CN107071231A - Image change recognition methods and device - Google Patents
Image change recognition methods and device Download PDFInfo
- Publication number
- CN107071231A CN107071231A CN201710245721.2A CN201710245721A CN107071231A CN 107071231 A CN107071231 A CN 107071231A CN 201710245721 A CN201710245721 A CN 201710245721A CN 107071231 A CN107071231 A CN 107071231A
- Authority
- CN
- China
- Prior art keywords
- image
- contrast images
- brightness
- change
- absolute value
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/147—Scene change detection
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
A kind of image change recognition methods, this method includes：Obtain at least two frame preview images that camera device is collected；Benchmark image and contrast images are chosen from the preview image；The brightness of the benchmark image and the brightness of the contrast images are contrasted, with the changing condition for the image content for recognizing the preview image.The present invention also provides a kind of image change identifying device.The present invention can recognize the situation of change of the image content of image.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of image change recognition methods and device.
Background technology
Being taken pictures, image, the IMAQ operation such as video monitoring or during image processing operations, it is necessary to recognize image
Image content with the presence or absence of change, so that operation is further processed.For example, obtaining in real time in the picture that camera is collected
Hold, after image content is stable, carry out the operation such as auto-focusing.If can not judge, image frame content whether there is change,
The unintelligible visual focus shot, the fuzzy pictures that photograph can be caused during IMAQ, the problems such as image noise is more, so that
Reduce the imaging effect of image.
The content of the invention
In consideration of it, being necessary to provide a kind of image change recognition methods and device, the change of the image content of image can recognize that
Change situation.
The first aspect of the application provides a kind of image change recognition methods, and methods described includes：
Obtain at least two frame preview images that camera device is collected；
Benchmark image and contrast images are chosen from the preview image；
The brightness of the benchmark image and the brightness of the contrast images are contrasted, to recognize the preview image
The changing condition of image content.
It is described to enter the brightness of the benchmark image and the brightness of the contrast images in alternatively possible implementation
Row contrast, to recognize that the changing condition of image content of the preview image includes：
Calculate the absolute value of the contrast images and the luminance difference of the benchmark image；
If the absolute value of the contrast images and the luminance difference of the benchmark image is more than or equal to the first brightness and changes threshold
Value, recognizes that the image content of the preview image has quick change.
It is described to enter the brightness of the benchmark image and the brightness of the contrast images in alternatively possible implementation
Row contrast, to recognize that the changing condition of image content of the preview image also includes：
If the absolute value of the contrast images and the luminance difference of the benchmark image is less than first brightness and changes threshold
Value, judges whether the absolute value of the luminance difference is more than the second brightness change threshold；
If so, judging the absolute value sum of the contrast images and the pixel difference of the previous frame image of the contrast images is
It is no to be more than or equal to the first image change threshold value；
If so, recognizing that the image content of the preview image has quick change.
It is described to enter the brightness of the benchmark image and the brightness of the contrast images in alternatively possible implementation
Row contrast, to recognize that the changing condition of image content of the preview image also includes：
If quick change is not present in the image content of the preview image, the contrast images and the contrast images are judged
Previous frame image pixel difference absolute value sum whether be more than the second image change threshold value；
If so, recognize the preview image image content exist it is slowly varying.
It is described to enter the brightness of the benchmark image and the brightness of the contrast images in alternatively possible implementation
Row contrast, to recognize that the changing condition of image content of the preview image also includes：
If quick change is not present in the image content of the preview image, the contrast images and the benchmark image are judged
The absolute value sum of pixel difference whether be less than the first change threshold and more than or equal to the second change threshold；
If so, recognize the preview image image content exist it is slowly varying.
The second aspect of the application provides a kind of image change identifying device, and described device includes：
Acquisition module, for obtaining at least two frame preview images that camera device is collected；
Module is chosen, for choosing benchmark image and contrast images from the preview image；
Identification module, for the brightness of the benchmark image and the brightness of the contrast images to be contrasted, to recognize
The changing condition of the image content of the preview image.
In alternatively possible implementation, the identification module includes：
Computing unit, the absolute value for calculating the contrast images and the luminance difference of the benchmark image；
Recognition unit, if the absolute value for the contrast images and the luminance difference of the benchmark image is more than or equal to the
One brightness change threshold, recognizes that the image content of the preview image has quick change.
In alternatively possible implementation, the identification module also includes：
First judging unit, if the absolute value for the contrast images and the luminance difference of the benchmark image is less than institute
The first brightness change threshold is stated, judges whether the absolute value of the luminance difference is more than the second brightness change threshold；
First judging unit is additionally operable to, if the absolute value of the luminance difference is more than the second brightness change threshold, is sentenced
Whether the absolute value sum of the contrast images of breaking and the pixel difference of the previous frame image of the contrast images is more than or equal to first
Image change threshold value；
The recognition unit is additionally operable to, if the contrast images and the pixel difference of the previous frame image of the contrast images
Absolute value sum is more than or equal to the first image change threshold value, recognizes that the image content of the preview image has quick change.
In alternatively possible implementation, the identification module also includes：
Second judging unit, if quick change is not present in the image content for the preview image, judges the contrast
Whether image and the absolute value sum of the pixel difference of the previous frame image of the contrast images are more than the second image change threshold value；
The recognition unit is additionally operable to, if the contrast images and the pixel difference of the previous frame image of the contrast images
Absolute value sum is more than the second image change threshold value, recognize the preview image image content exist it is slowly varying.
In alternatively possible implementation, the identification module also includes：
3rd judging unit, if quick change is not present in the image content for the preview image, judges the contrast
Whether the absolute value sum of image and the pixel difference of the benchmark image is less than the first change threshold and more than or equal to the second change
Threshold value；
The recognition unit is additionally operable to, if the absolute value sum of the contrast images and the pixel difference of the benchmark image is small
In the first change threshold and more than or equal to the second change threshold, recognize the preview image image content exist it is slowly varying.
The present invention obtains at least two frame preview images that camera device is collected；Reference map is chosen from the preview image
Picture and contrast images；The brightness of the benchmark image and the brightness of the contrast images are contrasted, to recognize the preview
The changing condition of the image content of image.Because when image, which exists, to be changed, the brightness of the image content of image can have change, because
This passes through benchmark image and the brightness contrast of contrast images, it is possible to achieve the mesh of the situation of change of the image content of identification image
's.
Brief description of the drawings
Technical scheme, is used required in being described below to embodiment in order to illustrate the embodiments of the present invention more clearly
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of flow chart of image change recognition methods provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart of image change recognition methods provided in an embodiment of the present invention；
Fig. 3 is the structure chart for the image change identifying device that the present invention is provided；
Fig. 4 is the structure chart for the image change identifying device that the present invention is provided；
Fig. 5 present invention realizes the structural representation of the electronic equipment of the preferred embodiment of image change recognition methods.
Following embodiment will further illustrate the present invention with reference to above-mentioned accompanying drawing.
Embodiment
It is below in conjunction with the accompanying drawings and specific real in order to be more clearly understood that the above objects, features and advantages of the present invention
Applying example, the present invention will be described in detail.It should be noted that in the case where not conflicting, embodiments herein and embodiment
In feature can be mutually combined.
Elaborate many details in the following description to facilitate a thorough understanding of the present invention, described embodiment only
Only it is a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill
The every other embodiment that personnel are obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Unless otherwise defined, all of technologies and scientific terms used here by the article is with belonging to technical field of the invention
The implication that technical staff is generally understood that is identical.Term used in the description of the invention herein is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Embodiment
Fig. 1 is the schematic flow diagram of image change recognition methods provided in an embodiment of the present invention.As shown in figure 1, image becomes
Changing recognition methods may include following steps：
S101：Obtain at least two frame preview images that camera device is collected.
Image change recognition methods of the present invention can be applied in electronic equipment, and the electronic equipment can be mobile phone, flat board
Etc. terminal.Specifically, IMAQ can be carried out by the camera device on electronic equipment, at the image on electronic equipment
Module is managed to carry out that on image procossing, electronic equipment one or more camera devices can be included.Common camera device has shooting
Head.
At least two frame preview images of above-mentioned camera device refer at least two field pictures that camera device is captured, from shooting
At least two field pictures referred to as preview image that device is got.
S102：Benchmark image and contrast images are chosen from the preview image.
After at least two frame preview images are got, benchmark image and contrast images are chosen from preview image.
Said reference image is the image for other images to be compared with it.Contrast images are to be used for and reference map
As the image being compared.
Specifically, when starting to compare, benchmark image can choose the first two field picture got from camera device.Will
The first two field picture that the image that camera device is continuously captured all is got with camera device is contrasted.Meanwhile, benchmark image
It can be the image of change, can not be and remain the first two field picture.When the image continuously acquired has differences, also may be used
To take previous image of contrast images to be contrasted as benchmark image, will before and after two images contrasted.Choose base
The method of quasi- image is not limited to above-mentioned several, can also be that other methods determine benchmark image.
Above-mentioned contrast images can be the image that other camera devices are captured in real time in addition to the first frame, above-mentioned comparison diagram
Image as that can also be the default frame in interval chosen among the image captured in real time from camera device.
For example, choose image on the basis of the first two field picture for being got from camera device, the got from camera device
Two two field pictures are contrast images, then the second two field picture is contrasted with the first two field picture.
S103：The brightness of the benchmark image and the brightness of the contrast images are contrasted, to recognize the preview
The changing condition of the image content of image.
The brightness of calculating benchmark image and the brightness of contrast images can be distinguished by brightness of image algorithm.Specifically,
When contrast images and benchmark image are carried out into brightness contrast, whole image contents of contrast images and benchmark image can be carried out
Brightness contrast, can also carry out brightness contrast by the subregion of contrast images and the subregion of benchmark image, for example will be right
Brightness contrast is carried out than the area-of-interest of image and the area-of-interest of benchmark image.Meanwhile, by contrast images and benchmark
During the brightness contrast of image, the mean flow rate of two images can be compared.
The embodiment of the present invention is by obtaining at least two frame preview images that camera device is collected；From the preview image
Choose benchmark image and contrast images；The brightness of the benchmark image and the brightness of the contrast images are contrasted, to know
The changing condition of the image content of not described preview image.When there is change due to image, the brightness meeting of the image content of image
In the presence of change, therefore pass through benchmark image and the brightness contrast of contrast images, it is possible to achieve the change of the image content of identification image
The purpose of change situation.
Embodiment
Fig. 2 is the schematic flow diagram of image change recognition methods provided in an embodiment of the present invention.As shown in Fig. 2 image becomes
Changing recognition methods may include following steps：
S201：Obtain at least two frame preview images that camera device is collected.
Step S201 is consistent with step S101 in previous embodiment in the present embodiment, specifically refers in previous embodiment and walks
Rapid S101 associated description, is not repeated herein.
S202：Benchmark image and contrast images are chosen from the preview image.
Step S202 is consistent with step S102 in previous embodiment in the present embodiment, specifically refers in previous embodiment and walks
Rapid S102 associated description, is not repeated herein.
S203：Calculate the absolute value of the contrast images and the luminance difference of the benchmark image.
When carrying out the comparison of contrast images and benchmark image, the brightness of contrast images and benchmark image can be specifically calculated
The absolute value of difference.Specifically, the brightness of image can be calculated by brightness of image algorithm.Then pass through brightness of image
Algorithm calculates the brightness of contrast images and benchmark image, then calculates the absolute value of both differences, contrast images and benchmark image
The absolute value of luminance difference embody the brightness relationships of two pictures.
Further, can be by contrast images and reference map when contrast images and benchmark image are carried out into brightness contrast
Whole image contents of picture carry out brightness contrast, can also enter the subregion of the subregion of contrast images and benchmark image
Row brightness contrast, for example, carry out brightness contrast by the area-of-interest of the area-of-interest of contrast images and benchmark image.
S204：If the absolute value of the contrast images and the luminance difference of the benchmark image becomes more than or equal to the first brightness
Change threshold value, recognize that the image content of the preview image has quick change.
Above-mentioned first brightness change threshold can be set as needed, be specifically as follows pre-set value or according to
The threshold value that the sensitivity of camera device is determined in real time.
If contrast images and the luminance difference of benchmark image are more than the first brightness change threshold, the picture of preview image is recognized
There is quick change in content.For example, when the brightness of the first frame picture is very dark, when the brightness of the second pin picture is very bright, illustrating preview
The image content of image occurs in that larger change.Above-mentioned quick change is the classification and life carried out to image content situation of change
Name, is limited without any, when implementing, and other name can also be carried out as needed, for example, recognizes the picture of preview image
There is brightness change in content.
Meanwhile, if the absolute value of the contrast images and the luminance difference of the benchmark image becomes more than or equal to the first brightness
Change threshold value, benchmark image can be adjusted, can using contrast images now as benchmark image when judging next time,
Even proceed to judge contrast, then contrasted the follow-up contrast images benchmark image stylish with this.
S205：If the absolute value of the contrast images and the luminance difference of the benchmark image becomes less than first brightness
Change threshold value, judge whether the absolute value of the luminance difference is more than the second brightness change threshold.
Above-mentioned second brightness change threshold is less than the first brightness change threshold, in contrast images and the luminance difference of benchmark image
When the absolute value of value is less than the first brightness change threshold, it can be determined that whether the absolute value of luminance difference is more than the second brightness change
Threshold value.
S206：If the absolute value of the luminance difference is more than the second brightness change threshold, the contrast images and institute are judged
Whether the absolute value sum for stating the pixel difference of the previous frame image of contrast images is more than or equal to the first image change threshold value.
If judging, the absolute value of luminance difference is more than the second brightness change threshold, illustrates contrast images compared with benchmark image
Brightness is changed but change and not up to the second luminance threshold.At this point it is possible to determine whether that preview image whether there is it
He changes.For example, when the brightness situation of change of benchmark image and contrast images is more or less the same, possible image content occurs in that change
Change, but brightness does not change.It therefore, it can be determined whether from the angle of picture pixel.
Specifically, judging whether the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images is more than
Equal to the first image change threshold value.Judge whether the pixel value difference of the image of adjacent two frame changes.
When benchmark image is the first two field picture, and contrast images are the second two field picture, due to the first two field picture and the second frame
Image is adjacent image, then now the previous frame image of contrast images is benchmark image.If contrast images are the 3rd two field picture
When, it is that the 3rd two field picture and the second two field picture are subjected to contrast judgement now.
The computational methods of the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images are to contrast
Image takes absolute value with corresponding subtract each other of pixel of the previous frame image correspondence position of contrast images, then by each obtained absolute value
It is added, to obtain situation of change of the contrast images relative to the previous frame image of contrast images.If two field pictures differ greatly,
The absolute value sum that its pixel is subtracted each other is also larger.
Meanwhile, can be with when judging the absolute value sum of the pixel difference of previous frame image of contrast images and contrast images
The predeterminable area for choosing the predeterminable area of contrast images and the previous frame image of contrast images is calculated, for example, choose contrast
The area-of-interest of the area-of-interest of image and the previous frame image of contrast images, calculates the area-of-interest of this two figures
Pixel difference absolute value sum whether be more than the first image change threshold value.
The selection of above-mentioned first image change threshold value can be set as needed.
S207：If the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images is more than or equal to first
During image change threshold value, there is quick change in the image content of identification preview image.
Further, when quick change is not present in the image content of preview image, it can be determined that the picture of preview image
Content changes with the presence or absence of other, can specifically be judged by the following method：
Judge whether the absolute value sum of the contrast images and the pixel difference of the previous frame image of the contrast images is big
In the second image change threshold value；If so, recognize the preview image image content exist it is slowly varying.
Quickly change if the picture of preview image is not present, the pixel of the previous frame image of contrast images and contrast images
The absolute value sum of difference is less than the first image change threshold value, now judges the picture of the previous frame image of contrast images and contrast images
Whether the absolute value sum of plain difference is more than the second change threshold.Wherein, the second change threshold is less than the first change threshold, and second becomes
Changing the occurrence of threshold value can be set as needed.
If the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images is more than the second change threshold,
Although then explanation preview image is not present quick change, preview image non-fully changes also and not, now recognizes preview graph
It is slowly varying as existing.It is above-mentioned it is slowly varying be to image content situation of change carry out classification and name, without it is any limit,
When implementing, other name can also be carried out as needed.
Further, when quick change is not present in the image content of preview image, it can be determined that the picture of preview image
Content changes with the presence or absence of other, can specifically be judged by the following method：
If quick change is not present in the image content of the preview image, the contrast images and the benchmark image are judged
The absolute value sum of pixel difference whether be less than the first change threshold and more than or equal to the second change threshold；If so, identification is described
The image content of preview image exists slowly varying.
The size of above-mentioned first change threshold and the second change threshold can be set as needed, wherein, the second change threshold
Value is less than the first change threshold.
The circular of the absolute value sum of contrast images and the pixel difference of benchmark image is by contrast images and base
The pixel correspondence of quasi- image correspondence position, which is subtracted each other, to be taken absolute value, then each obtained absolute value is added, to obtain contrast images
Relative to the situation of change of benchmark image.If two field pictures differ greatly, the absolute value sum that its pixel is subtracted each other is also larger.
Meanwhile, when judging the absolute value sum of the pixel difference of contrast images and benchmark image, contrast images can be chosen
Predeterminable area and the predeterminable area of benchmark image calculated, for example choose the area-of-interest and benchmark of contrast images
Whether the area-of-interest of image, the absolute value sum for calculating the pixel difference of the area-of-interest of this two figures is less than the first change
Threshold value and more than or equal to the second change threshold.
In other embodiments, when the picture of preview image has quick change or be slowly varying, it can not enter
Row focusing, is just focused until change is not present in the image content of image.Either according to the difference of the image content of image
Situation of change adjusts exposure time during IMAQ, so as to obtain the higher image of quality.
The present embodiment by obtaining at least two frame preview images of camera device, chosen from preview image benchmark image and
Contrast images, then by the way that benchmark image and contrast images are carried out into adjacent the two of brightness contrast, pixel comparison, and contrast images
The pixel comparison of two field picture judges the changing condition of the image content of preview image, determines the picture of preview image from many aspects
Face content is with the presence or absence of change, and judged result is more accurate.And the judgement to image content is conducive to further carrying out image
The control of collection and image procossing, improve the imaging effect of image.
Above is the detailed description carried out to method provided by the present invention.According to different demands, in shown flow chart
The execution sequence of square can change, and some squares can be omitted, and image change, which knows method for distinguishing, to be become in above-mentioned image
It is selective in change recognition methods to be applied in combination, or be applied in combination with other above-mentioned NM image change recognition methods.
Device provided by the present invention is described below.
Embodiment
Fig. 3 is the structure chart of image change identifying device provided in an embodiment of the present invention.As shown in figure 3, image change is known
The structure chart of other device may include acquisition module 310, choose module 320 and identification module 330.
Acquisition module 310, for obtaining at least two frame preview images that camera device is collected.
Image change identifying device of the present invention can be applied in electronic equipment, and the electronic equipment can be mobile phone, flat board
Etc. terminal.Specifically, IMAQ can be carried out by the camera device on electronic equipment, at the image on electronic equipment
Module is managed to carry out that on image procossing, electronic equipment one or more camera devices can be included.Common camera device has shooting
Head.
At least two frame preview images of above-mentioned camera device refer at least two field pictures that camera device is captured, from shooting
At least two field pictures referred to as preview image that device is got.
Module 320 is chosen, for choosing benchmark image and contrast images from the preview image.
After acquisition module 310 gets at least two frame preview images, choose module 320 and benchmark is chosen from preview image
Image and contrast images.
Said reference image is the image for other images to be compared with it.Contrast images are to be used for and reference map
As the image being compared.
Specifically, when starting to compare, benchmark image can choose the first two field picture got from camera device.Will
The first two field picture that the image that camera device is continuously captured all is got with camera device is contrasted.Meanwhile, benchmark image
It can be the image of change, can not be and remain the first two field picture.When the image continuously acquired has differences, also may be used
To take previous image of contrast images to be contrasted as benchmark image, will before and after two images contrasted.Choose base
The method of quasi- image is not limited to above-mentioned several, can also be that other methods determine benchmark image.
Above-mentioned contrast images can be the image that other camera devices are captured in real time in addition to the first frame, above-mentioned comparison diagram
Image as that can also be the default frame in interval chosen among the image captured in real time from camera device.
For example, choose image on the basis of the first two field picture for being got from camera device, the got from camera device
Two two field pictures are contrast images, then the second two field picture is contrasted with the first two field picture.
Identification module 330, for the brightness of the benchmark image and the brightness of the contrast images to be contrasted, to know
The changing condition of the image content of not described preview image.
The brightness of calculating benchmark image and the brightness of contrast images can be distinguished by brightness of image algorithm.Specifically,
When contrast images and benchmark image are carried out into brightness contrast, whole image contents of contrast images and benchmark image can be carried out
Brightness contrast, can also carry out brightness contrast by the subregion of contrast images and the subregion of benchmark image, for example will be right
Brightness contrast is carried out than the area-of-interest of image and the area-of-interest of benchmark image.Meanwhile, by contrast images and benchmark
During the brightness contrast of image, the mean flow rate of two images can be compared.
The embodiment of the present invention is by obtaining at least two frame preview images that camera device is collected；From the preview image
Choose benchmark image and contrast images；The brightness of the benchmark image and the brightness of the contrast images are contrasted, to know
The changing condition of the image content of not described preview image.When there is change due to image, the brightness meeting of the image content of image
In the presence of change, therefore pass through benchmark image and the brightness contrast of contrast images, it is possible to achieve the change of the image content of identification image
The purpose of change situation.
Embodiment
Fig. 4 is the structure chart of image change identifying device provided in an embodiment of the present invention.As shown in figure 4, image change is known
The structure chart of other device may include acquisition module 310, choose module 320 and identification module 330, wherein, identification module includes meter
Calculate unit 331, recognition unit 332, the first judging unit 333.
Acquisition module 310, for obtaining at least two frame preview images that camera device is collected.
Acquisition module 310 is consistent with acquisition module 310 in previous embodiment in the present embodiment, specifically refers to foregoing implementation
The associated description of acquisition module 310, is not repeated herein in example.
Module 320 is chosen, for choosing benchmark image and contrast images from the preview image.
Module 320 is chosen in the present embodiment consistent with choosing module 320 in previous embodiment, specifically refer to foregoing implementation
The associated description of module 320 is chosen in example, is not repeated herein.
Identification module 330, for the brightness of the benchmark image and the brightness of the contrast images to be contrasted, to know
The changing condition of the image content of not described preview image.
Further, the recognition unit 330 includes computing unit 331, recognition unit 332, the first judging unit 333.
Computing unit 331, the absolute value for calculating the contrast images and the luminance difference of the benchmark image.
When carrying out the comparison of contrast images and benchmark image, computing unit 331 calculates contrast images and benchmark image
The absolute value of luminance difference.Specifically, the brightness of image can be calculated by brightness of image algorithm.Then pass through image
Brightness algorithm calculates the brightness of contrast images and benchmark image, then calculates the absolute value of both differences, contrast images and benchmark
The absolute value of the luminance difference of image embodies the brightness relationship of two pictures.
Further, can be by contrast images and reference map when contrast images and benchmark image are carried out into brightness contrast
Whole image contents of picture carry out brightness contrast, can also enter the subregion of the subregion of contrast images and benchmark image
Row brightness contrast, for example, carry out brightness contrast by the area-of-interest of the area-of-interest of contrast images and benchmark image.
Recognition unit 332, if the absolute value for the contrast images and the luminance difference of the benchmark image is more than etc.
In the first brightness change threshold, recognize that the image content of the preview image has quick change.
Above-mentioned first brightness change threshold can be set as needed, be specifically as follows pre-set value or according to
The threshold value that the sensitivity of camera device is determined in real time.
If contrast images and the luminance difference of benchmark image are more than the first brightness change threshold, the picture of preview image is recognized
There is quick change in content.For example, when the brightness of the first frame picture is very dark, when the brightness of the second pin picture is very bright, illustrating preview
The image content of image occurs in that larger change.Above-mentioned quick change is the classification and life carried out to image content situation of change
Name, is limited without any, when implementing, and other name can also be carried out as needed, for example, recognizes the picture of preview image
There is brightness change in content.
Meanwhile, if the absolute value of the contrast images and the luminance difference of the benchmark image becomes more than or equal to the first brightness
Change threshold value, benchmark image can be adjusted, can using contrast images now as benchmark image when judging next time,
Even proceed to judge contrast, then contrasted the follow-up contrast images benchmark image stylish with this.
First judging unit 333, if the absolute value for the contrast images and the luminance difference of the benchmark image is small
In the first brightness change threshold, judge whether the absolute value of the luminance difference is more than the second brightness change threshold.
Above-mentioned second brightness change threshold is less than the first brightness change threshold, in contrast images and the luminance difference of benchmark image
When the absolute value of value is less than the first brightness change threshold, it can be determined that whether the absolute value of luminance difference is more than the second brightness change
Threshold value.
First judging unit 333 is additionally operable to, if the absolute value of the luminance difference is more than the second brightness change threshold,
Judge whether the absolute value sum of the pixel difference of the previous frame image of the contrast images and the contrast images is more than or equal to the
One image change threshold value.
If judging, the absolute value of luminance difference is more than the second brightness change threshold, illustrates contrast images compared with benchmark image
Brightness is changed but change and not up to the second luminance threshold.At this point it is possible to determine whether that preview image whether there is it
He changes.For example, when the brightness situation of change of benchmark image and contrast images is more or less the same, possible image content occurs in that change
Change, but brightness does not change.It therefore, it can be determined whether from the angle of picture pixel.
Specifically, judging whether the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images is more than
Equal to the first image change threshold value.Judge whether the pixel value difference of the image of adjacent two frame changes.
When benchmark image is the first two field picture, and contrast images are the second two field picture, due to the first two field picture and the second frame
Image is adjacent image, then now the previous frame image of contrast images is benchmark image.If contrast images are the 3rd two field picture
When, it is that the 3rd two field picture and the second two field picture are subjected to contrast judgement now.
The computational methods of the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images are to contrast
Image takes absolute value with corresponding subtract each other of pixel of the previous frame image correspondence position of contrast images, then by each obtained absolute value
It is added, to obtain situation of change of the contrast images relative to the previous frame image of contrast images.If two field pictures differ greatly,
The absolute value sum that its pixel is subtracted each other is also larger.
Meanwhile, can be with when judging the absolute value sum of the pixel difference of previous frame image of contrast images and contrast images
The predeterminable area for choosing the predeterminable area of contrast images and the previous frame image of contrast images is calculated, for example, choose contrast
The area-of-interest of the area-of-interest of image and the previous frame image of contrast images, calculates the area-of-interest of this two figures
Pixel difference absolute value sum whether be more than the first image change threshold value.
The selection of above-mentioned first image change threshold value can be set as needed.
The recognition unit 332 is additionally operable to, if the contrast images and the pixel of the previous frame image of the contrast images
The absolute value sum of difference is more than or equal to the first image change threshold value, recognizes that the image content of the preview image has quick change
Change.
Further, the identification module 330 also includes：
Second judging unit, if quick change is not present in the image content for the preview image, judges the contrast
Whether image and the absolute value sum of the pixel difference of the previous frame image of the contrast images are more than the second image change threshold value.
The recognition unit 332 is additionally operable to, if the contrast images and the pixel of the previous frame image of the contrast images
The absolute value sum of difference is more than the second image change threshold value, recognize the preview image image content exist it is slowly varying.
Quickly change if the picture of preview image is not present, the pixel of the previous frame image of contrast images and contrast images
The absolute value sum of difference is less than the first image change threshold value, now judges the picture of the previous frame image of contrast images and contrast images
Whether the absolute value sum of plain difference is more than the second change threshold.Wherein, the second change threshold is less than the first change threshold, and second becomes
Changing the occurrence of threshold value can be set as needed.
If the absolute value sum of the pixel difference of the previous frame image of contrast images and contrast images is more than the second change threshold,
Although then explanation preview image is not present quick change, preview image non-fully changes also and not, now recognizes preview graph
It is slowly varying as existing.It is above-mentioned it is slowly varying be to image content situation of change carry out classification and name, without it is any limit,
When implementing, other name can also be carried out as needed.
Further, the identification module 330 also includes：
3rd judging unit, if quick change is not present in the image content for the preview image, judges the contrast
Whether the absolute value sum of image and the pixel difference of the benchmark image is less than the first change threshold and more than or equal to the second change
Threshold value.
The recognition unit 332 is additionally operable to, if the absolute value of the pixel difference of the contrast images and the benchmark image it
With less than the first change threshold and more than or equal to the second change threshold, recognize that the image content of the preview image has slow change
Change.
The size of above-mentioned first change threshold and the second change threshold can be set as needed, wherein, the second change threshold
Value is less than the first change threshold.
The circular of the absolute value sum of contrast images and the pixel difference of benchmark image is by contrast images and base
The pixel correspondence of quasi- image correspondence position, which is subtracted each other, to be taken absolute value, then each obtained absolute value is added, to obtain contrast images
Relative to the situation of change of benchmark image.If two field pictures differ greatly, the absolute value sum that its pixel is subtracted each other is also larger.
Meanwhile, when judging the absolute value sum of the pixel difference of contrast images and benchmark image, contrast images can be chosen
Predeterminable area and the predeterminable area of benchmark image calculated, for example choose the area-of-interest and benchmark of contrast images
Whether the area-of-interest of image, the absolute value sum for calculating the pixel difference of the area-of-interest of this two figures is less than the first change
Threshold value and more than or equal to the second change threshold.
In other embodiments, when the picture of preview image has quick change or be slowly varying, it can not enter
Row focusing, is just focused until change is not present in the image content of image.Either according to the difference of the image content of image
Situation of change adjusts exposure time during IMAQ, so as to obtain the higher image of quality.
The present embodiment by obtaining at least two frame preview images of camera device, chosen from preview image benchmark image and
Contrast images, then by the way that benchmark image and contrast images are carried out into adjacent the two of brightness contrast, pixel comparison, and contrast images
The pixel comparison of two field picture judges the changing condition of the image content of preview image, determines the picture of preview image from many aspects
Face content is with the presence or absence of change, and judged result is more accurate.And the judgement to image content is conducive to further carrying out image
The control of collection and image procossing, improve the imaging effect of image.
Embodiment
Fig. 5 is refer to, Fig. 5 is the structure of the electronic equipment for the preferred embodiment that the present invention realizes image change recognition methods
Schematic diagram.
The electronic equipment 50 be it is a kind of can according to the instruction for being previously set or storing, it is automatic carry out numerical computations and/
Or the equipment of information processing, its hardware includes but is not limited to microprocessor, application specific integrated circuit (Application Specific
Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), number
Word processing device (Digital Signal Processor, DSP), embedded device etc..
The electronic equipment 50 may be, but not limited to, any one can with user by keyboard, mouse, remote control, touch
The mode such as template or voice-operated device carries out the electronic product of man-machine interaction, for example, tablet personal computer, smart mobile phone, individual digital are helped
Manage (Personal Digital Assistant, PDA), intellectual Wearable etc..
Network residing for the electronic equipment 50 includes, but are not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN, virtual
Dedicated network (Virtual Private Network, VPN) etc..
The electronic equipment 50 includes at least one dispensing device 51, at least one storage device 52, at least one processing
Equipment 53, at least one reception device 54, at least one display device 55 and at least one communication bus.Wherein, it is described logical
Letter bus is used to realize the connection communication between these components.
Wherein, the reception device 54 and the dispensing device 51 can be wired sending ports, or wirelessly set
It is standby, such as including antenna assembly, for entering row data communication with other equipment.
The processing equipment 53 can include one or more microprocessor, digital processing unit.
The storage device 52 is used for the program code that storage image changes each program segment in identifying device.The storage
Equipment 52 can be smart media card (smart media card), safe digital card (secure digital card), quick flashing
The storage facilities such as memory card (flash card).
Preferably, image change recognition methods of the invention is recognized by the image change stored in the electronic equipment 50
Device is realized.
Described image changes identifying device by obtaining at least two frame preview images that camera device is collected；From described pre-
Look at and benchmark image and contrast images are chosen in image；By the brightness of the benchmark image and the brightness of contrast images progress pair
Than with the changing condition for the image content for recognizing the preview image.When there is change due to image, the image content of image
Brightness can have change, therefore pass through benchmark image and the brightness contrast of contrast images, it is possible to achieve in the picture of identification image
The purpose of the situation of change of appearance.
The display device 55 can be touch-screen etc. other be used for display picture equipment.
In several embodiments provided by the present invention, it should be understood that disclosed method and apparatus, it can also pass through
Other modes are realized.For example, device embodiment described above is only schematical, for example, the module and unit
Division, only a kind of division of logic function can have other dividing mode when actually realizing.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.This
Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in device claim is multiple
Device can also be realized by same device or system by software or hardware.The first, the second grade word is used for representing name
Claim, and be not offered as any specific order.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although reference
The present invention is described in detail for preferred embodiment, it will be understood by those within the art that, can be to the present invention's
Technical scheme is modified or equivalent substitution, without departing from the spirit and scope of technical solution of the present invention.
Claims (10)
1. a kind of image change recognition methods, it is characterised in that methods described includes：
Obtain at least two frame preview images that camera device is collected；
Benchmark image and contrast images are chosen from the preview image；
The brightness of the benchmark image and the brightness of the contrast images are contrasted, to recognize the picture of the preview image
The changing condition of content.
2. the method as described in claim 1, it is characterised in that described by the brightness of the benchmark image and the contrast images
Brightness contrasted, to recognize that the changing condition of image content of the preview image includes：
Calculate the absolute value of the contrast images and the luminance difference of the benchmark image；
If the absolute value of the contrast images and the luminance difference of the benchmark image is more than or equal to the first brightness change threshold, know
There is quick change in the image content of not described preview image.
3. method as claimed in claim 2, it is characterised in that described by the brightness of the benchmark image and the contrast images
Brightness contrasted, to recognize that the changing condition of image content of the preview image also includes：
If the absolute value of the contrast images and the luminance difference of the benchmark image is less than the first brightness change threshold, sentence
Whether the absolute value for the luminance difference of breaking is more than the second brightness change threshold；
If so, judging whether the absolute value sum of the contrast images and the pixel difference of the previous frame image of the contrast images is big
In equal to the first image change threshold value；
If so, recognizing that the image content of the preview image has quick change.
4. method as claimed in claim 2 or claim 3, it is characterised in that described by the brightness of the benchmark image and the contrast
The brightness of image is contrasted, to recognize that the changing condition of image content of the preview image also includes：
If quick change is not present in the image content of the preview image, judge before the contrast images and the contrast images
Whether the absolute value sum of the pixel difference of one two field picture is more than the second image change threshold value；
If so, recognize the preview image image content exist it is slowly varying.
5. method as claimed in claim 2 or claim 3, it is characterised in that described by the brightness of the benchmark image and the contrast
The brightness of image is contrasted, to recognize that the changing condition of image content of the preview image also includes：
If quick change is not present in the image content of the preview image, the picture of the contrast images and the benchmark image is judged
Whether the absolute value sum of plain difference is less than the first change threshold and more than or equal to the second change threshold；
If so, recognize the preview image image content exist it is slowly varying.
6. a kind of image change identifying device, it is characterised in that described device includes：
Acquisition module, for obtaining at least two frame preview images that camera device is collected；
Module is chosen, for choosing benchmark image and contrast images from the preview image；
Identification module, it is described to recognize for the brightness of the benchmark image and the brightness of the contrast images to be contrasted
The changing condition of the image content of preview image.
7. device as claimed in claim 6, it is characterised in that the identification module includes：
Computing unit, the absolute value for calculating the contrast images and the luminance difference of the benchmark image；
Recognition unit, if the absolute value for the contrast images and the luminance difference of the benchmark image is bright more than or equal to first
Change threshold is spent, recognizes that the image content of the preview image has quick change.
8. device as claimed in claim 7, it is characterised in that the identification module also includes：
First judging unit, if the absolute value for the contrast images and the luminance difference of the benchmark image is less than described the
One brightness change threshold, judges whether the absolute value of the luminance difference is more than the second brightness change threshold；
First judging unit is additionally operable to, if the absolute value of the luminance difference is more than the second brightness change threshold, judges institute
Whether the absolute value sum for stating contrast images and the pixel difference of the previous frame image of the contrast images is more than or equal to the first image
Change threshold；
The recognition unit is additionally operable to, if the contrast images and the pixel difference of the previous frame image of the contrast images is absolute
It is worth sum and is more than or equal to the first image change threshold value, recognizes that the image content of the preview image has quick change.
9. device as claimed in claim 7 or 8, it is characterised in that the identification module also includes：
Second judging unit, if quick change is not present in the image content for the preview image, judges the contrast images
Whether it is more than the second image change threshold value with the absolute value sum of the pixel difference of the previous frame image of the contrast images；
The recognition unit is additionally operable to, if the contrast images and the pixel difference of the previous frame image of the contrast images is absolute
Be worth sum and be more than the second image change threshold value, recognize the preview image image content exist it is slowly varying.
10. device as claimed in claim 7 or 8, it is characterised in that the identification module also includes：
3rd judging unit, if quick change is not present in the image content for the preview image, judges the contrast images
Whether it is less than the first change threshold and more than or equal to the second change threshold with the absolute value sum of the pixel difference of the benchmark image；
The recognition unit is additionally operable to, if the absolute value sum of the pixel difference of the contrast images and the benchmark image is less than the
One change threshold and more than or equal to the second change threshold, recognize the preview image image content exist it is slowly varying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710245721.2A CN107071231A (en) | 2017-04-14 | 2017-04-14 | Image change recognition methods and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710245721.2A CN107071231A (en) | 2017-04-14 | 2017-04-14 | Image change recognition methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107071231A true CN107071231A (en) | 2017-08-18 |
Family
ID=59599521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710245721.2A Pending CN107071231A (en) | 2017-04-14 | 2017-04-14 | Image change recognition methods and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107071231A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050069A (en) * | 2019-12-12 | 2020-04-21 | 维沃移动通信有限公司 | Shooting method and electronic equipment |
| CN112070113A (en) * | 2020-07-28 | 2020-12-11 | 北京旷视科技有限公司 | Camera scene change judgment method and device, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101155287A (en) * | 2006-09-25 | 2008-04-02 | 深圳Tcl工业研究院有限公司 | Video image processing method |
| US20130063666A1 (en) * | 2009-04-23 | 2013-03-14 | Canon Kabushiki Kaisha | Image processing apparatus and image processing method for performing correction processing on input video |
| CN105744116A (en) * | 2016-02-25 | 2016-07-06 | 广东欧珀移动通信有限公司 | Detection method, control method, detection device, control device and electronic device |
| CN106131414A (en) * | 2016-07-18 | 2016-11-16 | 广东欧珀移动通信有限公司 | Dynamically adjust the method and system of shooting frame per second |
-
2017
- 2017-04-14 CN CN201710245721.2A patent/CN107071231A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101155287A (en) * | 2006-09-25 | 2008-04-02 | 深圳Tcl工业研究院有限公司 | Video image processing method |
| US20130063666A1 (en) * | 2009-04-23 | 2013-03-14 | Canon Kabushiki Kaisha | Image processing apparatus and image processing method for performing correction processing on input video |
| CN105744116A (en) * | 2016-02-25 | 2016-07-06 | 广东欧珀移动通信有限公司 | Detection method, control method, detection device, control device and electronic device |
| CN106131414A (en) * | 2016-07-18 | 2016-11-16 | 广东欧珀移动通信有限公司 | Dynamically adjust the method and system of shooting frame per second |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111050069A (en) * | 2019-12-12 | 2020-04-21 | 维沃移动通信有限公司 | Shooting method and electronic equipment |
| CN111050069B (en) * | 2019-12-12 | 2021-11-23 | 维沃移动通信有限公司 | Shooting method and electronic equipment |
| CN112070113A (en) * | 2020-07-28 | 2020-12-11 | 北京旷视科技有限公司 | Camera scene change judgment method and device, electronic equipment and readable storage medium |
| CN112070113B (en) * | 2020-07-28 | 2024-03-26 | 北京旷视科技有限公司 | Imaging scene change judging method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229277B (en) | Gesture recognition method, gesture control method, multilayer neural network training method, device and electronic equipment | |
| CN111178183B (en) | Face detection method and related device | |
| CN107370942B (en) | Photographing method, photographing device, storage medium and terminal | |
| US8750573B2 (en) | Hand gesture detection | |
| US8792722B2 (en) | Hand gesture detection | |
| EP2336949B1 (en) | Apparatus and method for registering plurality of facial images for face recognition | |
| KR20200118076A (en) | Biometric detection method and device, electronic device and storage medium | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN106384348B (en) | The method for detecting abnormality and device of monitoring image | |
| CN108764139B (en) | Face detection method, mobile terminal and computer readable storage medium | |
| CN113688820B (en) | Stroboscopic band information identification method and device and electronic equipment | |
| CN109840885B (en) | Image fusion method and related product | |
| CN113596344A (en) | Shooting processing method and device, electronic equipment and readable storage medium | |
| CN112150444A (en) | Method and device for identifying attribute features of face image and electronic equipment | |
| CN107071231A (en) | Image change recognition methods and device | |
| CN112949467B (en) | Face detection method, device, electronic equipment and storage medium | |
| CN104866194B (en) | Image searching method and device | |
| CN112532884A (en) | Identification method and device and electronic equipment | |
| CN107026978A (en) | IMAQ control method and device | |
| CN106557766B (en) | Fuzzy character processing method and system and electronic equipment | |
| CN115661890A (en) | Model training method, face recognition device, face recognition equipment and medium | |
| CN112153291B (en) | Photographing method and electronic equipment | |
| CN110705447A (en) | Hand image detection method and device and electronic equipment | |
| CN112884797B (en) | Image background removing method and device and electronic equipment | |
| CN115205939B (en) | Training method and device for human face living body detection model, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170818 |
|
| RJ01 | Rejection of invention patent application after publication |