CN112862702A

CN112862702A - Image enhancement method, device, equipment and storage medium

Info

Publication number: CN112862702A
Application number: CN202110064519.6A
Authority: CN
Inventors: 李佳琳; 王健宗; 瞿晓阳
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-01-18
Filing date: 2021-01-18
Publication date: 2021-05-28
Anticipated expiration: 2041-01-18
Also published as: CN112862702B; WO2022151589A1

Abstract

The invention relates to the field of big data and discloses an image enhancement method, device, equipment and storage medium. The method comprises the following steps: the preset image recognition model recognizes field image data acquired from a traffic accident field and judges whether the field image data meets a preset image standard; if the live image data does not meet the preset image standard, prompting the user to shoot again; if the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field; and inputting the target accident vehicle image into a preset image enhancement model for image enhancement to generate a target enhancement image. According to the scheme, the conversion from low-quality images to high-quality images can be completed only by learning the mapping function of the high-quality images, the accuracy and the processing timeliness of the vehicle insurance claims are improved, and the technical problem of low claim settlement efficiency is solved.

Description

Image enhancement method, device, equipment and storage medium

Technical Field

The present invention relates to the field of big data, and in particular, to an image enhancement method, apparatus, device, and storage medium.

Background

With the popularization of personal mobile phones and the advancement of science and technology, the imaging processing flow in the traditional car insurance claim settlement flow generally needs a professional team, uses professional photographic equipment, and shoots and collects image data of each area according to a set of complete collection flow. In the face of increasing private car reserves and various small-sized accidents, great pressure is applied to car insurance claim settlement, and the current requirements cannot be met by the number of people and the processing efficiency, so that the self-service, online submission of materials, quick claim settlement and even full-automatic claim settlement which appear in recent years become a symbolic selling point of the internet insurance claim settlement service.

However, the quality of the image or video information acquired in the step of shooting and uploading the car insurance claim settlement material directly determines the accuracy of the subsequent step, and a common user often does not have the operation skills of professionals, the used equipment is a camera carried by a common mobile phone, and the shooting conditions of the location cannot be determined when the car insurance is determined, so that the shot image or video often has the problems of wrong shooting target, unreasonable shooting angle, imaging blur, insufficient exposure or strong light reflection and the like.

Disclosure of Invention

The invention mainly aims to improve the accuracy and the processing timeliness of vehicle insurance claim settlement and solve the technical problem of low claim settlement efficiency.

The invention provides an image enhancement method in a first aspect, which comprises the following steps:

acquiring field image data of a traffic accident scene;

identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

if not, prompting the user to shoot again;

if so, entering a next shooting task to obtain a target accident vehicle image of the traffic accident scene;

and inputting the target accident vehicle image into a preset image enhancement model, and carrying out image enhancement on the target accident vehicle image to generate a target enhanced image.

Optionally, in a first implementation manner of the first aspect of the present invention, before the acquiring the scene image data of the traffic accident scene, the method further includes:

acquiring historical vehicle images of an accident scene from a preset database;

taking the historical vehicle images as training samples to construct a training sample data set;

and inputting the training sample data set into a preset image enhancement generator, and training the image enhancement generator to obtain a target image enhancement model.

Optionally, in a second implementation manner of the first aspect of the present invention, before the identifying, by a preset image identification model, the field image data and determining whether the field image data meets a preset image criterion, the method further includes:

acquiring a plurality of training pictures from a preset training picture database, and inputting the training pictures into a preset neural network model to obtain a prediction type label of the training pictures;

generating a real category label of the training picture according to the category of the training picture;

generating a first loss function of the training picture according to the prediction category label of the training picture and the real category label of the training picture;

and updating parameters in the neural network model according to the first loss function to obtain a target picture identification model.

Optionally, in a third implementation manner of the first aspect of the present invention, the inputting the training sample data set into a preset image enhancement generator, and training the image enhancement generator to obtain a target image enhancement model includes:

performing image enhancement on the training sample data set to obtain a preset number of target original images and corresponding enhanced images;

inputting the target original image into a CNN image enhancement network in a preset image enhancement generator to obtain an output image corresponding to the target original image;

determining a second loss function between the output image and the enhanced image;

and iteratively training the CNN image enhancement network in the image enhancement generator based on the second loss function until the CNN image enhancement network converges to obtain a target image enhancement model.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the inputting the target accident vehicle image into a preset image enhancement model, performing image enhancement on the target accident vehicle image, and generating the target enhanced image includes:

performing down-sampling processing on the target accident vehicle image to obtain a down-sampled image;

inputting the down-sampling image into the target image enhancement model to obtain image enhancement data corresponding to the target accident vehicle image;

determining a matching point of each pixel point in the target accident vehicle image in the down-sampling image;

determining a target enhancement parameter corresponding to the pixel point based on enhancement data corresponding to the matching point of the pixel point in the image enhancement data;

and adjusting the pixel value of the pixel point based on the target enhancement parameter corresponding to the pixel point to obtain a target enhancement image corresponding to the target accident vehicle image.

