Traffic accident monitoring method and device, electronic equipment and storage medium

Abstract

The invention relates to a traffic accident monitoring method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring target sound information, target image information, target smoke information and target temperature information in a target area; determining a target sound matching degree between the target sound information and preset sound information and a target image matching degree between the target image information and preset image information; determining a target smoke concentration change rate based on the target smoke information, and determining a target temperature change rate based on the target temperature information; determining a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate; and when the target monitoring result meets a preset reminding condition, outputting accident reminding information. According to the invention, traffic accident monitoring is carried out based on the sound information, the image information, the smoke information and the temperature information, and the traffic accident can be timely and accurately found and reported.

Description

Technical Field

[0001] The present invention relates to the field of traffic safety technology, and in particular to a traffic accident monitoring method, device, electronic equipment and storage medium. Background Art

[0002] At crossroads and T-intersections, especially at blocked traffic intersections, traffic accidents such as car-to-car collisions and car-to-pedestrian collisions are prone to occur because traffic lights are not installed or are not functioning properly. Especially at intersections with less vehicle and pedestrian traffic, serious traffic accidents are not easily discovered, affecting the handling of traffic accidents and the rescue of the injured. Summary of the invention

[0003] In order to solve the above technical problems, the present invention discloses a traffic accident monitoring method, device, electronic device and storage medium, which monitor traffic accidents based on sound information, image information, smoke information and temperature information, and can detect and report traffic accidents in a timely and accurate manner.

[0004] In order to achieve the above object, the present invention provides a traffic accident monitoring method, the method comprising: Acquire target sound information, target image information, target smoke information and target temperature information in the target area; Determining a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; determining a target smoke concentration change rate based on the target smoke information, and determining a target temperature change rate based on the target temperature information; Determining a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; When the target monitoring result meets the preset reminder condition, the accident reminder information is output.

[0005] In an optional embodiment, the preset sound information includes first preset sound information and second preset sound information, the target sound matching degree includes first sound matching degree and second sound matching degree, the preset image information includes first preset image information and second preset image information, the target image matching degree includes first image matching degree and second image matching degree, and determining the target sound matching degree between the target sound information and the preset sound information, and the target image matching degree between the target image information and the preset image information, includes: Comparing the target sound information with the first preset sound information to determine the matching degree of the first sound; the first preset sound information represents the environmental sound information related to the traffic accident; comparing the target sound information with the second preset sound information to determine the matching degree of the second sound; the second preset sound information represents voice information related to the traffic accident; Comparing the target image information with the first preset image information to determine the matching degree of the first image; the first preset image information represents environmental image information related to the traffic accident; The target image information is compared with the second preset image information to determine the matching degree of the second image; the second preset image information represents still human image information related to the traffic accident.

[0006] In an optional embodiment, determining the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate includes: Determine weight coefficients corresponding to the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate, respectively; The target sound matching degree, the target image matching degree, the target smoke concentration change rate, the target temperature change rate and their corresponding weight coefficients are subjected to weighted summation processing to obtain the target monitoring result.

[0007] In an optional embodiment, the determining the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate further includes: The target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate are input into the accident prediction model to obtain the target monitoring result; the accident prediction model is obtained by training a preset machine learning model based on the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area.

[0008] In an optional embodiment, when the target monitoring result meets the preset reminder condition, outputting the accident reminder information includes: When the target monitoring result is greater than a preset monitoring threshold, the accident reminder information is output.

[0009] In an optional embodiment, the accident reminder information includes alarm information and warning information, and when the target monitoring result is greater than a preset monitoring threshold, outputting the accident reminder information includes: When the target monitoring result is greater than the preset monitoring threshold, outputting the alarm information; the alarm information includes the location information of the target area and the target image information; Output the warning information; the warning information includes sound reminder information and / or light reminder information.

