CN103679684A - Device, method and electronic equipment for detecting cloud in image - Google Patents
Device, method and electronic equipment for detecting cloud in image Download PDFInfo
- Publication number
- CN103679684A CN103679684A CN201210333163.2A CN201210333163A CN103679684A CN 103679684 A CN103679684 A CN 103679684A CN 201210333163 A CN201210333163 A CN 201210333163A CN 103679684 A CN103679684 A CN 103679684A
- Authority
- CN
- China
- Prior art keywords
- cloud
- image
- processing unit
- basic processing
- pixel
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention provides device, method and electronic equipment for detecting cloud in an image, and overcomes the problem of poor detection effect in a conventional cloud detection method. The device comprises a calculation module and a determination module, wherein the calculation module is configured to calculate an albinism degree of each basic processing unit according to the pixel information in a preset-size neighboring region of each basic processing unit in the image; the determination module is configured to determine that the basic processing unit within a preset range of the albinism degree is cloud. The method is used for executing the processing of achieving the function of the device for detecting cloud in the image. The electronic equipment comprises the device for detecting cloud in the image. The technology provided by the invention can be applied to the image processing field.
Description
Technical field
The present invention relates to image processing field, relate in particular to a kind of device for detection of the cloud in image, method and electronic equipment.
Background technology
Traditional cloud detection method of optic is generally seen as the classification problem of two classes, it is conventionally using some known cloud image blocks and non-cloud image block as training sample, and therefrom extract the visual signatures such as color and/or texture and be described, then by building someway sorter.In this traditional cloud detection method of optic, the test pattern that need to carry out cloud detection is divided into some image blocks, output based on sorter judges respectively whether each image block is cloud, and the classification results of comprehensive all image blocks can obtain final cloud detection result again.
From said process, can see, using visual signature to carry out effectively describing to the image block of cloud and non-cloud is the committed step in classic method.But, because the cloud in image is varied, the scene of cloud below also cannot limit in advance, is often difficult to extract effective visual signature the image block of cloud and non-cloud is effectively described, therefore the detection effect of traditional cloud detection method of optic is poor, often can not be satisfactory.
Summary of the invention
Provided hereinafter about brief overview of the present invention, to the basic comprehension about some aspect of the present invention is provided.Should be appreciated that this general introduction is not about exhaustive general introduction of the present invention.It is not that intention is determined key of the present invention or pith, and nor is it intended to limit the scope of the present invention.Its object is only that the form of simplifying provides some concept, usings this as the preorder in greater detail of discussing after a while.
Given this, the invention provides a kind of device for detection of the cloud in image, method and electronic equipment, at least to solve the problem of the detection weak effect of traditional cloud detection method of optic.
According to an aspect of the present invention, a kind of device for detection of the cloud in image is provided, this device comprises: computing module, and it is arranged to according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculates the albefaction degree of each basic processing unit; And determination module, it is arranged to the basic processing unit in preset range by albefaction degree and is defined as cloud.
According to another aspect of the present invention, also provide a kind of method for detection of the cloud in image, this comprises: according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculate the albefaction degree of each basic processing unit; And the basic processing unit in preset range is defined as cloud by albefaction degree.
According to another aspect of the present invention, also provide a kind of electronic equipment, this electronic equipment comprises the device for detection of the cloud in image as above.
Above-mentioned according to the device for detection of the cloud in image of the embodiment of the present invention, method and electronic equipment, it utilizes Pixel Information in the neighborhood of each basic processing unit in image to calculate the albefaction degree of each basic processing unit, thereby the basic processing unit by albefaction degree in preset range is defined as cloud, and does not need to use visual signature to be described the image block of cloud and non-cloud.So, overcome the deficiency of traditional cloud detection method of optic, thereby can improve the effect of Cloud detection.
By the detailed description to most preferred embodiment of the present invention below in conjunction with accompanying drawing, these and other advantage of the present invention will be more obvious.
Accompanying drawing explanation
The present invention can, by reference to hereinafter given description and being better understood by reference to the accompanying drawings, wherein use same or analogous Reference numeral to represent identical or similar parts in institute's drawings attached.Described accompanying drawing comprises in this manual and forms the part of this instructions together with detailed description below, and is used for further illustrating the preferred embodiments of the present invention and explains principle and advantage of the present invention.In the accompanying drawings:
Fig. 1 is schematically illustrated according to an embodiment of the invention for detection of the block diagram of a kind of example structure of the device of the cloud in image.
Fig. 2 is the block diagram of a kind of possible example structure of schematically illustrated computing module as shown in Figure 1.
Fig. 3 is the block diagram of the possible example structure of the another kind of schematically illustrated computing module as shown in Figure 1.
Fig. 4 is schematically illustrated according to an embodiment of the invention for detection of the block diagram of the another kind of example structure of the device of the cloud in image.
Fig. 5 is the block diagram of the possible example structure of schematically illustrated the first filtering module as shown in Figure 4.
Fig. 6 is schematically illustrated according to an embodiment of the invention for detection of the block diagram of another example structure of the device of the cloud in image.
Fig. 7 is schematically illustrated according to an embodiment of the invention for detection of the process flow diagram of a kind of exemplary process of the method for the cloud in image.
Fig. 8 is schematically illustrated according to an embodiment of the invention for detection of the process flow diagram of other possible exemplary process of the method for the cloud in image.
Fig. 9 shows the structure diagram can be used to realize according to an embodiment of the invention for detection of the hardware configuration of a kind of possible messaging device of the apparatus and method of the cloud in image.
It will be appreciated by those skilled in the art that the element in accompanying drawing is only used to simply and for the purpose of clear illustrate, and not necessarily draw in proportion.For example, in accompanying drawing, the size of some element may have been amplified with respect to other elements, to contribute to improve the understanding to the embodiment of the present invention.
Embodiment
In connection with accompanying drawing, one exemplary embodiment of the present invention is described hereinafter.All features of actual embodiment are not described for clarity and conciseness, in instructions.Yet, should understand, in the process of any this practical embodiments of exploitation, must make a lot of decisions specific to embodiment, to realize developer's objectives, for example, meet those restrictive conditions with system and traffic aided, and these restrictive conditions may change to some extent along with the difference of embodiment.In addition,, although will also be appreciated that development is likely very complicated and time-consuming, concerning having benefited from those skilled in the art of present disclosure, this development is only routine task.
At this, also it should be noted is that, for fear of the details because of unnecessary fuzzy the present invention, only show in the accompanying drawings with according to the closely-related apparatus structure of the solution of the present invention and/or treatment step, and omitted other details little with relation of the present invention.
Embodiments of the invention provide a kind of device for detection of the cloud in image, this device comprises: computing module, it is arranged to according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, and calculates the albefaction degree of each basic processing unit; And determination module, it is arranged to the basic processing unit in preset range by albefaction degree and is defined as cloud.
Below in conjunction with Fig. 1, describe according to an embodiment of the invention an example for detection of the device of the cloud in image in detail.
As shown in Figure 1, for detection of the device 100 of the cloud in image, comprise computing module 110 and determination module 120 according to an embodiment of the invention.In device 100, computing module 110 can be according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculate the albefaction degree of each basic processing unit, 120 of determination modules can be according to the result of calculation of computing module 110, and the basic processing unit by albefaction degree in preset range is defined as cloud.
Wherein, in the specific implementation for detection of the device of the cloud in image according to an embodiment of the invention, above-mentioned image can be the image that the surfaces such as satellite image or Aerial Images may exist cloud.
It should be noted that in different implementations, " basic processing unit " in said image can be different processing units here.For example, in some implementations, above-mentioned basic processing unit can be each pixel in image, and in some other implementation, and above-mentioned basic processing unit can be also by the resulting image block of Image Segmentation Using, etc.
In addition,, in the specific implementation for detection of the device of the cloud in image according to an embodiment of the invention, " the pre-sizing neighborhood of basic processing unit " refers to the region with predetermined size dimension that comprises this basic processing unit.Wherein, " Pixel Information in pre-sizing neighborhood " can be for example gray-scale value or the rgb value of the pixel in this pre-sizing neighborhood, or can be also the Pixel Information of the other types except gray-scale value and rgb value.In addition, it should be noted that, the pre-sizing neighborhood of basic processing unit can preset, for example, can set based on experience value, or can determine by the method for test.
In addition, also it should be noted that the degree that " the albefaction degree " of said basic processing unit bleaches due to the existence of cloud for describing above-mentioned basic processing unit here.Below will be respectively in conjunction with Fig. 2 and Fig. 3, be described under two kinds of possible exemplary configuration of computing module 110 how to realize the calculating to the albefaction degree of each basic processing unit.
As shown in Figure 2, in an implementation for detection of the device of the cloud in image according to an embodiment of the invention, computing module 110 can comprise and obtains submodule 210 and chooser module 220.
In this implementation, obtain submodule 210 and can determine the pre-sizing neighborhood of each basic processing unit, and obtain rgb value or the gray-scale value of each pixel in the pre-sizing neighborhood of each basic processing unit.
It should be noted that, in this implementation, (at computing module 110, comprise obtain submodule 210 and chooser module 220 in the situation that), basic processing unit can be pixel, can be also by the resulting image block of described Image Segmentation Using.Wherein, the size of each image block can be all identical, also can part identical, or also can be different.
Wherein, in the situation that above-mentioned detected image is gray level image, obtain the gray-scale value of each pixel in the pre-sizing neighborhood that submodule 210 can obtain each basic processing unit in this image.In addition,, in the situation that above-mentioned detected image is coloured image, obtain the rgb value of each pixel in the pre-sizing neighborhood that submodule 210 can obtain each basic processing unit in this image.
In this implementation, for each basic processing unit, chooser module 220 can select that minimum value in rgb value or gray-scale value to be used as reflecting the tolerance of the albefaction degree of this basic processing unit in the pre-sizing neighborhood of this basic processing unit.
In an example, suppose that above-mentioned detected image is gray level image, with certain basic processing unit in this image (certain pixel or certain image block) E
0for example, suppose basic processing unit E
0pre-sizing neighborhood in total L pixel, in L pixel, each pixel respectively has a gray-scale value, using that gray-scale value of minimum in L gray-scale value corresponding to this L pixel as basic processing unit E
0the value of albefaction degree.
The situation that the pixel of take is basic processing unit is example, for arbitrary pixel x, and its pre-sizing neighborhood
be for example the region of the n * n pixel size centered by pixel x, wherein the value of parameter n is relevant with the resolution of image, and generally speaking, the resolution of image is higher, and the value of parameter n is also larger.So the albefaction degree of pixel x can be calculated by following formula:
in above formula, W (x) represents the albefaction degree of pixel x, and y is the pre-sizing neighborhood of pixel x
in any pixel, f (y) is the gray-scale value of pixel y.For a person skilled in the art, according to take above the description that situation that pixel is basic processing unit carried out, easily know the respective handling of take in the situation that image block is basic processing unit, therefore omit its detailed description here.
In another example, suppose that above-mentioned detected image is coloured image, with certain basic processing unit in this image (certain pixel or certain image block) E '
0for example, suppose basic processing unit E '
0pre-sizing neighborhood in the total individual pixel of L ', in L ' pixel, each pixel respectively has three RGB component values, using that RGB component value minimum in the individual RGB component value of 3L ' corresponding to the individual pixel of this L ' as basic processing unit E '
0the value of albefaction degree.
With above similar, the situation that the pixel of take is basic processing unit is example, for arbitrary pixel x ', and its pre-sizing neighborhood
be for example the region of the n * n pixel size centered by pixel x ', here, the value of parameter n can adopt above described mode.So the albefaction degree of pixel x ' can be calculated by following formula:
in above formula, W (x') represents the albefaction degree of pixel x ', and y ' is the pre-sizing neighborhood of pixel x '
in any pixel, f
r(y'), f
gand f (y')
b(y') be respectively redness, green and the blue component value of pixel y '.For a person skilled in the art, according to take above the description that situation that pixel is basic processing unit carried out, easily know the respective handling of take in the situation that image block is basic processing unit, therefore omit its detailed description here.
Usually, because the existence of cloud can increase the gray-scale value (or value of each color component) of pixel (or image block), therefore, the value of the W calculating (x) (or W (x')) is less, pixel x(or x ') to be positioned at possibility on the object being covered by cloud also just less.
Fig. 3 schematically shows the possible example structure of another kind of computing module 110 as shown in Figure 1.As shown in Figure 3, in another implementation for detection of the device of the cloud in image according to an embodiment of the invention, computing module 110 can comprise that image cuts apart submodule 310 and calculating sub module 320.
It should be noted that, in this implementation (in the situation that computing module 110 comprises that image is cut apart submodule 310 and calculating sub module 320), basic processing unit is image block.
In this implementation, image is cut apart submodule 310 can be first to above-mentioned Image Segmentation Using, and to obtain a plurality of image blocks, wherein, each image block is here as " basic processing unit " of image.Wherein, image is cut apart submodule 310 and can be adopted more existing image Segmentation Technology to realize cutting apart above-mentioned image, the result of cutting apart can be the image block that obtains a plurality of formed objects, also can be the unfixed a plurality of image blocks of shape, because image Segmentation Technology can, by obtaining in conjunction with common practise and/or open source literature, therefore no longer be described its detailed processing procedure here for a person skilled in the art.
Then, cut apart a plurality of image blocks of submodule 310 acquisition by image after, calculating sub module 320 can be for calculating the albefaction degree of above-mentioned each image block.Illustrate calculating sub module 320 below and how to calculate the albefaction degree of each image block.
With image, cut apart any the image block B in a plurality of image blocks that submodule 310 obtains
0for example, first calculating sub module 320 can determine image block B
0in the albefaction degree of each pixel.
In an example, calculating sub module 320 can be by image block B
0minimum value in the albefaction degree of all pixels that comprise is as image block B
0the value of albefaction degree.In this example, can utilize following formula to carry out computed image piece B
0albefaction degree:
in the formula, W (B
0) presentation video piece B
0albefaction degree, x
0image block B
0in any pixel, W (x
0) be pixel x
0albefaction degree.
In another example, calculating sub module 320 can be by image block B
0maximal value in the albefaction degree of all pixels that comprise is as image block B
0the value of albefaction degree.In this example, can utilize following formula to carry out computed image piece B
0albefaction degree:
in the formula, W (B
0), x
0, W (x
0) meaning identical with the meaning in upper example, repeat no more here.
In other examples, calculating sub module 320 also can be by image block B
0the mean value of the albefaction degree of all pixels that comprise is as image block B
0the value of albefaction degree.In this example, can utilize following formula to carry out computed image piece B
0albefaction degree:
in the formula, W (B
0), x
0, W (x
0) meaning identical with the meaning in upper example, repeat no more here; In addition the total pixel count comprising in l presentation video piece B0.
Wherein, calculating sub module 320 can be carried out computed image piece B according to the mode that will describe as follows
0in the albefaction degree of each pixel.With image block B
0in arbitrary pixel P
0for example, determine and comprise pixel P
0predetermined size area (size of said predetermined size area also can preset here, as determined based on experience value or by test method, repeats no more), obtain the above-mentioned pixel P that comprises
0predetermined size area in the rgb value of each pixel or gray-scale value (for coloured image, be the rgb value that obtains each pixel; For gray level image, be the gray-scale value that obtains each pixel), and at the above-mentioned pixel P that comprises
0predetermined size area in select minimum value in rgb value or gray-scale value as reflection pixel P
0the tolerance of albefaction degree (also, using this minimum value as pixel P
0the value of albefaction degree).
Then, determination module 120 can be defined as cloud by the basic processing unit in preset range by albefaction degree.
In an example, determination module 120 can be defined as cloud higher than those basic processing units of the 4th predetermined threshold by the value of albefaction degree.In this example, be also about to albefaction degree and be judged to be because surface is covered and bleached by cloud higher than those basic processing units of the 4th predetermined threshold (for example, higher than 100).
In another example, determination module 120 also can for example, be defined as cloud by the value of albefaction degree those basic processing units of (between 100 and 200) between the 5th predetermined threshold and the 6th predetermined threshold.In this example, albefaction degree is judged to be to cloud higher than the 5th predetermined threshold and lower than those basic processing units of the 6th predetermined threshold, albefaction degree is not judged as cloud higher than those basic processing units of the 6th predetermined threshold.In this case, for some applicable scenes, (for example gray-scale value equals or approaches 255 pure white pixel in possible image, or each component value of RGB is equal to or approaches 255) a lot, for example, when the albefaction degree of calculating during higher than the 6th predetermined threshold (higher than 200 time), think that basic processing unit corresponding to these albefaction degree is not owing to being covered and bleaching by cloud, but itself be exactly white or connect subalbous object.Thus, in some cases, can be so that the result detecting be more accurate.
It should be noted that, above-mentioned the 4th, the 5th and the 6th predetermined threshold can be taken the factors such as illumination, cloud layer form, photographed scene into consideration and carry out value.If can obtain the training sample obtaining under similar shooting condition, can determine the above-mentioned the 4th, the 5th and the value of the 6th predetermined threshold by the method for adding up or learn.
Below in conjunction with Fig. 4, describe according to an embodiment of the invention another example for detection of the device of the cloud in image in detail.
As shown in Figure 4, for detection of the device 400 of the cloud in image, except comprising computing module 410 and determination module 420, also comprise the first filtering module 430.Wherein, the computing module 410 in the device 400 shown in Fig. 4 and determination module 420 can have the 26S Proteasome Structure and Function identical with corresponding unit in device 100 described in conjunction with Figure 1 above, and can reach similar technique effect, repeat no more here.
With the similar ground of device 100, in device 400, according to the result of calculation of computing module 410, determination module 420 can be defined as cloud by some qualified basic processing units.Yet, at these, be confirmed as in the basic processing unit of cloud, may there are some misjudged basic processing units.That is to say, although part basic processing unit is because albefaction degree is in preset range and be defined as cloud by determination module 420, but itself is cloud (itself be exactly for example white object but those basic processing units of non-cloud) not, therefore, if the basic processing unit that can this part be mistaken for to cloud by some approach is got rid of, can effectively improve the detection effect of the above-mentioned device for detection of the cloud in image.
As shown in Figure 4, in device 400, after at determination module 420, by albefaction degree, the basic processing unit in preset range is defined as cloud, the first filtering module 430 can be based on priori rules, and the basic processing unit that the part in these basic processing units is mistaken for to cloud abandons.The exemplary process of the first filtering module 430 is described in connection with Fig. 5 hereinafter.
As shown in Figure 5, in the specific implementation for detection of the device of the cloud in image according to an embodiment of the invention, the first filtering module 430 can comprise the first filtration submodule 510 and second at least one of filtering in submodule 520.Possible function and the processing of the submodule that the first filtering module 430 comprises will be illustrated below.
In an example, in the situation that the first filtering module 430 comprises the first filtration submodule 510, first filters submodule 510 can be for calculating the contrast of the pre-sizing neighborhood of each basic processing unit that has been defined as cloud, and from cloud, abandon such basic processing unit: the contrast of its pre-sizing neighborhood is greater than the first predetermined threshold.
Because piece image comprises a lot of basic processing units, so the pre-sizing neighborhood of each basic processing unit is also often less with respect to whole image.Thus, in the ordinary course of things, be really that the contrast of pre-sizing neighborhood of basic processing unit of cloud is conventionally lower.Therefore, if the contrast excessive (for example, higher than above-mentioned the first predetermined threshold) of the pre-sizing neighborhood of each basic processing unit that the first filtration submodule 510 calculates, can think that this pixel is not real cloud, but be mistaken for cloud by determination module 420, therefore can in the testing result of determination module 420, remove such basic processing unit by the first filtration submodule 510.
Wherein, contrast can be calculated based on gray level co-occurrence matrixes.Computing method corresponding to the gray level co-occurrence matrixes of a certain image block are: if image block is colored, is first translated into gray scale, and is m level (m can be taken as 8 conventionally) by gray level re-quantization.Gray level co-occurrence matrixes P is the matrix of m * m, element P (i, the j) statistics of the capable j of its i row be pixel that in image block, value is i and the number of times of value pixel level adjacent (or being positioned at predefined relative position) appearance that is j.After making its all elements sum be 1 gray level co-occurrence matrixes P normalization, the contrast of image block is calculated as follows:
Wherein,
the pre-sizing neighborhood that represents pixel x
contrast.The span of the contrast calculating according to above formula for [0, (m-1)
2].It should be noted that, the value of above-mentioned the first predetermined threshold can consider the factors such as shooting condition, the scene in image and above-mentioned span of image and determine, also can determine by the method for the statistics based on training sample or study.
In another example, in the situation that the first filtering module 430 comprises the second filtration submodule 520, second filters submodule 520 can be for calculating the quantity of the marginal point in the pre-sizing neighborhood of each basic processing unit that has been defined as cloud, and from cloud, abandon such basic processing unit: the quantity of the marginal point in its pre-sizing neighborhood is greater than the second predetermined threshold.
Generally, really for the quantity of the marginal point that comprises in the region of cloud conventionally all seldom.For example, so adding up current cloud detection result by the second filtration submodule 520 (is the resulting testing result of determination module 420; Or the testing result obtaining after the first filtration submodule 510 is processed) quantity of marginal point in the pre-sizing neighborhood of each basic processing unit in, if this quantity is greater than the second predetermined threshold, its corresponding basic processing unit is removed from testing result.
Wherein, marginal point can obtain according to edge detection operator, method is as follows: if image is coloured image, first coloured image is converted into gray level image, re-use the approximate value of each pixel place gradient in the gray level image after Sobel or other operator are transformed, and determine marginal point according to gradient magnitude.Thus, can obtain the quantity of the marginal point comprising in the pre-sizing neighborhood of each basic processing unit.
It should be noted that, the value of above-mentioned the second predetermined threshold can consider shooting condition, the factors such as scene in image of image and determine, also can determine by the method for the statistics based on training sample or study.
In addition, also it should be noted that, in other examples, if the first filtering module 430 comprises the first filtration submodule 510 and second and filters submodule 520 simultaneously, can first carry out processing, second according to the first filtration submodule 510 filters the order that the rear execution of submodule 520 processes and carries out, also can be that the second filtration submodule 520 is first carried out processing, first and filtered the order that the rear execution of submodule 510 processes and carry out, the detailed process of processing can be carried out in conjunction with above two examples, no longer describes in detail here.
Below in conjunction with Fig. 6, describe according to an embodiment of the invention another example for detection of the device of the cloud in image in detail.
As shown in Figure 6, for detection of the device 600 of the cloud in image, except comprising computing module 610 and determination module 620, also comprise the second filtering module 640.Wherein, the computing module 610 in the device 600 shown in Fig. 6 and determination module 620 can have the 26S Proteasome Structure and Function identical with corresponding unit in device 100 described in conjunction with Figure 1 above, and can reach similar technique effect, repeat no more here.
With the similar ground of device 100, in device 600, according to the result of calculation of computing module 610, determination module 620 can be defined as cloud by some qualified basic processing units.Yet, as described above, at these, be confirmed as in the basic processing unit of cloud, may there are some misjudged basic processing units.For example, by the processing of the modules such as computing module 610, determination module 620, in the testing result (basic processing unit) of current gained, may there is the connected region that some sizes are less (pixel that for example wherein only comprises single pixel or some), and this class connected region is not often real cloud, this is because actual cloud exists often in flakes.Therefore,, if can the less connected region of this part size be got rid of by some approach, can improve the detection effect of the above-mentioned device for detection of the cloud in image.
As shown in Figure 6, in device 600, after at determination module 620, by albefaction degree, the basic processing unit in preset range is defined as cloud, the second filtering module 640 can calculate the size that has been defined as each connected region that the basic processing unit of cloud forms.In an implementation for detection of the device of the cloud in image according to an embodiment of the invention, the second filtering module 640 can for example, by calculating the quantity (pixel quantity comprising of the basic processing unit that is defined as cloud comprising in each connected region, or the quantity of the image block comprising, etc.), the numerical value using the value of this quantity as the size of corresponding connected region then.
Then, according to above-mentioned result of calculation, the second filtering module 640 can be less than size connected region filtering from cloud of the 3rd predetermined threshold.
It should be noted that, above-mentioned the 3rd value of predetermined threshold is relevant with the resolution of image, and generally speaking, the resolution of image is higher, and the value of the 3rd predetermined threshold is also larger.
In addition, it should be noted that, in other implementations, device 600 also can optionally comprise the first filtering module 630.Wherein, the first filtering module 630 can have with above in conjunction with Fig. 4 and/or the identical 26S Proteasome Structure and Function of described the first filtering module 430 of Fig. 5, and can reach similar technique effect, repeats no more here.It should be noted that the processing of the first filtering module 630 and the second filtering module 640 in no particular order in the situation that device 600 comprises the first filtering module 630; Preferably, for example can be so that the first filtering module 630 and the second filtering module 640 be carried out processing successively.
Known by above description, above-mentioned according to an embodiment of the invention for detection of the device of the cloud in image, it utilizes the Pixel Information in the neighborhood of each basic processing unit in image, calculate the albefaction degree of each basic processing unit, thereby the basic processing unit in preset range is defined as cloud by albefaction degree.Different from traditional cloud detection technology is, above-mentionedly for detection of the device of the cloud in image, do not need to use visual signature to be described the image block of cloud and non-cloud according to an embodiment of the invention, overcome the deficiency of traditional cloud detection method of optic, the effect of Cloud detection can be improved, thereby more gratifying testing result can be obtained.
In addition, embodiments of the invention also provide a kind of method for detection of the cloud in image, describe a kind of exemplary process of the above-mentioned method for detection of the cloud in image below in conjunction with Fig. 7.
As shown in Figure 7, the treatment scheme 700 for detection of the method for the cloud in image starts from step S710 according to an embodiment of the invention, then performs step S720.
In step S720, according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculate the albefaction degree of each basic processing unit.Then perform step S730.Wherein, in step S720, performed processing example as can be with above identical in conjunction with the processing of Fig. 1, Fig. 2 and/or the described computing module 110 of Fig. 3, and can reach similar technique effect, does not repeat them here.
In step S730, the basic processing unit by albefaction degree in preset range is defined as cloud.Then perform step S740.Wherein, in step S730, performed processing example as can be identical with the processing of determination module 120 described in conjunction with Figure 1 above, and can reach similar technique effect, does not repeat them here.
Fig. 8 schematically shows according to an embodiment of the invention other the possible exemplary process for detection of the method for the cloud in image.As shown in Figure 8, the treatment scheme 800 for detection of the method for the cloud in image starts from S810 according to an embodiment of the invention, then performs step S820.
The processing procedure of step S820 can be identical with the processing procedure of step S720 described in conjunction with Figure 7 above, and can reach similar technique effect, at this, omits its detailed description.Then perform step S830.
The processing procedure of step S830 can be identical with the processing procedure of step S730 described in conjunction with Figure 7 above, and can reach similar technique effect, at this, omits its detailed description.
After execution of step S830, treatment scheme 800 can optionally perform step at least one in S840 and S850, then ends at step S860.
In an example, after execution of step S820 and S830, can perform step successively S840 and S860, and not perform step S850.In this example, after the basic processing unit in preset range is defined as cloud by albefaction degree by step S830, can in step S840, based on priori rules, abandon the basic processing unit that part is mistaken for cloud.Wherein, in step S840, performed processing example as can be with above identical in conjunction with the processing of Fig. 4 and/or described the first filtering module 430 of Fig. 5, and can reach similar technique effect, does not repeat them here.
In another example, after execution of step S820 and S830, can perform step successively S850 and S860, and not perform step S840.In this example, after by step S830, by albefaction degree, the basic processing unit in preset range is defined as cloud, can in step S850, calculate the size that has been defined as the connected region that the basic processing unit of cloud forms, and the connected region filtering from cloud that size is less than to the 3rd predetermined threshold.Wherein, in step S850, performed processing example as can be identical with the processing of the second filtering module 640 described in conjunction with Figure 6 above, and can reach similar technique effect, does not repeat them here.
In another example, after execution of step S820 and S830, can perform step successively S840, S850 and S860, or perform step successively S850, S840 and S860.In this example, the processing procedure of step S840 and S850 is can be respectively identical with the processing procedure of corresponding step described in above two examples, repeats no more here.
Known by above description, above-mentioned according to an embodiment of the invention for detection of the method for the cloud in image, it utilizes the Pixel Information in the neighborhood of each basic processing unit in image, calculate the albefaction degree of each basic processing unit, thereby the basic processing unit in preset range is defined as cloud by albefaction degree.Different from traditional cloud detection method of optic is, above-mentionedly for detection of the method for the cloud in image, do not need to use visual signature to be described the image block of cloud and non-cloud according to an embodiment of the invention, overcome the deficiency of traditional cloud detection method of optic, the effect of Cloud detection can be improved, thereby more gratifying testing result can be obtained.
In addition, embodiments of the invention also provide a kind of electronic equipment, and this electronic equipment comprises the device for detection of the cloud in image as above.
The result of cloud detection can have multiple application.For example, according to the result of cloud detection, can be by the cloud demand that further classification is applied to meet meteorology.And for example, in the situation that cloud layer is thinner, can manage to be removed, and recover the scene of cloud layer below.In addition,, if the operation of cloud detection completes on satellite, area that can also be shared according to image medium cloud, judges whether to be sent it back ground.
Thus, these electronic equipments for example can utilize the device for detection of the cloud in image comprising in it to carry out cloud detection, and then recycling cloud detection result is carried out some follow-up processing.Effect improved due to cloud detection, testing result is more accurate, so the effect of subsequent treatment also can correspondingly improve.
In the specific implementation of above-mentioned according to an embodiment of the invention electronic equipment, this electronic equipment can be any one equipment in following equipment: mobile phone; Computing machine; Panel computer; Personal digital assistant; Multimedia play equipment; And electric paper book etc.Wherein, this electronic equipment has various functions and the technique effect of the above-mentioned device for detection of the cloud in image, repeats no more here.
