CN109348089A

CN109348089A - Night scene image processing method, device, electronic equipment and storage medium

Info

Publication number: CN109348089A
Application number: CN201811399541.0A
Authority: CN
Inventors: 黄杰文
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2018-11-22
Filing date: 2018-11-22
Publication date: 2019-02-15
Anticipated expiration: 2038-11-22
Also published as: CN109348089B; WO2020103503A1

Abstract

The application proposes a kind of night scene image processing method, device, electronic equipment and storage medium, belongs to technical field of imaging.Wherein, this method comprises: successively acquiring multiple image according to preset exposure compensation mode；Using preset image recognition model, identifying processing is carried out to the default frame image in multiple image, to determine target area and nontarget area in default frame image；Using different noise reduction parameters values, target area and nontarget area to multiple image carry out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction parameters value in target area is greater than the corresponding noise reduction parameters value in nontarget area.As a result, by this night scene image processing method, the noise reduction effect of image entirety and the degree of purity of target area not only ensure that, but also preferably remain the detailed information of nontarget area, improve the quality of shooting image, improve user experience.

Description

Night scene image processing method, device, electronic equipment and storage medium

Technical field

This application involves technical field of imaging more particularly to a kind of night scene image processing method, device, electronic equipment and deposit Storage media.

Background technique

With the development of science and technology, intelligent mobile terminal (such as smart phone, tablet computer) is more more and more universal.It is most Smart phone and tablet computer are all built-in with camera, and with the enhancing of mobile terminal processing capacity and camera technology Development, the performance of built-in camera is stronger and stronger, and the quality for shooting image is also higher and higher.The operation of present mobile terminal Simple and easy to carry, people are taken pictures using mobile terminals such as smart phone and tablet computers in daily life has become one Kind normality.

Intelligent mobile terminal to people it is daily take pictures bring convenient while, people want to the picture quality of shooting Ask also higher and higher.Currently, in night scene photographed scene, mobile terminal is usual in order to meet requirement of the people to picture quality By way of passing through the different image of acquisition multi-frame exposure duration and being merged, the shooting of night scene image is carried out.But this In style of shooting, how to carry out noise reduction to night scene sky areas is a big difficulty.

Since the brightness of night scene sky areas is all than darker, final image fusion when generally use exposure time compared with Long image data, merges sky areas, and the noise in the longer image of exposure time is usually higher, so as to cause The noise of night scene sky areas is higher.It has been found that when carrying out noise reduction to night scene shooting image using traditional noise-reduction method, It can not only guarantee the noise reduction effect of sky areas, but also guarantee that the detailed information in other regions keeps good, and affect user experience.

Summary of the invention

Night scene image processing method, device, electronic equipment and the storage medium that the application proposes, for solving the relevant technologies It is middle when carrying out noise reduction to night scene shooting image using traditional noise-reduction method, it can not only guarantee the noise reduction effect of sky areas, but also protect The problem of detailed information holding for demonstrate,proving other regions is good, influences user experience.

The night scene image processing method that the application one side embodiment proposes, comprising: according to preset exposure compensation mode, Successively acquire multiple image；Using preset image recognition model, the default frame image in the multiple image is identified Processing, with the target area and nontarget area in the determination default frame image；Using different noise reduction parameters values, to described The target area and nontarget area of multiple image carry out noise reduction process respectively, to generate target image, wherein the target area The corresponding noise reduction parameters value in domain is greater than the corresponding noise reduction parameters value in the nontarget area.

The night scene image processing unit that the application another aspect embodiment proposes, comprising: acquisition module, for according to default Exposure compensation mode, successively acquire multiple image；Determining module, for utilizing preset image recognition model, to described more Default frame image in frame image carries out identifying processing, in the determination default frame image target area and non-target area Domain；Noise reduction module, target area and nontarget area difference for using different noise reduction parameters values, to the multiple image Noise reduction process is carried out, to generate target image, wherein the corresponding noise reduction parameters value in the target area is greater than the non-target area The corresponding noise reduction parameters value in domain.

The electronic equipment that the application another further aspect embodiment proposes comprising: the camera module, memory, processor And store the computer program that can be run on a memory and on a processor, which is characterized in that described in the processor executes Foregoing night scene image processing method is realized when program.

The computer readable storage medium that the application another further aspect embodiment proposes, is stored thereon with computer program, It is characterized in that, foregoing night scene image processing method is realized when described program is executed by processor.

The computer program that the another aspect embodiment of the application proposes, when which is executed by processor, to realize this Shen It please night scene image processing method described in embodiment.

Night scene image processing method provided by the embodiments of the present application, device, electronic equipment, computer readable storage medium and Computer program can successively acquire multiple image, and utilize preset image recognition mould according to preset exposure compensation mode Type carries out identifying processing to the default frame image in multiple image, to determine target area in default frame image and non-targeted Region, and then different noise reduction parameters values is used, target area and nontarget area to multiple image carry out at noise reduction respectively Reason, to generate target image, wherein the corresponding noise reduction parameters value in target area is greater than the corresponding noise reduction parameters in nontarget area Value.It, later can be according to target as a result, by being split processing to default frame image using preset image recognition model The characteristic in region and nontarget area carries out noise reduction to target area and nontarget area respectively using different noise reduction parameters values Processing, to not only ensure that the noise reduction effect of image entirety and the degree of purity of target area, but also preferably remains non-mesh The detailed information for marking region improves the quality of shooting image, improves user experience.

The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description It obtains obviously, or recognized by the practice of the application.

Detailed description of the invention

The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments Obviously and it is readily appreciated that, in which:

Fig. 1 is a kind of flow diagram of night scene image processing method provided by the embodiment of the present application；

Fig. 2 is the flow diagram of another kind night scene image processing method provided by the embodiment of the present application；

Fig. 3 is a kind of structural schematic diagram of night scene image processing unit provided by the embodiment of the present application；

Fig. 4 is the structural schematic diagram of electronic equipment provided by the embodiment of the present application.

Specific embodiment

Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end Same or similar label indicates same or similar element.The embodiments described below with reference to the accompanying drawings are exemplary, It is intended for explaining the application, and should not be understood as the limitation to the application.

When the embodiment of the present application is for noise reduction is carried out to night scene shooting image using traditional noise-reduction method in the related technology, nothing Method had not only guaranteed the noise reduction effect of sky areas, but also guaranteed that the detailed information in other regions keeps good, influenced asking for user experience Topic, proposes a kind of night scene image processing method.

Night scene image processing method provided by the embodiments of the present application can successively be adopted according to preset exposure compensation mode Collect multiple image, and utilize preset image recognition model, identifying processing is carried out to the default frame image in multiple image, with true Surely target area and nontarget area in default frame image, and then different noise reduction parameters values is used, to the mesh of multiple image Mark region and nontarget area carry out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction parameters in target area Value is greater than the corresponding noise reduction parameters value in nontarget area.As a result, by utilizing preset image recognition model, to default frame image It is split processing, can be distinguished later according to the characteristic of target area and nontarget area using different noise reduction parameters values Noise reduction process is carried out to target area and nontarget area, to not only ensure that noise reduction effect and the target area of image entirety Degree of purity, and preferably remain the detailed information of nontarget area, improve the quality of shooting image, improve user Experience.

Below with reference to the accompanying drawings to night scene image processing method, device, electronic equipment, storage medium and meter provided by the present application Calculation machine program is described in detail.

Fig. 1 is a kind of flow diagram of night scene image processing method provided by the embodiment of the present application.

As shown in Figure 1, the night scene image processing method, comprising the following steps:

Step 101, according to preset exposure compensation mode, multiple image is successively acquired.

Wherein, in preset exposure compensation mode, when may include the corresponding exposure value of every frame image, sensitivity, exposure The parameters such as long.In the embodiment of the present application, multiframe figure can successively be acquired according to the parameter in preset exposure compensation mode Picture.

It should be noted that since the overall brightness of night scene photographed scene is lower, it can be by adjusting every frame image Corresponding exposure time, the different image of acquisition multi-frame exposure value are made with obtaining the image of Different Dynamic range and being synthesized Image after must synthesizing has higher dynamic range, improves the overall brightness and quality of image.

Further, preset exposure compensation mode can be determined according to current photographed scene in real time, it is best to obtain Shooting effect.I.e. in a kind of possible way of realization of the embodiment of the present application, before above-mentioned steps 101, may include:

According to the current degree of jitter of the illuminance of present filming scene and camera module, determine that the preset exposure is mended Repay mode.

It is understood that when the illuminance difference of present filming scene, the corresponding exposure value of every frame image be can be not With.For example, can suitably reduce the corresponding exposure value of every frame image when the illuminance of present filming scene is larger；It is current to clap When the illuminance taken the photograph is smaller, the corresponding exposure value of every frame image can be properly increased.

It in the embodiment of the present application, can be by obtaining current gyroscope (Gyro-sensor) information of electronic equipment, really Determine the current degree of jitter of camera module, the i.e. current degree of jitter of camera module.

Gyroscope is called angular-rate sensor, can measure rotational angular velocity when physical quantity deflection, inclination.It is set in electronics In standby, gyroscope can be very good the movement of measurement rotation, deflection, judge that the reality of user is dynamic so as to Accurate Analysis Make.The gyroscope information (gyro information) of electronic equipment may include electronic equipment in three dimensions on three dimension directions Motion information, three dimensions of three-dimensional space can be expressed as three X-axis, Y-axis, Z axis directions, wherein X-axis, Y-axis, Z axis For vertical relation two-by-two.

It should be noted that in a kind of possible way of realization of the embodiment of the present application, it can be current according to electronic equipment Gyro information, determine the current degree of jitter of camera module.The absolute value of the gyro movement of electronic equipment in three directions Bigger, then the degree of jitter of camera module is bigger.Specifically, the absolute value threshold of gyro movement in three directions can be preset Value, and the sum of the absolute value moved according to the current gyro in three directions got, the relationship with preset threshold value, really Determine the current degree of jitter of camera module.

As an example it is assumed that preset threshold value is first threshold A, second threshold B, third threshold value C, and A < B < C is currently obtained The sum of absolute value for the movement of gyro in three directions got is S.If S < A, it is determined that the current degree of jitter of camera module For " non-jitter "；If A < S < B, it can determine that the current degree of jitter of camera module is " slight jitter "；If B < S < C, can To determine the current degree of jitter of camera module for " small shake "；If S > C, the current degree of jitter of camera module can be determined For " big shake ".

It should be noted that the example above is exemplary only, the limitation to the application cannot be considered as.In actual use, Can the quantity of preset threshold and each threshold value according to actual needs specific value, and the pass according to gyro information and each threshold value System presets the mapping relations of gyro information and camera module degree of jitter.

It is understood that when the quantity of the image of acquisition and the sensitivity of acquisition image influence whether whole shooting Long, shooting duration of video is too long, the degree of jitter aggravation of camera module when may result in hand-held shooting, to influence picture quality. Therefore, degree of jitter that can be current according to camera module determines amount of images, the corresponding sensitivity of every frame image of acquisition, And the corresponding exposure time of every frame image to be collected, so that shooting duration of video control in suitable range, avoids shake journey The ghost that degree aggravation introduces.

Specifically, in a kind of possible way of realization of the embodiment of the present application, the illumination according to present filming scene Degree and the current degree of jitter of camera module, determine the preset exposure compensation mode, comprising:

According to the illuminance of present filming scene, the target light exposure value of every frame image in the multiple image is determined；

According to the current degree of jitter of the camera module, the sensitivity of every frame image is determined；

According to the sensitivity of every frame image and the target light exposure value of every frame image, the exposure of every frame image is determined Duration.

Wherein, exposure value refers in the time for exposure through the quantity of the light of camera lens.

Wherein, sensitivity, also known as ISO value refer to and measure egative film for the index of the sensitivity level of light.For sensitivity Lower egative film needs to expose the longer time to reach the identical imaging with the higher egative film of sensitivity.The sense of digital camera Luminosity is a kind of a kind of index similar to film speed, and the ISO of digital camera can be by adjusting the sensitive of sensor devices Degree merges sensitivity speck to adjust, that is to say, that can be by promoting the light sensitivity of sensor devices or merging several Adjacent sensitivity speck come achieve the purpose that promoted ISO.It should be noted that either digital or egative film photography, in order to reduce Time for exposure would generally introduce more noise using relatively high sensitivity, so as to cause picture quality reduction.

Wherein, exposure time refers to time of the light by camera lens.

It should be noted that exposure value is related with aperture size, exposure time and sensitivity.Wherein, aperture is namely logical Optical port diameter determines the quantity that light passes through in the unit time.When the corresponding sensitivity of every frame image is identical, and aperture size phase Meanwhile the corresponding light exposure of illuminance of present filming scene is bigger, the corresponding exposure time of every frame image is longer.

In the embodiment of the present application, it can use the survey optical module in camera module, obtain the illumination of present filming scene Degree, and auto-exposure control (Auto Exposure Control, abbreviation AEC) algorithm is utilized, determine that current light degree is corresponding Exposure value.In the screening-mode of acquisition multiple image, the exposure value of every frame image be can be different, and have difference to obtain The image of dynamic range improves the overall brightness and quality of image so that the image after synthesis has higher dynamic range.I.e. It can be when acquiring every frame image, using different exposure compensating strategies, and according to exposure compensating strategy and current illumination Degree, determines the corresponding target light exposure value of every frame image.

In the embodiment of the present application, different exposures can be taken respectively to every frame image by presetting exposure compensating strategy Light compensation policy, so that every frame image corresponds to different exposure values, to obtain the image with Different Dynamic range.

In the embodiment of the present application, preset exposure compensating strategy refers to and distinguishes preset exposure value for every frame image The combination of (Exposure Value, abbreviation EV).In the initial definition of exposure value, exposure value does not imply that an accurately number Value, and refer to " all camera apertures and the combination of exposure time that identical light exposure can be provided ".Sensitivity, aperture and exposure Light time is long to have determined the light exposure of camera, different parameter combinations can produce equal light exposure, i.e. these various combinations EV value is the same, for example, combined in the identical situation of sensitivity using the aperture of 1/125 second exposure time and F/11, with Using the combination of 1/250 second time for exposure and F/8.0 shutter, the light exposure of acquisition be it is identical, i.e., EV value is identical.EV value When being 0, refer to the light exposure obtained when sensitivity is 100, aperture-coefficient F/1, exposure time are 1 second；Light exposure increases by one Shelves, i.e., exposure time double perhaps sensitivity double or aperture increase by one grade, EV value increase by 1, that is to say, that The corresponding light exposure of 1EV is twice of the corresponding light exposure of 0EV.It as shown in table 1, is exposure time, aperture, sensitivity difference list Solely when variation, the corresponding relationship with EV value.

Table 1

Camera work entered after the digital age, and the light measuring function of camera internal is very powerful, and EV is then through common Differential to indicate to expose one on scale, many cameras all allow that exposure compensating is arranged, and are usually indicated with EV.This In the case of, EV refers to that the difference of camera photometering data corresponding light exposure and actual exposure amount, such as the exposure compensating of+1EV are Refer to and increase by one grade of exposure relative to the corresponding light exposure of camera photometering data, is i.e. actual exposure amount is that camera photometering data are corresponding Twice of light exposure.

It in the embodiment of the present application, can be by the determining corresponding EV value of benchmark light exposure when presetting exposure compensating strategy It is preset as 0 ,+1EV refers to one grade of exposure of increase, i.e. light exposure is 2 times of benchmark light exposure, and+2EV refers to two grades of exposures of increase, I.e. light exposure is 4 times of benchmark light exposure, and -1EV refers to one grade of exposure of reduction, i.e. light exposure is 0.5 times etc. of benchmark light exposure Deng.

For example, if the quantity of multiple image is 7 frames, the corresponding EV value range of preset exposure compensating strategy can be with It is [+1 ,+1 ,+1 ,+1,0, -3, -6].Wherein, exposure compensating strategy is the frame of+1EV, can solve noise problem, passes through brightness Relatively high frame carries out time domain noise reduction, inhibits noise while promoting dark portion details；Exposure compensating strategy is the frame of -6EV, can To solve the problems, such as bloom overexposure, retain the details of highlight area；Exposure compensating strategy is the frame of 0EV and -3EV, then can use In holding bloom to the transition between dark space, the effect of preferable light and shade transition is kept.

It should be noted that the corresponding each EV value of preset exposure compensating strategy either specifically set according to actual needs It sets, is also possible to the EV value range according to setting, and the principle equal according to the difference between each EV value acquires, the application Embodiment does not limit this.

In a kind of possible way of realization of the embodiment of the present application, according to the illuminance of present filming scene, calculated by ACE After method determines an exposure value, it can determine that every frame image is corresponding according to the exposure value and preset exposure compensating strategy Target light exposure value.

In the embodiment of the present application, the sensitivity of every frame image refers to the degree of jitter current according to camera module, determines With current degree of jitter be adapted minimum sensitivity.

It should be noted that in the embodiment of the present application, can by acquiring the lower image of multiframe sensitivity simultaneously, and The multiple image of acquisition is synthesized in a manner of generating target image, can not only be promoted night scene shooting image dynamic range and Overall brightness, and by the value of control sensitivity, effectively inhibit the noise in image, improves the quality of night scene shooting image.

In the embodiment of the present application, degree of jitter that can be current according to camera module, determines the sensitivity of every frame image, So that shooting duration of video control is in suitable range.Specifically, if camera module it is current degree of jitter it is smaller, can will The lesser value of the appropriate boil down to of sensitivity of every frame image, effectively to inhibit the noise of every frame image, improve the matter of shooting image Amount；If the current degree of jitter of camera module is larger, the sensitivity of every frame image can be properly increased as biggish value, with Shorten shooting duration of video, the ghost for avoiding degree of jitter aggravation from introducing.

For example, however, it is determined that the current degree of jitter of camera module is " non-jitter ", then can determine currently to be Sensitivity can be determined as lesser value by foot prop screening-mode at this time, to obtain higher-quality image as far as possible, for example be determined Sensitivity is 100；If it is determined that the current degree of jitter of camera module is " slight jitter ", then can determine currently may be hand-held Sensitivity can be determined as biggish value by screening-mode at this time, to reduce shooting duration of video, for example determine that sensitivity is 200；If It determines that the current degree of jitter of camera module is " small shake ", then can be further reduced the quantity of image to be collected, go forward side by side one Step increases sensitivity, to reduce shooting duration of video, for example determines that sensitivity is 220；If it is determined that the degree of jitter that camera module is current For " big shake ", then it can determine that current degree of jitter is excessive, can further increase sensitivity, when reducing shooting at this time It is long, for example determine that sensitivity is 250.

It is understood that the quantity of the image of acquisition also influences whether whole shooting duration of video, the image of acquisition is more, Shooting duration of video is longer, the degree of jitter aggravation of camera module when may result in shooting, to influence picture quality.Therefore, In the alternatively possible way of realization of the embodiment of the present application, degree of jitter that can be current according to camera module adjusts simultaneously The sensitivity of the quantity of multiple image and every frame image, so that shooting duration of video control is in suitable range.

Specifically, if camera module it is current degree of jitter it is smaller, the image compared with multiframe, and every frame figure can be acquired The sensitivity of picture can the appropriate lesser value of boil down to, effectively to inhibit the noise of every frame image, improve the quality of shooting image； If the current degree of jitter of camera module is larger, the image of less frame can be acquired, and the sensitivity of every frame image can be with It properly increases as biggish value, to shorten shooting duration of video.

For example, however, it is determined that the current degree of jitter of camera module is " non-jitter ", then can determine currently to be Foot prop screening-mode can acquire the image compared with multiframe at this time, and sensitivity is determined as lesser value, higher to obtain as far as possible The image of quality, for example determine that the quantity of multiple image is 17 frames, sensitivity 100；If it is determined that the shake that camera module is current Degree is " slight jitter ", then can determine currently to be hand-held screening-mode, can acquire the image of less frame at this time, and Sensitivity is determined as biggish value, to reduce shooting duration of video, for example determines that the quantity of multiple image is 7 frames, sensitivity is 200；If it is determined that the current degree of jitter of camera module is " small shake ", then it can be further reduced the quantity of multiple image, and Sensitivity is further increased, to reduce shooting duration of video, for example determines that the quantity of multiple image is 5 frames, sensitivity 220；If really Determining the current degree of jitter of camera module is " big shake ", then can determine that current degree of jitter is excessive, at this time can be into one Step reduces the quantity of multiple image, and further increases sensitivity, to reduce shooting duration of video, for example determines the quantity of multiple image For 3 frames, sensitivity 250.

Correspondingly, multiple groups exposure can also be preset when the degree of jitter according to camera module determines the quantity of multiple image Light compensation policy determines the preset exposure compensating plan being consistent with the quantity of multiple image with the quantity according to multiple image Slightly.

It should be noted that the example above is exemplary only, the limitation to the application cannot be considered as.In actual use, When the variation of the degree of jitter of camera module, amount of images and benchmark sensitivity to be collected can have both been changed simultaneously, it can also be with Change one of them, to obtain optimal scheme.Wherein, the degree of jitter of camera module and amount of images to be collected and every frame The mapping relations of the corresponding benchmark sensitivity of image to be collected, can preset according to actual needs.

In the embodiment of the present application, the sense of the target light exposure value of every frame image and every frame image in multiple image is determined It, can be according to the sensitivity of every frame image and the target light exposure value of every frame image, when determining the exposure of every frame image after luminosity It is long.

Step 102, using preset image recognition model, the default frame image in the multiple image is carried out at identification Reason, with the target area and nontarget area in the determination default frame image.

Wherein, preset image recognition model refers to by instructing to the night scene image data largely after mark Practice, obtained Image Segmentation Model.

Wherein, target area refers to the flat brightness abnormal area for needing to carry out high-strength noise reduction.Nontarget area, Refer to the region in default frame image in addition to target area, usually brightness always and include more detailed information texture area Domain.I.e. in a kind of possible way of realization of the embodiment of the present application, above-mentioned steps 102 may include:

Using preset image recognition model, identifying processing is carried out to the default frame image in the multiple image, with true The region of brightness exception is target area in the fixed default frame image.

Wherein, the region of brightness exception can refer to that with the luminance difference in the region on its periphery be more than preset threshold value Region.For example, compared with other regions, the brightness of sky areas is usually very dark, therefore night scene image in night scene photographed scene In sky areas can be determined as the region of brightness exception, i.e. target area；And compared with other regions in image, it is reflective The brightness in region is usually very big, therefore the retroreflective regions in image can be determined as the region of brightness exception, i.e. target area；Again Such as, the GLOW INCLUSION AREA near light source, compared with source region, brightness is usually lower, therefore the GLOW INCLUSION AREA in image can also To be determined as the region of brightness exception, i.e. target area.

In actual use, the threshold value of preset luminance difference can be preset according to actual needs, and the embodiment of the present application is to this Without limitation.

It should be noted that in night scene photographed scene, by way of passing through acquisition multiple image and being synthesized, to improve When the shooting quality of night scene image, for the very low flat site of the brightness such as sky, it will usually using the number of excessive overexposure frame According to fusion, to obtain higher brightness, and biggish noise is generally comprised in overexposure frame, thus cause include in the regions such as sky Noise it is more.If carry out noise reduction to image, noise reduction process is carried out to entire image using identical noise reduction parameters, is easy to make At the regions such as sky noise reduction effect is undesirable or the informative region of other details in detailed information destroyed.Cause This, in the embodiment of the present application, can by preset image recognition model, determined from default frame image target area and Nontarget area, and noise reduction is carried out to target area and nontarget area respectively using different noise reduction parameters.

In the embodiment of the present application, preset image recognition model can generate offline, and be integrated in electronic equipment.Instruction When practicing image recognition model, a large amount of night scene image data can be acquired first, and to the picture of collected night scene image data Vegetarian refreshments is labeled according to default rule, to obtain that the markup information of target area and nontarget area can be distinguished, and it is right Night scene image data after mark are trained by way of deep learning, corresponding with the pixel value for obtaining pixel Regular information between markup information is to get arriving image recognition model.The image recognition model trained can be to input figure As the image data of identification model is analyzed, and according to the pass between the pixel value of each pixel and each pixel pixel value System, determines the markup information of each pixel, and be labeled to the pixel of input picture, obtains that target area can be distinguished The exposure mask in domain and nontarget area, so that it is determined that target area and nontarget area out.

For example, when being labeled to a large amount of night scene image data of acquisition, default rule be can be " by target The corresponding pixel in region is labeled as 1, and the corresponding pixel in nontarget area is labeled as 0 ".Image data after mark is carried out The image recognition model that training obtains, can analyze the image data of input picture identification model, and according to each pixel Relationship between the pixel value and each pixel pixel value of point, is labeled the pixel of input picture with identical rule, It is target area that i.e. markup information, which is the pixel of " 1 ", and markup information is that the pixel of " 0 " is nontarget area.

It is understood that the default frame image in multiple image is inputted preset image recognition model, preset figure As identification model can be to default frame image progress identifying processing, i.e., according to the pixel value of each pixel in default frame image and respectively Relationship between pixel pixel value, determines the markup information of each pixel, and then determines the mesh in default frame image Mark region and nontarget area.

It further, can be from multiple image since the image of acquisition has multiframe and multiple image is alignment One frame image of middle selection carries out identifying processing by preset image recognition model, and is obtained in multiple image according to recognition result Target area and nontarget area.Wherein, the frame image of selection is default frame image.I.e. in the embodiment of the present application one kind In possible way of realization, before above-mentioned steps 102, can also include:

According to the corresponding exposure value of frame image every in the multiple image, the default frame image is determined.

It should be noted that in a kind of possible way of realization of the embodiment of the present application, it can be high by brightness and clarity Image as default frame image, to obtain optimal segmentation effect.Usually, exposure value is bigger, the brightness of image and clear Clear degree is higher, therefore the maximum image of corresponding exposure value can be preset as to default frame image, it can according to every frame image Corresponding exposure value determines the maximum image of exposure value, i.e., default frame image.If the corresponding maximum image of exposure value has more Frame can then randomly select out a frame as default frame image from the maximum multiple image of exposure value.

Step 103, target area and nontarget area difference using different noise reduction parameters values, to the multiple image Noise reduction process is carried out, to generate target image, wherein the corresponding noise reduction parameters value in the target area is greater than the non-target area The corresponding noise reduction parameters value in domain.

In the embodiment of the present application, using preset image recognition model, determine target area in multiple image and It, can be right respectively using different noise reduction parameters values according to the characteristic of target area and nontarget area after nontarget area Target area and nontarget area carry out noise reduction process.

It should be noted that the noise for including in target area is larger and detailed information is less, and nontarget area Zhong Bao The noise contained it is smaller and have detailed information abundant, and to image carry out noise reduction process while, inevitably introduce Image detail obscures, and this obscure may offset raising of the noise reduction to picture quality.Therefore, it is dropped to multiple image When making an uproar, biggish noise reduction parameters value can be used to target area, for example increase noise reduction intensity, to remove a large amount of of target area Noise reaches optimal noise reduction effect；And when carrying out noise reduction process to nontarget area, lesser noise reduction parameters can be used Value, for example reduce noise reduction intensity, to mitigate destruction of the noise reduction process to image detail information while reducing noise, improve figure The quality of picture.

In a kind of possible way of realization of the embodiment of the present application, the side that can be mixed with time domain noise reduction using airspace noise reduction Formula carries out noise reduction process to multiple image.Wherein, airspace noise reduction carries out noise reduction, time domain using the spatial coherence in single-frame images Noise reduction carries out noise reduction using the correlation of multiple image in time.The most common method of airspace filter is low-pass filtering, low pass Filter method achievees the purpose that noise reduction by the high frequency section filtered out in picture signal, but due to the edge of image and jump part In high-frequency region, it is easy to cause image border and jump part to obscure, causes the image concentrated in signal high frequency thin Save the damage of information.Simultaneously as airspace noise reduction does not consider time-domain information, and the noise of interframe same position is there are randomness, It is easy to cause the change of adjacent interframe picture material after noise reduction.

The most common method of time domain noise reduction is averaging of multiple image, since picture material has very strong correlation in interframe Property, picture material is consecutive variations in each frame, and noise always occurs at random in interframe, does not have correlation, noise It is all discontinuous in each frame, therefore noise is utilized the interframe the characteristics of in time domain noise reduction, can effectively remove noise, together When protect the detailed information of image.But when acquiring multiple image in the event of biggish shake, simple time domain noise reduction It is easy noise residual or " ghost " phenomenon occur in the presence of it fails to match or error.Therefore, mixed using airspace noise reduction and time domain noise reduction The mode of conjunction carries out noise reduction process to multiple image, can effectively inhibit the noise in multiple image, and preferably retain The detailed information such as edge, the texture of image.

In a kind of possible way of realization of the application, emergence processing can also be carried out to target area, determine target Transitional region between region and nontarget area, and using different noise reduction parameters values respectively to target area, nontarget area, Transitional region carries out noise reduction process and further increases picture quality to realize the natural transition of mesh noise reduction effect.

Below with reference to Fig. 2, another night scene image processing method provided by the embodiments of the present application is further described.

Fig. 2 is the flow diagram of another kind night scene image processing method provided by the embodiment of the present application.

As shown in Fig. 2, the night scene image processing method, comprising the following steps:

Step 201, according to preset exposure compensation mode, multiple image is successively acquired.

Step 202, using preset image recognition model, the default frame image in the multiple image is carried out at identification Reason, with the target area and nontarget area in the determination default frame image.

The specific implementation process and principle of above-mentioned steps 201-202, is referred to the detailed description of above-described embodiment, herein It repeats no more.

Step 203, emergence processing is carried out to the target area, with determining positioned at the target area and described non-targeted Interregional transitional region.

Wherein, emergence is handled, and is referred to and is carried out Fuzzy Processing to the edge of image, so that the edge of image reaches dim effect Fruit.Emergence processing is carried out to target area, is that Fuzzy Processing is carried out to the edge of target area, with reach target area with it is non- The effect of natural transition between target area.

It should be noted that can control the dim range at edge by adjusting Feather Radius value, i.e., transitional region is big It is small.Feather Radius value is bigger, and dim range is wider, and transitional region is bigger；Feather Radius value is smaller, and dim range is narrower, transition Region is smaller.

In the embodiment of the present application, emergence processing is carried out to target area, is that place is redefined by certain method In the process of the pixel value of the pixel of the target area adjacent edges in Feather Radius.For example, carrying out plumage by mean value smoothing Change processing, refers to the mean value of the neighborhood territory pixel point of a certain pixel, is redefined as the pixel value of the pixel.For example, false If Size of Neighborhood is 11 × 11, the pixel value mean value of pixel is in the neighborhood that the pixel value of pixel A is 100,11 × 11 85, then the pixel value of pixel A is 85 after processing of sprouting wings.

Step 204, using different noise reduction parameters values, to the target area of the multiple image, transitional region and non-mesh Mark region carries out noise reduction process respectively, to generate target image.

In the embodiment of the present application, it after determining the transitional region between target area and nontarget area, that is, can be used Different noise reduction parameters values carries out noise reduction process to target area, transitional region and the nontarget area in multiple image respectively, Target image is generated.Wherein, the corresponding noise reduction parameters value in target area is greater than the corresponding noise reduction parameters value of transitional region, transition The corresponding noise reduction parameters value in region is greater than the corresponding noise reduction parameters value in nontarget area.The corresponding noise reduction parameters value in each region can be with It is determined according to the noise intensity for including in image, to obtain optimal noise reduction effect.

Further, the noise level in the multiple image of acquisition is related with current photographed scene, such as when shooting Sensitivity, the illuminance of photographed scene, the details in scene can influence the noise level in the image of acquisition.For example, sense Luminosity is bigger, and the noise level in the image of acquisition is higher；Detailed information in scene is abundanter, and the noise that human eye can perceive is got over It is small, therefore, it can be determined according to current photographed scene with reference to noise reduction parameters, and then determined respectively according to reference noise reduction parameters The corresponding noise reduction parameters value in region.I.e. in a kind of possible way of realization of the embodiment of the present application, before above-mentioned steps 204, also May include:

According to current photographed scene, determines and refer to noise reduction parameters；

According to the corresponding weighted value in preset each region and it is described refer to noise reduction parameters, determine the target area, transition The current corresponding noise reduction parameters value in region and nontarget area.

It should be noted that the noise level in the multiple image of current photographed scene and acquisition is closely bound up, therefore The noise level that the noise level in multiple image can be estimated, and determine and estimate according to current photographed scene Adaptable reference noise reduction parameters.

For example, if the detailed information in the smaller or to be captured scene of current sensitivity is relatively abundant, it can really Surely the noise level in multiple image acquired is lower, then can will be determined as lesser value with reference to noise reduction parameters；If current Detailed information in the larger or to be captured scene of sensitivity is less, it can determines the noise water in the multiple image of acquisition It is flat higher, then it can will be determined as biggish value with reference to noise reduction parameters.

In a kind of possible way of realization of the embodiment of the present application, weighted value when noise reduction can be preset for each region, and The corresponding noise reduction parameters value in each region is determined with reference to noise reduction parameters according to weighted value.For example, can join using with reference to noise reduction Several pairs of nontarget areas carry out noise reduction, i.e. the corresponding weighted value in nontarget area can be 1；And the corresponding noise reduction ginseng in target area Numerical value is greater than the corresponding noise reduction parameters value in nontarget area, i.e. the corresponding weighted value in target area needs to be greater than 1, such as can be with It is 1.5；The corresponding noise reduction parameters value of transitional region is needed between the corresponding noise reduction parameters value in target area and nontarget area Between corresponding noise reduction parameters value, for example it can be 1.2.

It should be noted that the example above is exemplary only, the limitation to the application cannot be considered as.In actual use, The corresponding noise reduction parameters value of transitional region, the corresponding drop of transitional region can be greater than according to the corresponding noise reduction parameters value in target area Parameter value of making an uproar is greater than the principle of the corresponding noise reduction parameters value in nontarget area, presets the corresponding weighted value in each region, to obtain most Good noise reduction effect.

Night scene image processing method provided by the embodiments of the present application can successively be adopted according to preset exposure compensation mode Collect multiple image, and utilize preset image recognition model, identifying processing is carried out to the default frame image in multiple image, with true Surely target area and nontarget area in default frame image, carry out emergence processing to target area later, are located at mesh to determine Mark the transitional region between region and nontarget area and then use different noise reduction parameters values, to the target area of multiple image, Transitional region and nontarget area carry out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction ginseng in target area Numerical value is greater than the corresponding noise reduction parameters value of transitional region, and it is corresponding that the corresponding noise reduction parameters value of transitional region is greater than nontarget area Noise reduction parameters value.As a result, by utilizing preset image recognition model, processing is split to default frame image, and to identification Target area out carries out emergence processing, determines transitional region, and different noise reduction parameters values can be used respectively to mesh later It marks region, transitional region and nontarget area and carries out noise reduction process, to not only ensure that the noise reduction effect and mesh of image entirety The degree of purity for marking region, preferably remains the detailed information of nontarget area, and realize target area and non-target area The natural transition of noise reduction effect between domain further improves the quality of shooting image, improves user experience.

In order to realize above-described embodiment, the application also proposes a kind of night scene image processing unit.

Fig. 3 is a kind of structural schematic diagram of night scene image processing unit provided by the embodiments of the present application.

As shown in figure 3, the night scene image processing unit 30, comprising:

Acquisition module 31, for successively acquiring multiple image according to preset exposure compensation mode；

First determining module 32, for utilizing preset image recognition model, to the default frame figure in the multiple image As carrying out identifying processing, with the target area and nontarget area in the determination default frame image；

Noise reduction module 33, for using different noise reduction parameters values, target area to the multiple image and non-targeted Region carries out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction parameters value in the target area is greater than described The corresponding noise reduction parameters value in nontarget area.

In actual use, night scene image processing unit provided by the embodiments of the present application, can be configured in any electronics In equipment, to execute aforementioned night scene image processing method.

Night scene image processing unit provided by the embodiments of the present application can successively be adopted according to preset exposure compensation mode Collect multiple image, and utilize preset image recognition model, identifying processing is carried out to the default frame image in multiple image, with true Surely target area and nontarget area in default frame image, and then different noise reduction parameters values is used, to the mesh of multiple image Mark region and nontarget area carry out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction parameters in target area Value is greater than the corresponding noise reduction parameters value in nontarget area.As a result, by utilizing preset image recognition model, to default frame image It is split processing, can be distinguished later according to the characteristic of target area and nontarget area using different noise reduction parameters values Noise reduction process is carried out to target area and nontarget area, to not only ensure that noise reduction effect and the target area of image entirety Degree of purity, and preferably remain the detailed information of nontarget area, improve the quality of shooting image, improve user Experience.

In a kind of possible way of realization of the application, above-mentioned night scene image processing unit 30, further includes:

Second determining module, the degree of jitter current for the illuminance and camera module according to present filming scene, really The fixed preset exposure compensation mode.

Further, in the alternatively possible way of realization of the application, above-mentioned second determining module is specifically used for:

Further, in the application in another possible way of realization, above-mentioned night scene image processing unit 30 is also wrapped It includes:

Third determining module, for determining described default according to the corresponding exposure value of frame image every in the multiple image Frame image.

4th determining module, for carrying out emergence processing to the target area, with determine be located at the target area and Transitional region between the nontarget area.

Correspondingly, above-mentioned noise reduction module 33, is specifically used for:

Using different noise reduction parameters values, to the target area of the multiple image, transitional region and nontarget area point It carry out not noise reduction process.

Further, in the alternatively possible way of realization of the application, above-mentioned night scene image processing unit 30 is also wrapped It includes:

5th determining module, for determining and referring to noise reduction parameters according to current photographed scene；

6th determining module, for according to the corresponding weighted value in preset each region and it is described refer to noise reduction parameters, determine The current corresponding noise reduction parameters value in the target area and nontarget area.

Further, in the application in another possible way of realization, above-mentioned first determining module 32 is specifically used for:

It should be noted that the aforementioned explanation to Fig. 1, night scene image processing method embodiment shown in Fig. 2 is also fitted For the night scene image processing unit 30 of the embodiment, details are not described herein again.

Night scene image processing unit provided by the embodiments of the present application can successively be adopted according to preset exposure compensation mode Collect multiple image, and utilize preset image recognition model, identifying processing is carried out to the default frame image in multiple image, with true Surely target area and nontarget area in default frame image, carry out emergence processing to target area later, are located at mesh to determine Mark the transitional region between region and nontarget area and then use different noise reduction parameters values, to the target area of multiple image, Transitional region and nontarget area carry out noise reduction process respectively, to generate target image, wherein the corresponding noise reduction ginseng in target area Numerical value is greater than the corresponding noise reduction parameters value of transitional region, and it is corresponding that the corresponding noise reduction parameters value of transitional region is greater than nontarget area Noise reduction parameters value.As a result, by utilizing preset image recognition model, processing is split to default frame image, and to identification Target area out carries out emergence processing, determines transitional region, and different noise reduction parameters values can be used respectively to mesh later It marks region, transitional region and nontarget area and carries out noise reduction process, to not only ensure that the noise reduction effect and mesh of image entirety The degree of purity for marking region, preferably remains the detailed information of nontarget area, and realize target area and non-target area The natural transition of noise reduction effect between domain further improves the quality of shooting image, improves user experience.

In order to realize above-described embodiment, the application also proposes a kind of electronic equipment.

Fig. 4 is the structural schematic diagram of electronic equipment provided by the embodiments of the present application.

As shown in figure 4, above-mentioned electronic equipment 200 includes:

Memory 210 and processor 220 connect the bus 230 of different components (including memory 210 and processor 220), Memory 210 is stored with computer program, realizes night scene described in the embodiment of the present application when processor 220 executes described program Image processing method.

Bus 230 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.

Electronic equipment 200 typically comprises various electronic readable medium.These media can be it is any can be electric The usable medium that sub- equipment 200 accesses, including volatile and non-volatile media, moveable and immovable medium.

Memory 210 can also include the computer system readable media of form of volatile memory, such as arbitrary access Memory (RAM) 240 and/or cache memory 250.Electronic equipment 200 may further include it is other it is removable/can not Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 260 can be used for reading and writing not Movably, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").It although not shown in fig 4, can be with The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") is provided, and non-volatile to moving The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving Device can be connected by one or more data media interfaces with bus 230.Memory 210 may include at least one program Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform the application The function of each embodiment.

Program/utility 280 with one group of (at least one) program module 270, can store in such as memory In 210, such program module 270 includes --- but being not limited to --- operating system, one or more application program, other It may include the realization of network environment in program module and program data, each of these examples or certain combination.Journey Sequence module 270 usually executes function and/or method in embodiments described herein.

Electronic equipment 200 can also be with one or more external equipments 290 (such as keyboard, sensing equipment, display 291 Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 200 communicate, and/or with make Any equipment (such as network interface card, the modem that the electronic equipment 200 can be communicated with one or more of the other calculating equipment Etc.) communication.This communication can be carried out by input/output (I/O) interface 292.Also, electronic equipment 200 can also lead to Cross network adapter 293 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, example Such as internet) communication.As shown, network adapter 293 is communicated by bus 230 with other modules of electronic equipment 200.It answers When understanding, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 200, including but unlimited In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number According to backup storage system etc..

Program of the processor 220 by operation storage in memory 210, thereby executing various function application and data Processing.

It should be noted that the implementation process and technical principle of the electronic equipment of the present embodiment are referring to aforementioned to the application reality The explanation of the night scene image processing method of example is applied, details are not described herein again.

Electronic equipment provided by the embodiments of the present application can execute foregoing night scene image processing method, according to pre- If exposure compensation mode, multiple image is successively acquired, and utilize preset image recognition model, to default in multiple image Frame image carries out identifying processing, to determine target area and nontarget area in default frame image, and then uses different drops It makes an uproar parameter value, target area and nontarget area to multiple image carry out noise reduction process respectively, to generate target image, In, the corresponding noise reduction parameters value in target area is greater than the corresponding noise reduction parameters value in nontarget area.It is preset by utilizing as a result, Image recognition model is split processing to default frame image, later can according to the characteristic of target area and nontarget area, Noise reduction process is carried out to target area and nontarget area respectively using different noise reduction parameters values, to not only ensure that image The degree of purity of whole noise reduction effect and target area, and the detailed information of nontarget area is preferably remained, it improves The quality for shooting image, improves user experience.

In order to realize above-described embodiment, the application also proposes a kind of computer readable storage medium.

Wherein, the computer readable storage medium, is stored thereon with computer program, when which is executed by processor, To realize night scene image processing method described in the embodiment of the present application.

In order to realize above-described embodiment, the application another further aspect embodiment provides a kind of computer program, which is located When managing device execution, to realize night scene image processing method described in the embodiment of the present application.

In a kind of optional way of realization, the present embodiment can be using any group of one or more computer-readable media It closes.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable to deposit Storage media for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor Part, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: to have The electrical connection of one or more conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD- ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device Using or it is in connection.

Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be Any computer-readable medium other than computer readable storage medium, which can send, propagate or Transmission is for by the use of instruction execution system, device or device or program in connection.

The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.

The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with It is fully executed on consumer electronic devices, partly executes on consumer electronic devices, held as an independent software package Row, partially part executes in devices in remote electronic or completely in devices in remote electronic or service on consumer electronic devices It is executed on device.In the situation for being related to devices in remote electronic, devices in remote electronic can pass through the network of any kind --- packet It includes local area network (LAN) or wide area network (WAN)-is connected to consumer electronic devices, or, it may be connected to external electronic device (example It is such as connected using ISP by internet).

Those skilled in the art will readily occur to its of the application after considering specification and practicing the invention applied here Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or The common knowledge in the art that person's adaptive change follows the general principle of the application and do not invent including the application Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are wanted by right It asks and points out.

It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.

Claims

1. a kind of night scene image processing method characterized by comprising

According to preset exposure compensation mode, multiple image is successively acquired；

Using preset image recognition model, identifying processing is carried out to the default frame image in the multiple image, to determine State the target area and nontarget area in default frame image；

Using different noise reduction parameters values, target area and nontarget area to the multiple image carry out at noise reduction respectively Reason, to generate target image, wherein the corresponding noise reduction parameters value in the target area is greater than the corresponding drop in the nontarget area It makes an uproar parameter value.

2. the method as described in claim 1, which is characterized in that it is described according to preset exposure compensation mode, it successively acquires more Before frame image, further includes:

According to the current degree of jitter of the illuminance of present filming scene and camera module, the preset exposure compensating mould is determined Formula.

3. method according to claim 2, which is characterized in that the illuminance and camera module according to present filming scene Current degree of jitter determines the preset exposure compensation mode, comprising:

According to the sensitivity of every frame image and the target light exposure value of every frame image, when determining the exposure of every frame image It is long.

4. the method as described in claim 1, which is characterized in that the default frame image in the multiple image is known Before the reason of other places, further includes:

5. the method as described in claim 1, which is characterized in that target area in the determination default frame image and non- After target area, further includes:

Emergence processing is carried out to the target area, to determine the transition between the target area and the nontarget area Region；

It is described using different noise reduction parameters values, target area and nontarget area to the multiple image carry out noise reduction respectively Processing, comprising:

Using different noise reduction parameters values, to the target area of the multiple image, transitional region and nontarget area respectively into Row noise reduction process.

6. method a method as claimed in any one of claims 1 to 5, which is characterized in that it is described using different noise reduction parameters values, to described The target area and nontarget area of multiple image are carried out respectively before noise reduction process, further includes:

According to the corresponding weighted value in preset each region and it is described refer to noise reduction parameters, determine the target area and non-target area The current corresponding noise reduction parameters value in domain.

7. method a method as claimed in any one of claims 1 to 5, which is characterized in that the target area in the determination default frame image Domain, comprising:

Using preset image recognition model, identifying processing is carried out to the default frame image in the multiple image, to determine The region for stating brightness exception in default frame image is target area.

8. a kind of night scene image processing unit characterized by comprising

Acquisition module, for successively acquiring multiple image according to preset exposure compensation mode；

Determining module identifies the default frame image in the multiple image for utilizing preset image recognition model Processing, with the target area and nontarget area in the determination default frame image；

Noise reduction module, target area and nontarget area point for using different noise reduction parameters values, to the multiple image Not carry out noise reduction process, to generate target image, wherein the corresponding noise reduction parameters value in the target area is greater than described non-targeted The corresponding noise reduction parameters value in region.

9. a kind of electronic equipment characterized by comprising the photography mould group, memory, processor and storage are on a memory And the computer program that can be run on a processor, when the processor executes the computer program, realize such as claim Night scene image processing method described in any one of 1-7.

10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor Such as night scene image processing method of any of claims 1-7 is realized when execution.