[0010] In an optional embodiment, the step of acquiring target sound information, target image information, target smoke information, and target temperature information in the target area includes: Acquiring initial sound information, initial image information, initial smoke information, and initial temperature information in the target area; The initial sound information, the initial image information, the initial smoke information and the initial temperature information are respectively subjected to denoising processing to obtain the target sound information, the target image information, the target smoke information and the target temperature information.

[0011] The present invention also provides a traffic accident monitoring device, the device comprising: An information acquisition module, used to acquire target sound information, target image information, target smoke information and target temperature information in the target area; A matching degree determination module, used to determine a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; a change rate determination module, configured to determine a target smoke concentration change rate based on the target smoke information, and to determine a target temperature change rate based on the target temperature information; A monitoring result determination module, used to determine a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; The accident reminder information output module is used to output accident reminder information when the target monitoring result meets the preset reminder condition.

[0012] The present invention also provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the traffic accident monitoring method as described above.

[0013] The present invention also provides a computer-readable storage medium, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the traffic accident monitoring method as described above. Implementing the embodiments of the present invention has the following beneficial effects: The traffic accident monitoring method disclosed in the present invention combines multi-dimensional information in traffic roads to monitor traffic accidents. The multi-dimensional information includes sound information, image information, smoke information and temperature information, which improves the accuracy and timeliness of traffic accident monitoring, can timely and accurately discover and report traffic accidents, and facilitates subsequent handling of traffic accidents and rescue of the injured. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the traffic accident monitoring method, device, electronic device and storage medium described in the present invention, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 A schematic diagram of the structure of a traffic accident monitoring system provided by an embodiment of the present invention; Figure 2 A flow chart of a traffic accident monitoring method provided by an embodiment of the present invention; Figure 3 A flowchart of a matching degree determination method provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a traffic accident monitoring device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices. Please refer to Figure 1 , which is a schematic diagram of the structure of a traffic accident monitoring system provided by an embodiment of the present invention. The traffic accident monitoring system at least includes a collection end 01, a control end 02 and an output end 03.

[0018] The acquisition terminal 01 is used to collect initial sound information, initial image information, initial smoke information and initial temperature information in the target area, and send the initial sound information, initial image information, initial smoke information and initial temperature information to the control terminal 02.

[0019] The control terminal 02 is used to perform denoising processing on the initial sound information, the initial image information, the initial smoke information and the initial temperature information respectively, to obtain the target sound information, the target image information, the target smoke information and the target temperature information; to determine the target sound matching degree between the target sound information and the preset sound information, and the target image matching degree between the target image information and the preset image information; to determine the target smoke concentration change rate based on the target smoke information, and to determine the target temperature change rate based on the target temperature information; to determine the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate; and when the target monitoring result meets the preset reminder condition, the control output terminal 03 outputs the accident reminder information.

[0020] The traffic accident monitoring system can be set up on the roadside, especially at traffic intersections, roads with less traffic and pedestrian flow, to monitor whether a traffic accident has occurred on the road. The acquisition end 01 can include at least a sound sensor, an image sensor, a smoke sensor, and a temperature sensor, and the output end 03 can include at least a communication device and an audio-visual alarm device.

[0021] The following combination Figure 2 The present invention introduces a traffic accident monitoring method based on the above system. This embodiment is applied to the control end side of the traffic accident monitoring system.

[0022] Please refer to Figure 2, which shows a flow chart of a traffic accident monitoring method provided by an embodiment of the present invention. This specification provides method operation steps as described in the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or server product is executed, it can be executed in the order of the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the traffic accident monitoring method includes: S201, acquiring target sound information, target image information, target smoke information and target temperature information in a target area; In the embodiment of this specification, the acquisition of target sound information, target image information, target smoke information and target temperature information in the target area includes: Acquiring initial sound information, initial image information, initial smoke information, and initial temperature information in the target area; The initial sound information, the initial image information, the initial smoke information and the initial temperature information are respectively subjected to denoising processing to obtain the target sound information, the target image information, the target smoke information and the target temperature information.