Above-mentionedly for detection of each component units in the device of the cloud in image, subelement, module etc., can be configured by the mode of software, firmware, hardware or its combination in any according to an embodiment of the invention.In the situation that realizing by software or firmware, can to the machine (example general-purpose machinery 900 as shown in Figure 9) with specialized hardware structure, the program that forms this software or firmware be installed from storage medium or network, this machine, when various program is installed, can be carried out the various functions of above-mentioned each component units, subelement.
Fig. 9 shows the structure diagram can be used to realize according to an embodiment of the invention for detection of the hardware configuration of a kind of possible messaging device of the apparatus and method of the cloud in image.
In Fig. 9, CPU (central processing unit) (CPU) 901 carries out various processing according to the program of storage in ROM (read-only memory) (ROM) 902 or from the program that storage area 908 is loaded into random access memory (RAM) 903.In RAM 903, also store as required data required when CPU 901 carries out various processing etc.CPU 901, ROM 902 and RAM 903 are connected to each other via bus 904.Input/output interface 905 is also connected to bus 904.
Following parts are also connected to input/output interface 905: importation 906(comprises keyboard, mouse etc.), output 907(comprises display, such as cathode-ray tube (CRT) (CRT), liquid crystal display (LCD) etc., and loudspeaker etc.), storage area 908(comprises hard disk etc.), communications portion 909(comprises such as LAN card, modulator-demodular unit etc. of network interface unit).Communications portion 909 is via for example the Internet executive communication processing of network.As required, driver 910 also can be connected to input/output interface 905.Detachable media 911 for example disk, CD, magneto-optic disk, semiconductor memory etc. can be installed on driver 910 as required, and the computer program of therefrom reading can be installed in storage area 908 as required.
In the situation that realizing above-mentioned series of processes by software, can from network for example the Internet or from storage medium for example detachable media 911 program that forms softwares is installed.
It will be understood by those of skill in the art that this storage medium is not limited to wherein having program stored therein shown in Fig. 9, distributes separately to user, to provide the detachable media 911 of program with equipment.The example of detachable media 911 comprises disk (comprising floppy disk), CD (comprising compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (comprising mini-disk (MD) (registered trademark)) and semiconductor memory.Or storage medium can be hard disk comprising in ROM 902, storage area 908 etc., computer program stored wherein, and be distributed to user together with the equipment that comprises them.
In addition, the invention allows for a kind of program product that stores the instruction code that machine readable gets.When above-mentioned instruction code is read and carried out by machine, can carry out above-mentioned according to an embodiment of the invention for detection of the method for the cloud in image.Correspondingly, for carrying the various storage mediums such as disk, CD, magneto-optic disk, semiconductor memory etc. of this program product, be also included within of the present invention open.
In the above in the description of the specific embodiment of the invention, the feature of describing and/or illustrating for a kind of embodiment can be used in same or similar mode in one or more other embodiment, combined with the feature in other embodiment, or substitute the feature in other embodiment.
In addition, during the method for various embodiments of the present invention is not limited to specifications, describe or accompanying drawing shown in time sequencing carry out, also can be according to other time sequencing, carry out concurrently or independently.The execution sequence of the method for therefore, describing in this instructions is not construed as limiting technical scope of the present invention.
In addition obviously, according to each operating process of said method of the present invention, also can realize to be stored in the mode of the computer executable program in various machine-readable storage mediums.
And, object of the present invention also can realize by following manner: the storage medium that stores above-mentioned executable program code is offered to system or equipment directly or indirectly, and said procedure code is read and carried out to the computing machine in this system or equipment or CPU (central processing unit) (CPU).
Now, as long as this system or equipment have the function of executive routine, embodiments of the present invention are not limited to program, and this program can be also form arbitrarily, for example, the program that target program, interpreter are carried out or the shell script that offers operating system etc.
Above-mentioned these machinable mediums include but not limited to: various storeies and storage unit, and semiconductor equipment, disc unit is light, magnetic and magneto-optic disk for example, and other is suitable for the medium of the information of storing etc.
In addition, client computer is by being connected to the corresponding website on the Internet, and will download and be installed in computing machine according to computer program code of the present invention and then carry out this program, also can realize the present invention.
Finally, also it should be noted that, in this article, relational terms such as left and right, first and second etc. is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply and between these entities or operation, have the relation of any this reality or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thereby the process, method, article or the equipment that make to comprise a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or be also included as the intrinsic key element of this process, method, article or equipment.The in the situation that of more restrictions not, the key element being limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment that comprises described key element and also have other identical element.
To sum up, in an embodiment according to the present invention, the invention provides following scheme but be not limited to this:
1. 1 kinds of devices for detection of the cloud in image of remarks, comprising:
Computing module, it is arranged to according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculates the albefaction degree of basic processing unit described in each; And
Determination module, it is arranged to the basic processing unit in preset range by albefaction degree and is defined as cloud.
Remarks 2. is according to the device for detection of the cloud in image described in remarks 1, and wherein, described computing module comprises:
Obtain submodule, it is arranged to the pre-sizing neighborhood of determining basic processing unit described in each, and obtains rgb value or the gray-scale value of each pixel in the pre-sizing neighborhood of each basic processing unit; And
Chooser module, it is arranged to for basic processing unit described in each, selects minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this basic processing unit of reflection in the pre-sizing neighborhood of this basic processing unit.
Remarks 3. is according to the device for detection of the cloud in image described in remarks 2, and wherein, described basic processing unit is:
Pixel; Or
By to the resulting image block of described Image Segmentation Using.
Remarks 4. is according to the device for detection of the cloud in image described in remarks 1, and wherein, described computing module comprises:
Image is cut apart submodule, and it is arranged to described Image Segmentation Using, obtains a plurality of image blocks; And
Calculating sub module, it is arranged to for each image block, calculate the albefaction degree of each pixel in this image block, and the mean value of the albefaction degree of all pixels of comprising of the minimum value in the albefaction degree of all pixels that this image block is comprised or maximal value or this image block is defined as the albefaction degree of this image block.
Remarks 5. is according to the device for detection of the cloud in image described in remarks 4, and wherein, described calculating sub module is arranged to:
For each pixel in each image block,
Determine the predetermined size area that comprises this pixel,
The rgb value or the gray-scale value that described in acquisition, comprise interior each pixel of predetermined size area of this pixel, and
In the described predetermined size area that comprises this pixel, select minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this pixel of reflection.
Remarks 6., according to arbitrary described device for detection of the cloud in image in remarks 1-5, also comprises:
The first filtering module, it is arranged to based on priori rules and abandons the basic processing unit that part is mistaken for cloud.
Remarks 7. is according to the device for detection of the cloud in image described in remarks 6, and wherein, described the first filtering module comprises:
First filters submodule, and it is arranged to the contrast of pre-sizing neighborhood that calculating has been defined as each basic processing unit of cloud, and from cloud, abandons such basic processing unit: the contrast of its pre-sizing neighborhood is greater than the first predetermined threshold; And/or
Second filters submodule, it is arranged to the quantity of the marginal point in the pre-sizing neighborhood of each basic processing unit that calculating has been defined as cloud, and from cloud, abandons such basic processing unit: the quantity of the marginal point in its pre-sizing neighborhood is greater than the second predetermined threshold.
Remarks 8., according to arbitrary described device for detection of the cloud in image in remarks 1-7, also comprises:
The second filtering module, it is arranged to the size of the connected region that basic processing unit that calculating has been defined as cloud forms, and the connected region filtering from cloud that size is less than to the 3rd predetermined threshold.
Remarks 9. is according to the device for detection of the cloud in image described in remarks 8, and wherein, the second filtering module is arranged to: the size that the quantity of the basic processing unit that is defined as cloud comprising in described connected region is defined as to described connected region.
Remarks 10. is according to arbitrary described device for detection of the cloud in image in remarks 1-9, and wherein said image is satellite image or Aerial Images.
11. 1 kinds of methods for detection of the cloud in image of remarks, comprising:
According to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculate the albefaction degree of basic processing unit described in each; And
Basic processing unit by albefaction degree in preset range is defined as cloud.
Remarks 12. is according to the method for detection of the cloud in image described in remarks 11, wherein, described calculating described in each the albefaction degree of basic processing unit comprise:
For basic processing unit described in each,
Determine the pre-sizing neighborhood of this basic processing unit,
Obtain rgb value or the gray-scale value of interior each pixel of pre-sizing neighborhood of this basic processing unit, and
In the pre-sizing neighborhood of this basic processing unit, select minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this basic processing unit of reflection.
Remarks 13. is according to the method for detection of the cloud in image described in remarks 11, wherein, described calculating described in each the albefaction degree of basic processing unit comprise:
To described Image Segmentation Using, obtain a plurality of image blocks; And
For each image block, obtain in the following way the albefaction degree of this image block:
For each pixel in this image block, determine the predetermined size area that comprises this pixel, the rgb value or the gray-scale value that described in acquisition, comprise interior each pixel of predetermined size area of this pixel, and in the described predetermined size area that comprises this pixel, select minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this pixel of reflection, and
The mean value of the albefaction degree of all pixels that the minimum value in the albefaction degree of all pixels that this image block is comprised or maximal value or this image block comprise is defined as the albefaction degree of this image block.
Remarks 14., according to arbitrary described method for detection of the cloud in image in remarks 11-13, also comprises: based on priori rules, abandon the basic processing unit that part is mistaken for cloud.
Remarks 15. is according to the method for detection of the cloud in image described in remarks 14, wherein, describedly based on priori rules, abandons the basic processing unit that part is mistaken for cloud and comprises:
Calculate the contrast of the pre-sizing neighborhood of each basic processing unit that has been defined as cloud, and from cloud, abandon such basic processing unit: the contrast of its pre-sizing neighborhood is greater than the first predetermined threshold; And/or
Calculate the quantity of the marginal point in the pre-sizing neighborhood of each basic processing unit be defined as cloud, and from cloud, abandon such basic processing unit: the quantity of the marginal point in its pre-sizing neighborhood is greater than the second predetermined threshold.
Remarks 16., according to arbitrary described method for detection of the cloud in image in remarks 11-15, also comprises:
Calculate the size be defined as the connected region that the basic processing unit of cloud forms; And
Size is less than to connected region filtering from cloud of the 3rd predetermined threshold.
17. 1 kinds of electronic equipments of remarks, comprise as the device for detection of the cloud in image as described in arbitrary in remarks 1-10.
Remarks 18. is according to the electronic equipment described in remarks 17, and wherein, described electronic equipment is any one in following equipment:
Mobile phone; Computing machine; Panel computer; Personal digital assistant; Multimedia play equipment; And electric paper book.
19. 1 kinds of remarks store the program product of the instruction code that machine readable gets, and described program product can make described machine carry out according to arbitrary described method for detection of the cloud in image in remarks 11-16 when carrying out.
20. 1 kinds of computer-readable recording mediums of remarks, store on it according to the program product described in remarks 19.
Claims (10)
1. for detection of a device for the cloud in image, comprising:
Computing module, it is arranged to according to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculates the albefaction degree of basic processing unit described in each; And
Determination module, it is arranged to the basic processing unit in preset range by albefaction degree and is defined as cloud.
2. the device for detection of the cloud in image according to claim 1, wherein, described computing module comprises:
Obtain submodule, it is arranged to the pre-sizing neighborhood of determining basic processing unit described in each, and obtains rgb value or the gray-scale value of each pixel in the pre-sizing neighborhood of each basic processing unit; And
Chooser module, it is arranged to for basic processing unit described in each, selects minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this basic processing unit of reflection in the pre-sizing neighborhood of this basic processing unit.
3. the device for detection of the cloud in image according to claim 2, wherein, described basic processing unit is:
Pixel; Or
By to the resulting image block of described Image Segmentation Using.
4. the device for detection of the cloud in image according to claim 1, wherein, described computing module comprises:
Image is cut apart submodule, and it is arranged to described Image Segmentation Using, obtains a plurality of image blocks; And
Calculating sub module, it is arranged to for each image block, calculate the albefaction degree of each pixel in this image block, and the mean value of the albefaction degree of all pixels of comprising of the minimum value in the albefaction degree of all pixels that this image block is comprised or maximal value or this image block is defined as the albefaction degree of this image block.
5. the device for detection of the cloud in image according to claim 4, wherein, described calculating sub module is arranged to:
For each pixel in each image block,
Determine the predetermined size area that comprises this pixel,
The rgb value or the gray-scale value that described in acquisition, comprise interior each pixel of predetermined size area of this pixel, and
In the described predetermined size area that comprises this pixel, select minimum value in rgb value or gray-scale value as the tolerance of the albefaction degree of this pixel of reflection.
6. according to arbitrary described device for detection of the cloud in image in claim 1-5, also comprise:
The first filtering module, it is arranged to based on priori rules and abandons the basic processing unit that part is mistaken for cloud.
7. the device for detection of the cloud in image according to claim 6, wherein, described the first filtering module comprises:
First filters submodule, and it is arranged to the contrast of pre-sizing neighborhood that calculating has been defined as each basic processing unit of cloud, and from cloud, abandons such basic processing unit: the contrast of its pre-sizing neighborhood is greater than the first predetermined threshold; And/or
Second filters submodule, it is arranged to the quantity of the marginal point in the pre-sizing neighborhood of each basic processing unit that calculating has been defined as cloud, and from cloud, abandons such basic processing unit: the quantity of the marginal point in its pre-sizing neighborhood is greater than the second predetermined threshold.
8. according to arbitrary described device for detection of the cloud in image in claim 1-7, also comprise:
The second filtering module, it is arranged to the size of the connected region that basic processing unit that calculating has been defined as cloud forms, and the connected region filtering from cloud that size is less than to the 3rd predetermined threshold.
9. for detection of a method for the cloud in image, comprising:
According to the Pixel Information in the pre-sizing neighborhood of each basic processing unit in image, calculate the albefaction degree of basic processing unit described in each; And
Basic processing unit by albefaction degree in preset range is defined as cloud.
10. an electronic equipment, comprises as the device for detection of the cloud in image as described in arbitrary in claim 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210333163.2A CN103679684B (en) | 2012-09-10 | 2012-09-10 | Device, method and electronic equipment for detecting cloud in image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210333163.2A CN103679684B (en) | 2012-09-10 | 2012-09-10 | Device, method and electronic equipment for detecting cloud in image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103679684A true CN103679684A (en) | 2014-03-26 |
| CN103679684B CN103679684B (en) | 2017-05-24 |
Family
ID=50317139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210333163.2A Active CN103679684B (en) | 2012-09-10 | 2012-09-10 | Device, method and electronic equipment for detecting cloud in image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103679684B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408534A (en) * | 2016-09-13 | 2017-02-15 | 北京金山安全软件有限公司 | Image processing method and device and electronic equipment |
| CN107492074A (en) * | 2017-07-21 | 2017-12-19 | 触景无限科技（北京）有限公司 | Image acquisition and processing method, device and terminal device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799921A (en) * | 2009-02-10 | 2010-08-11 | 中国科学院计算技术研究所 | Cloud detection method of optic remote sensing image |
-
2012
- 2012-09-10 CN CN201210333163.2A patent/CN103679684B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799921A (en) * | 2009-02-10 | 2010-08-11 | 中国科学院计算技术研究所 | Cloud detection method of optic remote sensing image |
Non-Patent Citations (5)
| Title |
|---|
| LINGJIA GU等: "Automatic Cloud Detection and Removal Algorithm for MODIS Remote Sensing Imagery", 《JOURNAL OF SOFTWARE》 * |
| RUHUL AMIN等: "Automated detection and removal of cloud shadows on HICO images", 《OCEAN SENSING AND MONITORING III》 * |
| YUEKUI YANG等: "Impacts of 3-D radiative effects on satellite cloud detection and their consequences on cloud fraction and aerosol optical depth retrievals", 《JOURNAL OF GEOPHYSICAL RESEARCH》 * |
| 杨俊等: "基于局部阈值插值的地基云自动检测方法", 《气象学报》 * |
| 邓晓智: "星空中云检测算法的研究", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408534A (en) * | 2016-09-13 | 2017-02-15 | 北京金山安全软件有限公司 | Image processing method and device and electronic equipment |
| CN106408534B (en) * | 2016-09-13 | 2019-07-26 | 北京金山安全软件有限公司 | Image processing method and device and electronic equipment |
| CN107492074A (en) * | 2017-07-21 | 2017-12-19 | 触景无限科技（北京）有限公司 | Image acquisition and processing method, device and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103679684B (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Berman et al. | Air-light estimation using haze-lines | |
| CN108389224B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN108154105B (en) | Underwater biological detection and identification method and device, server and terminal equipment | |
| Yeh et al. | Haze effect removal from image via haze density estimation in optical model | |
| KR101282196B1 (en) | Apparatus and method for separating foreground and background of based codebook In a multi-view image | |
| CN104052979B (en) | For device and the technology of image processing | |
| CN105096347B (en) | Image processing apparatus and method | |
| CN112348765A (en) | Data enhancement method and device, computer readable storage medium and terminal equipment | |
| CN108510491A (en) | Blur the filter method of skeleton critical point detection result under background | |
| CN108765333B (en) | Depth map perfecting method based on depth convolution neural network | |
| CN111738045B (en) | Image detection method and device, electronic equipment and storage medium | |
| CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
| CN105590307A (en) | Transparency-based matting method and apparatus | |
| CN108377374A (en) | Method and system for generating depth information related to an image | |
| CN110490839A (en) | The method, apparatus and computer equipment of failure area in a kind of detection highway | |
| CN106326895A (en) | Image processing device and image processing method | |
| Leavline et al. | On teaching digital image processing with MATLAB | |
| CN111340831A (en) | Point cloud edge detection method and device | |
| CN108960012B (en) | Feature point detection method and device and electronic equipment | |
| Wang et al. | Combining semantic scene priors and haze removal for single image depth estimation | |
| Zhu et al. | Atmospheric light estimation in hazy images based on color-plane model | |
| CN114155375A (en) | Method and device for detecting airport pavement diseases, electronic equipment and storage medium | |
| CN106530286A (en) | Method and device for determining definition level | |
| CN103679684A (en) | Device, method and electronic equipment for detecting cloud in image | |
| CN109035210B (en) | Dyed picture processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |