Whistling vehicle detection method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a whistling vehicle detection method and device, electronic equipment and a medium. The method comprises the steps that if a sound pickup of a deployed image collector collects vehicle whistling sound, image collection is conducted through the image collector, and candidate vehicles suspected to whistling are determined; determining whistling associated features for the vehicle whistling sound and the candidate vehicles; the whistling associated features include voiceprint features of vehicle whistling sounds, whistling rule features, vehicle information of candidate vehicles and road condition features of the candidate vehicles; and determining an association relationship between the same voiceprint feature and the whistling rule feature, the vehicle information of the candidate vehicle and the road condition feature of the candidate vehicle according to the at least two accumulated whistling association features, so as to determine the whistling vehicle of the collected target whistling sound based on the association relationship. According to the scheme, the sound pickup of the existing deployed image collector can be fully utilized to detect the whistling sound, the vehicle is detected according to the image collector, and the whistling vehicle is accurately and efficiently determined.

Description

Technical Field

[0001] This application relates to the field of vehicle behavior detection technology, and in particular to a method, device, electronic device and medium for detecting vehicles that honk their horns. Background Technology

[0002] Honking vehicles indiscriminately on the road causes serious noise pollution, severely impacting the daily lives and work of nearby residents and their health. Currently, many road sections or areas prohibit vehicle horns, and those found honking will be warned or fined.

[0003] However, current detection of vehicle horn honking generally relies on additional sonar cameras. Only with sophisticated hardware can horn honking be detected and captured. But there are many areas and road sections where honking is prohibited, and deploying additional sonar cameras for all of them would be too costly. Summary of the Invention

[0004] This application provides a method, device, electronic device, and medium for detecting vehicles honking their horns, so as to accurately detect vehicles honking their horns without adding additional hardware.

[0005] According to one aspect of this application, a method for detecting vehicles honking their horns is provided, the method comprising:

[0006] If a vehicle horn sound is detected by the microphone of an image acquisition device deployed around the road, the image acquisition device is used to identify the candidate vehicle suspected of horn honking.

[0007] For the vehicle horn sound and the candidate vehicle, determine the horn-related features; wherein, the horn-related features include the voiceprint features of the vehicle horn sound, the horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle;

[0008] For at least two accumulated horn-related features, determine the association between the same voiceprint feature and the horn-honking pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle, so as to determine the horn-honking vehicle of the collected target horn sound based on the association.

[0009] According to one aspect of this application, a vehicle horn detection device is provided, the device comprising:

[0010] The candidate vehicle determination module is used to determine the suspected candidate vehicle honking by acquiring images through the image acquisition device if the sound of a vehicle honking is acquired by the microphone of the image acquisition device deployed around the road.

[0011] The horn association feature determination module is used to determine horn association features for the vehicle horn sound and the candidate vehicle; wherein, the horn association features include the voiceprint features of the vehicle horn sound, the horn pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle.

[0012] The association determination module is used to determine the association between the same voiceprint feature and the horn pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle for at least two accumulated horn association features, so as to determine the horn vehicle of the collected target horn sound based on the association.

[0013] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] Memory connected to at least one processor for data processing; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the horn-honking vehicle detection method of any embodiment of this application.

[0017] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the horn-honking vehicle detection method of any embodiment of this application.

[0018] The technical solution of this application embodiment, if a vehicle horn sound is captured by the microphone of an image acquisition device deployed around the road, then the image acquisition device is used to identify candidate vehicles suspected of honking. For the vehicle horn sound and the candidate vehicles, horn-related features are determined. These horn-related features include the voiceprint features of the vehicle horn sound, horn-honking pattern features, vehicle information of the candidate vehicles, and road condition features at the location of the candidate vehicles. For at least two accumulated horn-related features, the association relationship between the same voiceprint feature and the horn-honking pattern features, the vehicle information of the candidate vehicles, and the road condition features at the location of the candidate vehicles is determined, so as to identify the horn-honking vehicle based on the association relationship. The above solution can fully utilize the microphone of the existing deployed image acquisition device to detect horn sounds, and combine the image acquisition device to detect vehicles, accurately and efficiently identifying the horn-honking vehicle.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for detecting vehicles that are honking, as provided in this application embodiment;

[0022] Figure 2 A first schematic diagram is determined for the candidate vehicles provided in the embodiments of this application;

[0023] Figure 3 A first schematic diagram is determined for the candidate vehicles provided in the embodiments of this application;

[0024] Figure 4 A flowchart illustrating a method for detecting vehicles that are honking, as provided in another embodiment of this application;

[0025] Figure 5 A flowchart of a method for detecting vehicles that are honking, provided in another embodiment of this application;

[0026] Figure 6 A flowchart illustrating a method for detecting vehicles that are honking, as provided in another embodiment of this application;

[0027] Figure 7 This is a schematic diagram of the structure of a vehicle horn detection device provided in an embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Figure 1 This is a flowchart illustrating a method for detecting vehicles that are honking, as provided in an embodiment of this application. This embodiment is applicable to detecting vehicles that are honking. Typically, this embodiment is applicable to detecting vehicles that are honking without adding additional hardware. The method can be executed by a vehicle honking detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110. If the sound of a vehicle horn is collected by the microphone of the image acquisition device deployed around the road, the image acquisition device is used to identify the candidate vehicle suspected of horn honking.

[0033] The image acquisition devices deployed around the road can be located on either side of the road or near intersections. The road can be a pre-determined road where honking is prohibited. In this embodiment, the image acquisition device is one already deployed around the road, requiring no additional hardware. The microphone is a built-in device of the image acquisition device used to acquire sounds around it. The vehicle horn sound refers to the sound of a vehicle horn, excluding other noise.

[0034] For example, if sound is captured by image acquisition devices already deployed around the road, the sound is identified, vehicle horn sounds are detected, and other noises are removed. If vehicle horn sounds are captured by the microphones of image acquisition devices already deployed around the road, it indicates that a vehicle is illegally honking on the current road, and the image acquisition devices are used to capture images of the road within the field of view to identify potential candidate vehicles that may be honking.

[0035] Specifically, an image acquisition device can be used to acquire images of the road within the intersection of the field of view and the pickup range of the microphone, and vehicles on the road within this intersection range can be selected as candidate vehicles. For example... Figure 2 As shown, CAM1 and CAM2 are checkpoint image acquisition devices, and CAM3 is a roadside image acquisition device. If the microphone of CAM3 detects a vehicle horn sound, then CAM3 detects vehicles on the road, identifying vehicles appearing within the intersection of the microphone's pickup range and the field of view as potential candidates for horn sounds. If the microphones of at least two image acquisition devices detect vehicle horn sounds, then the intersection of the pickup ranges of the at least two image acquisition devices is determined. Images of vehicles within this intersection are then acquired by the image acquisition devices to identify potential candidate vehicles for horn sounds. Figure 3 As shown, if both CAM2 and CAM3 collect vehicle horn sounds, the intersection of the pickup ranges of CAM2 and CAM3 is determined, i.e., region 1. This indicates that the vehicle that produced the horn sound is located within this intersection range. Vehicles within the intersection range are detected by CAM2 and / or CAM3, and the vehicles detected in the region are considered as candidate vehicles that may have produced the horn sound.

[0036] S120. For the vehicle horn sound and the candidate vehicle, determine the horn-related features; wherein, the horn-related features include the voiceprint features of the vehicle horn sound, the horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle.

[0037] For example, candidate vehicles and vehicle horn sounds are detected separately to determine horn-related features. For vehicle horn sounds, the voiceprint features and horn-honking patterns are identified. The processor in the image acquisition unit can identify the vehicle horn sounds captured by the microphone to determine the voiceprint features and horn-honking patterns.

[0038] For candidate vehicles, the system identifies their vehicle information and road condition features. This can be done by the image acquisition unit associated with the microphone. If the image acquisition unit cannot accurately detect all the information of a candidate vehicle—for example, due to the acquisition angle preventing it from accurately detecting only part of the information—other image acquisition units deployed around the road can be used in conjunction to detect the candidate vehicle. For instance, the system can predict the candidate vehicle's future travel trend, thus predicting which image acquisition units the candidate vehicle might appear within, and then using those units to detect it. For example, it can predict that the candidate vehicle will approach a checkpoint image acquisition unit at an intersection, and then detect the candidate vehicle and determine its information when it appears within the checkpoint's field of view.

[0039] S130. For at least two accumulated horn-related features, determine the association between the same voiceprint feature and the horn-honking pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle, so as to determine the horn-honking vehicle of the collected target horn sound based on the association.

[0040] For example, at least two horn-related features are accumulated through multiple detections by roadside image acquisition devices. For these at least two horn-related features, clustering is performed based on the same voiceprint feature to find common voiceprint features. A correlation is established between the same voiceprint feature and its corresponding horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle's location. This facilitates the rapid and efficient identification of the horn-honking vehicle based on the voiceprint features of the currently detected target horn sound during subsequent applications. The correlation can be recorded in tabular form.

[0041] The technical solution of this application embodiment, if a vehicle horn sound is captured by the microphone of an image acquisition device deployed around the road, then the image acquisition device is used to identify candidate vehicles suspected of honking. For the vehicle horn sound and the candidate vehicles, horn-related features are determined. These horn-related features include the voiceprint features of the vehicle horn sound, horn-honking pattern features, vehicle information of the candidate vehicles, and road condition features at the location of the candidate vehicles. For at least two accumulated horn-related features, the association relationship between the same voiceprint feature and the horn-honking pattern features, the vehicle information of the candidate vehicles, and the road condition features at the location of the candidate vehicles is determined, so as to identify the horn-honking vehicle based on the association relationship. The above solution can fully utilize the microphone of the existing deployed image acquisition device to detect horn sounds, and combine the image acquisition device to detect vehicles, accurately and efficiently identifying the horn-honking vehicle.

[0042] Figure 4 This is a flowchart illustrating a method for detecting vehicles that are honking, as provided in another embodiment of this application. This embodiment is an optimization based on the above embodiment; solutions not described in detail in this embodiment are found in the above embodiment. Figure 4 As shown, the method in this embodiment of the application specifically includes the following steps:

[0043] S210. If the sound of a vehicle horn is collected by the microphone of the image acquisition device deployed around the road, the image acquisition device is used to collect images to identify the candidate vehicle suspected of horn honking.

[0044] S220. If the image acquisition device is a roadside image acquisition device, then the vehicle body features of the candidate vehicle are detected by the roadside image acquisition device.

[0045] For example, such as Figure 2 As shown, if the image acquisition device that detects the horn sound is a roadside image acquisition device, then the vehicle body features of the candidate vehicle can be detected through the roadside image acquisition device, such as the vehicle brand, model, color, size and other features of the candidate vehicle.

[0046] S230. Detect the license plate features of the candidate vehicles using the roadside image acquisition device and the checkpoint image acquisition device.

[0047] For example, in some cases, due to the relative angle limitation between the candidate vehicle and the roadside image acquisition device, the roadside image acquisition device may not be able to detect the license plate features of the candidate vehicle. Since the checkpoint image acquisition device is generally facing the direction of travel of the candidate vehicle, the license plate features of the candidate vehicle can be detected by combining the roadside image acquisition device and the checkpoint image acquisition device. Specifically, the roadside image acquisition device can be used to lock onto and track the candidate vehicle, while the checkpoint image acquisition device can be used to detect the license plate features of the appearing candidate vehicle.

[0048] In this embodiment of the application, detecting the license plate features of the candidate vehicle using the roadside image acquisition device and the checkpoint image acquisition device includes:

[0049] The candidate vehicle's driving direction and speed are detected by the roadside image acquisition device;

[0050] Determine the distance between the roadside image acquisition device and the next checkpoint image acquisition device along the driving direction, and predict the target time for the candidate vehicle to reach the next checkpoint image acquisition device based on the distance and the vehicle speed;

[0051] The license plate features of the candidate vehicle are determined based on the image captured by the next checkpoint image collector at the target time.

[0052] For example, the direction of travel of a candidate vehicle can be determined based on images captured by a roadside image acquisition device at different times. The speed of a candidate vehicle can be determined based on the distance traveled by the candidate vehicle over a period of time. The distance between the roadside image acquisition device and the next checkpoint image acquisition device along the travel direction can be determined in advance based on road network information. Based on the distance and speed, the target time for the candidate vehicle to reach the next checkpoint image acquisition device can be predicted. Images of passing vehicles are then captured by the next checkpoint image acquisition device. Vehicles detected passing through the checkpoint image acquisition device at the target time are identified as candidate vehicles, and their license plate features are recognized.

[0053] The beneficial effect of the above scheme is that, even when the acquisition angle of the roadside image acquisition device is limited, it can link the checkpoint image acquisition device in the direction of the candidate vehicle's travel to detect the candidate vehicle, thereby accurately identifying the license plate features of the candidate vehicle and making the vehicle information of the candidate vehicle more accurate and richer.

[0054] In this embodiment of the application, for vehicles that arrive within the field of view of the next checkpoint camera at the target time, the vehicle body information detected by the roadside image acquisition device can be used for filtering. Vehicles whose vehicle body information matches the vehicle body information detected by the roadside image acquisition device can be selected from the vehicles that arrive at the target time as candidate vehicles, and then the license plate information of the candidate vehicles can be identified.

[0055] It should be noted that if the roadside image acquisition device can clearly and accurately capture the license plate features of the candidate vehicle from the front or rear, detection can be performed without a checkpoint image acquisition device.

[0056] S240. Detect the number of times the vehicle horn sounds and the time interval within a preset time period, as the horn sound pattern characteristics.

[0057] For example, an image acquisition device that captures vehicle horn sounds can detect the number of horns and the time interval between them, recording the number of horns and the time interval within a preset time period, which reflects the typical horn duration. Alternatively, it can record the number of horns and the time interval between consecutive vehicle horn sounds with consistent voiceprint characteristics.

[0058] S250. The image acquisition device detects at least one of the following: road conditions, traffic light conditions, vehicle conditions in front and behind, and pedestrian conditions in the lane where the candidate vehicle is located, as the road condition features.

[0059] For example, an image acquisition device can be used to detect road conditions in the lane where the candidate vehicle is located, such as the presence of water accumulation, snow accumulation, obstacles, slopes, depressions, and bumps. Traffic light conditions can be detected, such as the traffic light conditions in the candidate vehicle's direction of travel. The conditions of vehicles in front of and behind the candidate vehicle can be detected, such as braking, lane changes, congestion, accidents, waiting at traffic lights, and yielding to pedestrians. Pedestrian conditions can be detected, such as crossing the road, falling, and moving in the motor vehicle lane. At least one of the above can be detected as road condition features. These road condition features can be used individually or categorized as waiting-type features and sudden-type features.

[0060] S260. For at least two accumulated horn-related features, determine the association between the same voiceprint feature and the horn-honking pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle, so as to determine the horn-honking vehicle of the collected target horn sound based on the association.

[0061] This application provides a method for detecting vehicles honking. If the image acquisition device is a roadside image acquisition device, the method detects the vehicle body features of the candidate vehicle using the roadside image acquisition device; it also detects the license plate features of the candidate vehicle using both the roadside image acquisition device and the checkpoint image acquisition device, thereby effectively linking the roadside image acquisition device and the checkpoint image acquisition device to collect vehicle information of the candidate vehicle more comprehensively. The method detects the number of honking sounds and the time interval within a preset time period as the honking pattern feature; it also detects the road conditions, traffic light conditions, surrounding vehicles, and pedestrian conditions in the lane where the candidate vehicle is located using the image acquisition device as the road condition feature, thereby obtaining factors related to the generation of vehicle honking sounds and the honking sound pattern feature for detection, facilitating subsequent more comprehensive multi-faceted comparison and identification of the honking vehicle.

[0062] Figure 5 This is a flowchart illustrating a method for detecting vehicles that are honking, as provided in another embodiment of this application. This embodiment is an optimization based on the above embodiments; solutions not described in detail in this embodiment are found in the above embodiments. Figure 5 As shown, the method in this embodiment of the application specifically includes the following steps:

[0063] S310. If the sound of a vehicle horn is collected by the microphone of the image acquisition device deployed around the road, the image acquisition device is used to collect images to identify the candidate vehicle suspected of horn honking.

[0064] S320. For the vehicle horn sound and the candidate vehicle, determine the horn-related features; wherein, the horn-related features include the voiceprint features of the vehicle horn sound, the horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle.

[0065] S330. For the same voiceprint feature, determine the number of identical vehicle information corresponding to the voiceprint feature in at least two horn-related features.

[0066] For example, to improve the accuracy of association when establishing relationships, for the same voiceprint feature, the number of identical vehicle information corresponding to at least two horn-related features containing that voiceprint feature can be counted. Identical vehicle information can mean that all information is the same, or it can mean that at least one of the features such as vehicle brand, model, color, and size is the same.

[0067] S340. If the number of identical vehicle information reaches a preset threshold, then establish the association between the voiceprint feature, the vehicle information, the horn-honking pattern feature in the horn-honking association feature corresponding to the vehicle information, and the road condition feature.

[0068] The preset quantity threshold can be determined based on actual conditions. For example, when the number of horn-related features is fixed, that is, when the horn-related features no longer update within a certain time period, the preset quantity threshold can be set as the number of vehicle information corresponding to the voiceprint feature multiplied by a proportional threshold, such as 60%. When the number of horn-related features is not fixed and is constantly updating, the preset quantity threshold can be set to a fixed value, such as 10. For example, if the number of identical vehicle information reaches the preset quantity threshold, it can effectively verify that the voiceprint feature is the horn sound feature that the vehicle corresponding to the vehicle information can emit. Therefore, the association relationship between the voiceprint feature and vehicle information, the horn-related feature in the vehicle information, and road condition features is established.

[0069] This application provides a method for detecting vehicles that are honking. For the same voiceprint feature, the method determines the number of identical vehicle information corresponding to that voiceprint feature in at least two honking-related features. If the number of identical vehicle information reaches a preset threshold, a correlation is established between the voiceprint feature, the vehicle information, the honking pattern feature in the honking-related features corresponding to the vehicle information, and road condition features. This method can further verify that the horn sound emitted by the vehicle corresponding to the vehicle information is indeed the voiceprint feature based on the number of identical vehicle information corresponding to the same voiceprint feature, improving the accuracy of the correlation and facilitating subsequent precise identification of the honking vehicle.

[0070] Figure 6This is a flowchart illustrating a method for detecting vehicles that are honking, as provided in another embodiment of this application. This embodiment is an optimization based on the above embodiments; solutions not described in detail in this embodiment are found in the above embodiments. Figure 6 As shown, the method in this embodiment of the application specifically includes the following steps:

[0071] S410. If the sound of a vehicle horn is collected by the microphone of the image acquisition device deployed around the road, the image acquisition device is used to collect images to identify the candidate vehicle suspected of horn honking.

[0072] S420. For the vehicle horn sound and the candidate vehicle, determine the horn-related features; wherein, the horn-related features include the voiceprint features of the vehicle horn sound, the horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle.

[0073] S430. For at least two accumulated horn-related features, determine the association between the same voiceprint feature and the horn-honking pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle location.

[0074] In this embodiment of the application, at least two horn-related features can be continuously acquired until no new features are added to the association for a period of time. Then it is determined that the data contained in the current association is relatively comprehensive, covering all vehicle horn sounds and vehicle information appearing on the current road. Therefore, the association can be saved for subsequent use.

[0075] S440. If a target horn sound is collected by the microphone of an image acquisition device deployed around the road, then for the target horn sound and the suspected vehicle that is suspected of producing the target horn sound, the horn sound association feature corresponding to the target horn sound is determined; wherein, the process of determining the horn sound association feature corresponding to the target horn sound is the same as the process of determining the horn sound association feature corresponding to the vehicle horn sound.

[0076] For example, in the subsequent road detection process, if the target horn sound is captured by the microphone of an image acquisition device deployed around the road, the image acquisition device is used to capture images and locate the suspected vehicle that generated the target horn sound. If the image acquisition device that detected the target horn sound is a roadside image acquisition device, the suspected vehicle is tracked using both the roadside image acquisition device and the checkpoint image acquisition device, and the target horn sound is detected to determine the horn sound association features corresponding to the target horn sound. The horn sound association features are the same as those in the above embodiments, including the voiceprint features of the vehicle horn sound, the horn sound pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle. The process of determining the horn sound association features corresponding to the target horn sound is consistent with the process of determining the horn sound association features corresponding to the vehicle horn sound.

[0077] S450, Match the voiceprint features of the target whistle sound with the voiceprint features in the association relationship.

[0078] For example, the voiceprint features of the target horn sound are matched with the voiceprint features in the association relationship, and the association relationship that matches the voiceprint features of the target horn sound is found from the association relationship, that is, the target association relationship where the voiceprint features are successfully matched.

[0079] If there is no association relationship in the association relationship that matches the voiceprint characteristics of the target horn sound, then the vehicle information, horn horn pattern characteristics, and road condition characteristics corresponding to the voiceprint information are recorded as a new horn horn association feature in the association relationship.

[0080] S460. Based on the target association relationship successfully matched by voiceprint features and the horn association features corresponding to the target horn sound, determine the vehicle that produced the target horn sound.

[0081] For example, after identifying the target association containing the target horn sound, other features in the horn association features of the target horn sound are matched with other features in the target association to determine the horn vehicle that produced the target horn sound.

[0082] In this embodiment of the application, determining the vehicle that produced the target horn sound based on the target association relationship of successfully matched voiceprint features and the horn association features corresponding to the target horn sound includes:

[0083] The vehicle information of the suspected vehicle is matched with the vehicle information in the target association relationship;

[0084] If the vehicle information is matched successfully and there is only one suspected vehicle, then that suspected vehicle will be designated as the vehicle that honked its horn.

[0085] If at least two suspected vehicles are successfully matched with the vehicle information, the horn association features corresponding to the target horn sound and the target association relationship of the successfully matched vehicle information are used for horn pattern feature matching and road condition feature matching to determine the horn-honking vehicle.

[0086] For example, the vehicle information of the suspected vehicle recorded in the horn association features of the target horn sound can be matched with the vehicle information in the target association information. If there is only one vehicle information record in the target association that successfully matches the vehicle information of the suspected vehicle, then the suspected vehicle is determined to be the vehicle that produced the target horn sound. If there are at least two records with successfully matched vehicle information, further matching of other features is required to determine the horn-honking vehicle. Specifically, the horn pattern feature in the horn association features corresponding to the target horn sound is matched with the horn pattern feature in the target association where the vehicle information has been successfully matched, and the road condition feature in the horn association features corresponding to the target horn sound is matched with the road condition feature in the target association where the vehicle information has been successfully matched. If both matches are successful, then the suspected vehicle is determined to be the horn-honking vehicle.

[0087] This application provides a method for detecting vehicles honking. If a target honking sound is captured by the microphone of an image acquisition device deployed around the road, then, for the target honking sound and the suspected vehicle that generated the target honking sound, the honking association features corresponding to the target honking sound are determined. The process of determining the honking association features corresponding to the target honking sound is consistent with the process of determining the honking association features corresponding to vehicle honking sounds. The voiceprint features of the target honking sound are matched with the voiceprint features in the association relationship. Based on the successfully matched target association relationship and the honking association features corresponding to the target honking sound, the vehicle that generated the target honking sound is determined. This solution can detect target honking sounds using the microphone of an already deployed image acquisition device, and accurately locate the vehicle that generated the target honking sound by comparing the target honking sound with the association relationship, thus accurately detecting vehicle honking without adding any additional hardware.

[0088] Figure 7 This is a schematic diagram of a vehicle horn detection device provided in an embodiment of this application. This device can execute the vehicle horn detection method provided in any embodiment of this application, and possesses the corresponding functional modules and beneficial effects for executing the method. Figure 7 As shown, the device includes:

[0089] The candidate vehicle determination module 510 is used to determine the candidate vehicle suspected of honking if the sound of a vehicle horn is collected by the microphone of the image acquisition device deployed around the road.

[0090] The horn association feature determination module 520 is used to determine horn association features for the vehicle horn sound and the candidate vehicle; wherein, the horn association features include the voiceprint features of the vehicle horn sound, the horn pattern features, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle location.

[0091] The association determination module 530 is used to determine the association between the same voiceprint feature and the horn pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle for at least two accumulated horn association features, so as to determine the horn vehicle of the collected target horn sound based on the association.

[0092] In this embodiment of the application, the horn association feature determination module 520 determines horn association features based on the vehicle horn sound and the candidate vehicle, including:

[0093] If the image acquisition device is a roadside image acquisition device, then the vehicle body features of the candidate vehicle are detected by the roadside image acquisition device;

[0094] The license plate features of the candidate vehicles are detected by the roadside image acquisition device and the checkpoint image acquisition device.

[0095] In this embodiment, the horn-related feature determination module 520 detects the license plate features of the candidate vehicle through the roadside image collector and the checkpoint image collector, including:

[0096] The candidate vehicle's driving direction and speed are detected by the roadside image acquisition device;

[0097] Determine the distance between the roadside image acquisition device and the next checkpoint image acquisition device along the driving direction, and predict the target time for the candidate vehicle to reach the next checkpoint image acquisition device based on the distance and the vehicle speed;

[0098] The license plate features of the candidate vehicle are determined based on the image captured by the next checkpoint image collector at the target time.

[0099] In this embodiment of the application, the horn association feature determination module 520 determines horn association features based on the vehicle horn sound and the candidate vehicle, including:

[0100] The number of times the vehicle horn sounds and the time interval within a preset time period are detected as the horn sound pattern characteristics;

[0101] The image acquisition device detects at least one of the following: road conditions, traffic light conditions, vehicle conditions in front and behind, and pedestrian conditions in the lane where the candidate vehicle is located, as the road condition features.

[0102] In this embodiment of the application, the association determination module 530 determines the association between the same voiceprint feature and the horn pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle location for at least two accumulated horn association features, including:

[0103] For the same voiceprint feature, determine the number of identical vehicle information corresponding to the voiceprint feature in at least two horn-related features;

[0104] If the number of identical vehicle information reaches a preset threshold, then the association between the voiceprint feature, the vehicle information, the horn-honking pattern feature in the horn-honking association feature corresponding to the vehicle information, and the road condition feature is established.

[0105] In this embodiment of the application, the device further includes:

[0106] The target horn sound detection module is used to determine the horn sound association features corresponding to the target horn sound and the suspected vehicle that is suspected of producing the target horn sound if the target horn sound is collected by the microphone of the image acquisition device deployed around the road. The process of determining the horn sound association features corresponding to the target horn sound is the same as the process of determining the horn sound association features corresponding to the vehicle horn sound.

[0107] The matching module is used to match the voiceprint features of the target whistle sound with the voiceprint features in the association relationship;

[0108] The horn-honking vehicle determination module is used to determine the vehicle that produced the target horn sound based on the target association relationship successfully matched by voiceprint features and the horn association features corresponding to the target horn sound.

[0109] In this embodiment of the application, the horn-honking vehicle determination module determines the horn-honking vehicle that generated the target horn sound based on the target association relationship successfully matched with the voiceprint features and the horn association features corresponding to the target horn sound, including:

[0110] The vehicle information of the suspected vehicle is matched with the vehicle information in the target association relationship;

[0111] If the vehicle information is matched successfully and there is only one suspected vehicle, then that suspected vehicle will be designated as the vehicle that honked its horn.

[0112] If at least two suspected vehicles are successfully matched with the vehicle information, the horn association features corresponding to the target horn sound and the target association relationship are matched with horn pattern features and road condition features to determine the horn-honking vehicle.

[0113] The vehicle horn detection device provided in this application embodiment can execute the vehicle horn detection method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.

[0114] Figure 8A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0115] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, connected to the at least one processor 11 for data processing. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and data processing unit 19, such as network card, modem, wireless data processing transceiver, etc. Data processing unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0117] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the horn-honking vehicle detection method.

[0118] In some embodiments, the horn-honking vehicle detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or data processing unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the horn-honking vehicle detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the horn-honking vehicle detection method by any other suitable means (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable horn-sounding vehicle detection device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected through digital data processing (e.g., data processing networks) of any form or medium. Examples of data processing networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0124] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via data processing networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0125] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting vehicles honking their horns, characterized in that, The method includes: If a vehicle horn sound is detected by the microphone of an image acquisition device deployed around the road, the image acquisition device is used to identify the candidate vehicle suspected of horn honking. For the vehicle horn sound and the candidate vehicle, determine the horn-related features; wherein, the horn-related features include the voiceprint features of the vehicle horn sound, the horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle; For at least two accumulated horn-related features, determine the association between the same voiceprint feature and the horn-honking pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle, so as to determine the horn-honking vehicle of the collected target horn sound based on the association.

2. The method according to claim 1, characterized in that, For the vehicle horn sound and the candidate vehicle, determine the horn-related features, including: If the image acquisition device is a roadside image acquisition device, then the vehicle body features of the candidate vehicle are detected by the roadside image acquisition device; The license plate features of the candidate vehicles are detected by the roadside image acquisition device and the checkpoint image acquisition device.

3. The method according to claim 2, characterized in that, The license plate features of the candidate vehicles are detected by the roadside image acquisition device and the checkpoint image acquisition device, including: The candidate vehicle's driving direction and speed are detected by the roadside image acquisition device; Determine the distance between the roadside image acquisition device and the next checkpoint image acquisition device along the driving direction, and predict the target time for the candidate vehicle to reach the next checkpoint image acquisition device based on the distance and the vehicle speed; The license plate features of the candidate vehicle are determined based on the image captured by the next checkpoint image collector at the target time.

4. The method according to claim 1, characterized in that, For the vehicle horn sound and the candidate vehicle, determine the horn-related features, including: The number of times the vehicle horn sounds and the time interval within a preset time period are detected as the horn sound pattern characteristics; The image acquisition device detects at least one of the following: road conditions, traffic light conditions, vehicle conditions in front and behind, and pedestrian conditions in the lane where the candidate vehicle is located, as the road condition features.

5. The method according to claim 1, characterized in that, For at least two accumulated horn-related features, determine the association between the same voiceprint feature and horn-honking pattern features, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle location, including: For the same voiceprint feature, determine the number of identical vehicle information corresponding to the voiceprint feature in at least two horn-related features; If the number of identical vehicle information reaches a preset threshold, then the association between the voiceprint feature, the vehicle information, the horn-honking pattern feature in the horn-honking association feature corresponding to the vehicle information, and the road condition feature is established.

6. The method according to claim 1, characterized in that, The method further includes: If a target horn sound is captured by the microphone of an image acquisition device deployed around the road, then for the target horn sound and the suspected vehicle that is suspected of producing the target horn sound, the horn sound association feature corresponding to the target horn sound is determined; wherein, the process of determining the horn sound association feature corresponding to the target horn sound is the same as the process of determining the horn sound association feature corresponding to the vehicle horn sound. Match the voiceprint features of the target whistle sound with the voiceprint features in the association relationship; Based on the successful target association relationship matched by voiceprint features and the horn association features corresponding to the target horn sound, the vehicle that produced the target horn sound is determined.

7. The method according to claim 6, characterized in that, Based on the successful target association relationship matched by voiceprint features and the horn association features corresponding to the target horn sound, the vehicle that produced the target horn sound is determined, including: The vehicle information of the suspected vehicle is matched with the vehicle information in the target association relationship; If the vehicle information is matched successfully and there is only one suspected vehicle, then that suspected vehicle will be designated as the vehicle that honked its horn. If at least two suspected vehicles are successfully matched with the vehicle information, the horn association features corresponding to the target horn sound and the target association relationship are matched with horn pattern features and road condition features to determine the horn-honking vehicle.

8. A vehicle horn detection device, characterized in that, The device includes: The candidate vehicle determination module is used to determine the suspected candidate vehicle honking by acquiring images through the image acquisition device if the sound of a vehicle honking is acquired by the microphone of the image acquisition device deployed around the road. The horn association feature determination module is used to determine horn association features for the vehicle horn sound and the candidate vehicle; wherein, the horn association features include the voiceprint features of the vehicle horn sound, the horn pattern features, the vehicle information of the candidate vehicle, and the road condition features at the location of the candidate vehicle. The association determination module is used to determine the association between the same voiceprint feature and the horn pattern feature, the vehicle information of the candidate vehicle, and the road condition features at the candidate vehicle for at least two accumulated horn association features, so as to determine the horn vehicle of the collected target horn sound based on the association.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and The memory is connected to the at least one processor for data processing; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the horn-honking vehicle detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the horn-honking vehicle detection method according to any one of claims 1-7.

Images