WO2019144604A1

WO2019144604A1 - Method and device for measuring vehicle damage

Info

Publication number: WO2019144604A1
Application number: PCT/CN2018/100920
Authority: WO
Inventors: 谷斌; 刘岩
Original assignee: 北京威远图易数字科技有限公司
Priority date: 2018-01-25
Filing date: 2018-08-17
Publication date: 2019-08-01
Also published as: CN108413891A

Abstract

A method and device for measuring vehicle damage, relating to the technical field of vehicle detection, wherein the method for measuring vehicle damage comprises: acquiring a vehicle damage photo of a vehicle (S110); selecting a reference object in the vehicle damage photo, and establishing a proportional relation between pixels and the actual size of the reference object (S120); acquiring pixels of a damaged region in the vehicle damage photo, and calculating the actual size of the damaged region according to the proportional relation (S130). The method and device for measuring vehicle damage increase the accuracy of measuring a damaged area of a damaged part according to a traffic accident scene image, and are capable of reaching the degree of accuracy required for claim settlement, thus achieving the technical effect of the accurate damage assessment of a vehicle.

Description

Vehicle damage measuring method and device

Cross-reference to related applications

The present application claims priority to the Chinese Patent Application No. CN2018100722947, filed on Jan. 25, 2018, the entire disclosure of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of vehicle detection technologies, and in particular, to a vehicle loss measurement method and apparatus.

Background technique

With the continuous development of the social economy, the retention rate of vehicles is also getting higher and higher. Correspondingly, the phenomenon of vehicle damage is also more and more frequent, so the rapid vehicle damage is especially important for people's work life. At present, most of the auto insurance claimants use the remote access to the scene image of the accident to damage the vehicle to improve the claims efficiency of the accident. However, in the specific claim process, people find that the scene image of the accident often does not accurately reflect the actual size of the damaged part, and often cannot achieve the accuracy required for the claim.

Summary of the invention

In view of this, the present disclosure provides a vehicle loss measuring method and apparatus.

In a first aspect, the present disclosure provides a vehicle damage measuring method, which is applied to a vehicle damage measuring platform, and the method includes: acquiring a vehicle damage photograph of the vehicle;

Selecting a reference object in the vehicle damage photo to establish a proportional relationship between a pixel of the reference object and an actual size;

Obtaining pixels of the damaged area in the car damage photo, and calculating an actual size of the damaged area according to the proportional relationship.

In a second aspect, the present disclosure further provides a vehicle damage measuring device, including: a photo acquisition module, configured to acquire a vehicle damage photo of the vehicle;

a proportional relationship module, configured to select a reference object in the vehicle damage photo, and establish a proportional relationship between a pixel of the reference object and an actual size;

And a calculation module, configured to acquire pixels of the damaged area in the car damage photo, and calculate an actual size of the damaged area according to a proportional relationship between a pixel of the reference object and an actual size.

In a third aspect, the present disclosure provides a vehicle damage measuring method, including:

Obtain a car damage photo of the vehicle;

Selecting a reference object in the vehicle damage photo, and calculating a proportional relationship between a pixel of the reference object in the vehicle damage photo and an actual size of the pre-stored reference object;

The present invention provides a vehicle damage measuring method and apparatus, wherein the method comprises: acquiring a vehicle damage photograph of the vehicle; selecting a reference object in the vehicle damage photograph to establish a proportional relationship between a pixel of the reference object and an actual size; Obtaining pixels of the damaged area in the car damage photo, and calculating an actual size of the damaged area according to the proportional relationship. The present disclosure calculates the actual size of the damaged area by obtaining the proportional relationship between the pixel of the reference object in the photo and the actual size, thereby realizing the precise determination of the vehicle and achieving the accuracy required for the claim.

Other features and advantages of the present disclosure will be set forth in the description which follows. The objectives and other advantages of the disclosure are realized and attained by the structure of the invention.

The above described objects, features, and advantages of the present invention will become more apparent from the description of the appended claims.

DRAWINGS

In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings to be used in the specific embodiments or the description of the prior art will be briefly described below, and obviously, the attached in the following description The figures are some embodiments of the present disclosure, and other drawings may be obtained from those of ordinary skill in the art without departing from the drawings.

1 is a flow chart of a method for measuring a vehicle damage according to the disclosure of the present disclosure;

FIG. 2 is a flowchart of establishing a relationship between a reference object pixel and an actual size according to the second disclosure;

FIG. 3 is a flow chart showing another relationship between establishing a reference object pixel and an actual size according to the second disclosure;

FIG. 4 is a schematic structural diagram of a vehicle damage measuring device according to the third disclosure.

Detailed ways

The present invention will be clearly and completely described in the following with reference to the accompanying drawings. example. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present disclosure without departing from the inventive scope are the scope of the disclosure.

At present, in the process of claim settlement, the scene image of the accident scene often cannot accurately reflect the actual size of the damaged part, and often cannot achieve the precision required for the claim. Based on this, the present invention provides a vehicle damage measuring method and device, which can achieve precise determination of the vehicle.

In order to facilitate understanding of the embodiment, a method for measuring vehicle damage in the present disclosure is first introduced in detail.

FIG. 1 shows a vehicle loss measurement method provided by the present disclosure, which is applied to a vehicle damage measurement platform, and the method includes:

Step S110: Acquire a vehicle damage photo of the vehicle;

It should be added that the vehicle model database needs to be established before the vehicle damage photo of the vehicle is obtained.

Among them, the model database includes model information of the vehicle, and the actual size of the reference object, such as the actual size of the hub, the actual size of the license plate, and the size and production year of the vehicle. By establishing a model database, the user can obtain vehicle information including vehicle model information based on a search for a certain item in the model database.

After acquiring the vehicle damage photograph of the vehicle, the vehicle damage measuring platform searches the vehicle model database according to the vehicle damage photograph to obtain the model information of the vehicle. Specifically, the vehicle damage measurement platform obtains rough information of the damaged vehicle according to the car damage photo analysis, such as the hub information, the vehicle size, the production year, the license plate, etc., and searches the model database according to the rough information to obtain the model information of the vehicle and the damage. The actual size of the reference object of the vehicle, such as the actual size of the hub, the actual size of the license plate, and the like.

Step S120: selecting a reference object in the car damage photo, and establishing a proportional relationship between the pixel of the reference object and the actual size;

It should be noted here that the vehicle damage may occur at different positions of the vehicle body, and thus the reference objects selected for the vehicle damage photos are also different. For example, the car damage occurs in the head or tail of the car. In the car damage photo, the license plate is selected as the reference object; when the car damage occurs on the side of the car, the wheel hub is selected as the reference object. The reason for choosing a license plate or hub is that the actual size of the two is fixed and is not affected by changes in the angle of the photo. Therefore, the car damage photo includes: car head photo, car tail photo and / or car side photo.

When the reference object is selected, the vehicle damage measurement platform obtains the pixel information W _p of the reference object, and the pixel information W _p refers to the pixel occupied by the reference object in the vehicle damage photo; and according to the reference object in the model database, such as the license plate Or the actual size W _{m of the} hub, get the proportional relationship between the two R:

Step S130: Acquire pixels of the damaged area in the car damage photo, and calculate the actual size of the damaged area according to the proportional relationship.

Specifically, the pixel W _{l of the} damaged area is obtained in the car damage photo. It should be noted that the damaged area may be only a line or an area area, and is uniformly considered as an area area in the calculation process. Further, according to the proportional relationship obtained by the formula (1), the area W _{s of} the damaged area is calculated:

W _s =W _l *R (2)

The vehicle loss measuring method provided by the present disclosure is applied to a vehicle damage measuring platform, first obtaining a vehicle damage photograph of the vehicle; then selecting a reference object in the vehicle damage photograph to establish a proportional relationship between the pixel of the reference object and the actual size; The pixel of the damaged area in the photo is calculated, and the actual size of the damaged area is calculated according to the proportional relationship. The present disclosure calculates the size of the damaged area by obtaining the proportional relationship between the pixel of the reference object in the photo and the actual size, thereby improving the accuracy of the calculation of the damaged area and achieving the accuracy required for the claim.

It should be understood that, depending on the location of the damaged vehicle, the difference in the selected reference object, the proportional relationship between the reference pixel in the vehicle damage photo and the actual size of the reference object can be obtained in various ways.

The vehicle damage photo includes a car head photo or a car tail photo, and the selected reference object is a license plate as an example. FIG. 2 shows a flow chart of obtaining a reference object pixel to actual size ratio provided by the present disclosure, specifically including the following. step.

Step S201: Select a license plate in the photo of the car head or a license plate in the photo of the tail of the car.

It should be pointed out here that after obtaining the car head or the car tail photo, the car damage measurement platform needs to realize the automatic selection of the reference object, such as the license plate, through the support vector machine or the deep learning algorithm. Optionally, the vehicle damage measurement platform can obtain a large number of photos with license plates by means of on-site photographing or web crawling, and then label the above-mentioned photos, and learn from the support vector machine or the deep learning training model to realize the license plate. Automatic acquisition.

Step S202: Calculate the pixel value of the license plate.

In the present disclosure, the pixel value of the license plate in the car damage photo is calculated.

Step S203: Establish a proportional relationship between the pixel value of the license plate and the actual size of the license plate.

It should be noted that the car damage photo is presented in the form of pixels. After selecting the license plate in the photo, the car damage measurement platform calculates the number of pixels included in the license plate, that is, the pixel information W _p , and then according to the actual license plate. The dimension W _m establishes the proportional relationship between the pixel information W _p of the license plate and the actual size W _m of the license plate.

In addition, the actual size W _m of the license plate may be the width information, the length information, or the area information of the license plate. The vehicle damage measuring platform prestores the actual size of the license plate. For example, the actual size of the license plate corresponding to each model is pre-stored in the established model database. Correspondingly, after obtaining the vehicle damage photo of the vehicle, the vehicle damage measurement platform obtains the vehicle model according to the vehicle damage photo analysis, and further finds the actual size of the license plate corresponding to the vehicle model in the vehicle model database.

For example, the vehicle damage photo includes a side view of the automobile, and the selected reference object is a hub. FIG. 3 is a flow chart showing another relationship between the reference object and the actual size provided by the present disclosure, which specifically includes:

Step S301: Select a hub in the photo of the side of the car.

It should be pointed out that after obtaining the side photo of the car, the vehicle damage measurement platform can realize the function of automatically selecting the wheel hub by deep learning the training model. Alternatively, the vehicle damage measurement platform can be photographed by site or web crawler. In a large way, photos with vehicle hubs are obtained, and then the above photos are manually labeled and classified, and the automatic acquisition of the hub is realized by learning the support vector machine or the deep learning training model.

Step S302: Calculate the pixel value of the hub.

In the present disclosure, the pixel value of the hub in the car damage photo is calculated.

Step S303: establishing a proportional relationship between the pixel value of the hub and the actual size of the hub.

It should be noted that the car damage photo is presented in the form of pixels. After selecting the hub in the photo, the car damage measurement platform calculates the number of pixels included in the hub, that is, the pixel information W _p , and then according to the hub. The actual size W _m establishes the proportional relationship between the pixel information W _p of the hub and the actual size W _m of the hub

Further, the hub actual size W _m may be hub radius information or area information. The vehicle damage measuring platform prestores the actual size of the hub. For example, the actual size of the hub corresponding to each model is pre-stored in the established vehicle model database. Correspondingly, after acquiring the vehicle damage photo of the vehicle, the vehicle damage measurement platform obtains the vehicle model according to the vehicle damage photo analysis, and then finds the actual size of the hub corresponding to the vehicle model in the vehicle model database.

It should be understood that the reference object may have other options. For example, if the vehicle damage occurs in the head of the car, the grille in the photo of the car head may be selected as a reference object. Accordingly, the vehicle damage measuring platform prestores the grille. The actual size, for example, the actual size of the grid corresponding to each model is pre-stored in the established model database. Correspondingly, after obtaining the vehicle damage photograph of the vehicle, the vehicle damage measuring platform obtains the vehicle model according to the vehicle damage photo analysis, and further finds the actual size of the grille corresponding to the vehicle model in the vehicle model database.

FIG. 4 is a schematic structural view of a vehicle damage measuring device provided by the present disclosure. Specifically include:

The photo acquisition module 401 is configured to obtain a car damage photo of the vehicle; specifically, the car damage photo includes: a car head photo, a car tail photo, and/or a car side photo.

The proportional relationship module 402 is configured to select a reference object in the car damage photo, and establish a proportional relationship between the pixel of the reference object and the actual size;

The calculating module 403 is configured to obtain pixels of the damaged area in the car damage photo, and calculate the actual size of the damaged area according to the proportional relationship between the pixels of the reference object and the actual size.

It should be noted that the foregoing vehicle damage measuring apparatus further includes: a database module 404 and a search module 405.

The database module 404 is used to create a vehicle model database that includes model information of the vehicle and the actual size of the reference object.

The search module 405 is configured to search the vehicle model database according to the vehicle damage photo, obtain the model information of the vehicle, and the actual size of the reference object.

Optionally, the car damage photo includes a car head photo or a car tail photo, and the proportional relationship module 402 is specifically configured to: select a license plate in the car head photo or a license plate in the car tail photo; The pixel value of the license plate; establishing a proportional relationship between the pixel value of the license plate and the actual size of the license plate.

Optionally, the vehicle damage photo includes a side view of the automobile, and the proportional relationship module 402 is specifically configured to: select a hub in the side view of the automobile; calculate a pixel value of the hub; establish a pixel value of the hub and The proportional relationship of the actual dimensions of the hub.

Optionally, the vehicle damage photo of the vehicle is selected by: if the vehicle damage occurs at the head or the tail of the automobile, selecting a photo of the car head or a photo of the tail of the car as a photo of the car damage; if the car damage occurs in the car On the side, select the car side photo as the car damage photo.

Optionally, the photo obtaining module 401 is specifically configured to select a reference object in the car damage photo by using a support vector machine or a depth learning algorithm.

The vehicle damage vehicle device provided by the present disclosure is similar to the vehicle loss measurement method provided by the above embodiments. The corresponding workflow can refer to the foregoing method embodiment, and can solve the same technical problem as the method embodiment, and achieve the same technical effect. I will not repeat them here.

On the basis of the above, the present disclosure further provides a vehicle damage measuring method, including: acquiring a vehicle damage photograph of the vehicle; selecting a reference object in the vehicle damage photograph, and calculating a pixel and pre-stored of the reference object in the vehicle damage photograph. a proportional relationship of the actual size of the reference object; acquiring pixels of the damaged area in the vehicle damage photograph, and calculating an actual size of the damaged area according to the proportional relationship.

Optionally, before acquiring the vehicle damage photo of the vehicle, the method further includes: establishing a vehicle type database, adding model information of the vehicle and an actual size of the reference object in the vehicle in the vehicle type database.

Optionally, after acquiring the vehicle damage photo of the vehicle, the method further includes: searching the vehicle model database according to the vehicle damage photo, acquiring model information of the vehicle and an actual size of the reference object in the vehicle of the vehicle model.

Optionally, the reference object comprises a license plate, and the car damage photo comprises a car head photo or a car tail photo. The step of selecting a reference object in the vehicle damage photo, calculating a proportional relationship between a pixel of the reference object in the vehicle damage photo and an actual size of the pre-stored reference object, including: according to the car head photo Or the car tail photo searches the model database, obtains the model information of the vehicle and the actual size of the license plate in the vehicle of the model; calculates the pixel value of the license plate in the car head photo or the car tail photo; calculates the pixel of the license plate The ratio of the value to the pre-stored actual size of the license plate.

Optionally, the reference object comprises a hub, and the vehicle damage photo comprises a side view of the automobile. The step of selecting a reference object in the vehicle damage photo, calculating a proportional relationship between a pixel of the reference object in the vehicle damage photo and an actual size of the pre-stored reference object, including: searching according to the car side photo The vehicle model database acquires model information of the vehicle and the actual size of the hub in the vehicle of the vehicle; calculates a pixel value of the hub in the side photograph of the automobile; calculates a pixel value of the hub and a pre-stored actual size of the hub The proportional relationship.

The method and device for measuring vehicle damage provided by the present disclosure obtain the ratio of the pixel of the reference object to the actual size of the reference object, thereby obtaining the pixel of the damaged area in the car damage photo, and calculating the actual area of the damaged area according to the proportional relationship. The size, which achieves the precise determination of the vehicle, can achieve the accuracy required for the claim.

In the present disclosure, the vehicle damage measurement platform is a hardware device capable of data processing, or a combination of hardware and software devices. The vehicle damage measurement platform can be a device having processing functions such as a server and a processing device. The vehicle damage measurement platform may include: a memory, a processor, a network module, and the above-described vehicle damage measuring device. The above described vehicle damage measurement method can be performed by a processor in the vehicle damage measurement platform.

The memory, the processor, and the network module are electrically connected directly or indirectly to each other to implement data transmission or interaction. For example, the components can be electrically connected to one another via one or more communication buses or signal lines. A memory loss measuring device is stored in the memory, the coordinate processing device comprising at least one software function module stored in the memory in the form of software or firmware, the processor running the software program stored in the memory And a module, such as a vehicle damage measuring device in the present disclosure, thereby performing various functional applications and data processing, that is, implementing the coordinate processing method in the present disclosure.

The memory may be, but not limited to, a random access memory (RAM), a read only memory (ROM), and a programmable read-only memory (PROM). Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), and the like. Wherein, the memory is used to store a program, and the processor executes the program after receiving the execution instruction.

The processor may be an integrated circuit chip with data processing capabilities. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), and the like. The methods, steps, and logic blocks disclosed in this disclosure may be implemented or carried out. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

The network module is used to establish a communication connection between the vehicle loss measurement platform and the external communication terminal through the network, and realize the transmission and reception operation of the network signal and the data. The above network signal may include a wireless signal or a wired signal.

In addition, in the description of the present disclosure, the terms "installation", "connected", and "connected" are to be understood broadly, and may be, for example, a fixed connection or a detachable connection, or Connected integrally; can be mechanical or electrical; can be directly connected or indirectly connected through an intermediate medium, which can be the internal communication between the two components. The specific meanings of the above terms in the present disclosure can be understood in the specific circumstances by those skilled in the art.

In the description of the present disclosure, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. The orientation or positional relationship indicated is based on the orientation or positional relationship shown in the drawings, and is merely for the convenience of describing the present disclosure and the simplified description, and does not indicate or imply that the device or component referred to has a specific orientation, in a specific orientation. The construction and operation are therefore not to be construed as limiting the disclosure. Moreover, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or Can be 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 may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in various embodiments of the present disclosure 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 functions, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-transitory computer readable storage medium executable by a processor. Based on such understanding, the portion of the technical solution of the present disclosure that contributes in essence or to the prior art or the portion of the technical solution may be embodied in the form of a software product stored in a storage medium, including The instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present disclosure. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

It should be noted that the above-mentioned embodiments are merely specific embodiments of the present disclosure, and are used to explain the technical solutions of the present disclosure, and are not limited thereto. The scope of protection of the present disclosure is not limited thereto, although reference is made to the foregoing. The embodiments are described in detail, and those skilled in the art should understand that any one skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope of the disclosure. The changes may be easily conceived, or equivalents may be substituted for some of the technical features; and the modifications, variations, or substitutions of the present invention are not intended to depart from the spirit and scope of the technical solutions of the present disclosure, and should be covered in the protection of the present disclosure. Within the scope. Therefore, the scope of protection of the present disclosure should be determined by the scope of the claims.

Industrial applicability

The vehicle loss measuring method and device provided by the present disclosure obtains the pixel of the damaged area in the car damage photo by obtaining the proportional relationship between the pixel of the reference object and the actual size of the reference object, and then calculates the damaged area according to the proportional relationship. The actual size, the vehicle's precise determination of the damage, can achieve the accuracy required for claims.

Claims

A vehicle damage measuring method is applied to a vehicle damage measuring platform, and the method comprises:

Obtain a car damage photo of the vehicle;

Selecting a reference object in the vehicle damage photo to establish a proportional relationship between a pixel of the reference object and an actual size;

Obtaining pixels of the damaged area in the car damage photo, and calculating an actual size of the damaged area according to the proportional relationship.
The vehicle damage measuring method according to claim 1, wherein the method further comprises: establishing a vehicle type database, wherein the vehicle type database includes model information of the vehicle and a reference object before the photograph of the vehicle damage of the vehicle is acquired. The actual size.
The vehicle damage measuring method according to claim 2, wherein after the obtaining a vehicle damage photograph of the vehicle, the method further comprises:

Searching the vehicle model database according to the vehicle damage photograph to obtain model information of the vehicle and an actual size of the reference object.
The vehicle damage measuring method according to any one of claims 1 to 3, wherein the vehicle damage photograph comprises: a car head photograph, a car tail photograph, and/or a car side photograph.
The vehicle damage measuring method according to claim 4, wherein the vehicle damage photo comprises a car head photo or a car tail photo, and the reference object in the car damage photo is selected to establish a pixel of the reference object. The ratio of the actual size to the actual size, including:

Selecting a license plate in the photo of the car head or a license plate in the photo of the tail of the car;

Calculating a pixel value of the license plate;

A proportional relationship between the pixel value of the license plate and the actual size of the license plate is established.
The vehicle damage measuring method according to claim 4, wherein the vehicle damage photograph comprises a side photograph of the automobile, wherein the reference object in the vehicle damage photograph is selected, and a ratio of a pixel of the reference object to an actual size is established. Relationships, including:

Selecting a hub in the side view of the car;

Calculating a pixel value of the hub;

A proportional relationship between the pixel value of the hub and the actual size of the hub is established.
The vehicle damage measuring method according to any one of claims 4 to 6, wherein the vehicle damage photograph of the vehicle is selected by:

If the car damage occurs at the head or tail of the car, select the car head photo or the car tail photo as the car damage photo;

If the car damage occurs on the side of the car, select the photo of the car side as the car damage photo.
A vehicle damage measuring device, comprising:

a photo acquisition module configured to obtain a vehicle damage photo of the vehicle;

a proportional relationship module configured to select a reference object in the vehicle damage photo to establish a proportional relationship between a pixel of the reference object and an actual size;

The calculation module is configured to acquire pixels of the damaged area in the car damage photo, and calculate an actual size of the damaged area according to a proportional relationship between a pixel of the reference object and an actual size.
The vehicle damage measuring apparatus according to claim 8, wherein said vehicle damage measuring device further comprises a database module, said database module being configured to establish a vehicle type database, said vehicle type database including model information of the vehicle and a reference object Actual size.
The vehicle damage measuring apparatus according to claim 9, wherein the vehicle damage measuring apparatus further comprises a search module, the search module being configured to search the vehicle type database to acquire the vehicle based on the vehicle damage photograph Model information and the actual size of the reference.
The vehicle damage measuring device according to any one of claims 8 to 10, wherein the vehicle damage photograph comprises: a photograph of a car head, a photograph of a tail of the car, and/or a photograph of a side of the car.
The vehicle damage measuring device according to claim 11, wherein the vehicle damage photo comprises a car head photo or a car tail photo, and the proportional relationship module is specifically configured to: select a license plate in the car head photo Or a license plate in the photo of the tail of the car; calculating a pixel value of the license plate; establishing a proportional relationship between the pixel value of the license plate and the actual size of the license plate.
The vehicle damage measuring device according to claim 11, wherein the vehicle damage photograph comprises a side view of the automobile, and the proportional relationship module is specifically configured to: select a hub in the side view of the automobile; calculate the hub Pixel value; establishes the proportional relationship between the pixel value of the hub and the actual size of the hub.
The vehicle damage measuring apparatus according to any one of claims 11 to 13, wherein the vehicle damage photograph of the vehicle is selected by:

If the car damage occurs at the head or tail of the car, select the car head photo or the car tail photo as the car damage photo;

If the car damage occurs on the side of the car, select the photo of the car side as the car damage photo.
The vehicle damage measuring device according to any one of claims 8 to 14, wherein the photo acquisition module is specifically configured to select a reference object in the vehicle damage photograph by a support vector machine or a depth learning algorithm.
A method for measuring vehicle damage, characterized in that it comprises:

Obtain a car damage photo of the vehicle;

Selecting a reference object in the vehicle damage photograph, and calculating a proportional relationship between a pixel of the reference object in the vehicle damage photograph and an actual size of the pre-stored reference object;

Obtaining pixels of the damaged area in the car damage photo, and calculating an actual size of the damaged area according to the proportional relationship.
The vehicle damage measuring method according to claim 16, wherein before the obtaining a vehicle damage photograph of the vehicle, the method further comprises:

A model database is created, and the model information of the vehicle and the actual size of the reference object in the vehicle are added to the vehicle model database.
The vehicle damage measuring method according to claim 17, wherein after the vehicle damage photograph of the vehicle is acquired, the method further comprises:

Searching the vehicle model database based on the vehicle damage photograph to obtain model information of the vehicle and the actual size of the reference object in the vehicle of the vehicle model.
The vehicle damage measuring method according to claim 17, wherein the reference object comprises a license plate, and the vehicle damage photo comprises a car head photo or a car tail photo;

The step of selecting a reference object in the vehicle damage photo, calculating a proportional relationship between a pixel of the reference object in the vehicle damage photo and an actual size of the pre-stored reference object, including:

Searching the vehicle model database according to the car head photo or the car tail photo to obtain model information of the vehicle and the actual size of the license plate in the vehicle of the model;

Calculating a pixel value of a license plate in the car head photo or the car tail photo;

A proportional relationship between the pixel value of the license plate and the pre-stored actual size of the license plate is calculated.
The vehicle damage measuring method according to claim 17, wherein the reference object comprises a hub, and the vehicle damage photograph comprises a side view of the automobile;

The step of selecting a reference object in the vehicle damage photo, calculating a proportional relationship between a pixel of the reference object in the vehicle damage photo and an actual size of the pre-stored reference object, including:

Searching the model database according to the side view of the automobile, acquiring model information of the vehicle and actual size of the hub in the vehicle of the model;

Calculating a pixel value of a hub in a photo of the side of the car;

A proportional relationship between the pixel value of the hub and the pre-stored actual size of the hub is calculated.