Optionally, in a fifth implementation manner of the first aspect of the present invention, after the inputting the target accident vehicle image into a preset image enhancement model, performing image enhancement on the target accident vehicle image, and generating a target enhanced image, the method further includes:

acquiring owner identity information of a user and damaged information of the accident vehicle, wherein the vehicle information comprises vehicle insurance information of the accident vehicle;

receiving a claim settlement request uploaded by the user, and inputting the target enhanced image into a trained convolutional neural network model for prediction to obtain a claim settlement probability of the target enhanced image;

judging whether the claim settlement probability of the target enhanced image is larger than a preset threshold value or not;

if the claim settlement probability of the target enhanced image is larger than a preset threshold value, determining that the target enhanced image can settle the claim;

and based on the owner identity information of the user and the identification information of the accident vehicle, carrying out claim settlement on the accident vehicle.

A second aspect of the present invention provides an image enhancement apparatus comprising:

the first acquisition module is used for acquiring field image data of a traffic accident scene;

the first judgment module is used for identifying the field image data through a preset image identification model and judging whether the field image data meets a preset image standard or not;

the prompting module is used for prompting the user to shoot again when the live image data does not meet the preset image standard;

the shooting module is used for entering the next shooting task when the site image data meets the preset image standard so as to obtain a target accident vehicle image of the traffic accident site;

and the image enhancement module is used for inputting the target accident vehicle image into a preset image enhancement model, and performing image enhancement on the target accident vehicle image to generate a target enhanced image.

Optionally, in a first implementation manner of the second aspect of the present invention, the image enhancement apparatus further includes:

the second acquisition module is used for acquiring historical vehicle images of an accident scene from a preset database;

the construction module is used for constructing a training sample data set by taking the historical vehicle image as a training sample;

and the training module is used for inputting the training sample data set into a preset image enhancement generator, training the image enhancement generator and obtaining a target image enhancement model.

Optionally, in a second implementation manner of the second aspect of the present invention, the image enhancement apparatus further includes:

the input module is used for acquiring a plurality of training pictures from a preset training picture database, and presetting a neural network model for the training pictures to obtain a prediction category label of the training pictures;

the generating module is used for generating a real category label of the training picture according to the category of the training picture; generating a first loss function of the training picture according to the prediction category label of the training picture and the real category label of the training picture;

and the updating module is used for updating the parameters in the neural network model according to the first loss function to obtain a target picture identification model.

Optionally, in a third implementation manner of the second aspect of the present invention, the training module includes:

the image enhancement unit is used for carrying out image enhancement on the training sample data set to obtain a preset number of target original images and corresponding enhanced images;

the input unit is used for inputting the target original image into a CNN image enhancement network in a preset image enhancement generator to obtain an output image corresponding to the target original image;

a determining unit for determining a second loss function between the output image and the enhanced image;

and the iterative training unit is used for performing on the CNN image enhancement network in the image enhancement generator based on the second loss function until the CNN image enhancement network converges to obtain a target image enhancement model.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the image enhancement module is specifically configured to:

Optionally, in a fifth implementation manner of the second aspect of the present invention, the image enhancement apparatus further includes:

the third acquisition module is used for acquiring owner identity information of a user and damaged information of the accident vehicle, wherein the vehicle information comprises vehicle insurance information of the accident vehicle;

the prediction module is used for receiving a claim settlement request uploaded by the user and inputting the target enhanced image into the trained convolutional neural network model for prediction to obtain the claim settlement probability of the target enhanced image;

the second judgment module is used for judging whether the claim settlement probability of the target enhanced image is greater than a preset threshold value or not;

the determining module is used for determining that the target enhanced image can be settled when the settlement probability of the target enhanced image is greater than a preset threshold value;

and the claim settlement module is used for settling a claim for the accident vehicle based on the owner identity information of the user and the identification information of the accident vehicle.

A third aspect of the present invention provides an image enhancement apparatus comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invokes the instructions in the memory to cause the image enhancement device to perform the image enhancement method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the image enhancement method described above.

In the technical scheme provided by the invention, the field image data acquired from a traffic accident field is identified through a preset image identification model, and whether the field image data meets the preset image standard is judged; if the live image data does not meet the preset image standard, prompting the user to shoot again; if the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field; and inputting the target accident vehicle image into a preset image enhancement model for image enhancement to generate a target enhancement image. According to the scheme, the conversion from low-quality images to high-quality images can be completed only by learning the mapping function of the high-quality images, the accuracy and the processing timeliness of the vehicle insurance claims are improved, and the technical problem of low claim settlement efficiency is solved.

Drawings

FIG. 1 is a schematic diagram of a first embodiment of the image enhancement method of the present invention;

FIG. 2 is a schematic diagram of a second embodiment of the image enhancement method of the present invention;

FIG. 3 is a schematic diagram of a third embodiment of the image enhancement method of the present invention;

FIG. 4 is a schematic diagram of a fourth embodiment of the image enhancement method of the present invention;

FIG. 5 is a schematic diagram of a fifth embodiment of the image enhancement method of the present invention;

FIG. 6 is a schematic diagram of a first embodiment of the image enhancement apparatus of the present invention;

FIG. 7 is a schematic diagram of a second embodiment of the image enhancement apparatus of the present invention;

fig. 8 is a schematic diagram of an embodiment of the image enhancement apparatus of the present invention.

Detailed Description

The embodiment of the invention provides an image enhancement method, an image enhancement device, image enhancement equipment and a storage medium, wherein in the technical scheme of the invention, an image recognition model is preset to recognize field image data acquired from a traffic accident field, and whether the field image data meets a preset image standard is judged; if the live image data does not meet the preset image standard, prompting the user to shoot again; if the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field; and inputting the target accident vehicle image into a preset image enhancement model for image enhancement to generate a target enhancement image. According to the scheme, the conversion from low-quality images to high-quality images can be completed only by learning the mapping function of the high-quality images, the accuracy and the processing timeliness of the vehicle insurance claims are improved, and the technical problem of low claim settlement efficiency is solved.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of an image enhancement method in an embodiment of the present invention includes:

101. acquiring field image data of a traffic accident scene;

in this embodiment, in order to ensure that sufficient information is obtained, the user needs to take a picture of 360 degrees around the accident vehicle and a picture of the critical damaged part at the traffic accident site. For example, the user needs to take images of corresponding vehicle parts including a frame number, a damaged part, a picture of the whole vehicle with a brand, a picture of the whole vehicle, and the like through a personal mobile phone on site according to directions.

102. Identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

in this embodiment, the quality of the image or video information acquired in the step of shooting and uploading the car insurance claim settlement material directly determines the accuracy of the subsequent step, and a common user often does not have the operation skills of a professional, the used device is a camera carried by a common mobile phone, and the shooting condition of the location often cannot be determined in the process of car insurance loss, so that the shot image or video often has the problems of wrong shooting target, unreasonable shooting angle, imaging blur, insufficient exposure or strong light reflection, and the like.

103. When the live image data does not meet the preset image standard, prompting the user to shoot again;

in this embodiment, whether the shot image meets the corresponding shooting standard is locally determined, whether the shot image is a corresponding photo required in the guidance is determined by the recognition model, and whether a blur condition exists is rapidly determined by schemes such as edge detection. If the standard is not met, the user is prompted to shoot again.

104. When the scene image data meets the preset image standard, entering the next shooting task to obtain a target accident vehicle image of the traffic accident scene;

in this embodiment, if the picture taken by the user on site meets the preset requirement, the next shooting task is performed to obtain an image with relatively high quality in terms of brightness, contrast, white balance, tolerance, noise, detail, color transition, and the like, that is, a target enhanced image.

105. And inputting the target accident vehicle image into a preset image enhancement model, and carrying out image enhancement on the target accident vehicle image to generate a target enhanced image.

In the embodiment, the low-quality image of the target accident vehicle shot by the mobile phone is input into the target image enhancement model, so that the aspects of brightness, contrast, white balance, tolerance, noise, detail, color transition and the like are comprehensively improved, and an enhanced image which is based on the original image content and achieves the visual effect similar to that of shooting by a professional digital camera is generated.

In this embodiment, the image enhancement method is to add some information or transform data to the original image by some means, to selectively highlight interesting features in the image or to suppress (mask) some unwanted features in the image, so that the image matches the visual response characteristics. In the image enhancement process, the reason of image degradation is not analyzed, and the processed image is not necessarily close to the original image. The image enhancement technology can be divided into two categories, namely an algorithm based on a space domain and an algorithm based on a frequency domain according to different spaces of the enhancement processing process.

In the embodiment of the invention, the site image data acquired from a traffic accident site is identified through a preset image identification model, and whether the site image data meets the preset image standard is judged; if the live image data does not meet the preset image standard, prompting the user to shoot again; if the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field; and inputting the target accident vehicle image into a preset image enhancement model for image enhancement to generate a target enhancement image. According to the scheme, the conversion from low-quality images to high-quality images can be completed only by learning the mapping function of the high-quality images, the accuracy and the processing timeliness of the vehicle insurance claims are improved, and the technical problem of low claim settlement efficiency is solved.

Referring to fig. 2, a second embodiment of the image enhancement method according to the embodiment of the present invention includes:

201. acquiring historical vehicle images of an accident scene from a preset database;

in this embodiment, after a traffic accident occurs, at least one target image of an accident vehicle at the traffic accident scene is acquired, and the target images can reflect specific conditions of the accident scene, such as the license plate number, the damaged part and the damaged degree of the accident vehicle.

202. Taking the historical vehicle image as a training sample to construct a training sample data set;

in this embodiment, a plurality of original image samples in various car insurance claim settlement scenes may be obtained from a database, where the original image samples may be images taken by a user from an accident scene, or images taken by professional professionals of a company using a professional camera. For example, the single lens reflex camera takes a picture with little noise and rich detail information. And then, responding to the user operation, carrying out image enhancement on the image parameters of each original image sample, and generating an enhanced image sample after image enhancement. For example, each original image sample can be adjusted by a professional special effect designer to obtain an enhanced image sample after image enhancement, so that the enhanced image sample has relatively good brightness and saturation.

203. Inputting a training sample data set into a preset image enhancement generator, and training the image enhancement generator to obtain a target image enhancement model;

in this embodiment, image enhancement refers to enhancing useful information in an image, which may be a distortion process, aiming to improve the visual effect of the image for a given image application. The method aims to emphasize the overall or local characteristics of the image, changes the original unclear image into clear or emphasizes certain interesting characteristics, enlarges the difference between different object characteristics in the image, inhibits the uninteresting characteristics, improves the image quality, enriches the information content, enhances the image interpretation and identification effects, and meets the requirements of certain special analysis.

In this embodiment, the training sample data is input into a preset image enhancement generator to train the image enhancement generator, and the specific implementation steps include: by inputting an original low-quality image x, an image y with improved brightness, exposure and other aspects is generated by a generator, a texture and color discriminator carries out calculation of texture and color loss functions by comparing y with a picture z shot by a professional camera, and the generator is trained by sub-feedback. At the same time, the low-quality picture y 'is generated by applying the generator G' to the image y in reverse, and the generation control of the generator G is achieved by calculating the content loss from the original picture x.

204. Acquiring field image data of a traffic accident scene;

205. identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

206. when the live image data does not meet the preset image standard, prompting the user to shoot again;

207. when the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field;

208. and inputting the target accident vehicle image into a preset image enhancement model, and carrying out image enhancement on the target accident vehicle image to generate a target enhanced image.

The steps 204-208 in this embodiment are similar to the steps 101-105 in the first embodiment, and are not described herein again.

Referring to fig. 3, a third embodiment of the image enhancement method according to the embodiment of the present invention includes:

301. acquiring historical vehicle images of an accident scene from a preset database;

302. taking the historical vehicle image as a training sample to construct a training sample data set;

303. inputting a training sample data set into a preset image enhancement generator, and training the image enhancement generator to obtain a target image enhancement model;

304. acquiring field image data of a traffic accident scene;

305. acquiring a plurality of training pictures from a preset training picture database, and inputting the training pictures into a preset neural network model to obtain a prediction class label of the training pictures;

in the embodiment, the picture of the accident vehicle shot in the past vehicle accident scene is obtained from the preset database and used as the picture to be identified, and the prediction type label of the picture to be identified is obtained; the pre-trained image recognition model adopts a convolutional neural network model, and the convolutional neural network model comprises at least one kernel pooling layer for upgrading the channel dimensionality from one dimension to multiple dimensions.

In this embodiment, in the process of training the picture recognition model, parameters in the picture recognition model are constantly changed, that is, the picture recognition model is constantly changed. And during each training, the adopted picture recognition models are the picture recognition models updated after the last training. The parameters of the image recognition model of the present embodiment are preset initial values when the image recognition model is used for the first time. The dimension of the prediction category label is determined during training, for example, if a plurality of training pictures in the training picture database include n classified pictures, the dimension of the prediction category label output by the picture recognition model may be set to n.

306. Generating a real category label of the training picture according to the category of the training picture;

in this embodiment, since the category of the training picture is known, the real category label of the category of the training picture may be generated according to the category of the training picture. Similarly, the real category label of the training picture is also in the form of a vector, in the vector, only the numerical value of the element at the position corresponding to the category of the training picture is 1, and the rest positions are 0.

307. Generating a first loss function of the training picture according to the prediction category label of the training picture and the real category label of the training picture;

in this embodiment, according to the obtained prediction category label of the training picture and the obtained real category label of the training picture, the difference between the prediction category label of the training picture and the real category label of the training picture can be known, and a loss function of the training picture is generated according to the difference. In the process of training the image recognition model, the value of the loss function is gradually decreased, so that the more accurate the image recognition model is trained. In this embodiment, more than two loss functions are used to calculate the feature difference values of the labels, respectively, and rank the feature difference values calculated according to the corresponding loss functions, and return the loss function corresponding to the feature difference value with the largest rank as the final loss function to adjust the weight of the model.

In this embodiment, because the loss function represents a value that decreases in the gradient direction, the larger the loss function value is, the more inaccurate the prediction type label that represents the picture recognition model and outputs after processing the input picture is, and in this embodiment, the gradient of the final point of the loss function is made to be 0 by continuously adjusting the loss function. The smaller the value of the loss function is, the more accurate the processing result representing the picture recognition model is. That is, the derivative of the loss function of the training picture to each parameter in the picture recognition model is calculated, and each parameter in the picture recognition model is updated according to each parameter in the picture recognition model and the derivative of the loss function corresponding to the training picture to each parameter, so that the picture recognition model after the training is determined.

The loss function (loss function) and the cost function (cost function) are functions that map the value of a random event or its associated random variable to a non-negative real number to represent the "risk" or "loss" of the random event. In application, the loss function is usually associated with the optimization problem as a learning criterion, i.e. the model is solved and evaluated by minimizing the loss function. For example, in statistics and machine learning, are used for parameter estimation (parametric estimation) of models. In this embodiment, the loss function is pre-constructed and used to calculate the feature difference between the true feature and the predicted feature.

308. Updating parameters in the neural network model according to the first loss function to obtain a target picture identification model;

in this embodiment, each parameter in the picture recognition model is updated according to each parameter in the picture recognition model and a derivative of a loss function of a training picture to each parameter, so as to obtain a target image recognition model.

Specifically, since the image recognition model includes a plurality of parameters, when the input training image is determined, the loss function may also be regarded as a function related to the parameters in the image recognition model, and at this time, the derivative of the loss function of the training image to each parameter in the image recognition model may be calculated; for each parameter in the picture recognition model, when updating, the parameter in the picture recognition model may be updated as the parameter minus the derivative of the loss function on the parameter, i.e. the picture recognition model is updated every time training.

Because the loss function represents a value that decreases in the gradient direction, the larger the loss function value is, the less accurate the prediction category label that represents the picture recognition model and is output after processing the input picture is, and in this embodiment, the gradient of the final point of the loss function is made to be 0 by continuously adjusting the loss function. The smaller the value of the loss function is, the more accurate the processing result representing the picture recognition model is. The technical solution of the above embodiment is to update the image recognition model, specifically, in a direction toward the gradual decrease of the loss function. Therefore, through continuous training, the loss function is continuously optimized, and the parameters of the picture recognition model are continuously updated, so that the picture recognition model is continuously updated, and the finally obtained picture recognition model can very accurately recognize the picture.

309. Identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

310. when the live image data does not meet the preset image standard, prompting the user to shoot again;

311. when the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field;

312. and inputting the target accident vehicle image into a preset image enhancement model, and carrying out image enhancement on the target accident vehicle image to generate a target enhanced image.

The steps 301-.

Referring to fig. 4, a fourth embodiment of the image enhancement method according to the embodiment of the present invention includes:

401. acquiring historical vehicle images of an accident scene from a preset database;

402. taking the historical vehicle image as a training sample to construct a training sample data set;

403. performing image enhancement on the training sample data set to obtain a preset number of target original images and corresponding enhanced images;

in this embodiment, a plurality of low-quality images are acquired from a preset database as training sample data, and the images are enhanced to obtain a preset number of original image samples and a corresponding preset number of enhanced image samples. Then, for each selected original image sample and the corresponding enhanced image samples in the preset number, randomly cropping the image with the target size at the same position in the original image sample and the corresponding enhanced image samples to obtain the original image with the target size and the corresponding enhanced image with the preset number.

404. Inputting the target original image into a CNN image enhancement network in a preset image enhancement generator to obtain an output image corresponding to the target original image;

in this embodiment, the collected target original images are input into a CNN image enhancement network in a preset image enhancement generator, so that an output image corresponding to each target original image can be obtained.

405. Determining a second loss function between the output image and the enhanced image;

in this embodiment, the loss function is pre-constructed and used to calculate a feature difference between a true feature and a predicted feature, rank the feature differences calculated according to the corresponding loss function, use the loss function corresponding to the feature difference with the largest rank as a final loss function, and after obtaining the loss function value, supervise training of the CNN image enhancement network based on the loss function value and update network parameters.

In this embodiment, a mean value blurring method may be used to perform blurring processing on the output image and the enhanced image, and a mean value error value of the output image and the enhanced image after the blurring processing is calculated to obtain a color _ loss value. The output image and the enhanced image are subjected to fuzzy processing by using a mean value fuzzy method, so that the interference of high-frequency information is eliminated, and the network can learn more color information. In practical implementation, the training of end2end can be realized by using a Mean pooling layer in a CNN image enhancement network and setting stride to be 1, so that l2Loss (namely Mean Square Error Loss) is performed on the output image and the enhanced image after the blurring processing to obtain the color _ Loss value.

Further, the output image and the enhanced image are subjected to error calculation through a feature map output by the CNN image enhancement network on the same layer, so that an vgg _ loss value is obtained. Wherein vgg _ loss is a semantic type loss, which can better generate semantic information. Illustratively, the present embodiment may use vgg19 as the network structure for generating the different layer feature map (feature map) while initializing vgg19 the network with network parameters trained on the ImageNet dataset. And performing l2loss on the feature map output by the same layer through an vgg19 network to obtain a vgg _ loss value.

Further, a gray scale map of the output image and a gray scale map of the enhanced image are respectively obtained, and error calculation is performed on the gray scale map of the output image and the gray scale map of the enhanced image to obtain a texture _ loss value. texture _ loss, namely texture loss, can increase texture details on the basis of the texture loss, and ensure that the detail information is not lost while the image is enhanced.

406. Performing iterative training on the CNN image enhancement network in the image enhancement generator based on the second loss function until the CNN image enhancement network converges to obtain a target image enhancement model;

in this embodiment, after obtaining the loss function value, the training of the CNN image enhancement network is supervised based on the loss function value and the network parameters are updated until the CNN image enhancement network converges to obtain a target image enhancement model;

in this embodiment, the manner of determining whether the CNN image enhancement network reaches the training convergence condition may be: and judging whether the variation value of the loss value is smaller than a preset value, if so, judging that the CNN image enhancement network reaches a training convergence condition, otherwise, judging that the CNN image enhancement network does not reach the training convergence condition. The preset value may be set according to actual requirements, for example, the preset value may be set to a value close to 0, or may also be set to 0, if the preset value is 0, when the loss value does not change, it is determined that the CNN image enhancement network reaches the training convergence condition, otherwise, it is determined that the CNN image enhancement network does not reach the training convergence condition. And if the CNN image enhancement network does not reach the training convergence condition, repeating the steps to continue training.

And when the CNN image enhancement network reaches a training convergence condition, updating the network parameters of the CNN image enhancement network so as to output a corresponding image enhancement model. The image enhancement model may perform image enhancement on an input image. In detail, after receiving the image to be processed, the image to be processed may be input into the image enhancement model, so as to obtain an enhanced image corresponding to the image to be processed. For example, a user inputs an image shot by a mobile phone as an image to be processed into the trained image enhancement model, and then obtains a corresponding enhanced image through layer-by-layer calculation of a network, wherein the corresponding enhanced image is a target enhanced image.

407. Acquiring field image data of a traffic accident scene;

408. identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

409. when the live image data does not meet the preset image standard, prompting the user to shoot again;

410. when the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field;

411. and inputting the target accident vehicle image into a preset image enhancement model, and carrying out image enhancement on the target accident vehicle image to generate a target enhanced image.

The steps 407-411 in this embodiment are similar to the steps 101-105 in the first embodiment, and are not described herein again.

Referring to fig. 5, a fifth embodiment of the image enhancement method according to the embodiment of the present invention includes:

501. acquiring field image data of a traffic accident scene;

502. identifying the field image data through a preset image identification model, and judging whether the field image data meets a preset image standard;

503. when the live image data does not meet the preset image standard, prompting the user to shoot again;

504. when the field image data meets the preset image standard, entering a next shooting task to obtain a target accident vehicle image of the traffic accident field;

505. carrying out down-sampling processing on the target accident vehicle image to obtain a down-sampled image;

in this embodiment, when image enhancement processing needs to be performed on a certain image, the image may be used as a target enhanced image to be enhanced. The target enhanced image may be a high resolution image. Moreover, the target enhanced image may be a single channel image or a multi-channel image. Wherein the color space of the multi-channel image may be: RGB (Red, Green, Blue, Red Green Blue), YUV (Luminance, Chroma), or other color spaces, to which the present disclosure is not limited. The electronic equipment can shoot the target enhanced image through a built-in or external camera device, and can also communicate with other equipment to receive the target enhanced image sent by the other equipment. The manner in which the electronic device obtains the target-enhanced image is not limited in this disclosure.

After the electronic device acquires the target enhanced image, the electronic device may perform downsampling on the target enhanced image to obtain a downsampled image. The obtained down-sampled image may be further input to a deep learning network, and the down-sampled image may be subjected to image enhancement processing by the deep learning network.

In this embodiment, the target enhanced image may be subjected to x-fold down-sampling processing, so that the resolution, the width, and the height of the obtained down-sampled image are all 1/x times of corresponding parameters of the target enhanced image.

506. Inputting the down-sampling image into a target image enhancement model to obtain image enhancement data corresponding to the target image enhancement model;

in this embodiment, in order to perform image enhancement processing on a downsampled image, a deep learning network may be trained in advance according to a sample image and a sample enhanced image corresponding to the sample image, so as to obtain a trained deep learning network. Wherein the sample images and corresponding sample enhanced images are training samples for training. The sampled image and the corresponding sample enhanced image may be obtained in an existing training library as training samples. The sample enhanced image may be obtained by means of multi-exposure fusion, or may be obtained by means of other single-frame image enhancement methods, which is not limited in this disclosure.

In this embodiment, the structure of the deep learning network may be any one of the existing deep learning network models. Specifically, during training, the number of training samples can be determined according to actual needs. Meanwhile, a reasonable loss function or an objective function and a corresponding target value can be set to determine whether the deep learning network is trained well.

After the deep learning network is trained, the network parameters of the deep learning network are determined. Because the deep learning network is trained according to the sample images and the corresponding sample enhancement images, the image enhancement data corresponding to the down-sampling images can be obtained after the down-sampling images are input into the trained deep learning network. The image enhancement data is data representing the degree of enhancement of an image enhanced by a down-sampled image with respect to the down-sampled image. The image enhancement data may be in a variety of forms, for example: the image enhancement data may include a mapping parameter for mapping each pixel in the down-sampled image to a corresponding pixel, where the corresponding pixel of any pixel is a pixel in the image after enhancement of the down-sampled image, the pixel having the same position as the pixel. As another example, the image enhancement data may include a downsampled image-enhanced image. Further, it is understood that the output result of the depth learning network is the same type as the image enhancement data corresponding to the down-sampled image, that is, when the output result of the depth learning network is a mapping parameter, the image enhancement data corresponding to the down-sampled image is a mapping parameter, and when the output result of the depth learning network is an enhanced image, the image enhancement data corresponding to the down-sampled image is an image enhanced by the down-sampled image.

507. Determining a matching point of each pixel point in the target accident vehicle image in the down-sampling image;

in this embodiment, since the resolution of the down-sampled image is lower than the resolution of the target enhanced image, the image enhancement data corresponding to the down-sampled image does not correspond to the target enhanced image. In order to obtain an enhanced image corresponding to the target enhanced image, in this embodiment, a matching point of each pixel point in the target enhanced image in the downsampled image may be determined first, then a target enhancement parameter corresponding to the pixel point is determined, and finally, the pixel value of the pixel point is adjusted by using the target enhancement parameter.

In this embodiment, for each pixel point in the target enhanced image, a corresponding pixel point of the pixel point in the downsampled image is determined, a pixel point with the minimum absolute value of the difference between the absolute value of the pixel value of the corresponding pixel point and the absolute value of the pixel value of the corresponding pixel point is found in a search area with the corresponding pixel point as the center and the size of the search area being mxn, and the found pixel point is used as a matching point of the pixel point in the downsampled image.

508. Determining a target enhancement parameter corresponding to a pixel point based on enhancement data corresponding to a matching point of the pixel point in the image enhancement data;

in this embodiment, after determining a matching point of each pixel point in the downsampled image for each pixel point in the target enhanced image, a target enhancement parameter corresponding to the pixel point may be determined based on enhancement data corresponding to the matching point, and a pixel value of the pixel point is further adjusted based on the target enhancement parameter. Specifically, the image enhancement data are in different forms, and the manner of determining the target enhancement parameter corresponding to each pixel point in the target enhanced image is also different. Two modes are given below for explanation.

Optionally, the image enhancement data may include: and each pixel point in the down-sampling image is mapped into a mapping parameter of a corresponding pixel point, and the corresponding pixel point of any pixel point is the pixel point which has the same position as the pixel point in the image after the down-sampling image is enhanced. So-called mapping a pixel to a corresponding pixel specifically means: and adjusting the pixel value of one pixel point to the pixel value of the corresponding pixel point.

Correspondingly, for each pixel point in the target enhanced image, determining a target enhancement parameter corresponding to the pixel point based on the enhanced data corresponding to the matching point of the pixel point in the image enhanced data may include: and aiming at each pixel point in the target enhanced image, determining a target parameter corresponding to the matching point of the pixel point from each mapping parameter, and taking the determined target parameter as a target enhanced parameter corresponding to the pixel point.

509. Adjusting the pixel value of the pixel point based on the target enhancement parameter corresponding to the pixel point to obtain a target enhancement image corresponding to the target accident vehicle image;

in this embodiment, for each pixel point in the target enhanced image, after the target enhancement parameter corresponding to the pixel point is determined, the pixel value of the pixel point may be adjusted based on the target enhancement parameter. This adjustment process is a process of performing image enhancement processing on the target enhanced image.

510. Acquiring owner identity information of a user and damaged information of an accident vehicle, wherein the vehicle information comprises vehicle insurance information of the accident vehicle;

in this embodiment, the accident type, the relative position information of the accident vehicle, the first vehicle identifier of the accident vehicle, the damaged position of the accident vehicle, and the damaged degree of the accident vehicle are sent to the client.

The accident type is the prerequisite of judging accident vehicle damage, and different accident types can influence accident vehicle's impaired position and impaired degree, and the accident type includes: rear-end collision, scraping, doubling collision, cornering collision and the like. For rear-end accidents, the damaged positions of the accident vehicle are the front end and the rear end of the accident vehicle, most of the accident vehicle is damaged by collision, and the damage degree is heavier than that of the scraping accident; for the parallel collision and scraping accidents, the damaged positions of the accident vehicle are two sides of the accident vehicle, and most of the damage is scraping damage; for a cornering collision accident, the damaged positions of the accident vehicle are one side and the front end of the accident vehicle, and the accident vehicle has collision damage and scraping damage. Therefore, the accident type needs to be determined from the accident image. And (4) carrying out claims settlement on the vehicle according to the owner identity information input by the user and the damaged information of the accident vehicle.

511. Receiving a claim settlement request uploaded by a user, and inputting a target enhanced image into the trained convolutional neural network model for prediction to obtain a claim settlement probability of the target enhanced image;

in this embodiment, the claim settlement request uploaded by the user includes a target enhanced image (that is, the target enhanced image in this embodiment) and claim settlement information, where the target enhanced image is a picture of a damaged portion of the vehicle, which is shot by the user in the event of a vehicle accident, for example, a picture of a rear-end collision of the vehicle, a picture of a side-turn of the vehicle, and a picture of a scratch of the vehicle. Claim settlement information refers to information related to claim settlement, such as a car model, a damage cause, a policy number, etc., uploaded by a user to an insurance company after a car accident occurs. After a vehicle accident occurs, a user fills in basic vehicle information and accident reasons through the mobile terminal 10, takes a picture of a damaged vehicle on site, and uploads a target enhanced image and claim settlement information to a server of an insurance company to generate a claim settlement request. And after a claim settlement request uploaded by a user is received, calling a trained convolutional neural network model, inputting the target enhanced image into the convolutional neural network model for prediction, and obtaining the claim settlement probability of the target enhanced image, namely the probability of whether the target enhanced image is to be claimed or not.

512. Judging whether the claim settlement probability of the target enhanced image is greater than a preset threshold value or not;

in this embodiment, a classifier SVM (support vector machine) is used for classification, which is a binary classification model used for performing binary classification on the target enhanced image, wherein one class is classified as belonging to claim, and the other class is classified as not belonging to claim. And after the one-dimensional feature vector is obtained, inputting the one-dimensional feature vector into a classifier, and mapping the one-dimensional feature vector to a numerical value in a range of 0 to 1 by the classifier, wherein the numerical value is the claim settlement probability.

513. When the claim settlement probability of the target enhanced image is larger than a preset threshold value, determining that the target enhanced image can settle the claim;

in this embodiment, after the claim settlement probability of the target enhanced image is obtained, the claim settlement probability is compared with a preset threshold, where the preset threshold is 0.7, and it is understood that the threshold may be any other numerical value. And when the claim settlement probability corresponding to the target enhanced image is greater than a preset threshold value, the target enhanced image is very close to the claimed target accident vehicle image, and the target enhanced image is judged to belong to the claimable object. And when the claim settlement probability corresponding to the target enhanced image is smaller than a preset threshold value, the target enhanced image is proved to have the risk of fraud or fraud, and the target enhanced image is judged not to belong to the claimable claim. For example, when the claim probability is 0.8, then the claim probability is greater than the preset threshold, then the target enhanced image is determined to be claimable.

514. And based on the owner identity information of the user and the identification information of the accident vehicle, the accident vehicle is settled.

In this embodiment, all the claim cases are screened from the preset database, the claim cases which have been claimed are selected, and the claim information of the screened claim cases is acquired, wherein the claim cases which have been claimed are marked after the claim completion, so that the claim cases which have been claimed are screened by selecting the claim cases with marks; and matching the claim information of the screened claim cases with the claim information uploaded by the user according to preset rules, wherein the preset rules are matched according to the vehicle model, the vehicle year and the damaged part, for example, if the vehicle model uploaded by the user is type A, the vehicle year is 2 years and the damaged part is the tail of a vehicle, the claim information matched with the vehicle model A is searched for from the claim information correspondingly, the amount of the claim filed in the matched claim information is used as the estimated amount of the claim, and the estimated amount of the claim filed is sent to the user.

The steps 501-504 in the present embodiment are similar to the steps 101-104 in the first embodiment, and are not described herein again.

With reference to fig. 6, the image enhancement method in the embodiment of the present invention is described above, and an image enhancement apparatus in the embodiment of the present invention is described below, where a first embodiment of the image enhancement apparatus in the embodiment of the present invention includes:

the first acquisition module 601 is used for acquiring field image data of a traffic accident scene;

a first determining module 602, configured to identify the field image data through a preset image identification model, and determine whether the field image data meets a preset image standard;

a prompting module 603, configured to prompt a user to shoot again when the live image data does not meet a preset image standard;

a shooting module 604, configured to enter a next shooting task when the field image data meets a preset image standard, so as to obtain a target accident vehicle image of the traffic accident field;

and the image enhancement module 605 is configured to input the target accident vehicle image into a preset image enhancement model, perform image enhancement on the target accident vehicle image, and generate a target enhanced image.

Referring to fig. 7, a second embodiment of the image enhancement apparatus according to the embodiment of the present invention specifically includes:

In this embodiment, the image enhancement apparatus further includes:

a second obtaining module 605, configured to obtain a historical vehicle image of an accident scene from a preset database;

a constructing module 606, configured to construct a training sample data set by using the historical vehicle image as a training sample;

and the training module 607 is configured to input the training sample data set into a preset image enhancement generator, and train the image enhancement generator to obtain a target image enhancement model.

In this embodiment, the image enhancement apparatus further includes:

the input module 608 is configured to obtain a plurality of training pictures from a preset training picture database, and preset the training pictures in a neural network model to obtain a prediction category label of the training pictures;

a generating module 609, configured to generate a real category label of the training picture according to the category of the training picture; generating a first loss function of the training picture according to the prediction category label of the training picture and the real category label of the training picture;

and the updating module 610 is configured to update parameters in the neural network model according to the first loss function to obtain a target picture identification model.

In this embodiment, the training module 607 is specifically configured to:

an image enhancement unit 6071, configured to perform image enhancement on the training sample data set to obtain a preset number of target original images and corresponding enhanced images;

an input unit 6072, configured to input the target original image into a CNN image enhancement network in a preset image enhancement generator, to obtain an output image corresponding to the target original image;

a determining unit 6073 for determining a second loss function between the output image and the enhanced image;

an iterative training unit 6074, configured to perform, based on the second loss function, on the CNN image enhancement network in the image enhancement generator until the CNN image enhancement network converges to obtain a target image enhancement model.

In this embodiment, the image enhancement module 605 is specifically configured to:

In this embodiment, the image enhancement apparatus further includes:

a third obtaining module 611, configured to obtain owner identity information of a user and damage information of the accident vehicle, where the vehicle information includes vehicle insurance information of the accident vehicle;

the prediction module 612 is configured to receive a claim settlement request uploaded by the user, and input the target enhanced image into the trained convolutional neural network model for prediction to obtain a claim settlement probability of the target enhanced image;

a second judging module 613, configured to judge whether the claim settlement probability of the target enhanced image is greater than a preset threshold;

the determining module 614 is configured to determine that the target enhanced image can claim when the claim settlement probability of the target enhanced image is greater than a preset threshold;

and a claim settlement module 615, configured to settle a claim for the accident vehicle based on the owner identity information of the user and the identification information of the accident vehicle.

Fig. 6 and 7 describe the image enhancement apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the image enhancement apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 8 is a schematic structural diagram of an image enhancement apparatus 800 according to an embodiment of the present invention, where the image enhancement apparatus 800 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a sequence of instructions operating on the image enhancement apparatus 800. Still further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the image enhancement device 800 to implement the steps of the image enhancement method provided by the above-mentioned method embodiments.

Image enhancing apparatus 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and so forth. It will be appreciated by those skilled in the art that the image enhancement device configuration shown in fig. 8 does not constitute a limitation of the image enhancement devices provided herein, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-mentioned image enhancement method.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. An image enhancement method, characterized in that the image enhancement method comprises:

acquiring field image data of a traffic accident scene;

if not, prompting the user to shoot again;

2. The image enhancement method of claim 1, prior to said acquiring live image data of a scene of a traffic accident, further comprising:

3. The image enhancement method according to claim 1, before said identifying the live image data by a preset image identification model and determining whether the live image data meets preset image criteria, further comprising:

4. The image enhancement method of claim 2, wherein inputting the training sample data set into a preset image enhancement generator, and training the image enhancement generator to obtain a target image enhancement model comprises:

5. The image enhancement method according to claim 1, wherein the inputting the target accident vehicle image into a preset image enhancement model, and the image enhancement of the target accident vehicle image to generate a target enhanced image comprises:

6. The image enhancement method according to claim 1, wherein after the inputting the target accident vehicle image into a preset image enhancement model, performing image enhancement on the target accident vehicle image, and generating a target enhanced image, the method further comprises:

7. An image enhancement apparatus, characterized in that the image enhancement apparatus comprises:

8. The image enhancement device according to claim 7, further comprising:

9. An image enhancement device, characterized in that the image enhancement device comprises: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invokes the instructions in the memory to cause the image enhancement device to perform the steps of the image enhancement method of any of claims 1-6.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the image enhancement method according to any one of claims 1 to 6.