CN110166708A

CN110166708A - Night scene image processing method, device, electronic equipment and storage medium

Info

Publication number: CN110166708A
Application number: CN201910509696.3A
Authority: CN
Inventors: 黄杰文
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2019-06-13
Filing date: 2019-06-13
Publication date: 2019-08-23
Anticipated expiration: 2039-06-13
Also published as: CN110166708B

Abstract

The application proposes a kind of night scene image processing method, device, electronic equipment and storage medium, wherein, method includes: by monitoring the system resource available quantity for carrying out image procossing, if available quantity is lower than threshold value, thumbnail is generated according to a frame image of acquisition, the multiple image of acquisition is synthesized to obtain target image, thumbnail is updated according to target image.This method is according to the system resource available quantity monitored for carrying out image procossing, the frame number of adjustment acquisition image, reduce the system resource available quantity for carrying out image procossing in turn, so as to shorten the total duration of whole shooting process, it is too long to avoid entire shooting process, lead to the technical problem that period of reservation of number is too long, and avoid shooting image during user there is the phenomenon that Caton sense, improve the usage experience of user.

Description

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

Technical field

This application involves technical field of image processing more particularly to a kind of night scene image processing methods, device, electronic equipment And storage medium.

Background technique

With the development of intelligent terminal technology, the use of mobile terminal device (such as smart phone, tablet computer) is more next It is more universal.Most mobile terminal devices are all built-in with camera, and with the enhancing of mobile terminal processing capacity and The performance of the development of camera technology, built-in camera is stronger and stronger, and the quality for shooting image is also higher and higher.Nowadays, it moves Dynamic terminal device is easy to operate and easy to carry, and more and more users use smart phone, plate electricity in daily life The mobile terminal devices such as brain are taken pictures.

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, especially in this special screne of night scene, picture quality is lower.

Currently, usually acquisition multiframe original image is synthesized, it is system resource that there are mobile terminals for image procossing The less situation of available quantity, causes entire shooting process longer, schemes relatively slowly, to affect user experience out.

Summary of the invention

The application is intended to solve at least some of the technical problems in related technologies.

The application proposes a kind of night scene image processing method, device, electronic equipment and storage medium, to realize according to prison The system resource available quantity for carrying out image procossing, the frame number of adjustment acquisition image are surveyed, and then is reduced for carrying out at image The system resource available quantity of reason solves in the prior art so as to shorten the total duration of whole shooting process for carrying out figure When less as the system resource available quantity of processing, entire shooting process is longer, schemes slower technical problem out.

The application first aspect embodiment proposes a kind of night scene image processing method, comprising:

Monitor the system resource available quantity for carrying out image procossing；

If the available quantity is lower than threshold value, thumbnail is generated according to a frame image of acquisition；

The multiple image of acquisition is synthesized to obtain target image；

The thumbnail is updated according to the target image.

The night scene image processing method of the embodiment of the present application, the system resource by monitoring for carrying out image procossing are available Amount generates thumbnail according to a frame image of acquisition, synthesizes to obtain target to the multiple image of acquisition if available quantity is lower than threshold value Image updates thumbnail according to target image.This method is adjusted according to the system resource available quantity monitored for carrying out image procossing The frame number of whole acquisition image, and then reduce the system resource available quantity for carrying out image procossing, so as to shorten whole shooting The total duration of process, avoids that entire shooting process is too long, leads to the technical problem that period of reservation of number is too long, and avoid There is the phenomenon that Caton sense in user during shooting image, improves the usage experience of user.

The application second aspect embodiment proposes a kind of night scene image processing unit, comprising:

Monitoring modular, for monitoring the system resource available quantity for carrying out image procossing；

Generation module generates thumbnail according to a frame image of acquisition if being lower than threshold value for the available quantity；

Synthesis module, for synthesizing to obtain target image to the multiple image of acquisition；

Update module, for updating the thumbnail according to the target image.

The night scene image processing unit of the embodiment of the present application, the system resource by monitoring for carrying out image procossing are available Amount generates thumbnail according to a frame image of acquisition, synthesizes to obtain target to the multiple image of acquisition if available quantity is lower than threshold value Image updates thumbnail according to target image.This method is adjusted according to the system resource available quantity monitored for carrying out image procossing The frame number of whole acquisition image, and then reduce the system resource available quantity for carrying out image procossing, so as to shorten whole shooting The total duration of process, avoids that entire shooting process is too long, leads to the technical problem that period of reservation of number is too long, and avoid There is the phenomenon that Caton sense in user during shooting image, improves the usage experience of user.

The application third aspect embodiment proposes a kind of electronic equipment, including memory, processor and is stored in storage On device and the computer program that can run on a processor, when the processor executes described program, such as above-described embodiment is realized Described in night scene image processing method.

The application fourth aspect embodiment proposes a kind of computer readable storage medium, is stored thereon with computer journey Sequence realizes such as above-mentioned night scene image processing method as described in the examples when the program is executed by processor.

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 the flow diagram of the first night scene image processing method provided by the embodiments of the present application；

Fig. 2 is the flow diagram of second of night scene image processing method provided by the embodiments of the present application；

Fig. 3 is the flow diagram of the third night scene image processing method provided by the embodiments of the present application；

Fig. 4 is the flow diagram of the 4th kind of night scene image processing method provided by the embodiments of the present application；

Fig. 5 is the flow diagram of the 5th kind of night scene image processing method provided by the embodiments of the present application；

Fig. 6 is the flow diagram of the 6th kind of night scene image processing method provided by the embodiments of the present application；

Fig. 7 is a kind of exemplary diagram of night scene image processing method provided by the embodiments of the present application；

Fig. 8 is a kind of structural schematic diagram of night scene image processing unit provided by the embodiments of the present application；

Fig. 9 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application；

Figure 10 is the schematic illustration of a kind of electronic equipment provided by the embodiments of the present application；

Figure 11 is a kind of schematic illustration of image processing circuit provided by the embodiments 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 or element with the same or similar functions.Below with reference to attached The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.

For in the related technology, since the load capacity of electronic equipment is limited, when shooting frame number is more, there are system resources The phenomenon of available quantity deficiency causes to shoot the slower problem of image, and present applicant proposes a kind of night scene image processing methods, pass through The system resource available quantity for carrying out image procossing is monitored, if available quantity is lower than threshold value, is generated according to a frame image of acquisition Thumbnail synthesizes to obtain target image to the multiple image of acquisition, updates thumbnail according to target image.

Below with reference to the accompanying drawings the night scene image processing method, device, electronic equipment and storage of the embodiment of the present application are described Medium.

Fig. 1 is the flow diagram of the first night scene image processing method provided by the embodiments of the present application.

The night scene processing method of the embodiment of the present application, is applied to electronic equipment, which can be mobile phone, plate electricity Brain, personal digital assistant, wearable device etc. have the hardware device of various operating systems, imaging device.

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

Step 101, the system resource available quantity for carrying out image procossing is monitored.

In the embodiment of the present application, monitoring modular can be set in electronic equipment, acquired for real-time monitoring electronic equipment For carrying out the system resource available quantity of image procossing in image process.

As an example, during using electronic equipment acquisition image, monitoring modular real-time monitoring can be passed through The central processing unit (Central Processing Unit/Processor, abbreviation CPU) of electronic equipment, graphics processor (Graphics Processing Unit, abbreviation GPU), digital signal processor (Digital Signal Processing, Abbreviation DSP), the resource availabilities such as neural network processor (Neural network Process Units, abbreviation NPU).Into And according to the system resource available quantity for carrying out image procossing, dynamic adjusts the quantity or letter of night scene acquisition multiple image Change Processing Algorithm, so that user does not wait for process time when shooting night scene under any circumstance, to improve user's bat According to experience.

Step 102, if available quantity is lower than threshold value, thumbnail is generated according to a frame image of acquisition.

Wherein, thumbnail, for the image of the image down that will acquire to preset ratio.

In the embodiment of the present application, when the monitoring module monitors of electronic equipment can to the system resource for carrying out image procossing When dosage is lower than threshold value, the system resource available quantity of image procossing can will be carried out with reduction by adjusting acquisition frame number.

For example, monitoring that CPU usage reaches 90% during the imaging sensor of electronic equipment acquires image When, EV0 can be taken frame number to become 1~3 frame from 3~6 original frames, negative EV takes number of frames to be become by original EV-2 and EV-4 Only to take an EV-3.

As a kind of possible implementation, when user shoots image by operation electronic equipment, in response to the bat of user Operation is taken the photograph, the imaging sensor of electronic equipment acquires multiple image.During imaging sensor acquires multiple image, electronics It, can be from the more of acquisition when the monitoring module monitors of equipment are lower than threshold value to the system resource available quantity for carrying out image procossing In frame image, a frame image is chosen, and then thumbnail is generated according to a frame image of selection.

As alternatively possible implementation, when electronic equipment is detected shooting operation, the monitoring mould of electronic equipment Block monitors that the system resource available quantity for carrying out image procossing in this case can be by the preview of acquisition lower than threshold value Image generates thumbnail as a frame image, and then according to a frame image of acquisition.

It should be noted that the multiple image that the imaging sensor of electronic equipment acquires, is the RAW for not doing any processing Original image, wherein RAW original image is exactly that the light signal captured is converted the original of digital signal by imaging sensor Image.RAW image has recorded the collected raw information of digital camera sensor, while caused by having recorded and being shot as camera Some metadata, such as the setting of sensitivity, shutter speed, f-number, white balance.

In the embodiment of the present application, the monitoring module monitors of electronic equipment are available to the system resource for carrying out image procossing When amount is lower than threshold value, night scene screening-mode can star, to acquire multiple image under different exposures.

Step 103, the multiple image of acquisition is synthesized to obtain target image.

As a kind of possible implementation, high dynamic synthesis can be carried out to the multiple image of acquisition, obtain target figure Picture.Wherein, high dynamic synthesizes, i.e., is synthesized by the picture that same scene difference exposes, to obtain high dynamic range images (High-Dynamic Range, abbreviation HDR).It should be noted that comparing common image, HDR image can be provided more Dynamic range and image detail, according to the low dynamic range echograms of different time for exposure (Low-Dynamic Range, letter Claim LDR), final HDR image is synthesized using the LDR image of corresponding best details of each time for exposure, it can be preferably anti- Mirror the visual effect in true environment.

Specifically, it by extracting the image information in multiple image, and is overlapped for corresponding image information, with To target image.

It should be noted that since multiple image is to shoot to obtain under different exposure status, in multiple image It include the image information of different brightness.It may be overexposure in different images for same scenery, it may be possible to exposure is owed, It is also possible to be appropriate exposure.After carrying out high dynamic synthesis for these images, make each scenery in target image appropriate as far as possible Exposure, it is also more close with actual scene.

Step 104, thumbnail is updated according to target image.

In the embodiment of the present application, the multiple image of imaging sensor acquisition is synthesized after obtaining target image, according to target Image update thumbnail, to be shown.

The night scene image processing method of the embodiment of the present application, the system resource by monitoring for carrying out image procossing are available Amount generates thumbnail according to a frame image of acquisition, synthesizes to obtain target to the multiple image of acquisition if available quantity is lower than threshold value Image updates thumbnail according to target image.This method is adjusted according to the system resource available quantity monitored for carrying out image procossing The frame number of whole acquisition image, and then reduce the system resource available quantity for carrying out image procossing, so as to shorten whole shooting The total duration of process, avoids that entire shooting process is too long, leads to the technical problem that period of reservation of number is too long, improves user Usage experience.

It,, can be according to monitoring when acquiring multiple image in a scenario on the basis of the embodiment described in Fig. 1 For carrying out the system resource available quantity of image procossing, determine exposure compensation mode, and then the base determined according to degree of jitter Quasi- sensitivity, acquisition meets the multiframe night scene image of exposure compensation mode, to obtain the image of Different Dynamic range, so that synthesis Image afterwards has higher dynamic range, improves the overall brightness and quality of image.Referring to fig. 2, Fig. 2 is the embodiment of the present application The flow diagram of second of the night scene image processing method provided, as shown in Fig. 2, specifically includes the following steps:

Step 201, according to available quantity, exposure compensation mode is determined.

Wherein, exposure compensation mode is used to indicate the exposure compensating grade of number of image frames and each frame image.

It should be noted that exposure compensation mode, which refers to, distinguishes preset exposure compensating grade for every frame image to be collected The combination of (Exposure Value, abbreviation EV).In the initial definition of light exposure, light exposure 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 length has determined that the light exposure of camera, different parameter combinations can produce equal light exposure.Exposure compensating grade is pair The parameter that light exposure is adjusted, so that certain images are under-exposure, certain image overexposures, it is also possible that certain images are appropriate Exposure.

For example, if amount of images to be collected be 7 frames, the corresponding EV value range of exposure compensation mode can be [+ 1,+1,+1,+1,0,-3,-6].Wherein, exposure compensation mode is the frame of EV+1, can solve noise problem, is compared by brightness High frame carries out time domain noise reduction, inhibits noise while promoting dark portion details；Exposure compensation mode is the frame of EV-6, can be solved Certainly the problem of bloom overexposure, retain the details of highlight area；Exposure compensation mode is the frame of EV0 and EV-3, then can be used for protecting Bloom is held to the transition between dark space, keeps the effect of preferable light and shade transition.

It should be noted that exposure compensation mode corresponding each EV value is either be specifically arranged according to actual needs, It 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 implemented Example does not limit this.

In a kind of possible way of realization of the embodiment of the present application, the size of aperture can be it is constant, and according to electricity The system resource available quantity for carrying out image procossing that the monitoring module monitors of sub- equipment obtain determines picture frame to be collected After number, the exposure compensation mode being consistent can be determined according to current amount of images to be collected.

Step 202, according to degree of jitter, corresponding benchmark sensitivity is determined.

In the embodiment of the present application, benchmark sensitivity is determined according to degree of jitter, can be the picture according to preview image Face degree of jitter, the setting sensitivity adaptable with current degree of jitter；It is also possible to the image according to acquisition preview image The current degree of jitter of sensor, the setting sensitivity adaptable with current degree of jitter, it is not limited here.Wherein, base The value range of quasi- sensitivity can be 100ISO to 200ISO.

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, ISO value is lower, and the picture quality of acquisition is higher, image Details performance is finer and smoother, and ISO value is higher, and light sensing performance is stronger, also more can receive more light, to generate more Heat more noise therefore would generally be introduced using relatively high sensitivity, so as to cause picture quality reduction.? In the embodiment of the present application, can by acquiring the lower image of multiframe sensitivity simultaneously, and by the multiple image of acquisition synthesize with The mode for generating target image, can not only promote the dynamic range and overall brightness of night scene shooting image, and pass through control The value of sensitivity effectively inhibits the noise in image, improves the quality of night scene shooting image.

It is understood that the sensitivity of acquisition image influences whether whole shooting duration of video, shooting duration of video is too long, may The degree of jitter aggravation of imaging sensor when will lead to hand-held shooting, to influence picture quality.It therefore, can be according to preview graph The float degree of picture can also determine that acquisition is pre- according to the current degree of jitter of imaging sensor of acquisition preview image The corresponding benchmark sensitivity of image of looking at, so that shooting duration of video control is in suitable range.

In the embodiment of the present application, in order to determine degree of jitter, it can be adopted according to the displacement sensor being arranged in electronic equipment Collect displacement information, in turn, according to the displacement information of collected electronic equipment, determine preview image float degree or Acquire the degree of jitter of the imaging sensor of preview image.

As an example, electricity can be determined by obtaining current gyroscope (Gyro-sensor) information of electronic equipment The current degree of jitter of sub- equipment, the i.e. degree of jitter of the imaging sensor of acquisition preview image.

Wherein, gyroscope is called angular-rate sensor, can measure rotational angular velocity when physical quantity deflection, inclination.? In electronic equipment, gyroscope can be very good the movement of measurement rotation, deflection, judge user's so as to Accurate Analysis Actual act.The gyroscope information (gyro information) of electronic equipment may include mobile phone 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 is vertical relation two-by-two.

It should be noted that gyro information that can be current according to electronic equipment, determines that the image of acquisition preview image passes The degree of jitter of sensor.The absolute value of the gyro movement of electronic equipment in three directions is bigger, then acquires the figure of preview image As the degree of jitter of sensor is bigger.Specifically, the absolute value threshold value of gyro movement in three directions can be preset, and according to The sum of the absolute value of the current gyro movement in three directions got, the relationship with preset threshold value determine that acquisition is pre- Look at image imaging sensor current degree of jitter.

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 acquire the image sensing of preview image The degree of jitter of device is " non-jitter "；If A < S < B, it can determine that the degree of jitter of the imaging sensor of acquisition preview image is " slight jitter "；If B < S < C, it can determine that the degree of jitter of the imaging sensor of acquisition preview image is " small shake "；If S > C can then determine that the degree of jitter of the imaging sensor of acquisition preview image is " 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 gyro information and acquires the mapping relations of the imaging sensor degree of jitter of preview image.

Specifically, if the degree of jitter of the imaging sensor of acquisition preview image is smaller, it can be by every frame figure to be collected As corresponding benchmark sensitivity can the appropriate lesser value of boil down to, effectively to inhibit the noise of every frame image, improve shooting figure The quality of picture；It, can be corresponding by every frame image to be collected if the degree of jitter for acquiring the imaging sensor of preview image is larger Benchmark sensitivity can properly increase as biggish value, to shorten shooting duration of video.

For example, however, it is determined that the degree of jitter for acquiring the imaging sensor of preview image is " non-jitter ", then can incite somebody to action Benchmark sensitivity is determined as lesser value, to obtain higher-quality image as far as possible, for example determines that benchmark sensitivity is 100；If Determine acquisition preview image imaging sensor degree of jitter be " slight jitter ", then benchmark sensitivity can be determined as compared with Big value to reduce shooting duration of video, for example determines that benchmark sensitivity is 120；If it is determined that the imaging sensor of acquisition preview image Degree of jitter be " small shake ", then can further increase benchmark sensitivity, to reduce shooting duration of video, for example determine benchmark sense Luminosity is 180；If it is determined that the degree of jitter of the imaging sensor of acquisition preview image is " big shake ", then can determine current Degree of jitter is excessive, can further increase benchmark sensitivity at this time, to reduce shooting duration of video, for example determines that benchmark sensitivity is 200。

It should be noted that the example above is exemplary only, the limitation to the application cannot be considered as.In actual use, When acquiring the variation of the degree of jitter of imaging sensor of preview image, benchmark sensitivity both can change, it is optimal to obtain Scheme.Wherein, the degree of jitter benchmark sensitivity corresponding with every frame image to be collected of the imaging sensor of preview image is acquired Mapping relations, can preset according to actual needs.

In the embodiment of the present application, the shake of the imaging sensor of the float degree and acquisition preview image of preview image Degree correlation sets the realization process of benchmark sensitivity referring to above-mentioned according to the float degree of preview image Process, details are not described herein.

But in the present embodiment, it is not limited to adjust benchmark sensitivity according only to degree of jitter, it can also be according to degree of jitter And the comprehensive determining benchmark sensitivity of the multiple parameters such as luminance information of photographed scene.It is not limited here.

Step 203, according to benchmark sensitivity, acquisition meets the multiframe night scene image of exposure compensation mode.

In the embodiment of the present application, after the benchmark sensitivity and exposure compensation mode for determining multiframe image to be collected, control Electronic equipment acquires the multiframe night scene image for meeting exposure compensation mode according to the benchmark sensitivity of each frame image to be collected, This, which does not do, specifically repeats.

It should be noted that carrying out Image Acquisition when acquiring multiple image based on same benchmark sensitivity, not only helping In the noise for reducing multiple image, it is thus also avoided that since sensitivity increase causes the increased technology of multiple image noise of acquisition to be asked Topic.

The night scene image processing method of the embodiment of the present application, by determining exposure compensation mode according to available quantity, according to trembling Traverse degree determines corresponding benchmark sensitivity, and according to benchmark sensitivity, acquisition meets the multiframe night scene figure of exposure compensation mode Picture.As a result, according to the system resource available quantity for being used to carry out image procossing monitored, exposure compensation mode, Jin Ergen are determined According to the benchmark sensitivity that degree of jitter determines, acquisition meets the multiframe night scene image of exposure compensation mode, not only improves night scene The dynamic range and overall brightness of image are shot under screening-mode, and effectively inhibits the noise in shooting image, are improved Night scene shoots the quality of image, improves user experience.

On the basis of the embodiment described in Fig. 2, as alternatively possible implementation, in the embodiment of the present application, in advance A variety of night scene modes are set, different night scene modes have corresponded to different exposure complementary modulus formulas, are the application implementation referring to Fig. 3, Fig. 3 The flow diagram for the third night scene image processing method that example provides, can specifically include following steps:

Step 301, according to available quantity, number of image frames is adjusted.

In the embodiment of the present application, number of image frames can be adjusted according to the system resource available quantity for carrying out image procossing. Specifically, when available quantity is more, the image compared with multiframe can be acquired；It, can be by reducing acquisition image when available quantity is less Frame number, to reduce the load of system, to improve the speed of Image Acquisition.

Step 302, identify in preview image whether include face.

In the embodiment of the present application, the preview image of available present filming scene, by identification preview image in whether Comprising face, to determine exposure compensation mode.

, whether can be by face recognition technology come really comprising face in preview image as a kind of possible implementation It is fixed.Face recognition technology is to compare face visual signature information by analysis to carry out identity identification, it belongs to living things feature recognition Technology is that organism individual is distinguished to the biological characteristic of organism (generally refering in particular to people) itself.

It should be noted that when detecting in the image that imaging sensor currently acquires comprising face, camera module Survey light can be carried out based on human face region automatically by surveying optical module, and determine benchmark light exposure according to the photometry result of human face region. However, the illuminance of human face region is usually lower in night scene mode, so as to cause determining benchmark light exposure, and do not include Determining benchmark light exposure is compared higher when face, if still acquiring excessive overexposure frame when comprising face, is easy to cause Human face region overexposure, it is poor so as to cause the effect of target image.Therefore, for identical degree of jitter, imaging sensor is In the image of acquisition comprising face compared with when not including face, corresponding exposure compensation mode needs to have lower exposure Compensation range.

Step 303, if comprising face, determine that exposure compensation mode is the first mode of frame number after meeting adjustment.

Step 304, if not including face, determine that exposure compensation mode is the second mode of frame number after meeting adjustment.

Wherein, the exposure compensating grade value range of second mode is greater than the exposure compensating grade value model of first mode It encloses.

In a kind of possible way of realization of the embodiment of the present application, for identical degree of jitter, it can be passed according to image It whether include face in the preview image that sensor currently acquires, using different exposure compensating strategies.Therefore, it is trembled for identical Traverse degree can correspond to multiple exposure compensation modes.The current degree of jitter of imaging sensor is being determined, and according to figure Whether it is consistent comprising after face, that is, can determine that with current actual conditions in the preview image currently acquired as sensor Preset exposure compensation mode.

As an example it is assumed that the current degree of jitter of imaging sensor is " slight jitter ", corresponding preset exposure benefit The mode of repaying has first mode and second mode, wherein the corresponding each EV value of first mode be [0,0,0,0, -2, -4, -6], second The corresponding each EV value of mode is [+1 ,+1 ,+1 ,+1,0, -3, -6], it is seen then that the exposure compensating range of first mode is less than the second mould The exposure compensating range of formula.If detecting in preview image that imaging sensor currently acquires comprising face, it is determined that preset Exposure compensation mode is the first mode of frame number after meeting adjustment, i.e., each EV value is [0,0,0,0, -2, -4, -6]；If detecting It does not include face in the preview image that imaging sensor currently acquires, it is determined that preset exposure compensation mode is after meeting adjustment The second mode of frame number, i.e., each EV value are [+1 ,+1 ,+1 ,+1,0, -3, -6].

The night scene image processing method of the embodiment of the present application identifies preview graph by adjusting number of image frames according to available quantity It whether include face as in, if determining that exposure compensation mode is the first mode of frame number after meeting adjustment, if not wrapping comprising face Containing face, determine that exposure compensation mode is the second mode of frame number after meeting adjustment.It is used to carry out figure according to what is monitored as a result, As the system resource available quantity of processing, the frame number of image to be collected is adjusted, and then by whether including people in identification preview image Face, adjusts the exposure compensation mode of each frame, not only improves the dynamic range for shooting image under night scene screening-mode and entirety is bright Degree, and the noise in shooting image is effectively inhibited, the quality of night scene shooting image is improved, user experience is improved.

Due to the imaging sensor in electronic equipment will receive during shooting it is different degrees of from peripheral circuit Photoelectricity magnetic disturbance between pixel itself, therefore inevitably there is noise in the original image that shooting obtains, also, interfere journey The difference of degree, the clarity of the image shot be not also identical.Therefore the target figure multiple image of acquisition synthesized As also certainly existing noise, need further to carry out noise reduction process to target image.For example, in night scene photographed scene, usually It shoots to obtain image using biggish aperture and longer time for exposure, at this time if selecting higher sensitivity to reduce and expose Between light time, the image shot will necessarily generate noise.

As a kind of possible implementation, can be dropped using the target image that neural network model obtains synthesis Make an uproar processing, can simultaneously in target image highlight area and half-light region carry out noise reduction, and then available preferable drop The target noise-reduced image for effect of making an uproar.It describes in detail below with reference to Fig. 4 to the above process, Fig. 4 provides for the embodiment of the present application The 4th kind of night scene image processing method flow diagram.

As shown in figure 4, this method specifically includes the following steps:

Step 401, using neural network model, noise characteristic identification is carried out to target image.

In the embodiment of the present application, neural network model has learnt to obtain the mapping between benchmark sensitivity and noise characteristic Relationship.

In the embodiment of the present application, noise characteristic can be the statistical property of the random noise due to caused by imaging sensor. Noise said herein mainly includes thermal noise and shot noise, wherein thermal noise meets Gaussian Profile, and shot noise meets Poisson It is distributed, the statistical property in the embodiment of the present application can refer to the variance yields of noise, naturally it is also possible to it is the value of other possible situations, It is not limited here.

As a kind of possible implementation, each sensitivity for being shot under the available brightness to varying environment After sample image, neural network model is trained using the sample image of each sensitivity.It makes an uproar what is marked in sample image Characteristic of the sound characteristics as model training will input neural network model by the sample image of noise characteristic mark, to mind It is trained through network model, and then identifies the noise characteristic of image.Certainly, neural network model is only to realize to be based on people A kind of possible implementation of the noise reduction of work intelligence can pass through any other possible mode in practical implementation The noise reduction based on artificial intelligence is realized, for example, can also be using traditional programming technique (such as simulation and engineering science side Method) it realizes, for another example, it can be realized with genetic algorithm.

Since neural network model has learnt to obtain the mapping relations between benchmark sensitivity and noise characteristic.Therefore, may be used Will pass through in the target image input neural network model of synthesis, to carry out noise to target image using neural network model Characteristic identification, to identify the noise characteristic of target image.

Step 402, according to the noise characteristic identified, to target image noise reduction.

In the embodiment of the present application, the noise characteristic identified according to neural network model carries out noise reduction to target image, obtains To target noise-reduced image, to achieve the purpose that noise reduction, the signal-to-noise ratio of image is improved.

The night scene image processing method of the embodiment of the present application makes an uproar to target image by using neural network model Sound characteristics identification, in turn, according to the noise characteristic identified, to target image noise reduction.Thereby, it is possible to obtain target figure to synthesis Light region and half-light region as in carry out noise reduction, the validity of noise reduction are improved, so that the target noise reduction that noise reduction obtains Image retains image detail while reducing picture noise, obtains the better imaging effect of clarity.

In order to obtain the noise reduction effect of preferable artificial intelligence, neural network model can be selected to carry out noise reduction, and use The sample image of each sensitivity is trained the neural network model, to improve the energy of neural network model identification noise characteristic Power, specific training process referring to Fig. 5, as shown in figure 5, specifically includes the following steps:

Step 501, the sample image of each sensitivity is obtained.

Wherein, the noise characteristic of image has been labelled in sample image.

In the embodiment of the present application, sample image be can be under different ambient brightness, and different sensitivity shootings is arranged Obtained image.That is, ambient brightness should be a variety of, under each ambient brightness, respectively in different sensitivity situations Lower shoot multi-frame images, as sample image.

In order to obtain more preferably accurate noise characteristic recognition result, ambient brightness and ISO can be finely divided, it can be with Increase the frame number of sample image, so that the neural network can accurately be known after the target image input neural network model of synthesis Not Chu image noise characteristic.

Step 502, neural network model is trained using the sample image of each sensitivity.

In the embodiment of the present application, after the sample image for getting each sensitivity shot under varying environment brightness, Neural network model is trained using sample image.Using the noise characteristic marked in sample image as the spy of model training Property, neural network model will be inputted by the sample image of noise characteristic mark, to be trained to neural network model, in turn Identify the noise characteristic of image.Certainly, neural network model is only a kind of possibility for realizing the noise reduction based on artificial intelligence Implementation the drop based on artificial intelligence can be realized by any other possible mode in practical implementation It makes an uproar, for example, can also be realized using traditional programming technique (such as simulation and ergonomic method), for another example, can also lose Pass the method for algorithm and artificial neural network to realize, it is not limited here.

Neural network model is trained it should be noted that marking noise characteristic in sample image, is because The sample image of mark can clearly represent noise position and the noise type of image, so that the noise characteristic of mark be made It can recognize that the noise characteristic in image after target image is inputted neural network model for the characteristic of model training.

Step 503, until the noise marked in noise characteristic and respective sample image that neural network model identifies is special Property matching when, neural network model training complete.

In the embodiment of the present application, neural network model is trained using the sample image of each sensitivity, until nerve The noise characteristic that network model identifies and the statistical property marked in respective sample image match,

In the embodiment of the present application, by obtaining the sample image of each sensitivity, using the sample image of each sensitivity to mind It is trained through network model, until the noise marked in noise characteristic and respective sample image that neural network model identifies When characteristics match, neural network model training is completed.Due to using the sample image under each sensitivity by marking noise characteristic Neural network model is trained, can be realized after image is inputted neural network model, accurately identify making an uproar for image Sound characteristics carry out noise reduction process to image to realize, to improve the shooting quality of image.

On the basis of the embodiment described in Fig. 1, under a kind of possible scene, the multiframe acquired in above-mentioned steps 103 is original It may include the first image of the identical light exposure of at least two frames in image, and extremely lower than the first image including light exposure Few second image of frame further increases into image quality in order to which subsequent middle phase should carry out noise reduction process to the multiple image of acquisition Amount.It describes in detail below with reference to Fig. 6 to the above process, Fig. 6 is at the 6th kind of night scene image provided by the embodiments of the present application The flow diagram of reason method, as shown in fig. 6, step 103 can specifically include:

Step 601, according to available quantity, to the alignment of at least two frame the first image selection piecemeals or global alignment.

It is available in the system resource that the monitoring module monitors of electronic equipment are used to carry out image procossing in the embodiment of the present application It, can be in the case where not adjusting number of image frames to be collected, using simplified image processing algorithm to image when amount is lower than threshold value It is handled.

As a kind of possible implementation, piecemeal alignment or global alignment can be carried out at least two the first images of frame.

It should be noted that can be according to the reference object determination of at least two the first images of frame carry out piecemeal alignment or Global alignment.It is carried out pair for example, shooting image when being mainly personage, can choose the personage region at least two the first images of frame Together.Image alignment method can repeat no more in the present embodiment with reference in the prior art.

Step 602, at least two the first images of frame, multiframe noise reduction is carried out, obtains synthesis noise-reduced image.

Wherein, multiframe noise reduction is exactly multiple image to be acquired by imaging sensor, not under night scene or half-light environment The different pixels with noise property is found under same frame number, it is more clean, pure by obtaining one after weighting synthesis Night scene or half-light photo.

In the embodiment of the present application, electronic equipment when shooting night scene or half-light environment, is adopted by imaging sensor Collect at least two the first images of frame, the noise quantity and position of multiple frame numbers at least two field pictures are calculated and screened, it will There is the frame number replacement position of the place of noise not noise just to obtain a very clean synthesis by weighting, replacing repeatedly Noise-reduced image.As a result, by multiframe noise reduction can by image dark portion treatment of details it is very soft, realizing reduces noise It is more simultaneously to retain image detail.

In the embodiment of the present application, at least two the first figures of frame that shooting obtains can also be judged according to the clarity threshold of image The clarity of picture, so at least two the first images of frame of acquisition carry out screening retain clearly image synthesize.Specifically, When the clarity of the first image is greater than or equal to clarity threshold, then illustrates first image clearly, retains first image, When the clarity of the first image is less than clarity threshold, then illustrates that first image is fuzzy, screen out first image.Into one Step ground, synthesizes clearly the first image of reservation, to obtain synthesis noise-reduced image.

Wherein, clarity threshold is the value determined by the clarity of manual testing's great amount of images, when the clarity of image When greater than the value, then illustrate the image clearly, when image definition is less than the value, then illustrates that the image is fuzzy.

As a kind of possible implementation, by the clarity threshold ratio of at least clarity of two the first images of frame and image Compared with being screened at least two the first images of frame, if the frame number of the first image screened out is not zero, according to screened out The frame number of one image improves noise suppressed degree on the basis of initial noisc inhibition level.

It is understood that when the frame number of the first image screened out is more, in the first image for shooting at this time Fuzzy frame number is more, needs to lose relatively fuzzy image, and the image for carrying out noise reduction at this time tails off, in initial noisc inhibition level On the basis of, noise suppressed degree is improved to make remaining image realize effective noise reduction.The first image screened out as a result, Frame number it is more, on the basis of initial noisc inhibition level, noise suppressed degree improve it is bigger.But it is made an uproar using higher After sound inhibition level is filtered noise reduction process to the first image, the details that image retains is less.

As alternatively possible implementation, by the clarity threshold of at least clarity of two the first images of frame and image Compare, at least two the first images of frame are screened, if the frame number of the first image screened out is zero, illustrates this time to obtain The clarity for shooting obtained at least two the first images of frame is all larger than or is equal to clarity threshold.

In the embodiment of the present application, noise suppressed degree is raised or lowered according to the frame number of the first image screened out, into And according to determining noise suppressed degree, synthesis noise reduction is weighted to the first image of reservation, obtains synthesis noise-reduced image, from And it is effectively reduced the noise of image, retain the information of image to greatest extent.

Step 603, synthesis noise-reduced image is carried out high dynamic at least second image of frame to synthesize, obtains target image.

In the embodiment of the present application, synthesis noise-reduced image is folded at least frame the second image partial image picture area Add, to obtain target image.Such as: if what synthesis noise-reduced image was obtained using the original image multiframe noise reduction of several frame EV0, There may be overexposures for highlight regions for the target image, may be appropriate exposure for middle low brightness area, and this at least one The EV value of the second image of frame is usually negative, thus may be appropriate exposure for highlight regions in second image, middle low-light level Region may be under-exposure.By synthesizing the part for corresponding to the same area in different images according to weight, figure is enabled to As can be realized appropriate exposure in each region, image quality is improved.

It should be noted that due to having significantly reduced the noise of image in synthesis noise-reduced image, to greatest extent Retain the information of image, therefore, includes in the target image after high dynamic synthesizes, obtained being carried out at least second image of frame There are more image informations, it is also more close with actual scene.

In the embodiment of the present application, according to available quantity, to the alignment of at least two frame the first image selection piecemeals or global alignment, into And at least two the first images of frame, multiframe noise reduction is carried out, synthesis noise-reduced image is obtained, by synthesis noise-reduced image and an at least frame Second image carries out high dynamic synthesis, obtains target image.In the target image obtained as a result, it is not only effectively reduced image Noise, to greatest extent retain image information, and improve shooting image quality, improve user experience.

It as an example, is a kind of showing for night scene image processing method provided by the embodiments of the present application referring to Fig. 7, Fig. 7 Example diagram.As shown in Figure 7, after by detecting to preview screen, when determining that photographed scene is night scene scene, image sensing is controlled Device acquires the original image that at least two frame sensitivity values are EV0, the original image of EV-2 and the original image of an EV-4. Wherein, original image is the RAW image without any processing.Noise reduction process is carried out to the original image of at least two frame EV0, is obtained To synthesis noise-reduced image, to improve the signal-to-noise ratio of picture, the original image and an EV- of noise-reduced image and an EV-2 will be synthesized 4 original image carries out high dynamic synthesis, obtains target image.Wherein, target image is similarly RAW format-pattern.Further Ground, the noise reduction process of artificial intelligence is carried out to target image, and the target after noise reduction drops in the target noise-reduced image after obtaining noise reduction Image of making an uproar input ISP processor formats, and the target noise-reduced image of RAW format is converted to yuv format image.Finally The suitable target noise-reduced image of YUV is inputted into jpeg coder, to obtain final JPG image.

It should be noted that on the basis of night scene image processing method described in Fig. 7, it can be according to shooting image mistake Cheng Zhong, the monitoring module monitors of electronic equipment to for carrying out the system resource available quantity of image procossing, adjust to be collected The frame number of original image, alternatively, simplify image processing algorithm so that user shoot under any circumstance night scene do not have it is very long Go out the figure waiting time, improve the quality and speed of shooting image, improve user and take pictures experience.

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

Fig. 8 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 8, the night scene image processing unit 100 includes: monitoring modular 110, generation module 120, synthesis module 130 and update module 140.

Monitoring modular 110, for monitoring the system resource available quantity for carrying out image procossing；

Generation module 120 generates thumbnail according to a frame image of acquisition if being lower than threshold value for available quantity.

Synthesis module 130, for synthesizing to obtain target image to the multiple image of acquisition.

Update module 140, for updating thumbnail according to target image.

As a kind of possible implementation, night scene image processing unit 100, further includes:

Acquisition module, for acquiring multiple image in response to shooting operation.

Processing module, for choosing a frame image from multiple image, alternatively, when will detect shooting operation, acquisition Preview image is as a frame image.

As alternatively possible implementation, acquisition module, further includes:

First determination unit, for determining exposure compensation mode according to available quantity；Wherein, exposure compensation mode, for referring to Show the exposure compensating grade of number of image frames and each frame image.

Second determination unit, for determining corresponding benchmark sensitivity according to degree of jitter.

Acquisition unit, for according to benchmark sensitivity, acquisition to meet the multiframe night scene image of exposure compensation mode.

As alternatively possible implementation, the first determination unit be can be also used for:

According to the available quantity, described image frame number is adjusted；

It whether identifies in the preview image comprising face；

If determining that the exposure compensation mode is the first mode of frame number after meeting adjustment comprising face；

If not including face, determine that the exposure compensation mode is the second mode of frame number after meeting adjustment；

Wherein, the exposure compensating grade value range of the second mode is greater than the exposure compensating grade of the first mode Value range.

As alternatively possible implementation, night scene image processing unit 100, further includes:

Recognition unit carries out noise characteristic identification to target image for using neural network model；Wherein, nerve net Network model has learnt to obtain the mapping relations between benchmark sensitivity and noise characteristic.

Noise reduction unit, for the noise characteristic that basis identifies, to target image noise reduction.

As alternatively possible implementation, neural network model is the sample image using each sensitivity to nerve Network model is trained, until the noise marked in noise characteristic and respective sample image that neural network model identifies is special Property matching when, neural network model training complete.

It include the first image of the identical light exposure of at least two frames as alternatively possible implementation, in multiple image, And it is lower than at least second image of frame for the first image including light exposure；Synthesis module 130, can be also used for:

To at least two the first images of frame, multiframe noise reduction is carried out, obtains synthesis noise-reduced image；By synthesis noise-reduced image and at least One the second image of frame carries out high dynamic synthesis, obtains target image.

As alternatively possible implementation, synthesis module 130 be can be also used for:

According to available quantity, to the alignment of at least two frame the first image selection piecemeals or global alignment.

It should be noted that the aforementioned explanation to night scene image processing method embodiment is also applied for the embodiment Night scene image processing unit, details are not described herein again.

In order to realize above-described embodiment, the application also proposes a kind of electronic equipment, including memory, processor and is stored in On memory and the computer program that can run on a processor, when the processor executes described program, such as above-mentioned reality is realized Apply night scene image processing method described in example.

As an example, the application also proposes a kind of electronic equipment 200, referring to Fig. 9, comprising: imaging sensor 210, Processor 220, memory 230 and it is stored in the computer program that can be run on memory 230 and on processor 220, it is described Imaging sensor 210 is electrically connected with the processor 220, when the processor 220 executes described program, realizes such as above-mentioned implementation Night scene image processing method described in example.

As a kind of possible situation, processor 220 may include: image signal process (Image Signal Processor, abbreviation ISP) processor, the GPU that is connect with ISP processor.

As an example, referring to Fig. 10, on the basis of the electronic equipment described in Fig. 9, implement in Figure 10 for the application The principle exemplary diagram for a kind of electronic equipment that example provides.The memory 230 of electronic equipment 200 include nonvolatile memory 80, Built-in storage 82 and processor 220.Computer-readable instruction is stored in memory 230.Computer-readable instruction is stored by When execution, so that processor 230 executes the night scene image processing method of any of the above-described embodiment.

As shown in Figure 10, which includes the processor 220 connected by system bus 81, non-volatile deposits Reservoir 80, built-in storage 82, display screen 83 and input unit 84.Wherein, the nonvolatile memory 80 of electronic equipment 200 stores There are operating system and computer-readable instruction.The computer-readable instruction can be executed by processor 220, to realize that the application is implemented The exposal control method of mode.The processor 220 supports the fortune of entire electronic equipment 200 for providing calculating and control ability Row.The built-in storage 82 of electronic equipment 200 provides environment for the operation of the computer-readable instruction in nonvolatile memory 80. The display screen 83 of electronic equipment 200 can be liquid crystal display or electric ink display screen etc., and input unit 84 can be aobvious The touch layer covered in display screen 83 is also possible to key, trace ball or the Trackpad being arranged on 200 shell of electronic equipment, can also To be external keyboard, Trackpad or mouse etc..The electronic equipment 200 can be mobile phone, tablet computer, laptop, a Personal digital assistant or wearable device (such as Intelligent bracelet, smartwatch, intelligent helmet, intelligent glasses) etc..Art technology Personnel are appreciated that structure shown in Figure 10, only the schematic diagram of part-structure relevant to application scheme, not structure The restriction for the electronic equipment 200 that pairs of application scheme is applied thereon, specific electronic equipment 200 may include than in figure Shown more or fewer components perhaps combine certain components or with different component layouts.

In order to realize above-described embodiment, the application also proposes a kind of image processing circuit, please refers to Figure 11, and Figure 11 is this Shen Please embodiment provide a kind of image processing circuit schematic illustration, as shown in figure 11, image processing circuit 90 include image Signal processing ISP processor 91 (ISP processor 91 is used as processor 220) and graphics processor GPU.

The image data that camera 93 captures is handled by ISP processor 91 first, and ISP processor 91 carries out image data It analyzes to capture the image statistics for the one or more control parameters that can be used for determining camera 93.Camera module 310 can Including one or more lens 932 and imaging sensor 934.Imaging sensor 934 may include colour filter array (such as Bayer Filter), imaging sensor 934 can obtain the luminous intensity and wavelength information that each imaging pixel captures, and provide and can be handled by ISP One group of raw image data of the processing of device 91.Sensor 94 (such as gyroscope) can be based on 94 interface type of sensor the figure of acquisition As the parameter (such as stabilization parameter) of processing is supplied to ISP processor 91.94 interface of sensor can be SMIA (Standard Mobile Imaging Architecture, Standard Mobile Imager framework) interface, other serial or parallel camera interfaces or The combination of above-mentioned interface.

In addition, raw image data can also be sent to sensor 94 by imaging sensor 934, sensor 94 can be based on sensing Raw image data is supplied to ISP processor 91 or sensor 94 and arrives raw image data storage by 94 interface type of device In video memory 95.

ISP processor 91 handles raw image data pixel by pixel in various formats.For example, each image pixel can have There is the bit depth of 8,10,12 or 14 bits, ISP processor 91 can carry out one or more image procossing behaviour to raw image data Make, statistical information of the collection about image data.Wherein, image processing operations can by identical or different bit depth precision into Row.

ISP processor 91 can also receive image data from video memory 95.For example, 94 interface of sensor is by original image Data are sent to video memory 95, and the raw image data in video memory 95 is available to ISP processor 91 for place Reason.Video memory 95 can be independent in memory 330, a part of memory 330, storage equipment or electronic equipment Private memory, and may include DMA (Direct Memory Access, direct direct memory access (DMA)) feature.

When receiving the original from 934 interface of imaging sensor or from 94 interface of sensor or from video memory 95 When beginning image data, ISP processor 91 can carry out one or more image processing operations, such as time-domain filtering.Treated image Data can be transmitted to video memory 95, to carry out other processing before shown.ISP processor 91 is stored from image Device 95 receives processing data, and carries out at the image data in original domain and in RGB and YCbCr color space to processing data Reason.Treated that image data may be output to display 97 (display 97 may include display screen 83) for ISP processor 91, for Family is watched and/or is further processed by graphics engine or GPU.It is stored in addition, the output of ISP processor 91 also can be transmitted to image Device 95, and display 97 can read image data from video memory 95.In one embodiment, video memory 95 can be matched It is set to the one or more frame buffers of realization.In addition, the output of ISP processor 91 can be transmitted to encoder/decoder 96, so as to Encoding/decoding image data.The image data of coding can be saved, and decompress before being shown in 97 equipment of display. Encoder/decoder 96 can be realized by CPU or GPU or coprocessor.

The statistical data that ISP processor 91 determines, which can be transmitted, gives control logic device Unit 92.For example, statistical data may include The imaging sensors such as automatic exposure, automatic white balance, automatic focusing, flicker detection, black level compensation, 932 shadow correction of lens 934 statistical informations.Control logic device 92 may include the processing element and/or microcontroller for executing one or more routines (such as firmware) Device, one or more routines can statistical data based on the received, determine the control parameter of camera 93 and the control of ISP processor 91 Parameter processed.For example, the control parameter of camera 93 may include 94 control parameter of sensor (such as the integral of gain, spectrum assignment Time, stabilization parameter etc.), camera flash control parameter, 932 control parameter of lens (such as focus or zoom focal length) or The combination of these parameters.ISP control parameter may include for automatic white balance and color adjustment (for example, during RGB processing) 932 shadow correction parameter of gain level and color correction matrix and lens.

The following are realize night scene image processing method with image processing techniques in Figure 11: monitoring is for carrying out figure As the system resource available quantity of processing；If available quantity is lower than threshold value, thumbnail is generated according to a frame image of acquisition；To acquisition Multiple image synthesizes to obtain target image；Thumbnail is updated according to target image.

In order to realize above-described embodiment, the application also proposes a kind of computer readable storage medium, is stored thereon with calculating Machine program realizes such as above-mentioned night scene image processing method as described in the examples when the program is executed by processor.

Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.

It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer In read/write memory medium.

Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of application Type.

Claims

1. a kind of night scene image processing method, which is characterized in that the described method comprises the following steps:

The multiple image of acquisition is synthesized to obtain target image；

The thumbnail is updated according to the target image.

2. night scene image processing method according to claim 1, which is characterized in that described raw according to a frame image of acquisition Before thumbnail, further includes:

In response to shooting operation, the multiple image is acquired；

From the multiple image, the frame image is chosen, alternatively, when will detect the shooting operation, the preview of acquisition Image is as the frame image.

3. night scene image processing method according to claim 2, which is characterized in that the acquisition multiple image, packet It includes:

According to the available quantity, exposure compensation mode is determined；Wherein, the exposure compensation mode, be used to indicate number of image frames and The exposure compensating grade of each frame image；

According to degree of jitter, corresponding benchmark sensitivity is determined；

According to the benchmark sensitivity, acquisition meets the multiframe night scene image of the exposure compensation mode.

4. night scene image processing method according to claim 3, which is characterized in that it is described according to the available quantity, it determines Exposure compensation mode, comprising:

It whether identifies in the preview image comprising face；

Wherein, the exposure compensating grade value range of the second mode is greater than the exposure compensating grade value of the first mode Range.

5. night scene image processing method according to claim 3, which is characterized in that the multiple image synthesis of described pair of acquisition After obtaining target image, further includes:

Using neural network model, noise characteristic identification is carried out to the target image；Wherein, the neural network model, Study obtains the mapping relations between the benchmark sensitivity and noise characteristic；

According to the noise characteristic identified, to the target image noise reduction.

6. night scene image processing method according to claim 5, which is characterized in that the neural network model is to use The sample image of each sensitivity is trained the neural network model, until the noise that the neural network model identifies When the noise characteristic marked in characteristic and respective sample image matches, the neural network model training is completed.

7. night scene image processing method according to claim 1-6, which is characterized in that wrapped in the multiple image The first image of the identical light exposure of at least two frames is included, and is lower than at least second figure of frame for the first image including light exposure Picture；

The multiple image of described pair of acquisition synthesizes to obtain target image, comprising:

To at least two first images of frame, multiframe noise reduction is carried out, obtains synthesis noise-reduced image；

The synthesis noise-reduced image is carried out high dynamic at least second image of frame to synthesize, obtains the target image.

8. night scene image processing method according to claim 7, which is characterized in that described at least two first figures of frame Picture, carry out multiframe noise reduction before, further includes:

According to the available quantity, at least two frame the first image selection piecemeals alignment or global alignment.

9. a kind of night scene image processing unit, which is characterized in that described device includes:

Update module, for updating the thumbnail according to the target image.

10. a kind of electronic equipment, which is characterized in that on a memory and can be in processor including memory, processor and storage The computer program of upper operation when the processor executes described program, realizes such as night scene described in any one of claims 1-8 Image processing method.

11. 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 described in any one of claims 1-8 is realized when execution.