[0023] In the embodiments of the present specification, initial sound information can be collected by a sound sensor, initial image information can be collected by an image sensor, initial smoke information can be collected by a smoke sensor, and initial temperature information can be collected by a temperature sensor; initial sound information refers to the ambient sound information and human voice information of the target area within a preset time period, initial image information refers to the ambient image information and human image information of the target area within a preset time period, initial smoke information refers to the smoke concentration data of the target area within a preset time period, and initial temperature information refers to the ground temperature data of the target area within a preset time period; wherein, the target area refers to areas in traffic roads such as traffic intersections and roads with less traffic and pedestrian flow, and the target area is within the range that can be monitored by the sound sensor, image sensor, smoke sensor and temperature sensor, and the preset time period can be set according to actual needs.

[0024] In the embodiments of the present specification, in order to cope with severe weather conditions such as heavy fog and heavy rain, the image sensor may include at least an optical image sensor and a microwave imaging sensor.

[0025] In the embodiments of the present specification, after the initial sound information, initial image information, initial smoke information and initial temperature information are obtained, the information needs to be preprocessed, and the preprocessing at least includes denoising. By denoising the initial sound information, initial image information, initial smoke information and initial temperature information respectively, abnormal data can be removed to obtain target sound information corresponding to the initial sound information, target image information corresponding to the initial image information, target smoke information corresponding to the initial smoke information and target temperature information corresponding to the initial temperature information. The target sound information, target image information, target smoke information and target temperature information are all pure information after denoising.

[0026] The embodiments of this specification collect multi-dimensional information on traffic roads through various sensors installed on traffic roads. The multi-dimensional information includes sound information, image information, smoke information and temperature information. The multi-dimensional information is denoised and then further combined with the denoised multi-dimensional information to perform traffic accident monitoring, thereby improving the accuracy and timeliness of traffic accident monitoring.

[0027] S203, determining a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; In an embodiment of the present specification, the preset sound information may be sound information pre-stored in a local database, the preset sound information including first preset sound information and second preset sound information, the first preset sound information representing environmental sound information related to the traffic accident, including impact sounds, explosion sounds, etc., the second preset sound information representing voice information related to the traffic accident, including keywords and key words such as "car accident", "rescue", "save lives", "save people", and "fire fighting"; the target sound matching degree includes the first sound matching degree and the second sound matching degree, the first sound matching degree refers to the matching degree between the target sound information and the first preset sound information, the second sound matching degree refers to the matching degree between the target sound information and the second preset sound information, the target sound information refers to the environmental sound information and human voice information of the target area within a preset time length.

[0028] In an embodiment of the present specification, the preset image information may be image information pre-stored in a local database, the preset image information including first preset image information and second preset image information, the first preset image information representing environmental image information related to the traffic accident, including flame images, smoke images, etc., the second preset image information representing still human image information related to the traffic accident, including fallen human images, etc.; the target image matching degree includes a first image matching degree and a second image matching degree, the first image matching degree refers to the matching degree between the target image information and the first preset image information, the second image matching degree refers to the matching degree between the target image information and the second preset image information, the target image information refers to the environmental image information and human image information of the target area within a preset time length.

[0029] In the examples of this manual, please refer to Figure 3 , which is a flow chart of a matching degree determination method provided by an embodiment of the present invention, wherein determining the target sound matching degree between the target sound information and the preset sound information, and the target image matching degree between the target image information and the preset image information, comprises: S301, comparing the target sound information with the first preset sound information to determine a matching degree of the first sound; the first preset sound information represents environmental sound information related to a traffic accident; In the embodiment of the present specification, the target sound information includes the environmental sound information of the target area within a preset time period, and the first preset sound information may be sound information pre-stored in a local database, which represents the environmental sound information related to the traffic accident, including impact sound, explosion sound, etc.; by extracting the sound characteristics such as the decibel number and timbre of the target sound information, and comparing the target sound information with the first preset sound information based on the sound characteristics, the matching degree between the target sound information and the first preset sound information, i.e., the first sound matching degree, can be obtained. The first sound matching degree can represent whether the target area has sounds related to traffic accidents such as impact sound and explosion sound within the preset time period.

[0030] S303, comparing the target sound information with the second preset sound information to determine the matching degree of the second sound; the second preset sound information represents voice information related to the traffic accident; In the embodiment of the present specification, the target sound information also includes human voice information in the target area within a preset time length, and the second preset sound information can be sound information pre-stored in a local database, which represents voice information related to traffic accidents, including keywords and key words such as "car accident", "rescue", "help", "save people", and "fire fighting"; by extracting sound features such as Linear Predictive Cepstral Coefficients (LPCC) and Mel Frequency Cepstral Coefficients (MFCC) of the target sound information, and comparing the target sound information with the second preset sound information based on the sound features, the matching degree between the target sound information and the second preset sound information can be obtained, that is, the second sound matching degree. The second sound matching degree can represent whether someone in the target area has said words related to traffic accidents such as "car accident", "rescue", "help", "save people", and "fire fighting" within the preset time length.

[0031] S305, comparing the target image information with the first preset image information to determine the matching degree of the first image; the first preset image information represents environmental image information related to the traffic accident; In the embodiment of the present specification, the target image information includes the environmental image information of the target area within a preset time period, and the first preset image information may be image information pre-stored in a local database, which represents environmental image information related to traffic accidents, including flame images, smoke images, etc.; by extracting image features such as color features and shape features of the target image information, and comparing the target image information with the first preset image information based on the image features, the matching degree between the target image information and the first preset image information, i.e., the first image matching degree, may be obtained. The first image matching degree may represent whether visual elements related to traffic accidents such as flames and smoke appear in the target area within the preset time period.

[0032] S307, comparing the target image information with the second preset image information to determine the matching degree of the second image; the second preset image information represents still human image information related to the traffic accident.

[0033] In the embodiment of the present specification, the target sound information also includes human image information in the target area within a preset time length, and the second preset image information may be image information pre-stored in a local database, which represents static human image information related to traffic accidents, including images of fallen human bodies, etc. By extracting image features such as shape features of the target image information, and comparing the target image information with the second preset image information based on the image features, the matching degree between the target image information and the second preset image information, i.e., the second image matching degree, may be obtained. The second image matching degree may represent whether there are visual elements related to traffic accidents such as fallen human bodies in the target area within a preset time length.

[0034] The embodiments of the present specification can determine whether there are sound elements and visual elements related to traffic accidents in the traffic road by comparing the sound information in the traffic road with the preset sound information, and comparing the image information in the traffic road with the preset image information, and then further combine the smoke information and temperature information in the traffic road to perform multi-dimensional traffic accident monitoring, thereby improving the accuracy and timeliness of traffic accident monitoring.

[0035] S205, determining a target smoke concentration change rate based on the target smoke information, and determining a target temperature change rate based on the target temperature information; In the embodiments of this specification, the target smoke information refers to the smoke concentration data of the target area within the preset time, and the target temperature information refers to the ground temperature data of the target area within the preset time. Based on the maximum smoke concentration and the minimum smoke concentration of the target area within the preset time, the smoke concentration change rate of the target area within the preset time, i.e., the target smoke concentration change rate, can be calculated; based on the maximum temperature and the minimum temperature of the target area within the preset time, the temperature change rate of the target area within the preset time, i.e., the target temperature change rate, can be calculated.

[0036] S207, determining a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; In the embodiment of the present specification, the target monitoring result is determined based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate, including: Determine weight coefficients corresponding to the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate, respectively; The target sound matching degree, the target image matching degree, the target smoke concentration change rate, the target temperature change rate and their corresponding weight coefficients are subjected to weighted summation processing to obtain the target monitoring result.

[0037] In the embodiment of the present specification, the weight coefficient corresponding to the target sound matching degree may be the first preset weight coefficient, the weight coefficient corresponding to the target image matching degree may be the second preset weight coefficient, the weight coefficient corresponding to the target smoke concentration change rate may be the third preset weight coefficient, and the weight coefficient corresponding to the target temperature change rate may be the fourth preset weight coefficient. The target sound matching degree includes the first sound matching degree and the second sound matching degree, the weight coefficient corresponding to the first sound matching degree may be the first preset sub-weight coefficient, and the weight coefficient corresponding to the second sound matching degree may be the second preset sub-weight coefficient; the target image matching degree includes the first image matching degree and the second image matching degree, the weight coefficient corresponding to the first image matching degree may be the third preset sub-weight coefficient, and the weight coefficient corresponding to the second image matching degree may be the fourth preset sub-weight coefficient.

[0038] In the embodiment of this specification, the target monitoring result can be calculated by the following formula: + + + +

[0039] in, is the first sound matching degree, is a weight coefficient corresponding to the first sound matching degree, that is, a first preset sub-weight coefficient; is the second sound matching degree, is a weight coefficient corresponding to the second sound matching degree, that is, a second preset sub-weight coefficient; is the first image matching degree, is the weight coefficient corresponding to the first image matching degree, that is, the third preset sub-weight coefficient; is the second image matching degree, is a weight coefficient corresponding to the second image matching degree, that is, a fourth preset sub-weight coefficient; is the target smoke concentration change rate, is the weight coefficient corresponding to the target smoke concentration change rate, that is, the third preset weight coefficient; is the target temperature change rate, is a weight coefficient corresponding to the target temperature change rate, that is, a fourth preset weight coefficient; , , , , , satisfy + + + + =1; the weight coefficients corresponding to the target sound matching degree, target image matching degree, target smoke concentration change rate and target temperature change rate can be set according to actual needs.

[0040] The embodiments of this specification combine multi-dimensional information in traffic roads to monitor traffic accidents. The multi-dimensional information includes sound information, image information, smoke information and temperature information, which improves the accuracy and timeliness of traffic accident monitoring, and can detect and report traffic accidents in a timely and accurate manner, facilitating subsequent handling of traffic accidents and rescuing the injured.

[0041] In the embodiment of the present specification, the determining of the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate also includes: The target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate are input into the accident prediction model to obtain the target monitoring result; the accident prediction model is obtained by training a preset machine learning model based on the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area.

[0042] In an embodiment of the present specification, the target monitoring result can be determined by establishing a machine learning model; specifically, a sample data set is constructed based on the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area, and each sample data in the sample data set includes the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area, and the accident label represents whether a traffic accident has occurred in the sample area, and then the preset machine learning model is further supervised trained based on the sample data set to obtain an accident prediction model; the preset machine learning model can be set according to actual needs.

[0043] In an embodiment of the present specification, target sound information, target image information, target smoke information and target temperature information in the target area are input into an accident prediction model to obtain a prediction result output by the accident prediction model, i.e., a target monitoring result. The target monitoring result can characterize whether a traffic accident has occurred in the target area.

[0044] The embodiments of the present specification input the sound information, image information, smoke information and temperature information on the traffic road into a pre-established machine learning model, and judge whether a traffic accident has occurred on the traffic road based on the output results of the machine learning model, thereby realizing multi-dimensional traffic accident monitoring, improving the accuracy and timeliness of traffic accident monitoring, and being able to timely and accurately discover and report traffic accidents, facilitating the subsequent handling of traffic accidents and rescuing the injured.

[0045] S209: Outputting accident reminder information when the target monitoring result meets the preset reminder condition.

[0046] In the embodiment of this specification, when the target monitoring result meets the preset reminder condition, outputting the accident reminder information includes: When the target monitoring result is greater than a preset monitoring threshold, the accident reminder information is output.

[0047] In the embodiments of this specification, the preset reminder condition may refer to the target monitoring result being greater than the preset monitoring threshold, and the preset monitoring threshold may be set according to actual needs. If the target monitoring result is greater than the preset monitoring threshold, it indicates that a traffic accident has occurred in the target area, and then the accident reminder information is output; if the target monitoring result is less than or equal to the preset monitoring threshold, it indicates that no traffic accident has occurred in the target area.

[0048] The embodiments of this specification combine multi-dimensional information on traffic roads to monitor traffic accidents. The multi-dimensional information includes sound information, image information, smoke information and temperature information. When it is determined that a traffic accident has occurred on the traffic road, accident reminder information is output, thereby improving the accuracy and timeliness of traffic accident monitoring, and being able to discover and report traffic accidents in a timely and accurate manner, facilitating subsequent handling of traffic accidents and rescuing the injured.

[0049] In the embodiment of the present specification, the accident reminder information includes alarm information and warning information, and when the target monitoring result is greater than a preset monitoring threshold, outputting the accident reminder information includes: When the target monitoring result is greater than the preset monitoring threshold, outputting the alarm information; the alarm information includes the location information of the target area and the target image information; Output the warning information; the warning information includes sound reminder information and / or light reminder information.

[0050] In the embodiment of the present specification, if the target monitoring result is greater than the preset monitoring threshold, it indicates that a traffic accident has occurred in the target area, and accident reminder information needs to be output, and the accident reminder information includes alarm information and warning information.

[0051] Specifically, an alarm message can be sent to an alarm center via the Internet or other communication methods. The alarm message includes the location information of the target area and the target image information, so that the staff can quickly understand the location of the traffic accident and the specific circumstances of the accident. At the same time, alarm information is output, and the alarm information includes sound reminder information and / or light reminder information, so as to remind passing vehicles and people through sound and light that there is a traffic accident in the current area.

[0052] In the embodiment of the present specification, if an alarm cancellation instruction is received from the alarm center, the output of the alarm information is stopped, that is, the on-site sound and light alarm is turned off.

[0053] The embodiments of this specification combine multi-dimensional information in traffic roads to monitor traffic accidents. The multi-dimensional information includes sound information, image information, smoke information and temperature information. When it is determined that a traffic accident has occurred on the traffic road, alarm information and warning information are output, thereby improving the accuracy and timeliness of traffic accident monitoring. Traffic accidents can be discovered and reported in a timely and accurate manner, facilitating subsequent handling of traffic accidents and rescuing the injured. At the same time, the accident scene alarm is activated to alert passing vehicles and people to avoid the occurrence of secondary accidents.

[0054] It can be seen from the above-mentioned embodiments of the traffic accident monitoring method provided by the present invention that the embodiments of the present invention obtain target sound information, target image information, target smoke information and target temperature information in the target area; determine the target sound matching degree between the target sound information and the preset sound information, and the target image matching degree between the target image information and the preset image information; determine the target smoke concentration change rate based on the target smoke information, and determine the target temperature change rate based on the target temperature information; determine the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate; output the accident reminder information when the target monitoring result meets the preset reminder condition. The technical solution provided by the embodiments of this specification combines multi-dimensional information in traffic roads to monitor traffic accidents. The multi-dimensional information includes sound information, image information, smoke information and temperature information, which improves the accuracy and timeliness of traffic accident monitoring, can timely and accurately discover and report traffic accidents, and facilitates the subsequent handling of traffic accidents and rescue of the injured.

[0055] The embodiment of the present invention also provides a traffic accident monitoring device, such as Figure 4 As shown, it is a schematic diagram of the structure of a traffic accident monitoring device provided by an embodiment of the present invention; specifically, the device includes: The information acquisition module 410 is used to acquire target sound information, target image information, target smoke information and target temperature information in the target area; A matching degree determination module 420 is used to determine a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; a change rate determination module 430, configured to determine a target smoke concentration change rate based on the target smoke information, and to determine a target temperature change rate based on the target temperature information; A monitoring result determination module 440, configured to determine a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; The accident reminder information output module 450 is used to output accident reminder information when the target monitoring result meets the preset reminder condition.

[0056] In the embodiment of the present specification, the preset sound information includes first preset sound information and second preset sound information, the target sound matching degree includes first sound matching degree and second sound matching degree, the preset image information includes first preset image information and second preset image information, the target image matching degree includes first image matching degree and second image matching degree, and the matching degree determination module 420 includes: A first sound matching degree determining unit is configured to compare the target sound information with the first preset sound information to determine the first sound matching degree; the first preset sound information represents environmental sound information related to the traffic accident; A second sound matching degree determining unit is used to compare the target sound information with the second preset sound information to determine the second sound matching degree; the second preset sound information represents voice information related to the traffic accident; A first image matching degree determining unit, configured to compare the target image information with the first preset image information to determine the first image matching degree; the first preset image information represents environmental image information related to the traffic accident; The second image matching degree determination unit is used to compare the target image information with the second preset image information to determine the second image matching degree; the second preset image information represents the still human body image information related to the traffic accident.

[0057] In the embodiment of this specification, the monitoring result determination module 440 includes: A weight coefficient determination unit, used to determine the weight coefficients corresponding to the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate, respectively; The first monitoring result determination unit is used to perform weighted sum processing on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, the target temperature change rate and their corresponding weight coefficients to obtain the target monitoring result.

[0058] In the embodiment of this specification, the monitoring result determination module 440 also includes: The second monitoring result determination unit is used to input the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate into the accident prediction model to obtain the target monitoring result; the accident prediction model is obtained by training a preset machine learning model based on the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area.

[0059] In the embodiment of this specification, the accident reminder information output module 450 includes: The accident reminder information output unit is used to output the accident reminder information when the target monitoring result is greater than a preset monitoring threshold.

[0060] In the embodiment of this specification, the accident reminder information includes alarm information and warning information, and the accident reminder information output unit includes: An alarm information output subunit, configured to output the alarm information when the target monitoring result is greater than the preset monitoring threshold; the alarm information includes the location information of the target area and the target image information; The alarm information output subunit is used to output the alarm information; the alarm information includes sound reminder information and / or light reminder information.

[0061] An embodiment of the present invention also provides an electronic device, which includes a processor and a memory; the memory stores one or more instructions, and the one or more instructions are suitable for the processor to load and execute to implement the traffic accident monitoring method as described in the above method embodiment.

[0062] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0063] Figure 5 The schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, the internal structure of the electronic device may include but is not limited to: a processor 501, a memory 502 and a communication interface 503, wherein the processor 501, the memory 502 and the communication interface 503 in the electronic device may be connected through a bus or other means, and the embodiment shown in this specification Figure 5 The example of connecting through bus is taken in the following.

[0064] Among them, the processor 501 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device. The communication interface 503 is used for communication between the memory 502 and the processor 501. The memory 502 (Memory) is used to store programs and data. It can be understood that the memory here can be a high-speed RAM storage device or a non-volatile storage device (non-volatile memory), such as at least one disk storage device; optionally, it can also be at least one storage device located away from the aforementioned processor. The memory provides a storage space, which stores the operating system of the electronic device, which may include but is not limited to: Windows system (an operating system), Linux system (an operating system), etc., and the present invention does not limit this; and, a computer program (including program code) suitable for being loaded and executed by the processor is also stored in the storage space. In the embodiment of this specification, the processor 501 loads and executes the computer program stored in the memory 502 to implement the traffic accident monitoring method provided in the above method embodiment.

[0065] An embodiment of the present invention also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction, at least one program, code set or instruction set related to a traffic accident monitoring method in a method embodiment. The at least one instruction, the at least one program, the code set or instruction set can be loaded and executed by a processor of the electronic device to implement the traffic accident monitoring method provided by the above-mentioned method embodiment.

[0066] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0067] It should be noted that the sequence of the embodiments of the present invention described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0069] Those skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

[0070] The above disclosure is only a preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A traffic accident monitoring method, characterized in that: The method comprises: Acquire target sound information, target image information, target smoke information and target temperature information in the target area; Determining a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; determining a target smoke concentration change rate based on the target smoke information, and determining a target temperature change rate based on the target temperature information; Determining a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; When the target monitoring result meets the preset reminder condition, the accident reminder information is output.

2. The traffic accident monitoring method according to claim 1, characterized in that: The preset sound information includes first preset sound information and second preset sound information, the target sound matching degree includes first sound matching degree and second sound matching degree, the preset image information includes first preset image information and second preset image information, the target image matching degree includes first image matching degree and second image matching degree, and determining the target sound matching degree between the target sound information and the preset sound information, and the target image matching degree between the target image information and the preset image information, includes: Comparing the target sound information with the first preset sound information to determine the matching degree of the first sound; the first preset sound information represents the environmental sound information related to the traffic accident; comparing the target sound information with the second preset sound information to determine the matching degree of the second sound; the second preset sound information represents voice information related to the traffic accident; Comparing the target image information with the first preset image information to determine the matching degree of the first image; the first preset image information represents environmental image information related to the traffic accident; The target image information is compared with the second preset image information to determine the matching degree of the second image; the second preset image information represents still human image information related to the traffic accident.

3. The traffic accident monitoring method according to claim 1, characterized in that: The determining of the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate includes: Determine weight coefficients corresponding to the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate, respectively; The target sound matching degree, the target image matching degree, the target smoke concentration change rate, the target temperature change rate and their corresponding weight coefficients are weighted and summed to obtain the target monitoring result.

4. The traffic accident monitoring method according to claim 1, characterized in that: The determining of the target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate also includes: The target sound matching degree, the target image matching degree, the target smoke concentration change rate and the target temperature change rate are input into the accident prediction model to obtain the target monitoring result; the accident prediction model is obtained by training a preset machine learning model based on the sample sound matching degree, sample image matching degree, sample smoke concentration change rate, sample temperature change rate and accident label corresponding to the sample area.

5. The traffic accident monitoring method according to claim 3 or 4, characterized in that: When the target monitoring result meets the preset reminder condition, outputting the accident reminder information includes: When the target monitoring result is greater than a preset monitoring threshold, the accident reminder information is output.

6. The traffic accident monitoring method according to claim 5, characterized in that: The accident reminder information includes alarm information and warning information. When the target monitoring result is greater than a preset monitoring threshold, the accident reminder information is output, including: When the target monitoring result is greater than the preset monitoring threshold, outputting the alarm information; the alarm information includes the location information of the target area and the target image information; Output the warning information; the warning information includes sound reminder information and / or light reminder information.

7. The traffic accident monitoring method according to claim 1, characterized in that: The obtaining of target sound information, target image information, target smoke information and target temperature information in the target area includes: Acquiring initial sound information, initial image information, initial smoke information, and initial temperature information in the target area; The initial sound information, the initial image information, the initial smoke information and the initial temperature information are respectively subjected to denoising processing to obtain the target sound information, the target image information, the target smoke information and the target temperature information.

8. A traffic accident monitoring device, characterized in that: The device comprises: An information acquisition module, used to acquire target sound information, target image information, target smoke information and target temperature information in the target area; A matching degree determination module, used to determine a target sound matching degree between the target sound information and the preset sound information, and a target image matching degree between the target image information and the preset image information; a change rate determination module, configured to determine a target smoke concentration change rate based on the target smoke information, and to determine a target temperature change rate based on the target temperature information; A monitoring result determination module, used to determine a target monitoring result based on the target sound matching degree, the target image matching degree, the target smoke concentration change rate, and the target temperature change rate; The accident reminder information output module is used to output accident reminder information when the target monitoring result meets the preset reminder condition.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the traffic accident monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the traffic accident monitoring method as described in any one of claims 1-7.

Images