CN110443766A - Image processing method, device, electronic equipment and readable storage medium storing program for executing - Google Patents
Image processing method, device, electronic equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110443766A CN110443766A CN201910720898.2A CN201910720898A CN110443766A CN 110443766 A CN110443766 A CN 110443766A CN 201910720898 A CN201910720898 A CN 201910720898A CN 110443766 A CN110443766 A CN 110443766A
- Authority
- CN
- China
- Prior art keywords
- exposure
- night scene
- image
- scene image
- collected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 27
- 238000011946 reduction process Methods 0.000 claims abstract description 24
- 230000009467 reduction Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000035945 sensitivity Effects 0.000 claims description 9
- 230000001419 dependent effect Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 21
- 230000007812 deficiency Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000288673 Chiroptera Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The embodiment of the present application provides a kind of image processing method, device, electronic equipment and readable storage medium storing program for executing, in view of the overexposure region of image is different from dark areas is crossed under different scenes, first night scene image of frame is obtained first, and using the overexposure region of first night scene image and dark areas is crossed as foundation, it is dynamically determined the exposure and the corresponding frame number to be collected of each exposure of image to be collected, then frame number image to be collected corresponding with the exposure is acquired respectively under determining each exposure, and multiframe noise reduction process is carried out to the frame number image to be collected under each exposure respectively, to avoid causing multiframe noise reduction effect bad because of frame number deficiency, or frame number excessively leads to the case where computing resource waste, improve night scene image shooting effect.
Description
Technical field
This application involves technical field of image processing, in particular to a kind of image processing method based on night scene image
Method, device, electronic equipment and readable storage medium storing program for executing.
Background technique
Camera function is in current mobile electronic device (such as smart phone, tablet computer, intelligent wearable device etc.)
One critical function.Even if the performance of taking pictures of general mobile electronic device can not show a candle to professional slr camera, but by image
Adjustment method combines some technical ability of taking pictures, and still can use mobile electronic device and shoots the photo that effect is pleasantly surprised, in effect of taking pictures
The daily demand of most of user is sufficient on fruit.
Currently, most of electronic product is under daytime or the good situation of weather conditions, imaging effect is not had usually
Too big difference, but under low-light scene (such as night), it is limited to the configuration of electronic product camera, it is difficult to realize preferable
Shooting effect.For example, highlighting photo if necessary under the scene of the insufficient lights such as night, then it is easy to increase image and makes an uproar
Sound causes the image quality of night scene image lower, seriously affects experience of taking pictures.
It is to be carried out using fixed setting frame number to shooting image mostly although presently, there are many Image denoising algorithms
Multiframe noise reduction process.However, these are fixed setting frame number and may be unable to reach since frame number is insufficient when noise level is stronger
Preferably denoising effect, or when noise level is lower, these fix setting frame number may be more than actually required, on the one hand
Computing resource can be wasted, on the other hand it is also possible that obtaining noise-reduced image becomes fuzzyyer.
Summary of the invention
In view of this, the application's is designed to provide a kind of image processing method, device, electronic equipment and readable storage
Medium can determine exposure and the corresponding frame number to be collected of each exposure for different scene dynamics, to avoid because
Frame number deficiency causes multiframe noise reduction effect bad or the case where frame number excessively leads to computing resource waste, improves night scene image
Shooting effect.
According to the one side of the application, a kind of image processing method is provided, is applied to electronic equipment, which comprises
First night scene image of frame is obtained, and according to the overexposure region of first night scene image and crosses dark areas, is determined
The exposure of image to be collected and the corresponding frame number to be collected of each exposure;
According to the exposure of the image to be collected and the corresponding frame number to be collected of each exposure, in each exposure
The second night scene image of lower acquisition multiframe;
Multiframe noise reduction process is carried out to each exposure the second night scene image of corresponding multiframe respectively, obtains each exposure
Corresponding third night scene image;
Image procossing is carried out to the corresponding third night scene image of each exposure, obtains target night scene image.
According to the another aspect of the application, a kind of image processing apparatus is also provided, is applied to electronic equipment, described device packet
It includes:
Determining module is obtained, for obtaining first night scene image of frame, and according to the overexposure area of first night scene image
Domain and excessively dark areas, determine the exposure of image to be collected and the corresponding frame number to be collected of each exposure;
Image collection module, for corresponding to be collected according to the exposure of the image to be collected and each exposure
Frame number obtains the second night scene image of multiframe under each exposure;
Noise reduction process module, for being carried out at multiframe noise reduction to each exposure the second night scene image of corresponding multiframe respectively
Reason, obtains the corresponding third night scene image of each exposure;
Image processing module is obtained for carrying out image procossing to the corresponding third night scene image of each exposure
Target night scene image.
According to the another aspect of the application, also offer a kind of electronic equipment, the electronic equipment includes machine readable storage
Medium and processor, the machine readable storage medium are stored with machine-executable instruction, and the processor is executing the machine
When device executable instruction, which realizes image processing method above-mentioned.
According to the another aspect of the application, a kind of readable storage medium storing program for executing is also provided, is stored in the readable storage medium storing program for executing
Machine-executable instruction, the machine-executable instruction, which is performed, realizes image processing method above-mentioned.
Based on any of the above-described aspect, the application considers the overexposure region of image under different scenes and crosses dark areas not
Together, first night scene image of frame is obtained first, and using the overexposure region of first night scene image and crosses dark areas as foundation, dynamically
The exposure and the corresponding frame number to be collected of each exposure for determining image to be collected, then under determining each exposure
Acquire corresponding with exposure frame number image to be collected respectively, and respectively to the frame number image to be collected under each exposure into
Row multiframe noise reduction process, to avoid causing multiframe noise reduction effect bad because of frame number deficiency or frame number excessively causes to calculate and provides
The case where source wastes improves night scene image shooting effect.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows one of the flow diagram of image processing method provided by the embodiment of the present application;
Fig. 2 shows the sub-process schematic diagrames of step S110 in a kind of embodiment shown in Fig. 1;
Fig. 3 shows a kind of acquisition order schematic diagram of the second night scene image provided by example;
Fig. 4 shows the sub-process schematic diagram of step S140 in a kind of embodiment shown in Fig. 1;
Fig. 5 shows the control of the characteristic point the selection result of the embodiment of the present application and the characteristic point the selection result of common approach
Schematic diagram;
Fig. 6 shows the two of the flow diagram of image processing method provided by the embodiment of the present application;
Fig. 7 shows the functional block diagram of image processing apparatus provided by the embodiment of the present application;
Fig. 8 is shown provided by the embodiment of the present application for realizing the structure of the electronic equipment of above-mentioned image processing method
Schematic block diagram.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it should be understood that attached drawing in the application
The purpose of illustration and description is only played, is not used to limit the protection scope of the application.In addition, it will be appreciated that schematical attached
Figure does not press scale.Process used herein shows real according to some embodiments of the embodiment of the present application
Existing operation.It should be understood that the operation of flow chart can be realized out of order, the step of context relation of logic can be with
Reversal order is implemented simultaneously.In addition, those skilled in the art under the guide of teachings herein, can add to flow chart
One or more of the other operation can also remove one or more operations from flow chart.
