A traffic accident evidence collection method and system based on image processing

Abstract

The present application discloses a traffic accident evidence collection method and system based on image processing. After the accident vehicle collides, the owner can choose to send an evidence collection request to the server; after receiving the evidence collection request, the server pushes an evidence collection message to the nearby terminal near the accident vehicle, requesting nearby vehicles / pedestrians to assist in the collection of evidence images; after receiving the evidence collection images uploaded by the nearby terminal, the evidence collection images are processed, and the evidence collection images with poor image quality and poor angles are removed before publishing the evidence collection images. Based on this method, the owner of the accident vehicle can avoid the danger of getting off the vehicle to collect evidence and take photos after the accident, and at the same time obtain evidence collection images taken from different angles by other vehicles or pedestrians, thereby ensuring the reliability of the evidence collection images.

Description

Technical Field

[0001] The present application relates to the field of traffic management technology, and in particular to a method and system for collecting evidence of traffic accidents based on image processing. Background Art

[0002] With the acceleration of urbanization and motorization, my country's automobile industry has developed rapidly. At the same time, with the introduction of national policies to encourage private car purchases, the proportion of personal car purchases has increased rapidly year by year, especially the market share of cars and buses will further increase, resulting in a rapid increase in traffic accident rates.

[0003] At present, after a vehicle accident, the owner is often required to get out of the car to take photos and collect evidence, so as to facilitate the subsequent division of traffic responsibility and insurance claims. On highways, bridges, and tunnels with high speeds, it is more dangerous for the owner to get out of the car to take photos and collect evidence. In addition, the owner may be panicked after the accident, which may affect the image quality and shooting angle, thus affecting the reliability of traffic responsibility division. Summary of the invention

[0004] The purpose of this application is to provide a traffic accident evidence collection method and system based on image processing, which can improve the above-mentioned problems.

[0005] The embodiment of the present application is implemented as follows:

[0006] In a first aspect, the present application provides a method for collecting evidence of a traffic accident based on image processing, which comprises:

[0007] S1: in response to receiving a forensics request sent by an accident main terminal, pushing a forensics message to a nearby terminal within a first distance threshold range from the accident main terminal;

[0008] S2: receiving the forensic image uploaded by the nearby terminal, and performing image processing on the forensic image;

[0009] S3: Publishing at least part of the forensic image after image processing.

[0010] Among them, S1, S2, etc. are only step identifiers, and the execution order of the method is not necessarily in the order of numbers from small to large. For example, step S2 may be executed first and then step S1. This application does not impose any limitation on this.

[0011] In an optional embodiment of the present application, the evidence collection request includes the identity information of the accident vehicle owner, the vehicle information of the accident vehicle, and the current location of the accident owner terminal. The identity information of the vehicle owner includes basic information such as the name, gender, and ID number of the vehicle owner; the vehicle information includes the vehicle model, brand, and license plate number.

[0012] It can be understood that the present application discloses a traffic accident evidence collection method based on image processing. After the accident vehicle collides, the owner can choose to send an evidence collection request to the server; after receiving the evidence collection request, the server pushes an evidence collection message to the nearby terminal near the accident vehicle, requesting nearby vehicles / pedestrians to assist in the collection of evidence images; after receiving the evidence collection images uploaded by the nearby terminal, the evidence collection images are processed, and evidence collection images with poor image quality and poor angles are removed before being released. Based on this method, the owner of the accident vehicle can avoid the danger of getting off the vehicle to collect evidence and take photos after the accident, and at the same time obtain evidence collection images taken from different angles by other vehicles or pedestrians, thereby ensuring the reliability of the evidence collection images.

[0013] In an optional embodiment of the present application, the image processing includes at least one of the following:

[0014] Calculating image quality parameters of the forensic images, and deleting the forensic images with unqualified image quality parameters;

[0015] The accident area in the forensic image is identified, and the forensic image whose accident area is smaller than a preset area threshold is deleted.

[0016] It is understandable that pedestrians and drivers around the accident site may take blurry and wrong-angle evidence images after receiving the evidence collection message pushed by the server due to haste, lack of experience, etc. The main purpose of "processing the evidence images" is to eliminate these unqualified images in a timely manner and improve the accuracy and reliability of the evidence images.

[0017] In an optional embodiment of the present application, identifying the accident area in the forensic image includes: identifying each vehicle element bounding box in the forensic image through a Faster R-CNN network; and splicing at least two vehicle element bounding boxes whose spacing is less than a second distance threshold into an accident area.

[0018] In an optional embodiment of the present application, the identifying the accident area in the forensic image includes: identifying each vehicle element bounding box in the forensic image through a Faster R-CNN network; extracting the high spatial frequency area in each vehicle element bounding box, identifying the content of the high spatial frequency area, and obtaining the license plate number; finding the vehicle element bounding box corresponding to the license plate number of the accident main terminal as the target bounding box; and splicing at least two vehicle element bounding boxes whose distance from the target bounding box is less than a second distance threshold together with the target bounding box into an accident area.

[0019] The extracting of the high spatial frequency region in each vehicle element boundary frame includes: performing Fourier transform on each vehicle element boundary frame to obtain the picture frequency domain information corresponding to each vehicle element boundary frame; in the picture frequency domain information, filtering out the part with a spatial frequency lower than a preset frequency threshold by a filter to obtain the high spatial frequency part; and performing inverse Fourier transform on the high spatial frequency part to obtain the high spatial frequency region.

[0020] It can be understood that high spatial frequency areas are usually areas with high degree of detail or texture changes in the image, and high spatial frequency areas in the vehicle element boundary box are often license plate areas. Therefore, this method uses a filter to filter out high spatial frequency areas in the vehicle element boundary box, that is, to filter out the license plate area in the vehicle element boundary box for identification.

[0021] In an optional embodiment of the present application, the traffic accident evidence collection method based on image processing further includes: S4: generating traffic accident information according to at least one of the following:

[0022] The current location of the accident main terminal;

[0023] the maximum value of the number of accident vehicles in the accident area in each of the forensic images;

[0024] The license plate number and / or vehicle type of the accident vehicle in the accident area in each of the forensic images.

[0025] It can be understood that the server can generate traffic accident information based on key information such as the accident location, the number of accident vehicles, and the accident vehicle information, that is, generate a brief description of the traffic accident and publish it to other terminals for understanding so that others can adjust their travel routes in time.

[0026] In an optional embodiment of the present application, the traffic accident evidence collection method based on image processing also includes: S5: in response to receiving a query request sent by other terminals, pushing the traffic accident information occurring within a third distance range to the other terminals.

[0027] It can be understood that the above query request includes location information such as query location and query route. The server can push the query location and traffic accident information near any location on the query route to the corresponding terminal based on the query request, so that others can adjust their travel routes in time.

[0028] In a second aspect, the present application discloses a server comprising a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute a method as described in any one of the first aspects.

[0029] In a third aspect, the present application discloses a traffic accident evidence collection system based on image processing, comprising:

[0030] The server as described in the second aspect;

[0031] The accident host terminal, including the accident vehicle terminal and / or the accident vehicle owner terminal, is used to send a forensic request to the server and download the forensic image from the server;

[0032] The nearby terminal, whose distance from the accident main terminal is less than the first distance threshold, is used to upload a forensic image to the server in response to receiving a forensic message pushed by the server.

[0033] Beneficial effects:

[0034] The present application discloses a traffic accident evidence collection method and system based on image processing. After the accident vehicle collides, the owner can choose to send an evidence collection request to the server; after receiving the evidence collection request, the server pushes an evidence collection message to the nearby terminal near the accident vehicle, requesting nearby vehicles / pedestrians to assist in the collection of evidence images; after receiving the evidence collection images uploaded by the nearby terminal, the evidence collection images are processed, and the evidence collection images with poor image quality and poor angles are removed before publishing the evidence collection images. Based on this method, the owner of the accident vehicle can avoid the danger of getting off the vehicle to collect evidence and take photos after the accident, and at the same time obtain evidence collection images taken from different angles by other vehicles or pedestrians, thereby ensuring the reliability of the evidence collection images.

[0035] In this application, the server can generate traffic accident information based on key information such as the accident location, number of accident vehicles, and accident vehicle information, that is, generate a brief description of the traffic accident and publish it to other terminals for understanding. The server can push and query the location and query traffic accident information near any location on the route based on the query request uploaded by other terminals, so that others can adjust their travel routes in time.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and understandable, optional embodiments are specifically listed below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 It is a flow chart of a traffic accident evidence collection method based on image processing provided by the present application;

[0039] Figure 2 It is a schematic diagram of a traffic accident scene provided by this application;

[0040] Figure 3 It is a forensic image provided by this application;

[0041] Figure 4 It is a flowchart of another traffic accident evidence collection method based on image processing provided by this application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] First, as Figure 1 As shown, the present application provides a traffic accident evidence collection method based on image processing, which includes:

[0044] S1: In response to receiving a forensics request sent by an accident main terminal, a forensics message is pushed to nearby terminals within a first distance threshold range from the accident main terminal.

[0045] In the embodiment of the present application, the accident main terminal can be the accident vehicle terminal, that is, the vehicle terminal of the accident vehicle, or it can be the accident vehicle owner terminal, that is, a mobile terminal such as a mobile phone or tablet computer used by the accident vehicle owner.

[0046] In the embodiment of the present application, the evidence collection request includes the identity information of the accident vehicle owner, the vehicle information of the accident vehicle, and the current location of the accident owner's terminal. The identity information of the vehicle owner includes basic information such as the name, gender, and ID number of the vehicle owner; the vehicle information includes the vehicle model, brand, license plate number, etc.

[0047] The first distance threshold can be set by those skilled in the art according to actual scenarios, and its purpose is to define the vicinity of the main terminal of the accident.

[0048] For example, Figure 2 In the traffic accident scenario shown, vehicles 11 and 12 collided. In order to ensure the safety of the accident vehicle owners, the vehicle computers or owners of the two accident vehicles can send evidence collection requests to the server through their respective terminals; the server then pushes evidence collection messages to nearby terminals, for example, sending evidence collection messages to the vehicle computer of vehicle 13 in the figure and the mobile phone or tablet terminal used by the driver of vehicle 13; it can also send evidence collection messages to the mobile phones or tablet terminals used by nearby pedestrians 21 to 28.

[0049] S2: Receive the forensic image uploaded by the nearby terminal and perform image processing on the forensic image.

[0050] It is understandable that pedestrians and drivers around the accident site may take blurry and wrong-angle evidence images after receiving the evidence collection message pushed by the server due to haste, lack of experience, etc. The main purpose of "processing evidence images" is to eliminate these unqualified images in a timely manner and improve the accuracy and reliability of evidence images.

[0051] S3: Release at least part of the forensic image after image processing.

[0052] Among them, S1, S2, etc. are only step identifiers, and the execution order of the method is not necessarily in the order of numbers from small to large. For example, step S2 may be executed first and then step S1. This application does not impose any limitation on this.

[0053] It can be understood that the present application discloses a traffic accident evidence collection method based on image processing. After the accident vehicle collides, the owner can choose to send an evidence collection request to the server; after receiving the evidence collection request, the server pushes an evidence collection message to the nearby terminal near the accident vehicle, requesting nearby vehicles / pedestrians to assist in the collection of evidence images; after receiving the evidence collection images uploaded by the nearby terminal, the evidence collection images are processed, and evidence collection images with poor image quality and poor angles are removed before being released. Based on this method, the owner of the accident vehicle can avoid the danger of getting off the vehicle to collect evidence and take photos after the accident, and at the same time obtain evidence collection images taken from different angles by other vehicles or pedestrians, thereby ensuring the reliability of the evidence collection images.

[0054] In an optional embodiment of the present application, the image processing includes at least one of the following:

[0055] Calculate the image quality parameters of the forensic images and delete the forensic images with unqualified image quality parameters; the image quality parameters include resolution, color purity, hue, color balance, sharpness, etc.

[0056] Identify the accident area in the forensic image and delete the forensic images where the accident area is smaller than the preset area threshold. It is understandable that if the accident area occupies too small a proportion of the image, it is not easy to see the accident information clearly, and the forensic image cannot be used.

[0057] In an optional embodiment of the present application, there are two recognition methods for identifying the accident area in the forensic image, the main function of which is to splice the identified accident vehicle element boundary boxes to form the accident area. Figure 3A forensic image 100 is shown, wherein a first element bounding box 301 includes an accident vehicle 11 , a second element bounding box 302 includes an accident vehicle 12 , and the first element bounding box 301 and the second element bounding box 302 are spliced ​​with the accident area.

[0058] Accident area recognition method 1: identify the bounding boxes of each vehicle element in the forensic image through the Faster R-CNN network; splice at least two vehicle element bounding boxes with a distance less than a second distance threshold into the accident area.

[0059] The second accident area recognition method identifies the accident area in the forensic image, including: identifying each vehicle element bounding box in the forensic image through the Faster R-CNN network; extracting the high spatial frequency area in each vehicle element bounding box, identifying the content of the high spatial frequency area, and obtaining the license plate number; finding the vehicle element bounding box corresponding to the license plate number of the accident main terminal as the target bounding box; and splicing at least two vehicle element bounding boxes whose distance from the target bounding box is less than a second distance threshold together with the target bounding box into the accident area.

[0060] Faster Region Convolutional Neural Network (Faster R-CNN) is an end-to-end deep learning detection algorithm. Its innovation lies in generating several candidate boxes through region proposal network and anchor mechanism, and integrating four modules of feature extraction, candidate box selection, bounding box regression and classification into one network, thereby effectively improving detection accuracy and efficiency.

[0061] The high spatial frequency region in each vehicle element boundary frame is extracted, including: performing Fourier transform on each vehicle element boundary frame to obtain the image frequency domain information corresponding to each vehicle element boundary frame; in the image frequency domain information, filtering out the part whose spatial frequency is lower than a preset frequency threshold through a filter to obtain the high spatial frequency part; performing inverse Fourier transform on the high spatial frequency part to obtain the high spatial frequency region.

[0062] It can be understood that high spatial frequency areas are usually areas with high degree of detail or texture changes in the image, and high spatial frequency areas in the vehicle element boundary box are often license plate areas. Therefore, this method uses a filter to filter out high spatial frequency areas in the vehicle element boundary box, that is, to filter out the license plate area in the vehicle element boundary box for identification.

[0063] In an embodiment of the present application, the distance between two element bounding boxes may be the distance between the geometric centers of the calculated element bounding boxes; the second distance threshold may be set by a person skilled in the art according to actual scenarios, with the purpose of safely limiting the distance between vehicles. When the distance is less than the second distance threshold, it may be determined that the two vehicles have collided.

[0064] In an optional embodiment of the present application, the traffic accident evidence collection method based on image processing further includes: S4: generating traffic accident information according to at least one of the following:

[0065] The current location of the accident main terminal;

[0066] The maximum number of accident vehicles in the accident area in each forensic image;

[0067] The license plate number and / or vehicle type of the accident vehicle within the accident area in each forensic image.

[0068] It can be understood that the server can generate traffic accident information based on key information such as the accident location, the number of accident vehicles, and the accident vehicle information, that is, generate a brief description of the traffic accident and publish it to other terminals for understanding so that others can adjust their travel routes in time.

[0069] In an optional embodiment of the present application, Figure 4 As shown, the traffic accident evidence collection method based on image processing also includes: S5: in response to receiving a query request sent by other terminals, pushing traffic accident information occurring within a third distance range to other terminals.

[0070] It can be understood that the above query request includes location information such as query location and query route. The server can push the query location and traffic accident information near any location on the query route to the corresponding terminal based on the query request, so that others can adjust their travel routes in time.

[0071] In a second aspect, the present application provides a server. The server includes one or more processors; one or more memories. The processor and the memory are connected via a bus. The memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor is configured to call the program instructions to perform the operation of any method of the first aspect:

[0072] It should be understood that in the embodiments of the present invention, the processor referred to may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0073] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0074] In a specific implementation, the processor, input device, and output device described in the embodiments of the present invention may execute the implementation method described in any method of the first aspect, or may execute the implementation method of the terminal device described in the embodiments of the present invention, which will not be repeated here.

[0075] Thirdly, Figure 1 As shown, the present application discloses a traffic accident evidence collection system based on image processing, including: a server, an accident main terminal and nearby terminals.

[0076] The server may be any server described in the second aspect.

[0077] The main terminal of the accident can be the terminal of the accident vehicle, i.e., the terminal of the vehicle of the accident vehicle, or the terminal of the owner of the accident vehicle, i.e., the mobile terminal such as the mobile phone or tablet computer used by the owner of the accident vehicle. The main terminal of the accident is used to send a forensic request to the server and download forensic images from the server.

[0078] Among them, the nearby terminal is a terminal device whose distance from the main terminal of the accident is less than the first distance threshold, which can be a nearby vehicle terminal, or a mobile terminal such as a mobile phone or tablet computer used by nearby pedestrians and drivers. The first distance threshold can be set by those skilled in the art according to the actual scenario, and its purpose is to circle the vicinity of the main terminal of the accident. The nearby terminal is used to respond to the evidence collection message pushed by the server and upload the evidence collection image to the server.

[0079] like Figure 4As shown, the traffic accident evidence collection system based on image processing also includes other terminals, namely, mobile terminals such as mobile phones and tablet computers used by any pedestrian or driver, or vehicle terminals of any vehicle. Other terminals are used to send query requests to the server, and the query request includes the current location of the other terminal; the server receives the query request sent by the other terminal, and can push traffic accident information occurring within the third distance range to the other terminal, so that it can adjust the travel route in time. The third distance threshold can be set by those skilled in the art according to the actual scenario, and its purpose is to circle the vicinity of other terminals.

[0080] In the several embodiments provided in the present application, it should be understood that the disclosed terminal device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0081] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0084] The expressions "first", "second", "the first" or "the second" used in various embodiments of the present disclosure may modify various components regardless of order and / or importance, but these expressions do not limit the corresponding components. The above expressions are only configured for the purpose of distinguishing an element from other elements. For example, a first user device and a second user device represent different user devices, although both are user devices. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the present disclosure.

[0085] When one element (e.g., a first element) is referred to as being "(operably or communicatively) coupled" or "(operably or communicatively) coupled to" or "connected to" another element (e.g., a second element), it is understood that the one element is directly connected to the other element or the one element is indirectly connected to the other element via yet another element (e.g., a third element). Conversely, it is understood that when an element (e.g., a first element) is referred to as being "directly connected" or "directly coupled" to another element (the second element), no element (e.g., a third element) is interposed between the two.

[0086] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0087] The above description is only an optional embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other.

[0088] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0089] The above description is only an optional embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other.

[0090] The above description is only an optional embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A traffic accident evidence collection method based on image processing, characterized in that: include: S1: in response to receiving a forensics request sent by an accident main terminal, pushing a forensics message to a nearby terminal within a first distance threshold range from the accident main terminal; S2: receiving the forensic image uploaded by the nearby terminal, and performing image processing on the forensic image; S3: publishing at least part of the forensic image after image processing; The image processing includes: identifying the accident area in the forensic image, and deleting the forensic image with an accident area smaller than a preset area threshold; The identifying the accident area in the forensic image comprises: Identify the bounding boxes of each vehicle element in the forensic image through the Faster R-CNN network; Extract the high spatial frequency region in the bounding box of each vehicle element, identify the content of the high spatial frequency region, and obtain the license plate number; Find the vehicle element bounding box corresponding to the license plate number of the main terminal of the accident as the target bounding box; splicing at least two vehicle element bounding boxes whose distance from the target bounding box is less than a second distance threshold together with the target bounding box into an accident area; The extracting of the high spatial frequency region in the bounding box of each vehicle element comprises: Perform Fourier transform on each vehicle element bounding box to obtain the picture frequency domain information corresponding to each vehicle element bounding box; In the picture frequency domain information, a portion whose spatial frequency is lower than a preset frequency threshold is filtered out by a filter to obtain a high spatial frequency portion; The high spatial frequency portion is subjected to inverse Fourier transformation to obtain a high spatial frequency region.

2. The traffic accident evidence collection method based on image processing according to claim 1 is characterized in that: Also includes: S4: Generate traffic accident information according to at least one of the following: The current location of the accident main terminal; the maximum value of the number of accident vehicles in the accident area in each of the forensic images; The license plate number and / or vehicle type of the accident vehicle in the accident area in each of the forensic images.

3. The traffic accident evidence collection method based on image processing according to claim 2 is characterized in that: Also includes: S5: In response to receiving a query request sent by other terminals, push the traffic accident information occurring within a third distance range to the other terminals.

4. The traffic accident evidence collection method based on image processing according to any one of claims 1 to 3, characterized in that: The evidence collection request includes the identity information of the accident vehicle owner, the vehicle information of the accident vehicle, and the current location of the accident owner terminal.

5. A server, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 4.

6. A traffic accident evidence collection system based on image processing, characterized in that: include: The server as claimed in claim 5; The accident host terminal, including the accident vehicle terminal and / or the accident vehicle owner terminal, is used to send a forensic request to the server and download the forensic image from the server; The nearby terminal, whose distance from the accident main terminal is less than the first distance threshold, is used to upload a forensic image to the server in response to receiving a forensic message pushed by the server.

Images