminal illustrated in FIG. 1.

[0181] The memory (11200) may include, for example, high-speed random access memory, a magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. The memory (11200) may include software modules, instruction sets, or various other data required for the operation of the computing device (11000).

[0182] At this time, access to memory (11200) from other components, such as the processor (11100) or peripheral device interface (11300), can be controlled by the processor (11100).

[0183] The peripheral device interface (11300) can connect input and / or output peripheral devices of the computing device (11000) to the processor (11100) and memory (11200). The processor (11100) can perform various functions for the computing device (11000) and process data by executing software modules or instruction sets stored in the memory (11200).

[0184] The input / output subsystem can connect various input / output peripherals to the peripheral interface (11300). For example, the input / output subsystem may include a controller for connecting peripherals such as a monitor, keyboard, mouse, printer, or, if necessary, a touchscreen or sensor to the peripheral interface (11300). According to another aspect, input / output peripherals may be connected to the peripheral interface (11300) without passing through the input / output subsystem.

[0185] The power circuit (11500) can supply power to all or part of the components of the terminal. For example, the power circuit (11500) may include one or more power sources such as a power management system, a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or any other components for power generation, management, and distribution.

[0186] The communication circuit (11600) can enable communication with another computing device using at least one external port.

[0187] Alternatively, as described above, the communication circuit (11600) may enable communication with other computing devices by including an RF circuit and transmitting and receiving an RF signal, also known as an electromagnetic signal.

[0188] The embodiment of FIG. 11 is merely an example of a computing device (11000), and the computing device (11000) may have some components shown in FIG. 11 omitted, additional components not shown in FIG. 11 added, or a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may include, in addition to the components shown in FIG. 11, a touchscreen or a sensor, and the communication circuit (11600) may include a circuit for RF communication of various communication methods (WiFi, 3G, LTE, Bluetooth, NFC, Zigbee, etc.). The components that can be included in the computing device (11000) may be implemented as hardware, software, or a combination of both hardware and software, including one or more integrated circuits specialized for signal processing or applications.

[0189] Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded on a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. An application to which the present invention is applied may be installed on a computing device (11000) through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file in response to a request from the computing device (11000).

[0191] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0192] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0193] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0195] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, appropriate results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents. Therefore, other implementations, other embodiments, and equivalents to the claims are also included within the scope of the claims set forth below.

Claims

Claim 1 A method for automatically detecting a noise-generating vehicle based on acoustic beamforming data, performed on a terminal comprising one or more processors and one or more memories, comprising: a data reception step of receiving image data from a video camera and an acoustic camera capturing the same surveillance area, respectively, and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on a plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; and a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated. A method for automatically detecting noise-causing vehicles based on acoustic beamforming data, comprising: a data transmission step for transmitting detection result data including acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the monitoring area and noise information generated by the noise-causing vehicle; and wherein the data transmission step comprises a data processing step for generating detection result data in which the acoustic beamforming data is overlaid on the image data so that the acoustic pressure level of a corresponding grid area is visually overlaid on the image of the monitoring area according to a plurality of grid areas, and the detection result data is displayed in different colors in stages distinguished according to the magnitude of the acoustic pressure level value in the image. Claim 2 A method for automatically detecting noise-causing vehicles based on acoustic beamforming data according to claim 1, wherein the acoustic beamforming data is data generated by mapping the sound pressure level (SPL) value measured in each of the corresponding grid areas separated in the monitoring area when a plurality of acoustic signals by a plurality of microphones embedded in the acoustic camera are beamformed with respect to the monitoring area. Claim 3 A method for automatically detecting a noise-generating vehicle based on acoustic beamforming data, performed on a terminal comprising one or more processors and one or more memories, comprising: a data reception step of receiving image data from a video camera and an acoustic camera capturing the same surveillance area, respectively, and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on a plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; and a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated. A method for automatically detecting noise-causing vehicles based on acoustic beamforming data, comprising: a data transmission step of transmitting detection result data including acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the monitoring area and noise information generated by the noise-causing vehicle, and the trigger condition includes a first trigger condition for determining whether the average value of the acoustic pressure level for the entire area included in the acoustic beamforming data is greater than a preset reference threshold value when the region of interest is not preset in a plurality of grid areas within the acoustic beamforming data. Claim 4 A method for automatically detecting a noise-generating vehicle based on acoustic beamforming data, performed on a terminal comprising one or more processors and one or more memories, comprising: a data reception step of receiving image data from a video camera and an acoustic camera capturing the same surveillance area, respectively, and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on a plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; and a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated. A method for automatically detecting noise-causing vehicles based on acoustic beamforming data, comprising: a data transmission step of transmitting detection result data including acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the monitoring area and noise information generated by the noise-causing vehicle; and wherein the trigger condition includes a second trigger condition that, when a region of interest is preset in a plurality of grid areas within the acoustic beamforming data, extracts the average value of the acoustic pressure level of the grid areas corresponding to the inside and outside of the region of interest, respectively, and determines whether the average value of the acoustic pressure level inside the region of interest is greater than a preset reference threshold value, and simultaneously determines whether the average value of the acoustic pressure level inside the region of interest is greater than the average value of the acoustic pressure level outside the region of interest. Claim 5 A method for automatically detecting noise-causing vehicles based on acoustic beamforming data according to claim 1, wherein the data receiving step stores the received image data and the acoustic beamforming data in a temporary storage buffer while updating them in real time, and the data storage step extracts the image data and the acoustic beamforming data of a preset time interval stored in the temporary storage buffer when the trigger signal is generated, and stores the image data and the acoustic beamforming data by synchronizing the timing of the image data and the acoustic beamforming data. Claim 6 delete Claim 7 A method for automatically detecting a noise-generating vehicle based on acoustic beamforming data, performed on a terminal comprising one or more processors and one or more memories, comprising: a data reception step of receiving image data from a video camera and an acoustic camera capturing the same surveillance area, respectively, and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on a plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; and a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated. A method for automatically detecting a noise-causing vehicle based on acoustic beamforming data, comprising: a data transmission step of transmitting detection result data including acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the monitoring area and noise information generated by the noise-causing vehicle; and wherein the data storage step further comprises a visibility enhancement processing step of, when the current external environment corresponds to an adverse weather environment including one or more of night, fog, and rain where the noise-causing vehicle is expected not to be easily identified in the image data, setting a correction area including a preset range centered on the noise-causing vehicle within the image data stored in the data storage section based on the location coordinates of the noise-causing vehicle corresponding to a grid area where the acoustic pressure level identified in the acoustic beamforming data stored in the data storage section exceeds a preset standard, and performing a visibility enhancement processing including one or more of dehazing and contrast enhancement on the correction area. Claim 8 An automatic noise-generating vehicle detection system based on acoustic beamforming data comprising a terminal including one or more processors and one or more memories, comprising: a data reception step of receiving image data from a video camera and an acoustic camera capturing the same surveillance area, respectively, and acoustic beamforming data in which acoustic pressure levels corresponding to noise values ​​are mapped and stored for each of a plurality of grid areas separated in the surveillance area; a trigger signal generation step of determining whether the acoustic beamforming data satisfies a preset trigger condition based on the plurality of acoustic pressure level information of the acoustic beamforming data, and generating a trigger signal if satisfied; and a data storage step of storing the image data and the acoustic beamforming data corresponding to a data storage section set based on the time when the trigger signal is generated. A noise-causing vehicle automatic detection system based on acoustic beamforming data, comprising: a data transmission step of transmitting detection result data including acoustic beamforming data and image data to an external server system; wherein the detection result data includes image information of a noise-causing vehicle identified in the monitoring area and noise information generated by the noise-causing vehicle; and wherein the data transmission step comprises a data processing step of overlaying the acoustic beamforming data onto the image data to generate detection result data in which the acoustic pressure level of a corresponding grid area is visually overlaid on the image of the monitoring area according to a plurality of grid areas, and the detection result data is displayed in different colors in stages distinguished according to the magnitude of the acoustic pressure level value in the image.

Images