In addition, described embodiments are only a part of embodiments of the present application, instead of all the embodiments.Usually exist
The component of the embodiment of the present application described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed the application's to the detailed description of the embodiments herein provided in the accompanying drawings below
Range, but it is merely representative of the selected embodiment of the application.Based on embodiments herein, those skilled in the art are not being done
All other embodiment obtained under the premise of creative work out, shall fall in the protection scope of this application.
Fig. 1 shows the flow diagram of image processing method provided by the embodiments of the present application.It should be appreciated that in other realities
It applies in example, the sequence of the image processing method part step of the present embodiment can be exchanged with each other according to actual needs, or
Part steps therein also can be omitted or delete.The detailed step of the image processing method is described below.
Step S110 obtains first night scene image of frame, and according to the overexposure region of the first night scene image and crosses dark areas,
Determine the exposure and the corresponding frame number to be collected of each exposure of image to be collected.
In the present embodiment, which can be the pre-stored night scene image shot in the past, can be with
It is the night scene image that the shooting of current night scene is obtained, the present embodiment is not specifically limited this.
Step S120, according to the exposure of image to be collected and the corresponding frame number to be collected of each exposure, each
The second night scene image of multiframe is obtained under exposure.
Step S130 carries out multiframe noise reduction process to each exposure the second night scene image of corresponding multiframe respectively, obtains
The corresponding third night scene image of each exposure.
Step S140 carries out image procossing to the corresponding third night scene image of each exposure, obtains target night scene image.
Compared to the prior art in such a way that fixed setting frame number carries out multiframe noise reduction to shooting image, the present embodiment is examined
It is different from dark areas is crossed to consider under different scenes the overexposure region of image, obtains first night scene image of frame, and first with this
The overexposure region of first night scene image is foundation with dark areas is crossed, and is dynamically determined the exposure and each exposure of image to be collected
Corresponding frame number to be collected is spent, then acquires frame number to be collected corresponding with the exposure respectively under determining each exposure
Image, and multiframe noise reduction process is carried out to the frame number image to be collected under each exposure respectively, to avoid because of frame number deficiency
Cause multiframe noise reduction effect bad or the case where frame number excessively leads to computing resource waste, improves night scene image shooting effect.
In a kind of possible embodiment, for step S110, Fig. 2 is please referred to, can specifically pass through following son
Step realizes that S111-S114 is realized, is described in detail below.
Sub-step S111 identifies overexposure region from the first night scene image and crosses dark areas.
As an example, the grey level histogram of the first night scene image available first.That is, by the first colored night scene
Image is converted to the night scene image of grayscale format, to remove the colouring information of first night scene image, indicates for the first night with gray scale
The luminance information of scape image.Each pixel occupies 3 bytes in the first colored night scene image, and is converted into the first night of gray scale
After scape image, each pixel occupies a byte, and the pixel that the gray value of each pixel can characterize in the first night scene image is bright
Degree.
Then, according to the gray value of pixel each in grey level histogram, gray value is greater than to the picture of the first gray threshold
Vegetarian refreshments is determined as the first pixel, and gray value is determined as the second pixel less than the pixel of the second gray threshold.For example, can
It is determined as the first pixel with the pixel by gray value greater than 230, the pixel by gray value less than 25 is determined as the second picture
Vegetarian refreshments.On this basis, the region including all first pixels can be determined as to overexposure region, and will include all second
The region of pixel was determined as dark areas.
Sub-step S112 calculates first ratio and excessively dark areas of the overexposure region in the first night scene image at the first night
The second ratio in scape image.
Sub-step S113, according to the exposure of the first ratio and the second ratio-dependent image to be collected.
For example, the exposure of image to be collected may include the first night scene image as a kind of alternative embodiment
First exposure, next then according to other exposures of the first ratio and the second ratio-dependent image to be collected.
In detail, if the first ratio is less than the first setting value, and the second ratio is less than the second setting value, it is determined that be collected
The exposure of image is the first exposure of the first night scene image.
If the first ratio is greater than third setting value, according to the first exposure and the difference of the first ratio and third setting value
It determines the second exposure, and determines that the exposure of image to be collected further includes the second exposure.For example, first can be preset
The corresponding coefficient of the difference of ratio and third setting value, then using the product of the coefficient and the first exposure as the second exposure.
If the second ratio is greater than the 4th setting value, according to the first exposure and the difference of the second ratio and the 4th setting value
It determines third exposure, and determines that the exposure of image to be collected further includes third exposure.For example, second can be preset
The corresponding coefficient of the difference of ratio and the 4th setting value, then using the product of the coefficient and the first exposure as third exposure.
In this way, if crossing, dark areas is too many, and the subsequent available higher picture frame of brightness is merged, if overexposure region is too
More, subsequent available slightly dark picture frame restores the image information of overexposure region.
Sub-step S114, according to the sensitivity of the first night scene image and each exposure of determination according to preset frame number
Corresponding relationship determines the corresponding frame number to be collected of each exposure.
In detail, after the exposure for determining image to be collected, it may further determine that each exposure is corresponding wait adopt
Collect frame number.For example, frame number corresponding relationship can be preset, which may include different exposures under each sensitivity
The corresponding frame number of degree, i.e. each frame number to be collected are corresponding with a sensitivity and an exposure.Thus, it is possible to according to
The sensitivity of first night scene image searches the corresponding frame number of difference exposure under the sensitivity, then further according to determining each exposure
Luminosity determines its corresponding frame number to be collected.
In this way, it is possible to prevente effectively from subsequent because frame number deficiency causes multiframe noise reduction effect bad or frame number excessively causes
The case where computing resource waste.
After the exposure for determining image to be collected and the corresponding frame number to be collected of each exposure, next need every
The second night scene image of multiframe is obtained under a exposure.It is found in the course of the research through present inventor, if successively according to not
Sequence with exposure acquires corresponding the second night scene image of multiframe respectively, will lead in the subsequent multiframe under each exposure
When second night scene image carries out multiframe noise reduction, since every adjacent two frame can have slight deviations in picture material, to make
There is ghost in image after obtaining multiframe noise reduction or image obscures the case where distorting.
Based on this, in a kind of possible embodiment, for step S120, it is assumed that the exposure packet of the image to be collected
The first exposure of the first night scene image, the second exposure less than the first exposure and the third greater than the first exposure is included to expose
Luminosity, then acquiring multiframe second first under the first exposure when obtaining the second night scene image of multiframe under each exposure
Then night scene image acquires second night scene image of frame under the second exposure, second night of frame is acquired under third exposure
Scape image.Later, remaining the second night scene image of every frame is acquired under the second exposure, and residue is acquired under third exposure
The second night scene image of every frame, to obtain corresponding the second night scene image of multiframe of each exposure.
For example, it is assumed that the first exposure of the first night scene image is EV0, the second exposure less than the first exposure is
EV-2, greater than the first exposure third exposure be EV+3.The corresponding frame number to be collected of EV0, EV-2 and EV+3 is respectively 3,
5,4, then please referring to Fig. 3,3 the second night scene images of frame are acquired at EV0 first, 1 frame second is then acquired at EV-2
Night scene image acquires 1 the second night scene image of frame at EV+3.Later, 4 second night scene images are acquired at EV-2, in EV+3
3 the second night scene images of frame of lower acquisition are the second night scene image of EV0,5 exposed frame degree for the of EV-2 to obtain 3 exposed frame degree
The second night scene image that two night scene images and 4 exposed frame degree are EV+3, finally obtains 12 the second night scene images of frame.
Using the above scheme, due to the second night scene image of every adjacent two frame can exist in picture material it is subtle inclined
Difference can first acquire a frame the so after having acquired the second night scene image under the first exposure under the second exposure respectively
Two night scene images and second night scene image of frame is acquired under third exposure, this make it is subsequent when carrying out multiframe denoising,
The reference frame of two exposures and the reference frame of third exposure and the reference frame of the first exposure are more nearly, and are facilitated subsequent
Image alignment, so that the image being effectively improved after multiframe noise reduction ghost occurs or image obscures the case where distorting.
Further, through present inventor the study found that above-mentioned the second exposure and third exposure are according to the
The overexposure region of one night scene image and the exposure that dark areas is dynamically determined is crossed, but subsequent is perhaps obtained under some exposure
Second night scene image promotes dynamic range later and helps there is no too many, if for corresponding under determining each exposure
The second night scene image of multiframe all carry out multiframe noise reduction process, extra calculation amount may be will increase, cause whole night scene image
The time of shooting process extends, and reduces shooting experience.
Based on this, in a kind of possible embodiment, the present embodiment, can be with needle before carrying out multiframe noise reduction process
To each exposure, the overexposure region of corresponding the second night scene image of first frame of the exposure is judged respectively and whether crosses dark areas
Meet preset condition.For example, the preset condition may include: the overexposure region and dark areas excessively of second night scene image of first frame
It is less than presetted pixel with the area pixel point difference value for crossing dark areas with the overexposure region of second night scene image of first frame respectively
Point threshold value.
It is if second night scene image of first frame is unsatisfactory for preset condition, the second night scene image of multiframe under exposure is true
It is set to multiframe noise reduction and removes image, stops carrying out multiframe noise reduction process to the exposure the second night scene image of corresponding multiframe.
Next, step S130 is directed to, in a kind of possible embodiment, for each exposure, in the exposure
Lower the second night scene image of first frame acquired of degree is benchmark frame, and remaining second night scene image is aligned the reference frame, then will
Each remaining second night scene image and the reference frame after alignment carry out image co-registration processing, obtain the corresponding third of the exposure
Night scene image.In this way, carrying out multiframe denoising again by first carrying out image alignment, the image after being effectively improved multiframe noise reduction goes out
The case where existing ghost or image obscure distortion.
For step S140, after by above-mentioned multiframe noise reduction process, the preferably different exposures of image quality are obtained
Next corresponding third night scene image needs to carry out HDR (High- using these corresponding third night scene figures of difference exposure
Dynamic Range, high dynamic range images) fusion, to improve the dynamic range of night scene image, that is, dark areas was highlighted, and
And restore the image detail of overly bright region.However, may be due to the other factors such as hand shaking, each frame third during actual photographed
Picture material between night scene image will necessarily have certain difference, so if directly corresponding to these different exposures
Third night scene figure carries out HDR fusion, and may result in the target night scene image that ultimately generates, there are ghost or scallopings
Situation.
Fig. 4 is please referred in a kind of possible embodiment based on this, step S140 can pass through following son
Step S141 and S142 are realized, are described in detail below.
Sub-step S141 carries out feature point alignment to the corresponding third night scene image of every two exposure respectively, obtains pair
Corresponding 4th night scene image of each exposure after neat.
Sub-step S142 is closed by high dynamic range images algorithm the 4th night scene image corresponding to each exposure
At obtaining target night scene image.
In the present embodiment, before carrying out HDR fusion to these corresponding third night scene images of difference exposure, Ke Yifen
It is other that feature point alignment is carried out to the corresponding third night scene image of every two exposure, to improve the target night scene image ultimately generated
The case where there are ghost or scallopings.Third night scene image due to needing exist for alignment is different exposures,
The scheme of traditional light stream alignment is not able to satisfy the image alignment demand of this programme, inventor prove after study by using
The scheme being aligned after Feature Points Matching effectively can carry out image alignment for the third night scene image of different exposures.
In a kind of alternative embodiment, characteristic point is being carried out to the corresponding third night scene image of every two exposure
Before alignment, in order to increase the probability of characteristic point successful match, the present embodiment can also be for every two exposure corresponding the
Three night scene images, by histogram specification algorithm by two third night scene images, the higher third night scene image of brightness
Brightness be reduced to the brightness of the lower third night scene image of brightness.It so, it is possible to reduce the two third nights for needing to be aligned
Luminance difference between scape image, to increase the probability of characteristic point successful match.
In a kind of alternative embodiment, for sub-step S141, inventor further study show that, in certain bats
It takes the photograph in scene, the feature dot density that may have some region is larger, the more sparse situation of remaining characteristic point, and is carrying out
When feature point alignment, the dense region of characteristic point (such as dense region of trees in photographed scene) usually can be all paid the utmost attention to,
Image alignment effect so as to cause above-mentioned third night scene image in the dense region of characteristic point is preferable, but the figure in other regions
As alignment effect is very poor.
For example, please refer to Fig. 5, if from being taken out in some third night scene image before wherein confidence level sequence is highest
X characteristic point, if do not imposed any restrictions to characteristic point, before confidence level comes in distribution meeting Fig. 5 of the characteristic point of X
Left figure, characteristic point may all concentrate on the more apparent region (upper left corner area) of some features mostly, so inevitably result in
It the third night scene image and the Feature Points Matching of other third night scene images and is aligned and all concentrates on image upper left corner area, finally
The alignment effect that the upper left corner area of the third night scene image occurs in maximum probability is fine, and the alignment effect in other regions is very poor
The case where situation, there are ghosts or distortion so as to cause the target night scene image being subsequently generated.
Based on this, in a kind of possible embodiment, the present embodiment can be directed to every two exposure corresponding third night
The two frames third night scene image is divided into multiple images region, then extracts the two frames third night scene image respectively by scape image
Each image-region each characteristic point, and calculate each characteristic point of each image-region of the two frames third night scene image
Confidence level.Then, according to calculated result, confidence level in each image-region of the two frames third night scene image is met into setting
The characteristic point of condition is determined as target feature point, to determine each target feature point in the two frames third night scene image.Finally,
Feature point alignment is carried out to the two frames third night scene image according to each target feature point in the two frames third night scene image, is obtained
The 4th night scene image of two frames after to alignment.
Wherein, the setting condition may include: characteristic point confidence level the image-region each characteristic point confidence
It spends and is located at preceding N in descending sequence, N is positive integer.
For example, it is directed to third night scene image A and third night scene image B, it can be with third night scene image A and third night scene figure
As B be divided into image-region 1, image-region 2, image-region 3 ..., image-region Y.Then, third night scene is extracted respectively
The image-region 1 of image A and third night scene image B, image-region 2, image-region 3 ..., each spy of image-region Y
Point is levied, and calculates the confidence level of each characteristic point.Then, by image-region 1, image-region 2, image-region 3 ... image
The characteristic point that confidence level size comes preceding 5 in the Y of region is determined as target feature point, so that it is determined that third night scene image A and third
Each target feature point in night scene image B, and characteristic point pair is carried out to third night scene image A and third night scene image B with this
Together, third night scene image A and third night scene image B after being aligned.
Still by taking Fig. 5 as an example, the distribution of the target feature point obtained after adopting the above scheme is as shown on the right, can see
Out, the present embodiment is when carrying out feature point alignment to the corresponding third night scene image of every two exposure, by carrying out multiple figures
As region characteristic point screen so that the target feature point screened be distributed on third night scene image it is more uniform, thus
The image alignment effect of whole third night scene image of overall thinking, to further improve the target night scene figure being subsequently generated
As the case where there are ghost or distortions.
Further, in a kind of possible embodiment, for above-mentioned sub-step S142, inventor's research be also found,
During being synthesized by high dynamic range images algorithm the 4th night scene image corresponding to each exposure, for skill
The brightness value of the image pixel of each 4th night scene image is often drawn close toward intermediate region, avoids the dark of image by art principle
Located black or bright place overexposure, the target night scene image contrast caused in this way is lower, and picture quality is bad.
Based on this, further referring to Fig. 6, image processing method provided in this embodiment can also include step S150,
It is described in detail below.
Step S150 is enhanced using contrast of the Auto Laves algorithm to target night scene image, is obtained enhanced
Target night scene image.
In this way, the present embodiment considers the caused target night scene image pair when carrying out the synthesis of high dynamic range images algorithm
The situation more lower than degree enhances by using contrast of the Auto Laves algorithm to target night scene image, can significantly mention
The visual effect of high target night scene image.
Fig. 7 shows the functional block diagram of image processing apparatus 200 provided by the embodiments of the present application, and the present embodiment can
The division of functional module is carried out to the image processing apparatus 200 according to above method embodiment.For example, each function can be corresponded to
Each functional module can be divided, two or more functions can also be integrated in a processing module.It is above-mentioned integrated
Module both can take the form of hardware realization, can also be realized in the form of software function module.It should be noted that
It is schematically that only a kind of logical function partition can have other in actual implementation to the division of module in the application
Division mode.For example, cluster resource pipe in the case where each function division of use correspondence each functional module, shown in Fig. 7
Managing device is a kind of schematic device.Wherein, image processing apparatus 200 may include obtaining determining module 210, image to obtain
Modulus block 220, noise reduction process module 230 and image processing module 240, separately below to each of the image processing apparatus 200
The function of a functional module is described in detail.
Determining module 210 is obtained, for obtaining first night scene image of frame, and according to the overexposure region of the first night scene image
With dark areas excessively, the exposure of image to be collected and the corresponding frame number to be collected of each exposure are determined.It is appreciated that this is obtained
Determining module 210 is taken to can be used for executing above-mentioned steps S110, the detailed implementation about the acquisition determining module 210 can be with
Referring to above-mentioned to the related content of step S110.
Image collection module 220, for corresponding to be collected according to the exposure of image to be collected and each exposure
Frame number obtains the second night scene image of multiframe under each exposure.It is appreciated that the image collection module 220 can be used for holding
Row above-mentioned steps S120, the detailed implementation about the image collection module 220 are referred to above-mentioned related to step S120
Content.
Noise reduction process module 230, for carrying out multiframe drop to each exposure the second night scene image of corresponding multiframe respectively
It makes an uproar processing, obtains the corresponding third night scene image of each exposure.It is appreciated that the noise reduction process module 230 can be used for holding
Row above-mentioned steps S130, the detailed implementation about the noise reduction process module 230 are referred to above-mentioned related to step S130
Content.
Image processing module 240 obtains mesh for carrying out image procossing to the corresponding third night scene image of each exposure
Mark night scene image.It is appreciated that the image processing module 2400 can be used for executing above-mentioned steps S140, about the image procossing
The detailed implementation of module 240 is referred to above-mentioned to the related content of step S140.
In a kind of possible embodiment, acquisition determining module 210 can specifically be determined as follows to be collected
The exposure of image and the corresponding frame number to be collected of each exposure:
Overexposure region is identified from the first night scene image and crosses dark areas;
First ratio and excessively dark areas of the overexposure region in the first night scene image are calculated in the first night scene image
Second ratio;
According to the exposure of the first ratio and the second ratio-dependent image to be collected;
According to the sensitivity of the first night scene image and each exposure of determination according to preset frame number corresponding relationship, really
Determine the corresponding frame number to be collected of each exposure, wherein each frame number to be collected and a sensitivity and an exposure
It is corresponding.
In a kind of possible embodiment, obtaining determining module 210 specifically can be in the following way from the first night scene
Overexposure region is identified in image and crosses dark areas:
Obtain the grey level histogram of the first night scene image;
According to the gray value of pixel each in grey level histogram, the pixel that gray value is greater than the first gray threshold is true
It is set to the first pixel, gray value is determined as the second pixel less than the pixel of the second gray threshold;
It will include that the regions of all first pixels is determined as overexposure region, and by the region including all second pixels
It was determined as dark areas.
In a kind of possible embodiment, the exposure of image to be collected includes the first exposure of the first night scene image
Degree, in a kind of possible embodiment, image to be collected can be specifically determined as follows by obtaining determining module 210
Exposure:
If the first ratio is less than the first setting value, and the second ratio is less than the second setting value, it is determined that image to be collected
Exposure is the first exposure of the first night scene image;
If the first ratio is greater than third setting value, according to the first exposure and the difference of the first ratio and third setting value
It determines the second exposure, and determines that the exposure of image to be collected further includes the second exposure;
If the second ratio is greater than the 4th setting value, according to the first exposure and the difference of the second ratio and the 4th setting value
It determines third exposure, and determines that the exposure of image to be collected further includes third exposure.
In a kind of possible embodiment, the exposure of image to be collected includes the first exposure of the first night scene image
Degree, the second exposure less than the first exposure and the third exposure greater than the first exposure, image collection module 220 are specific
The second night scene image of multiframe can be obtained under each exposure in the following way:
The second night scene image of multiframe is acquired under the first exposure;
Second night scene image of frame is acquired under the second exposure;
Second night scene image of frame is acquired under third exposure;
Remaining the second night scene image of every frame is acquired under the second exposure;
Remaining the second night scene image of every frame is acquired, under third exposure to obtain the corresponding multiframe of each exposure
Two night scene images.
In a kind of possible embodiment, image processing apparatus 200 can be used for image remove module:
For each exposure, judges the overexposure region of corresponding the second night scene image of first frame of the exposure and cross dark space
Whether domain meets preset condition;
It is if second night scene image of first frame is unsatisfactory for preset condition, the second night scene image of multiframe under exposure is true
It is set to multiframe noise reduction and removes image, stops carrying out multiframe noise reduction process to the exposure the second night scene image of corresponding multiframe;
Wherein, preset condition include: the overexposure region of second night scene image of first frame and cross dark areas respectively with this
The overexposure region of one the second night scene image of frame and the area pixel point difference value for crossing dark areas are less than presetted pixel point threshold value.
In a kind of possible embodiment, noise reduction process module 230 specifically can be in the following way respectively to each
Corresponding the second night scene image of multiframe of exposure carries out multiframe noise reduction process, obtains the corresponding third night scene figure of each exposure
Picture:
It will be remaining using the second night scene image of first frame acquired under the exposure as benchmark frame for each exposure
The second night scene image be aligned the reference frame;
Each remaining second night scene image after alignment is subjected to image co-registration processing with the reference frame, obtains the exposure
Corresponding third night scene image.
In a kind of possible embodiment, image processing module 240 specifically can be in the following way to each exposure
It spends corresponding third night scene image and carries out image procossing, obtain target night scene image:
Feature point alignment is carried out to the corresponding third night scene image of every two exposure respectively, each exposure after being aligned
Corresponding 4th night scene image of luminosity;
It is synthesized by high dynamic range images algorithm the 4th night scene image corresponding to each exposure, obtains target
Night scene image.
In a kind of possible embodiment, image processing module 240 specifically can be in the following way respectively to every two
The corresponding third night scene image of a exposure carries out feature point alignment, corresponding 4th night scene of each exposure after being aligned
Image:
For the corresponding third night scene image of every two exposure, which is divided into multiple images
Region;
Each characteristic point of each image-region of the two frames third night scene image is extracted respectively;
Calculate the confidence level of each characteristic point of each image-region of the two frames third night scene image;
According to calculated result, confidence level in each image-region of the two frames third night scene image is met into setting condition
Characteristic point is determined as target feature point, to determine each target feature point in the two frames third night scene image;
Feature is carried out to the two frames third night scene image according to each target feature point in the two frames third night scene image
Point alignment, the 4th night scene image of two frames after being aligned;
Wherein, setting condition include: characteristic point confidence level the image-region each characteristic point confidence level by big
It is located at preceding N into small sequence, N is positive integer.
In a kind of possible embodiment, image processing module 240 can also be further directed to every two exposure pair
The third night scene image answered, by histogram specification algorithm by two third night scene images, brightness higher third night
The brightness of scape image is reduced to the brightness of the lower third night scene image of brightness.
In a kind of possible embodiment, image processing module 240 can also further use Auto Laves algorithm pair
The contrast of target night scene image is enhanced, and enhanced target night scene image is obtained.
Further, referring to Fig. 8, showing the structural schematic block diagram of electronic equipment 100 provided by the embodiments of the present application,
The electronic equipment 100 may include machine readable storage medium 120 and processor 130.
Wherein, processor 130 can be a general central processing unit (Central Processing Unit,
CPU), microprocessor, application-specific integrated circuit (Application-Specific Integrated Circuit,
ASIC), or it is one or more for controlling the integrated electricity of the program execution of the image processing method of following methods embodiment offer
Road.
Machine readable storage medium 120 can be ROM or can store static information and the other types of static state of instruction is deposited
Equipment, RAM or the other types of dynamic memory that information and instruction can be stored are stored up, is also possible to electric erazable programmable only
Read memory (Electrically Erasable Programmabler-Only MEMory, EEPROM), CD-ROM
(Compactdisc Read-Only MEMory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, swash
Optical disc, optical disc, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can use
In carry or storage have instruction or data structure form desired program code and can by computer access it is any its
Its medium, but not limited to this.Machine readable storage medium 120, which can be, to be individually present, and communication bus and 130 phase of processor are passed through
Connection.Machine readable storage medium 120 can also be integrated with processor.Wherein, machine readable storage medium 120 is used
The machine-executable instruction of application scheme is executed in storage.Processor 130 is for executing in machine readable storage medium 120
The machine-executable instruction of storage, to realize embodiment of the method above-mentioned.
Since electronic equipment 100 provided by the embodiments of the present application is the image processing method that embodiment of the method above-mentioned provides
Another way of realization, and electronic equipment 100 can be used for executing the image processing method that embodiment of the method above-mentioned provides
Another way of realization, therefore it can be obtained technical effect can refer to above method embodiment, details are not described herein.
The embodiment of the present application also provides a kind of readable storage medium storing program for executing comprising computer executable instructions, and computer is executable
Instruction can be used for executing when executed the relevant operation in the image processing method that embodiment of the method above-mentioned provides.
The embodiment of the present application is referring to the flow chart according to the method for the embodiment of the present application, equipment and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
Although the application is described in conjunction with each embodiment herein, however, implementing the application claimed
In the process, those skilled in the art are by checking the attached drawing, disclosure and the appended claims, it will be appreciated that and it is real
Other variations of the existing open embodiment.In the claims, one word of " comprising " is not excluded for other component parts or step,
"a" or "an" is not excluded for multiple situations.Single processor or other units may be implemented to enumerate in claim several
Item function.Mutually different has been recited in mutually different dependent certain measures, it is not intended that these measures cannot group close
To generate good effect.
The above, the only various embodiments of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (14)
1. a kind of image processing method, which is characterized in that be applied to electronic equipment, which comprises
First night scene image of frame is obtained, and according to the overexposure region of first night scene image and crosses dark areas, is determined wait adopt
Collect the exposure and the corresponding frame number to be collected of each exposure of image;
According to the exposure of the image to be collected and the corresponding frame number to be collected of each exposure, obtained under each exposure
Take the second night scene image of multiframe;
Multiframe noise reduction process is carried out to each exposure the second night scene image of corresponding multiframe respectively, it is corresponding to obtain each exposure
Third night scene image;
Image procossing is carried out to the corresponding third night scene image of each exposure, obtains target night scene image.
2. image processing method according to claim 1, which is characterized in that the mistake according to first night scene image
The step of exposing region and crossing dark areas, determine the exposure of image to be collected and each exposure corresponding frame number to be collected,
Include:
Overexposure region is identified from first night scene image and crosses dark areas;
First ratio and the cross dark areas of the overexposure region in first night scene image are calculated described first
The second ratio in night scene image;
According to the exposure of first ratio and the second ratio-dependent image to be collected;
According to the sensitivity of first night scene image and each exposure of determination according to preset frame number corresponding relationship, really
Determine the corresponding frame number to be collected of each exposure, wherein each frame number to be collected and a sensitivity and an exposure
It is corresponding.
3. image processing method according to claim 2, which is characterized in that described to be identified from first night scene image
The step of overexposure region is with dark areas is crossed out, comprising:
Obtain the grey level histogram of first night scene image;
According to the gray value of pixel each in the grey level histogram, the pixel that gray value is greater than the first gray threshold is true
It is set to the first pixel, gray value is determined as the second pixel less than the pixel of the second gray threshold;
Region including all first pixels is determined as overexposure region, and the region including all second pixels is determined
To cross dark areas.
4. image processing method according to claim 2, which is characterized in that the exposure of the image to be collected includes institute
State the first exposure of the first night scene image, it is described according to first ratio and the second ratio-dependent image to be collected
The step of exposure, comprising:
If first ratio is less than the first setting value, and second ratio is less than the second setting value, it is determined that described wait adopt
The exposure for collecting image is the first exposure of first night scene image;
If first ratio is greater than third setting value, set according to first exposure and the first ratio with the third
The difference of definite value determines the second exposure, and determines that the exposure of the image to be collected further includes second exposure;
If second ratio is greater than the 4th setting value, set according to first exposure and the second ratio with the described 4th
The difference of definite value determines third exposure, and determines that the exposure of the image to be collected further includes the third exposure.
5. image processing method described in any one of -4 according to claim 1, which is characterized in that the image to be collected
Exposure includes the first exposure of first night scene image, less than the second exposure of first exposure and greater than institute
State the third exposure of the first exposure, it is described according to the exposure of the image to be collected and each exposure it is corresponding to
The step of acquiring frame number, the second night scene image of multiframe obtained under each exposure, comprising:
The second night scene image of multiframe is acquired under first exposure;
Second night scene image of frame is acquired under second exposure;
Second night scene image of frame is acquired under the third exposure;
Remaining the second night scene image of every frame is acquired under second exposure;
Remaining the second night scene image of every frame is acquired, under the third exposure to obtain the corresponding multiframe of each exposure
Two night scene images.
6. image processing method described in any one of -4 according to claim 1, which is characterized in that described respectively to each exposure
Corresponding the second night scene image of multiframe of luminosity carries out multiframe noise reduction process, obtains the corresponding third night scene image of each exposure
Before step, the method also includes:
For each exposure, judge that the overexposure region of corresponding the second night scene image of first frame of the exposure is with dark areas is crossed
It is no to meet preset condition;
If second night scene image of first frame is unsatisfactory for preset condition, the second night scene image of multiframe under exposure is determined as
Multiframe noise reduction removes image, to stop carrying out multiframe noise reduction process to the exposure the second night scene image of corresponding multiframe;
Wherein, the preset condition include: the overexposure region of second night scene image of first frame and cross dark areas respectively with this
The overexposure region of one the second night scene image of frame and the area pixel point difference value for crossing dark areas are less than presetted pixel point threshold value.
7. image processing method described in any one of -4 according to claim 1, which is characterized in that described respectively to each exposure
Corresponding the second night scene image of multiframe of luminosity carries out multiframe noise reduction process, obtains the corresponding third night scene image of each exposure
Step, comprising:
For each exposure, using the second night scene image of first frame acquired under the exposure as benchmark frame, by remaining
Two night scene images are aligned the reference frame;
Each remaining second night scene image after alignment is subjected to image co-registration processing with the reference frame, it is corresponding to obtain the exposure
Third night scene image.
8. image processing method described in any one of -4 according to claim 1, which is characterized in that described to each exposure
The step of corresponding third night scene image of luminosity carries out image procossing, obtains target night scene image, comprising:
Feature point alignment is carried out to the corresponding third night scene image of every two exposure respectively, each exposure after being aligned
Corresponding 4th night scene image;
It is synthesized by high dynamic range images algorithm the 4th night scene image corresponding to each exposure, obtains target night scene
Image.
9. image processing method according to claim 8, which is characterized in that described corresponding to every two exposure respectively
The step of third night scene image carries out feature point alignment, each exposure after be aligned corresponding four night scene image, wraps
It includes:
For the corresponding third night scene image of every two exposure, which is divided into multiple images area
Domain;
Each characteristic point of each image-region of the two frames third night scene image is extracted respectively;
Calculate the confidence level of each characteristic point of each image-region of the two frames third night scene image;
According to calculated result, confidence level in each image-region of the two frames third night scene image is met to the feature to impose a condition
Point is determined as target feature point, to determine each target feature point in the two frames third night scene image;
Characteristic point pair is carried out to the two frames third night scene image according to each target feature point in the two frames third night scene image
Together, the 4th night scene image of two frames after being aligned;
Wherein, the setting condition includes: the confidence level of each characteristic point of the confidence level of characteristic point in the image-region by big
It is located at preceding N into small sequence, N is positive integer.
10. image processing method according to claim 8, which is characterized in that described corresponding to every two exposure respectively
Third night scene image carry out feature point alignment, the step of each exposure after being aligned corresponding four night scene image it
Before, the method also includes:
For the corresponding third night scene image of every two exposure, by histogram specification algorithm by two third night scene figures
As in, the brightness of the higher third night scene image of brightness is reduced to the brightness of the lower third night scene image of brightness.
11. image processing method according to claim 1, which is characterized in that the method also includes:
Enhanced using contrast of the Auto Laves algorithm to the target night scene image, obtains enhanced target night scene figure
Picture.
12. a kind of image processing apparatus, which is characterized in that be applied to electronic equipment, described device includes:
Obtain determining module, for obtain first night scene image of frame, and according to the overexposure region of first night scene image with
Dark areas is crossed, determines the exposure of image to be collected and the corresponding frame number to be collected of each exposure;
Image collection module, for according to the exposure of the image to be collected and the corresponding frame to be collected of each exposure
Number obtains the second night scene image of multiframe under each exposure;
Noise reduction process module, for carrying out multiframe noise reduction process to each exposure the second night scene image of corresponding multiframe respectively,
Obtain the corresponding third night scene image of each exposure;
Image processing module obtains target for carrying out image procossing to the corresponding third night scene image of each exposure
Night scene image.
13. a kind of electronic equipment, which is characterized in that the electronic equipment includes machine readable storage medium and processor, described
Machine readable storage medium is stored with machine-executable instruction, and the processor, should when executing the machine-executable instruction
Electronic equipment realizes image processing method described in any one of claim 1-11.
14. a kind of readable storage medium storing program for executing, which is characterized in that be stored with machine-executable instruction, institute in the readable storage medium storing program for executing
It states machine-executable instruction and is performed image processing method described in any one of realization claim 1-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910720898.2A CN110443766B (en) | 2019-08-06 | 2019-08-06 | Image processing method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910720898.2A CN110443766B (en) | 2019-08-06 | 2019-08-06 | Image processing method and device, electronic equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110443766A true CN110443766A (en) | 2019-11-12 |
CN110443766B CN110443766B (en) | 2022-05-31 |
Family
ID=68433356
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910720898.2A Active CN110443766B (en) | 2019-08-06 | 2019-08-06 | Image processing method and device, electronic equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110443766B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111242860A (en) * | 2020-01-07 | 2020-06-05 | 影石创新科技股份有限公司 | Super night scene image generation method and device, electronic equipment and storage medium |
CN111310727A (en) * | 2020-03-13 | 2020-06-19 | 浙江大华技术股份有限公司 | Object detection method and device, storage medium and electronic device |
CN111654623A (en) * | 2020-05-29 | 2020-09-11 | 维沃移动通信有限公司 | Photographing method and device and electronic equipment |
CN112003996A (en) * | 2020-08-12 | 2020-11-27 | Oppo广东移动通信有限公司 | Video generation method, terminal and computer storage medium |
CN112907701A (en) * | 2019-11-19 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Method and device for acquiring image, computer equipment and storage medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101166240A (en) * | 2006-10-19 | 2008-04-23 | 索尼株式会社 | Image processing device, image forming device and image processing method |
CN103413286A (en) * | 2013-08-02 | 2013-11-27 | 北京工业大学 | United reestablishing method of high dynamic range and high-definition pictures based on learning |
CN103973988A (en) * | 2013-01-24 | 2014-08-06 | 华为终端有限公司 | Scene recognition method and device |
CN105578068A (en) * | 2015-12-21 | 2016-05-11 | 广东欧珀移动通信有限公司 | High-dynamic-range image generation method, device and mobile terminal |
CN107465882A (en) * | 2017-09-22 | 2017-12-12 | 维沃移动通信有限公司 | A kind of image capturing method and mobile terminal |
CN107679470A (en) * | 2017-09-22 | 2018-02-09 | 天津大学 | A kind of traffic mark board detection and recognition methods based on HDR technologies |
CN108288253A (en) * | 2018-01-08 | 2018-07-17 | 厦门美图之家科技有限公司 | HDR image generation method and device |
CN108322646A (en) * | 2018-01-31 | 2018-07-24 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
CN109218627A (en) * | 2018-09-18 | 2019-01-15 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and storage medium |
CN109218613A (en) * | 2018-09-18 | 2019-01-15 | Oppo广东移动通信有限公司 | High dynamic-range image synthesis method, device, terminal device and storage medium |
CN109348089A (en) * | 2018-11-22 | 2019-02-15 | Oppo广东移动通信有限公司 | Night scene image processing method, device, electronic equipment and storage medium |
CN109862282A (en) * | 2019-02-18 | 2019-06-07 | Oppo广东移动通信有限公司 | Character image treating method and apparatus |
CN110072051A (en) * | 2019-04-09 | 2019-07-30 | Oppo广东移动通信有限公司 | Image processing method and device based on multiple image |
-
2019
- 2019-08-06 CN CN201910720898.2A patent/CN110443766B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101166240A (en) * | 2006-10-19 | 2008-04-23 | 索尼株式会社 | Image processing device, image forming device and image processing method |
CN103973988A (en) * | 2013-01-24 | 2014-08-06 | 华为终端有限公司 | Scene recognition method and device |
CN103413286A (en) * | 2013-08-02 | 2013-11-27 | 北京工业大学 | United reestablishing method of high dynamic range and high-definition pictures based on learning |
CN105578068A (en) * | 2015-12-21 | 2016-05-11 | 广东欧珀移动通信有限公司 | High-dynamic-range image generation method, device and mobile terminal |
CN107465882A (en) * | 2017-09-22 | 2017-12-12 | 维沃移动通信有限公司 | A kind of image capturing method and mobile terminal |
CN107679470A (en) * | 2017-09-22 | 2018-02-09 | 天津大学 | A kind of traffic mark board detection and recognition methods based on HDR technologies |
CN108288253A (en) * | 2018-01-08 | 2018-07-17 | 厦门美图之家科技有限公司 | HDR image generation method and device |
CN108322646A (en) * | 2018-01-31 | 2018-07-24 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
CN109218627A (en) * | 2018-09-18 | 2019-01-15 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and storage medium |
CN109218613A (en) * | 2018-09-18 | 2019-01-15 | Oppo广东移动通信有限公司 | High dynamic-range image synthesis method, device, terminal device and storage medium |
CN109348089A (en) * | 2018-11-22 | 2019-02-15 | Oppo广东移动通信有限公司 | Night scene image processing method, device, electronic equipment and storage medium |
CN109862282A (en) * | 2019-02-18 | 2019-06-07 | Oppo广东移动通信有限公司 | Character image treating method and apparatus |
CN110072051A (en) * | 2019-04-09 | 2019-07-30 | Oppo广东移动通信有限公司 | Image processing method and device based on multiple image |
Non-Patent Citations (2)
Title |
---|
孙婧: "高动态范围图像合成与显示技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
江燊煜: "基于多曝光融合及伪影去除的动态范围扩展技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112907701A (en) * | 2019-11-19 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Method and device for acquiring image, computer equipment and storage medium |
CN111242860A (en) * | 2020-01-07 | 2020-06-05 | 影石创新科技股份有限公司 | Super night scene image generation method and device, electronic equipment and storage medium |
CN111242860B (en) * | 2020-01-07 | 2024-02-27 | 影石创新科技股份有限公司 | Super night scene image generation method and device, electronic equipment and storage medium |
CN111310727A (en) * | 2020-03-13 | 2020-06-19 | 浙江大华技术股份有限公司 | Object detection method and device, storage medium and electronic device |
CN111310727B (en) * | 2020-03-13 | 2023-12-08 | 浙江大华技术股份有限公司 | Object detection method and device, storage medium and electronic device |
CN111654623A (en) * | 2020-05-29 | 2020-09-11 | 维沃移动通信有限公司 | Photographing method and device and electronic equipment |
CN111654623B (en) * | 2020-05-29 | 2022-03-22 | 维沃移动通信有限公司 | Photographing method and device and electronic equipment |
CN112003996A (en) * | 2020-08-12 | 2020-11-27 | Oppo广东移动通信有限公司 | Video generation method, terminal and computer storage medium |
CN112003996B (en) * | 2020-08-12 | 2023-04-18 | Oppo广东移动通信有限公司 | Video generation method, terminal and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110443766B (en) | 2022-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110072051B (en) | Image processing method and device based on multi-frame images | |
CN109218628B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
CN110443766A (en) | Image processing method, device, electronic equipment and readable storage medium storing program for executing | |
CN109348089B (en) | Night scene image processing method and device, electronic equipment and storage medium | |
CN109005366B (en) | Night scene shooting processing method and device for camera module, electronic equipment and storage medium | |
CN110166708B (en) | Night scene image processing method and device, electronic equipment and storage medium | |
CN108335279B (en) | Image fusion and HDR imaging | |
WO2020207262A1 (en) | Image processing method and apparatus based on multiple frames of images, and electronic device | |
KR101661215B1 (en) | Image processing method and image processing apparatus | |
CN109218627B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
CN110191291B (en) | Image processing method and device based on multi-frame images | |
CN110166709B (en) | Night scene image processing method and device, electronic equipment and storage medium | |
CN104104886B (en) | Overexposure image pickup method and device | |
WO2020207261A1 (en) | Image processing method and apparatus based on multiple frames of images, and electronic device | |
CN111028190A (en) | Image processing method, image processing device, storage medium and electronic equipment | |
CN110248106B (en) | Image noise reduction method and device, electronic equipment and storage medium | |
CN109729274B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
CN109040609A (en) | Exposal control method, device and electronic equipment | |
CN109672819B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN110798627B (en) | Shooting method, shooting device, storage medium and terminal | |
CN109618102B (en) | Focusing processing method and device, electronic equipment and storage medium | |
CN110166711B (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
CN111953893B (en) | High dynamic range image generation method, terminal device and storage medium | |
CN109005367A (en) | A kind of generation method of high dynamic range images, mobile terminal and storage medium | |
CN110740266B (en) | Image frame selection method and device, storage medium and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |