CN103905737A - Backlight detection method and device - Google Patents
Backlight detection method and device Download PDFInfo
- Publication number
- CN103905737A CN103905737A CN201210572564.3A CN201210572564A CN103905737A CN 103905737 A CN103905737 A CN 103905737A CN 201210572564 A CN201210572564 A CN 201210572564A CN 103905737 A CN103905737 A CN 103905737A
- Authority
- CN
- China
- Prior art keywords
- backlight
- environment
- gray scale
- image
- gray
- 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
Abstract
The invention provides a backlight detection method and device. The backlight detection method comprises the following steps: an image is acquired; a gray histogram of the image is extracted; and the current environment is determined whether to be the backlight environment according to the gray histogram. When a CMOS backlight detection sensor is not needed, backlight detection is performed simply based on the acquired image, so the backlight detection cost can be reduced advantageously, and the cost of an electronic device adopting the backlight detection method and device can be further reduced.
Description
Technical field
The present invention relates to backlight environment measuring, and relate more specifically to a kind of backlighting detecting and device.
Background technology
At present, the application of digital camera is more and more extensive.Except professional digital camera product, the integrated digital camera of different accuracy on numerous electronic equipments.For example, mostly integrated digital camera head in notebook computer, mostly integrated digital camera in PDA(Personal Digital Assistant) and smart mobile phone, also integrated digital camera in panel computer.
In the time utilizing digital camera to carry out image taking, inevitably can run into the problem that backlight scene is taken and non-backlight scene is taken.Under backlight scene, the acquisition parameters that need to adjust digital camera suppresses to take thing and crosses dark and background is excessively bright.Described acquisition parameters generally comprises F-number, time for exposure etc.
In existing digital camera, often comprise CMOS backlight detecting sensor, and utilize this CMOS backlight detecting sensor automatically to detect the shooting state of backlight.In the time that digital camera detects backlight environment, can automatically adjust acquisition parameters and suppress to take thing and cross dark and background is excessively bright.
Along with digital camera is applied in various electronic equipments more and more, in order to reduce as much as possible the manufacturing cost of electronic equipment, the cost that how to reduce digital camera also more and more comes into one's own.Therefore, the present invention is desirable to provide a kind of method of carrying out the estimation of backlight environment without CMOS backlight detecting sensor in the situation that, thereby even if in digital camera and even various electronic equipment, does not comprise that CMOS backlight detecting sensor also can obtain high-quality photographic images.
Summary of the invention
Consider the problems referred to above, made the present invention.The present invention aims to provide a kind of backlighting detecting and device, and it directly carries out backlight detection according to the image of current collection without CMOS backlight detecting sensor in the situation that.Thus, make automatically to adjust acquisition parameters according to this backlight testing result.
According to an aspect of the present invention, provide a kind of backlighting detecting, having comprised: gathered an image; Extract the grey level histogram of described image; And determine according to described grey level histogram whether current environment is backlight environment.
Preferably, in described backlighting detecting, determine according to described grey level histogram whether current environment is that backlight environment comprises: the variance of calculating the grey level histogram of described image; And determine according to described variance whether current environment is backlight environment.
Preferably, in described backlighting detecting, determine according to described grey level histogram whether current environment is that backlight environment comprises: the local peaking distributing according to gray probability in described grey level histogram determines whether current environment is backlight environment, wherein, when the gray scale at the place of local peaking distributing at described gray probability is less than the first gray scale or is greater than the second gray scale, determine that current environment is backlight environment; And the gray scale at the place of local peaking distributing at described gray probability is when being greater than the 3rd gray scale and being less than the 4th gray scale, determine that current environment is non-backlight environment, wherein, described the first gray scale is less than or equal to the 3rd gray scale, described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
Preferably, in described backlighting detecting, this image is coloured image, and the grey level histogram that extracts this image comprises: convert the image to gray level image; And extract the grey level histogram of described gray level image.
Preferably, in described backlighting detecting, determine according to described variance whether current environment is that backlight environment comprises: determine backlight degree according to described variance; And in the time that described backlight degree is greater than predetermined threshold, determine that current environment is backlight environment.
Preferably, in described backlighting detecting, determine according to described variance whether current environment is that backlight environment comprises: determine backlight degree according to described variance; And determine that according to described backlight degree current environment is the probability of backlight environment.
Preferably, in described backlighting detecting, determine according to described variance whether current environment is that backlight environment also comprises: in the time that determined probability is greater than predetermined probability threshold value, determine that current environment is backlight environment.
Preferably, in described backlighting detecting, described method also comprises: by described probability and the backlight ambient probability combination of calculating by other method, to determine that whether current environment is as backlight environment.
According to a further aspect of the invention, provide a kind of backlight checkout gear, having comprised: image acquisition component, for obtaining image, this image is the image of taking under current environment; Histogram extracts parts, for extracting the grey level histogram of described image; And informating part, for determining according to described grey level histogram whether described current environment is backlight environment.
Preferably, described informating part comprises: variance calculating unit, for calculating the variance of grey level histogram of described image; And environment determining means, for determining according to described variance whether current environment is backlight environment.
Preferably, the local peaking that described informating part distributes according to gray probability in described grey level histogram determines whether current environment is backlight environment, wherein, when the gray scale at the place of local peaking distributing at described gray probability is less than the first gray scale or is greater than the second gray scale, described informating part determines that current environment is backlight environment; And the gray scale at the place of local peaking distributing at described gray probability is when being greater than the 3rd gray scale and being less than the 4th gray scale, described informating part determines that current environment is non-backlight environment, wherein, described the first gray scale is less than or equal to the 3rd gray scale, described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
Preferably, described backlight checkout gear also comprises: image converting member, for described coloured image being converted to gray level image in the time that described image is coloured image, wherein, described histogram extraction parts extract the grey level histogram of described gray level image.
Preferably, described environment determining means comprises: backlight degree calculating unit, and for determining backlight degree according to described variance, and backlight determining means, for determining that in the time that described backlight degree is greater than predetermined threshold current environment is backlight environment.
Preferably, described environment determining means comprises: backlight degree calculating unit, for determining backlight degree according to described variance; Backlight ambient probability calculating unit, for determining that according to described backlight degree current environment is the probability of backlight environment; And backlight determining means, for determining that in the time that determined probability is greater than predetermined probability threshold value current environment is backlight environment.
Preferably, described environment determining means comprises: backlight degree calculating unit, for determining backlight degree according to described variance; Backlight ambient probability calculating unit, for determining that according to described backlight degree current environment is the probability of backlight environment; And backlight determining means, for determined probability and the backlight ambient probability calculating by other method are combined, to determine that whether current environment is as backlight environment.
Preferably, in described backlighting detecting and device, described grey level histogram comprises multiple gray scales and the corresponding pixel quantity of each gray scale, or described grey level histogram is normalized grey level histogram, described normalized grey level histogram comprises multiple gray scales and the corresponding probability of occurrence of each gray scale.
Utilize according to the backlighting detecting of the embodiment of the present invention and device, can without CMOS backlight detecting sensor in the situation that, carry out simply backlight detection by the image based on gathered, thereby advantageously reduce the cost that backlight detects, and and then reduced the cost of the electronic equipment of applying described backlighting detecting and device.
Brief description of the drawings
Describe according to the embodiment of the present invention by reference to accompanying drawing, the various feature and advantage of the embodiment of the present invention will be more obvious, and also more easily be understood, in the accompanying drawings:
Fig. 1 is according to the flow chart of the backlighting detecting of the embodiment of the present invention;
Fig. 2 shows according to the particular flow sheet of the first example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention;
Fig. 3 shows according to the particular flow sheet of the second example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention;
Fig. 4 shows according to the particular flow sheet of the third example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention;
Fig. 5 shows according to the particular flow sheet of the 4th of the step S130 in Fig. 1 of the embodiment of the present invention the kind of example implementation mode;
Fig. 6 shows according to the schematic block diagram of the backlight checkout gear of the embodiment of the present invention;
The grey level histogram that Fig. 7 A shows under exemplary backlight environment distributes;
The grey level histogram that Fig. 7 B shows under exemplary non-backlight environment distributes; And
Fig. 8 shows exemplary backlight degree and the curve chart of backlight ambient probability.
Embodiment
Describe below with reference to the accompanying drawings according to the backlighting detecting of the embodiment of the present invention and electronic equipment.
In Fig. 7 A and Fig. 7 B, the grey level histogram showing respectively under grey level histogram distribution and the non-backlight environment under exemplary backlight environment distributes, and wherein transverse axis represents gray scale.
Under a kind of sample situation, grey level histogram can be the histogram that embodies the relation between each gray scale and the corresponding pixel count of each gray scale, in the case, grey level histogram comprises multiple gray scales (for example 128,256,512 gray scales etc.) and the corresponding pixel quantity of each gray scale.In the case, the longitudinal axis of Fig. 7 A and Fig. 7 B represents pixel quantity.
Under another kind of sample situation, grey level histogram can be normalized grey level histogram, described normalized grey level histogram embodies the relation between each gray scale and the corresponding probability of occurrence of each gray scale, in the case, grey level histogram comprises multiple gray scales (for example 128,256,512 gray scales etc.) and the corresponding probability of occurrence of each gray scale, and described probability of occurrence can be the corresponding pixel count of each gray scale and the ratio of total pixel number.In the case, the longitudinal axis of Fig. 7 A and Fig. 7 B represents the probability of occurrence of each gray scale.
From Fig. 7 A and Fig. 7 B, can find out, the grey level histogram under backlight environment distributes and distributes completely different from the grey level histogram under non-backlight environment.As shown in Figure 7 A, the feature that grey level histogram under backlight environment distributes is: be distributed in pixel in incandescent and utmost point dark gray many, and it is relatively less to be distributed in pixel in middle gray.In contrast, as shown in Figure 7 B, grey level histogram under non-backlight environment distributes and is characterised in that: pixel mainly concentrates in middle gray, and it is considerably less to be distributed in pixel in incandescent and utmost point dark gray.As can be seen here, the distribution of the grey level histogram under backlight environment distributes and has significant difference with the grey level histogram under non-backlight environment.
Although the grey level histogram only having provided in Fig. 7 A and Fig. 7 B under grey level histogram distribution and the non-backlight environment under exemplary backlight environment distributes, and for different photographed scenes, grey level histogram under backlight environment distributes and may be not quite similar, and for different photographed scenes, grey level histogram under non-backlight environment distributes and is also not quite similar, be also that grey level histogram under non-backlight environment distributes but be no matter that grey level histogram under backlight environment distributes, all there is good statistical property.That is, the feature that grey level histogram under backlight environment distributes is: be distributed in pixel in incandescent and utmost point dark gray many, and it is relatively less to be distributed in pixel in middle gray; Grey level histogram under non-backlight environment distributes and is characterised in that: pixel mainly concentrates in middle gray, and it is considerably less to be distributed in pixel in incandescent and utmost point dark gray.
Consider above-mentioned characteristic, inventor has proposed a kind of method of carrying out backlight detection based on image itself.
First, with reference to Fig. 1, the backlighting detecting 100 according to the embodiment of the present invention is described.Start at step S101 according to the backlighting detecting 100 of the embodiment of the present invention.
At step S110, gather image.Gather image and can comprise with exposal model collection image, or gather image with image pickup mode, or gather image with preview mode.In addition, gather image and can comprise memory image or non-memory image.For example, collection image can be included in the process of focusing while taking pictures and gather image and storage or non-memory image, can be included under preview mode and gather image and storage or non-memory image, can be included in and under image pickup mode, gather image and memory image.In addition, collection image can be included under default backlight detecting pattern and gather image and storage or non-memory image.
At step S120, extract the grey level histogram of the image gathering.The image gathering can be gray level image or coloured image.Be coloured image at gathered image, can first gathered image be converted to gray level image.Then, then based on gray level image extract grey level histogram.How coloured image being converted to gray level image is well known to a person skilled in the art, therefore omits its specific descriptions at this.
How to travel through the each pixel of gathered image and also well known to a person skilled in the art to extract grey level histogram, therefore also omit its specific descriptions at this.
At step S130, determine according to described grey level histogram whether current environment is backlight environment.Particularly, determine according to the feature of described grey level histogram whether current environment is backlight environment.
As previously mentioned, the feature that grey level histogram under backlight environment distributes is: be distributed in pixel in incandescent and utmost point dark gray many, and it is relatively less to be distributed in pixel in middle gray; Grey level histogram under non-backlight environment distributes and is characterised in that: pixel mainly concentrates in middle gray, and it is considerably less to be distributed in pixel in incandescent and utmost point dark gray.
In addition, aspect statistical property, distribute for the grey level histogram under backlight environment, the gray variance σ that its grey level histogram distributes
2very large; And distribute for the grey level histogram under non-backlight environment, the gray variance σ that its grey level histogram distributes
2very little.
Then,, at step S199, finish according to the backlighting detecting 100 of the embodiment of the present invention.
The normalized grey level histogram of supposing gathered image I is X=(x
1, x
2..., x
256)
t, wherein x
irepresent the probability that i gray scale occurs in gathered image I.
Next,, based on this normalized grey level histogram, will illustrate according to the specific implementation of step S130 in the backlighting detecting 100 of the embodiment of the present invention.
In Fig. 2, illustrate according to the particular flow sheet of the first example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention.
In the first example implementation mode, the local peaking distributing according to gray probability in described grey level histogram determines whether current environment is backlight environment.
At step S2310, determine the local peaking that in described grey level histogram, gray probability distributes.And, correspondingly determine the corresponding gray scale of described local peaking.In conjunction with Fig. 7 A, determined local peaking can be for example corresponding gray probability of gray value 3 and for example corresponding gray probability of gray value 250.
Then,, at step S2320, determine whether the gray scale at the place of local peaking of described gray probability distribution is less than the first gray scale or is greater than the second gray scale.
In the time determining that at step S2320 the gray scale at the place of local peaking that described gray probability distributes is less than the first gray scale or is greater than the second gray scale, at step S2330, determine that current environment is backlight environment.For example, still in conjunction with Fig. 7 A, described the first gray scale can be for example gray value 30, described the second gray scale can be for example gray value 180, determined local peaking (gray value 3) is less than described the first gray scale, and determined local peaking (gray value 250) is greater than described the second gray scale, and therefore, the current environment of this image is confirmed as backlight environment.
In the time determining that at step S2320 the gray scale at the place of local peaking that described gray probability distributes is not less than the first gray scale and is not more than the second gray scale, this backlighting detecting advances to step S2340.
At step S2340, determine whether the gray scale at the place of local peaking of described gray probability distribution is greater than the 3rd gray scale and is less than the 4th gray scale.
In the time determining that at step S2340 the gray scale at the place of local peaking that described gray probability distributes is greater than the 3rd gray scale and is less than the 4th gray scale, at step S2350, determine that current environment is non-backlight environment, for example, in conjunction with Fig. 7 B, described the 3rd gray scale can be for example gray value 80, described the 4th gray scale can be for example gray value 180, determined local peaking (gray value 100) is greater than described the 3rd gray scale and is less than described the 4th gray scale, therefore, the current environment of this image is confirmed as non-backlight environment.
In the time determining that at step S2340 the gray scale at the place of local peaking that described gray probability distributes is not more than the 3rd gray scale and is not less than the 4th gray scale, this backlighting detecting can be back to step S110 Resurvey image, or adopts other backlighting detecting to carry out backlight detection.
Described the first gray scale is less than or equal to the 3rd gray scale, and described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
The situation of the gray scale that is less than described the 3rd gray scale and determined local peaking place for described the first gray scale between described the first gray scale and described the 3rd gray scale, can Resurvey image and re-start backlight and detect, or can adopt other method to carry out backlight detection.
Similarly, the situation of the gray scale that is less than described the second gray scale and determined local peaking place for described the 4th gray scale between described the 4th gray scale and described the second gray scale, can Resurvey image and re-start backlight and detect, or can adopt other method to carry out backlight detection.
Fig. 3 shows according to the particular flow sheet of the second example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention.
In the second example implementation mode, determine according to the variance of grey level histogram whether current environment is backlight environment.
For described normalized grey level histogram X=(x
1, x
2..., x
256)
t, the population mean μ of intensity profile and variances sigma
2can be represented as:
Can set variance threshold values, in the time that the variance of extracted grey level histogram is greater than this variance threshold values, determine that current environment is backlight environment, otherwise current environment be non-backlight environment.Described variance threshold values can be according to test, rule of thumb, arrange according to personal like etc.
At step S3310, calculate as described above the variance of the grey level histogram extracting.
Then,, at step S3320, determine according to calculated variance whether current environment is backlight environment.
Fig. 4 shows according to the particular flow sheet of the third example implementation mode of the step S130 in Fig. 1 of the embodiment of the present invention.
In the third example implementation mode, can calculate backlight degree based on variance, and can define backlight degree threshold value, the relation between the backlight degree based on calculated and described backlight degree threshold value determines whether current environment is backlight environment.
At step S4310, calculate as described above the variance of the grey level histogram extracting.
Then,, at step S4320, determine backlight degree according to calculated variance.Backlight degree can represent the backlight degree of present image.Backlight degree can be described variance, can be also the function of described variance.As an example, can be by backlight degree d
bLbe defined as:
d
BL=f(X)=σ
At step S4330, whether the backlight degree that judgement is calculated is greater than predetermined backlight degree threshold value.
When in the time that step S4330 judges that the backlight degree calculating is greater than predetermined backlight degree threshold value, determine that at step S4340 current environment is backlight environment.
When in the time that step S4330 judges that the backlight degree calculating is not more than predetermined backlight degree threshold value, determine that at step S4350 current environment is non-backlight environment.
In order to reduce False Rate, the 4th kind of example implementation mode further proposed.
Fig. 5 shows according to the particular flow sheet of the 4th of the step S130 in Fig. 1 of the embodiment of the present invention the kind of example implementation mode.
In the 4th kind of example implementation mode, can calculate backlight degree based on variance, and backlight degree based on calculated determines backlight ambient probability, and then determine based on backlight ambient probability whether current environment is backlight environment.
Consider to build following sample (d
bL, Y), wherein Y only gets positive and negative 1 (± 1), and positive 1 (+1) represents backlight, and negative 1 (1) represents non-backlight, d
bLfor backlight degree defined above.
By gathering multiple samples, and utilize these samples to do binary Logistic recurrence, training obtains Sigmoid form probability function:
This Sigmoid form probability function represents that working as backlight degree is d
bLtime, current environment is the probability of backlight environment.Thus, can be by backlight degree d
bLbe converted to the probability of gathered image I under backlight environment.Then, can adjudicate whether backlight of image I by this probability.
Figure 8 illustrates this transformation curve, wherein transverse axis represents backlight degree d
bL, the longitudinal axis represents backlight ambient probability.In the time that backlight degree is greater than certain threshold value T, P (Y=1) is greater than 0.5, and in the time that backlight degree is less than T, P (Y=1) is less than 0.5.
At step S5310, calculate as described above the variance of the grey level histogram extracting.
At step S5320, determine backlight degree according to calculated variance as described above.
Then,, at step S5330, determine that according to described backlight degree whether current environment is the probability of backlight environment,, determines backlight ambient probability according to described backlight degree that is.
Can be as the formula (3) or as illustrated in fig. 8, determine backlight ambient probability according to backlight degree.
At step S5340, determine according to determined backlight ambient probability whether current environment is backlight environment.
In one example, backlight ambient probability threshold value (for example, 0.7) is set, in the time that determined backlight ambient probability is greater than this backlight ambient probability threshold value, determines that current environment is backlight environment.Otherwise, determine that current environment is non-backlight environment.
In another example, in step S5340, can combine the backlight ambient probability calculating or other parameter from another backlighting detecting, and backlight ambient probability based on calculating according to the backlighting detecting of the embodiment of the present invention detects with carry out final backlight from the testing result of another backlighting detecting, thereby improve accuracy of detection.
Next, describe according to the backlight checkout gear 600 of the embodiment of the present invention with reference to Fig. 6.
Figure 6 illustrates according to the schematic block diagram of the backlight checkout gear 600 of the embodiment of the present invention.
As shown in Figure 6, this backlight checkout gear 600 comprises that image acquisition component 610, histogram extract parts 620 and informating part 630.
The image that image acquisition component 610 is taken under current environment from taking component retrieval.
In the first example implementation mode, the local peaking that described informating part 630 distributes according to gray probability in described grey level histogram determines whether current environment is backlight environment.
Particularly, when the gray scale at the place of local peaking distributing at described gray probability is less than the first gray scale or is greater than the second gray scale, described informating part 630 determines that current environment is backlight environment; When the gray scale at the place of local peaking distributing at described gray probability is greater than the 3rd gray scale and is less than the 4th gray scale, described informating part 630 determines that current environment is non-backlight environment, wherein, described the first gray scale is less than or equal to the 3rd gray scale, described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
In the second example implementation mode, described informating part 630 can comprise variance calculating unit and environment determining means.
Variance calculating unit calculates the variance of the grey level histogram of described image as described above.
Environment determining means determines according to described variance whether current environment is backlight environment.
Particularly, in the time that the variance of extracted grey level histogram is greater than pre-determined variance threshold value, described environment determining means determines that current environment is backlight environment.
In the third example implementation mode, described informating part 630 can comprise variance calculating unit and environment determining means, and described environment determining means further can comprise backlight degree calculating unit and backlight determining means.
Backlight degree calculating unit is determined backlight degree according to described variance as described above.In the time that described backlight degree is greater than predetermined threshold, described backlight determining means determines that current environment is backlight environment.
In the 4th kind of example implementation mode, described informating part 630 can comprise variance calculating unit and environment determining means, and described environment determining means further can comprise backlight degree calculating unit, backlight ambient probability calculating unit and backlight determining means.
Backlight degree calculating unit is determined backlight degree according to described variance as described above.
Backlight ambient probability calculating unit determines that according to described backlight degree current environment is the probability of backlight environment as described above.
In the time that determined probability is greater than predetermined probability threshold value, described backlight determining means determines that current environment is backlight environment.
Alternatively, described backlight determining means can also be by determined probability and the combination of the backlight calculating by other method ambient probability, to determine that whether current environment is as backlight environment.
As previously mentioned, the image that described image acquisition component 610 is obtained can be coloured image or gray level image.
Described backlight checkout gear can also comprise image converting member, for described coloured image is converted to gray level image.And described histogram extraction parts extract the grey level histogram of described gray level image.
Described backlight checkout gear can be applied to having in the various electronic equipments of digital camera, and can realize with independent processor, or moves corresponding program by the central processing unit of respective electronic equipment and realize.
Although illustrated as an example of normalized grey level histogram example according to the backlighting detecting of the embodiment of the present invention and device above, but should be understood that according to the backlighting detecting of the embodiment of the present invention and install and can apply in a similar manner equally the grey level histogram that embodies the relation between each gray scale and the corresponding pixel count of each gray scale.
According to the backlighting detecting of the embodiment of the present invention and device, the image based on taking under current environment can carry out backlight detection simply, has eliminated the needs to special CMOS backlight detecting sensor, thereby has advantageously reduced manufacturing cost.
Be described with reference to the drawings above according to the backlighting detecting of the embodiment of the present invention and device.It will be understood by a person skilled in the art that, the invention is not restricted to above-described embodiment, in the situation that not departing from spirit of the present invention, can make various amendments, described amendment also should be included within the scope of the present invention.Scope of the present invention should be limited by claims and equivalent thereof.
Claims (19)
1. a backlighting detecting, comprising:
Gather an image;
Extract the grey level histogram of described image; And
Determine according to described grey level histogram whether current environment is backlight environment.
2. backlighting detecting as claimed in claim 1, wherein, determine according to described grey level histogram whether current environment is that backlight environment comprises:
Calculate the variance of the grey level histogram of described image; And
Determine according to described variance whether current environment is backlight environment.
3. backlighting detecting as claimed in claim 1, wherein, determine according to described grey level histogram whether current environment is that backlight environment comprises:
The local peaking distributing according to gray probability in described grey level histogram determines whether current environment is backlight environment, wherein,
When the gray scale at the place of local peaking distributing at described gray probability is less than the first gray scale or is greater than the second gray scale, determine that current environment is backlight environment; And
When the gray scale at the place of local peaking distributing at described gray probability is greater than the 3rd gray scale and is less than the 4th gray scale, determine that current environment is non-backlight environment,
Wherein, described the first gray scale is less than or equal to the 3rd gray scale, and described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
4. backlighting detecting as claimed in claim 1, wherein, this image is coloured image, the grey level histogram that extracts this image comprises:
Convert the image to gray level image; And
Extract the grey level histogram of described gray level image.
5. backlighting detecting as claimed in claim 1, wherein, described grey level histogram comprises multiple gray scales and the corresponding pixel quantity of each gray scale, or
Described grey level histogram is normalized grey level histogram, and described normalized grey level histogram comprises multiple gray scales and the corresponding probability of occurrence of each gray scale.
6. backlighting detecting as claimed in claim 2, wherein, determine according to described variance whether current environment is that backlight environment comprises:
Determine backlight degree according to described variance; And
In the time that described backlight degree is greater than predetermined threshold, determine that current environment is backlight environment.
7. backlighting detecting as claimed in claim 6, wherein,
Described backlight degree is described variance, or is the function of described variance.
8. backlighting detecting as claimed in claim 2, wherein, determine according to described variance whether current environment is that backlight environment comprises:
Determine backlight degree according to described variance; And
Determine that according to described backlight degree current environment is the probability of backlight environment.
9. backlighting detecting as claimed in claim 8, wherein, determine according to described variance whether current environment is that backlight environment also comprises:
In the time that determined probability is greater than predetermined probability threshold value, determine that current environment is backlight environment.
10. backlighting detecting as claimed in claim 8, wherein, described method also comprises:
By described probability and the backlight ambient probability combination of calculating by other method, to determine that whether current environment is as backlight environment.
11. 1 kinds of backlight checkout gears, comprising:
Image acquisition component, for obtaining image, this image is the image of taking under current environment;
Histogram extracts parts, for extracting the grey level histogram of described image; And
Informating part, for determining according to described grey level histogram whether described current environment is backlight environment.
12. backlight checkout gears as claimed in claim 11, wherein, described informating part comprises:
Variance calculating unit, for calculating the variance of grey level histogram of described image; And
Environment determining means, for determining according to described variance whether current environment is backlight environment.
13. backlight checkout gears as claimed in claim 11, wherein, the local peaking that described informating part distributes according to gray probability in described grey level histogram determines whether current environment is backlight environment, wherein,
When the gray scale at the place of local peaking distributing at described gray probability is less than the first gray scale or is greater than the second gray scale, described informating part determines that current environment is backlight environment; And
When the gray scale at the place of local peaking distributing at described gray probability is greater than the 3rd gray scale and is less than the 4th gray scale, described informating part determines that current environment is non-backlight environment,
Wherein, described the first gray scale is less than or equal to the 3rd gray scale, and described the 3rd gray scale is less than the 4th gray scale, and described the 4th gray scale is less than or equal to described the second gray scale.
14. backlight checkout gears as claimed in claim 11, wherein, described image is coloured image,
Described backlight checkout gear also comprises: image converting member, and for described coloured image is converted to gray level image,
Wherein, described histogram extraction parts extract the grey level histogram of described gray level image.
15. backlight checkout gears as claimed in claim 11, wherein, described grey level histogram comprises multiple gray scales and the corresponding pixel quantity of each gray scale, or
Described grey level histogram is normalized grey level histogram, and described normalized grey level histogram comprises multiple gray scales and the corresponding probability of occurrence of each gray scale.
16. backlight checkout gears as claimed in claim 12, wherein, described environment determining means comprises:
Backlight degree calculating unit, for determining backlight degree according to described variance,
Backlight determining means, for determining that in the time that described backlight degree is greater than predetermined threshold current environment is backlight environment.
17. backlight checkout gears as claimed in claim 12, wherein, described environment determining means comprises:
Backlight degree calculating unit, for determining backlight degree according to described variance; And
Backlight ambient probability calculating unit, for determining that according to described backlight degree current environment is the probability of backlight environment.
18. backlight checkout gears as claimed in claim 17, wherein, described environment determining means also comprises:
Backlight determining means, for determining that in the time that determined probability is greater than predetermined probability threshold value current environment is backlight environment.
19. backlight checkout gears as claimed in claim 17, wherein, described environment determining means also comprises:
Backlight determining means, for determined probability and the backlight ambient probability calculating by other method are combined, to determine that whether current environment is as backlight environment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210572564.3A CN103905737B (en) | 2012-12-25 | 2012-12-25 | Backlighting detecting and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210572564.3A CN103905737B (en) | 2012-12-25 | 2012-12-25 | Backlighting detecting and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103905737A true CN103905737A (en) | 2014-07-02 |
CN103905737B CN103905737B (en) | 2017-09-29 |
Family
ID=50996867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210572564.3A Active CN103905737B (en) | 2012-12-25 | 2012-12-25 | Backlighting detecting and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103905737B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105049743A (en) * | 2015-08-21 | 2015-11-11 | 宇龙计算机通信科技(深圳)有限公司 | Backlight testing method, backlight testing system, picture taking device and terminal |
CN105227843A (en) * | 2015-10-20 | 2016-01-06 | 宇龙计算机通信科技(深圳)有限公司 | The filming control method of terminal, the imaging control device of terminal and terminal |
CN105611140A (en) * | 2015-07-31 | 2016-05-25 | 宇龙计算机通信科技(深圳)有限公司 | Photographing control method, photographing control device and terminal |
CN105657287A (en) * | 2015-08-24 | 2016-06-08 | 宇龙计算机通信科技(深圳)有限公司 | Backlighting scene detection method and device and imaging device |
CN105812622A (en) * | 2014-12-30 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN105872399A (en) * | 2016-04-19 | 2016-08-17 | 奇酷互联网络科技(深圳)有限公司 | Backlighting detection method and system |
CN107395988A (en) * | 2017-08-31 | 2017-11-24 | 华勤通讯技术有限公司 | The control method and system of the camera of mobile terminal |
CN107451969A (en) * | 2017-07-27 | 2017-12-08 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
CN107682611A (en) * | 2017-11-03 | 2018-02-09 | 广东欧珀移动通信有限公司 | Method, apparatus, computer-readable recording medium and the electronic equipment of focusing |
CN107862290A (en) * | 2017-11-10 | 2018-03-30 | 智车优行科技(北京)有限公司 | Method for detecting lane lines and system |
CN107888840A (en) * | 2017-10-30 | 2018-04-06 | 广东欧珀移动通信有限公司 | High-dynamic-range image acquisition method and device |
CN108337448A (en) * | 2018-04-12 | 2018-07-27 | Oppo广东移动通信有限公司 | High-dynamic-range image acquisition method, device, terminal device and storage medium |
CN110708469A (en) * | 2018-07-10 | 2020-01-17 | 北京地平线机器人技术研发有限公司 | Method and device for adapting exposure parameters and corresponding camera exposure system |
CN110868533A (en) * | 2019-10-15 | 2020-03-06 | 宇龙计算机通信科技(深圳)有限公司 | HDR mode determination method, device, storage medium and terminal |
CN112312001A (en) * | 2019-07-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Image detection method, device, equipment and computer storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101582991B (en) * | 2008-05-13 | 2011-02-09 | 华为终端有限公司 | Method and device for processing image |
CN102196182A (en) * | 2010-03-09 | 2011-09-21 | 株式会社理光 | Backlight detection equipment and method |
CN102542552B (en) * | 2010-12-21 | 2015-06-03 | 北京汉王智通科技有限公司 | Frontlighting and backlighting judgment method of video images and detection method of shooting time |
-
2012
- 2012-12-25 CN CN201210572564.3A patent/CN103905737B/en active Active
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105812622A (en) * | 2014-12-30 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN105611140A (en) * | 2015-07-31 | 2016-05-25 | 宇龙计算机通信科技(深圳)有限公司 | Photographing control method, photographing control device and terminal |
WO2017020382A1 (en) * | 2015-07-31 | 2017-02-09 | 宇龙计算机通信科技(深圳)有限公司 | Photography control method, photography control device and terminal |
CN105049743B (en) * | 2015-08-21 | 2019-03-22 | 宇龙计算机通信科技(深圳)有限公司 | Backlighting detecting, backlight detection system, photographing device and terminal |
CN105049743A (en) * | 2015-08-21 | 2015-11-11 | 宇龙计算机通信科技(深圳)有限公司 | Backlight testing method, backlight testing system, picture taking device and terminal |
CN105657287A (en) * | 2015-08-24 | 2016-06-08 | 宇龙计算机通信科技(深圳)有限公司 | Backlighting scene detection method and device and imaging device |
CN105227843A (en) * | 2015-10-20 | 2016-01-06 | 宇龙计算机通信科技(深圳)有限公司 | The filming control method of terminal, the imaging control device of terminal and terminal |
CN105872399A (en) * | 2016-04-19 | 2016-08-17 | 奇酷互联网络科技(深圳)有限公司 | Backlighting detection method and system |
CN105872399B (en) * | 2016-04-19 | 2019-10-08 | 奇酷互联网络科技(深圳)有限公司 | Backlighting detecting and backlight detection system |
CN107451969A (en) * | 2017-07-27 | 2017-12-08 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
CN107451969B (en) * | 2017-07-27 | 2020-01-10 | Oppo广东移动通信有限公司 | Image processing method, image processing device, mobile terminal and computer readable storage medium |
CN107395988A (en) * | 2017-08-31 | 2017-11-24 | 华勤通讯技术有限公司 | The control method and system of the camera of mobile terminal |
CN107888840B (en) * | 2017-10-30 | 2019-10-15 | Oppo广东移动通信有限公司 | High-dynamic-range image acquisition method and device |
CN107888840A (en) * | 2017-10-30 | 2018-04-06 | 广东欧珀移动通信有限公司 | High-dynamic-range image acquisition method and device |
CN107682611A (en) * | 2017-11-03 | 2018-02-09 | 广东欧珀移动通信有限公司 | Method, apparatus, computer-readable recording medium and the electronic equipment of focusing |
CN107862290A (en) * | 2017-11-10 | 2018-03-30 | 智车优行科技(北京)有限公司 | Method for detecting lane lines and system |
CN107862290B (en) * | 2017-11-10 | 2021-09-24 | 智车优行科技(北京)有限公司 | Lane line detection method and system |
CN108337448A (en) * | 2018-04-12 | 2018-07-27 | Oppo广东移动通信有限公司 | High-dynamic-range image acquisition method, device, terminal device and storage medium |
CN110708469A (en) * | 2018-07-10 | 2020-01-17 | 北京地平线机器人技术研发有限公司 | Method and device for adapting exposure parameters and corresponding camera exposure system |
CN112312001A (en) * | 2019-07-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Image detection method, device, equipment and computer storage medium |
CN112312001B (en) * | 2019-07-30 | 2022-08-23 | 阿波罗智能技术(北京)有限公司 | Image detection method, device, equipment and computer storage medium |
CN110868533A (en) * | 2019-10-15 | 2020-03-06 | 宇龙计算机通信科技(深圳)有限公司 | HDR mode determination method, device, storage medium and terminal |
Also Published As
Publication number | Publication date |
---|---|
CN103905737B (en) | 2017-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103905737A (en) | Backlight detection method and device | |
Choi et al. | Referenceless prediction of perceptual fog density and perceptual image defogging | |
CN101520842B (en) | Information processing apparatus, eye open/closed degree determination method and image sensing apparatus | |
US9838616B2 (en) | Image processing method and electronic apparatus | |
CN105227843A (en) | The filming control method of terminal, the imaging control device of terminal and terminal | |
CN105979125A (en) | Photographing method and system based on screen light supplement | |
WO2018228310A1 (en) | Image processing method and apparatus, and terminal | |
CN110572636B (en) | Camera contamination detection method and device, storage medium and electronic equipment | |
CN105872399B (en) | Backlighting detecting and backlight detection system | |
CN113992861A (en) | Image processing method and image processing device | |
CN103093458A (en) | Detecting method and detecting device for key frame | |
CN112507923B (en) | Certificate copying detection method and device, electronic equipment and medium | |
CN107221005A (en) | Object detecting method and device | |
CN109961403B (en) | Photo adjusting method and device, storage medium and electronic equipment | |
WO2023005827A1 (en) | Exposure compensation method and apparatus, and electronic device | |
CN106327531A (en) | Panorama video identification method and device, and video playing method and device | |
CN114494442A (en) | Image processing method, device and equipment | |
CN105913403A (en) | Image denoising method and system | |
CN107180417B (en) | Photo processing method and device, computer readable storage medium and electronic equipment | |
CN102821240A (en) | Method and system for capturing images based on object detection technologies | |
WO2023071933A1 (en) | Camera photographing parameter adjustment method and apparatus and electronic device | |
CN107742165A (en) | Data processing method and related product | |
CN108389182B (en) | Image quality detection method and device based on deep neural network | |
CN105657287A (en) | Backlighting scene detection method and device and imaging device | |
CN113132762B (en) | Retention behavior factor analysis method and device, electronic equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |