CN105227948A - A kind of method and device searching distorted region in image - Google Patents
A kind of method and device searching distorted region in image Download PDFInfo
- Publication number
- CN105227948A CN105227948A CN201510598683.XA CN201510598683A CN105227948A CN 105227948 A CN105227948 A CN 105227948A CN 201510598683 A CN201510598683 A CN 201510598683A CN 105227948 A CN105227948 A CN 105227948A
- Authority
- CN
- China
- Prior art keywords
- foreground target
- region
- depth information
- image
- foreground
- 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
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a kind of method of searching distorted region in image, comprising: the target image obtaining camera collection, obtains the foreground target region in described target image; Obtain the depth information of foreground target corresponding to described foreground target region; According to preset linear function with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region; Search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is distorted region.The present invention also proposes a kind of device searching distorted region in image accordingly.Adopt the present invention, decrease the amount of calculation in the process of the process lens distortion phenomenon in the process of taking pictures, improve treatment effeciency, improve Consumer's Experience.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to a kind of method and the device of searching distorted region in image.
Background technology
In the prior art, lens distortion to a certain degree all can be there is in general optical lens when imaging, be difficult to the effect reaching perfect lens imaging, and the inherent characteristic that this lens distortion optical lens is intrinsic (convex lens converge light, concavees lens divergent rays) causes, so, although this distortion is very disadvantageous for the image quality of photo, also cannot eliminate completely.
In general, user is when using portable equipment to take pictures as smart mobile phone etc., its object is to reproduce the scene of taking pictures at that time mostly, especially in order to reproduce the imaging region of the targets such as article, personage or building and whether object region is real, or whether there is distortion situation, and the image fault to a certain degree of non-object image region existence can be ignored.For the problem such as distortion, distortion that image occurs, the method that the distortion of image is corrected is there is in prior art, namely the distortion factor of camera lens is asked in advance, after imaging the coordinate of imaging point is revised, thus improve the accuracy of picture point coordinate, thus the distortion phenomenon occurred in correcting image to a certain extent.But the method for above-mentioned distortion correction needs to carry out a series of calculating after imaging, can increase the amount of calculation in image processing process after imaging.
Therefore, in prior art, the large problem of amount of calculation is existed for the processing mode of the lens distortion occurred in the process of taking pictures.
Summary of the invention
Based on this, for solving the excessive technical problem of the amount of calculation that exists for the processing mode of the lens distortion occurred in the process of taking pictures in the above-mentioned conventional art mentioned, spy provides a kind of method of searching distorted region in image.
Search a method for distorted region in image, comprising:
Obtain the target image of camera collection, obtain the foreground target region in described target image;
Obtain the depth information of foreground target corresponding to described foreground target region;
According to preset linear function with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region;
Search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is distorted region.
Optionally, the step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises: the depth information being obtained foreground target corresponding to described foreground target region by dual camera.
Optionally, the step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises: the reference image vegetarian refreshments choosing predetermined number in described foreground target region, obtain the depth information corresponding with described reference image vegetarian refreshments, and calculate the mean value of the depth information of all reference image vegetarian refreshments, take the mean value of the depth information of described all reference image vegetarian refreshments as the depth information of foreground target corresponding to described foreground target region.
Optionally, the step in the foreground target region in the described target image of described acquisition also comprises: obtain at least two foreground target regions in described target image;
The step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises: the depth information of at least two foreground targets that at least two foreground target regions are corresponding described in obtaining respectively;
The linear function that described basis is preset with the depth information of described foreground target for independent variable, the step calculating the distortion radius corresponding with described foreground target region also comprises: according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described at least two foreground target regions respectively;
Describedly search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the step that the regional determination formed by the described pixel found is distorted region also comprises: the pixel being greater than described distortion radius at least two foreground target regions described in searching respectively with the distance of the central point of target image, and the regional determination formed by the described pixel found respectively is the distorted region corresponding with described at least two foreground target regions.
Optionally, the described regional determination by the described pixel formation found also comprises after being the step of distorted region: the outstanding described distorted region shown in described target image, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
In addition, for solving the excessive technical problem of the amount of calculation that exists for the processing mode of the lens distortion occurred in the process of taking pictures in the above-mentioned conventional art mentioned, present invention also offers a kind of device of distorted region of searching in image.
Searching a device for the distorted region in image, comprising: foreground target region acquisition module, for obtaining the target image of camera collection, obtaining the foreground target region in described target image;
Depth Information Acquistion module, for obtaining the depth information of foreground target corresponding to described foreground target region;
Distortion radius calculation module, for according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region;
Distorted region determination module, for searching the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is distorted region.
Optionally, described Depth Information Acquistion module is also for the depth information that obtained foreground target corresponding to described foreground target region by dual camera.
Optionally, described Depth Information Acquistion module is also for the reference image vegetarian refreshments of choosing predetermined number in described foreground target region, obtain the depth information corresponding with described reference image vegetarian refreshments, and calculate the mean value of the depth information of all reference image vegetarian refreshments, take the mean value of the depth information of described all reference image vegetarian refreshments as the depth information of foreground target corresponding to described foreground target region.
Optionally, described foreground target region acquisition module also for: obtain at least two foreground target regions in described target image; Described Depth Information Acquistion module is also for the depth information of at least two foreground targets that at least two foreground target regions are corresponding described in obtaining respectively;
Described distortion radius calculation module also for: according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described at least two foreground target regions respectively;
Described distorted region determination module is also for the pixel being greater than described distortion radius at least two foreground target regions described in searching respectively with the distance of the central point of target image, and the regional determination formed by the described pixel found respectively is the distorted region corresponding with described at least two foreground target regions.
Optionally, described device also comprises outstanding display module, and for the described distorted region in the described target image of outstanding displaying, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
Implement the embodiment of the present invention, following beneficial effect will be had:
After have employed the method and apparatus of above-mentioned distorted region of searching in image, in the process of taking pictures, for the lens distortion phenomenon that the optics inherent characteristic of camera lens causes, calculate the distance of the foreground target of user's care or the positional distance camera lens at the shooting body place, thus determine the region that there will be distortion phenomenon under this distance and position, if the region at foreground target place and the area coincidence that there will be distortion phenomenon, be then distorted region by this area identification, that is, there is distortion in the foreground target that user is concerned about or the shooting body, need to adjust.Compare with conventional art, the method and apparatus of above-mentioned distorted region of searching in image is in the process of process lens distortion, avoid and carry out a series of distortion correction calculating after imaging, decrease the amount of calculation in imaging process, improve the treatment effeciency of imaging.
Meanwhile, user can also be informed in the distortion phenomenon that may occur in the process of taking pictures, and further adjusts, thus can initiatively go to avoid distortion phenomenon to appear on the shot object of user's care, improves Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Wherein:
Fig. 1 is the method flow schematic diagram of a kind of distorted region of searching in image in an embodiment;
Fig. 2 is the schematic diagram in the foreground target region of target image in an embodiment;
Fig. 3 is the schematic diagram in the foreground target region of target image in an embodiment;
Fig. 4 is the schematic diagram of the Region dividing in an embodiment in target image;
Fig. 5 is the space schematic diagram in the region at tolerance unit place corresponding with camera lens in an embodiment;
Fig. 6 is the space schematic diagram in the region at tolerance unit place corresponding with camera lens in an embodiment in another embodiment;
Fig. 7 is the schematic diagram of the Region dividing in an embodiment in an embodiment in target image;
Fig. 8 is the structural representation of the device of a kind of distorted region of searching in image in an embodiment.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
For solving the excessive technical problem of the amount of calculation that exists for the processing mode of the lens distortion occurred in the process of taking pictures in the above-mentioned conventional art mentioned, spy provides a kind of method of searching distorted region in image, the method can be dependent on computer and realizes program, this computer program can be the camera application program in smart mobile phone, also can be the image processing program run in camera terminal.This computer program can run in the computer system based on von Neumann system.This computer system can be the terminal equipment such as smart mobile phone, panel computer, palmtop PC or camera being provided with camera applications or image procossing application.
Concrete, this searches the method for distorted region in image as shown in Figure 1, and the method comprises the steps:
Step S102: the target image obtaining camera collection, obtains the foreground target region in described target image.
Target image is the image that the camera by being arranged in terminal obtains, and this target image can be shown by the display screen be arranged in terminal, carry out preview for user to the scene crossing the shooting of this camera or determine, and further can operate according to this target image, such as, manual focus, namely user manually selects the target that needs to carry out focusing.It should be noted that, the determination of the focus process mid-focal length in the acquisition process of above-mentioned target image, or need the selection carrying out the shooting body of focusing, can be that terminal completes voluntarily, i.e. auto-focusing also can be that user manually selects according to the needs of oneself thus completes this focus process.
Target image includes background and foreground target, after obtaining target image, and the foreground target region that the foreground target that can extract in target image according to the partitioning algorithm of foreground target is corresponding.It should be noted that, in the present embodiment, the acquisition process in foreground target region, both can be terminal according to the target image got, automatically extract the region at foreground target place in the target image; Can also be that the shooting body selected according to user determines the foreground target that user is concerned about, thus determine the foreground target region needing acquisition in the method.
The shape in foreground target region can be changeable, such as, can be with the center of foreground target corresponding points be in the target image the center of circle, the default length circle that is radius, also can be the arbitrary preset shape centered by the corresponding points in the target image of the center of foreground target, can also be the region that pixel that the foreground target that extracts according to actual conditions is corresponding is formed, this region be foreground target region.
As shown in Figure 2, Fig. 2 illustrates the photographic images under the application scenarios of the shooting of a personage, and this image is the target image obtained by camera, and the region being wherein labeled as 1,2,3,4 is the foreground target region in target image.
As shown in Figure 3, Fig. 3 illustrates the shooting schematic diagram under a camera applications scene, region C shown in this schematic diagram is the region at the target image place obtained by camera, the point being wherein labeled as A is the reference point of user from the shooting body of main separation, with this reference point be the center of circle, the default radius length R border circular areas B that is radius is foreground target region in target image.
Step S104: the depth information obtaining foreground target corresponding to described foreground target region.
The depth information of foreground target is the range information between foreground target and camera lens.In the present embodiment, the obtain manner of the distance between foreground target and camera lens can have multiple.
Such as, in one embodiment, the range information between foreground target and camera lens is obtained by range sensor, concrete, range sensor passes through to electromagnetic signals such as testee Emission Lasers or infrared lights and detection of echoes, thus determines the distance between testee and camera lens.
Again such as, in another embodiment, the range information between foreground target and camera lens is obtained by dual camera.Concrete, use the imaging respectively of two cameras, because the certain distance existed before two cameras, so certain difference can be there is in the information such as pixel coordinate in same object imaging, that is, the difference imaging of two cameras, has certain parallax and exists.The parallax of above-mentioned dual camera imaging, can be used for estimating and calculate the physical distance of object distance camera lens, i.e. depth information, and the depth information that can obtain each pixel further, Formation Depth image.
It should be noted that, in the acquisition of the depth information of above-mentioned foreground target, the depth information obtained, in order to represent whole foreground target region by the depth information of all pixels, in the present embodiment, is used for representing the depth information of the foreground target corresponding with foreground target region with which point or the depth information in which region, can select, as, can for user realize set, also can be systemic presupposition, or, also can be a kind of mode that system is selected at random.
Concrete, the depth information of any point in foreground target region can be got, represent the depth information in whole foreground target region with the depth information of this point.It can also be the depth information getting in foreground target region the correspondence meeting pre-conditioned some specified points, in order to replace the depth information in whole foreground target region, such as get the depth information of the maximum pixel of value corresponding to depth information, such as, get the depth information that the central point in foreground target region is corresponding.In another embodiment, the acquisition of the depth information in foreground target region can also be by distance corresponding to each pixel in acquisition foreground target region, and calculate the mean value of the distance that all-pair is answered, the depth information of foreground target is represented with this mean value.
In embodiment at another, the acquisition of the depth information of foreground target can also be following account form: the pixel of some in random selecting foreground target region, with these pixels for reference image vegetarian refreshments, obtain range information corresponding to above-mentioned reference image vegetarian refreshments or depth information, then all depth informations of reference image vegetarian refreshments or the mean value of range information is calculated, with the depth information of this mean value for foreground target corresponding to foreground target region.
Step S106: according to preset linear function with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region.
Camera lens occurs that the situation such as distortion, distortion causes due to the characteristic of camera lens itself, and, camera lens from subject more away from, the region of the pixel formation of subject shared by image is less, and its size variation is in appearance less.Because distortion is all appear at image neighboring area, that is, near the central point of imaging picture, generally there will not be distortion or distortion phenomenon.In the present embodiment, may occur that the region of distorting is called the region at distortion range place, and there will not be the region of distortion phenomenon to be called the region at tolerance scope place.In general, from camera lens more close to, distort larger, distortion range is larger, and acceptable tolerance scope is also less; Accordingly, from camera lens more away from, distort less, distortion range is less, and acceptable tolerance scope is also larger.Therefore, if tolerance scope is in fixed situation, the distortion range in image just directly can be tried to achieve.
As shown in Figure 4, the scene shown in figure is the Region dividing schematic diagram at distortion range and tolerance scope place in target image.In figure, S2 represents the region at acceptable tolerance scope place, and S1 represents the region that there will be the distortion range place of distortion or distortion phenomenon in target image.
In the present embodiment, the tolerance scope of a certain position object outside camera lens, when seeing camera lens as a bit, namely the impact that the size ignoring camera lens is brought, tolerance scope can be regarded as the cone progressively outwards dispersed with the center of circle of camera lens, this cone using the center of circle of camera lens as summit, with the distance between this object and camera lens for high (namely with the height that the depth information of the foreground target obtained in step S104 is cone), bottom surface radius are for preset value.
As shown in Figure 5, D shown in figure is the distance between this object and camera lens, the depth information namely obtained in step S104, and the scope in figure shown in cone is tolerance scope, does not namely occur the scope distorted.According to the difference of camera lens, the angle theta between the bus of cone and height also can be different, that is, the setting of this angle θ be by the hardware setting of camera lens or hardware configuration determined, after camera is shaping, this angle just can be decided.
For calculating the radius of border circular areas in the cross section at subject place, can according to the geometry of cone by following formula:
r＝tanθ·D。
The radius of the border circular areas at tolerance scope place can be determined according to above-mentioned formula, thus the scope of distorted region can be determined, described distortion range be in target image remove tolerance scope place region outside all regions.
In another embodiment, consider the impact that the size of camera lens is brought, the tolerance scope of the object of the outer a certain position of described camera lens, can be regarded as with the plane at the eyeglass place plane that is upper base place, with optical center point for the upper base center of circle and with the distance between this object and camera lens for high (namely with the height that the depth information of the foreground target obtained in step S104 is cone), bottom surface radius are preset value round platform.
As shown in Figure 6, θ is the angle between bus and height, and r is the radius of the radius of camera lens, R bottom surface, i.e. described distortion radius, and D is the distance between this object and camera lens, can calculate the radius of bottom surface according to following formula, and namely distort radius:
R＝r+tanθ·D。
Step S108: search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is for being distorted region.
In step s 106, consider in the process of tolerance scope, tolerance scope is considered as one with the central point of target image, the border circular areas that is radius with the radius that distorts, so, every bit within the scope of tolerance, to the distance of the central point of target image, is bound to be less than or equal to above-mentioned distortion radius.Conversely, if certain is a bit greater than distortion radius to the distance of central point, then this point is not within above-mentioned tolerance scope.
Concrete, all pixels comprised in traversal foreground target region, and according to the coordinate position of this pixel, calculate the distance between itself and the pixel corresponding to central point of target image.
Such as, if target image is the image (namely laterally have 1440 pixel columns, longitudinally have 900 pixel columns) of 1400*900, then the coordinate of the central point of target image is (x
0, y
0)=(700,450); Further, the size that each pixel is spatially shared is a × a (namely transverse width is a unit, and longitudinal width is a unit).Then coordinate is (x
1, y
1) the pixel pixel corresponding with central point between distance be:
Then the magnitude relationship between d and distortion radius R is judged.
If d>R, then illustrate that this coordinate is (x
1, y
1) the set of pixel that do not comprise in the region at tolerance scope place of pixel in, in the set of the pixel namely comprised in the region at distortion range place; If d>R, then illustrate that this coordinate is (x
1, y
1) the set of pixel that comprises in the region at tolerance scope place of pixel in.
The all pixels comprised in traversal foreground target region, when the distance of the central point of this pixel and target image is greater than described distortion radius, this pixel is added in the pixel set of distorted region, and the regional determination formed by all pixels in this set is distorted region, that is, be distorted region by this zone marker.
If the pixel set of above-mentioned distorted region is not empty set, then illustrate in the foreground target region in this target image and occurred distortion phenomenon, that is, there is the phenomenon of distortion or distortion in the target image in the foreground target that user is concerned about or the shooting body, relevant information is then needed to show user, which region concrete should be comprised there will be distortion phenomenon in this information, thus operate accordingly according to information, thus the shooting body or foreground target is avoided to occur distortion in the target image.
As shown in Figure 7, Fig. 7 illustrates the Region dividing schematic diagram of a target image, the region being numbered S1 is the region at tolerance scope place, the region being numbered S2 is the region at distortion phenomenon place, the region being numbered S3 is foreground target region, the region being numbered S4 is the common factor of S2 and S3, is greater than the region at the pixel place of described distortion radius, i.e. described distorted region in the foreground target region namely found in step S108 with the distance of the central point of target image.
Further, in the present embodiment, in step S108: search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel that finds is for after i.e. distorted region, this method also comprises step: the outstanding described distorted region shown in described target image, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
Concrete, the display screen of terminal is shown the image of preview, immediately carries out the preview of target image, in the images, distorted region is given prominence to and is illustrated on the display screen of terminal.
Such as, as shown in Figure 7, what Fig. 7 showed is the image shown on the display screen of terminal, when S4 be empty, and adding frame to the region at S4 place, distorted region and show in the displayed page of the display screen of terminal as shown in the figure.
Optionally, the display screen of terminal shows in the preview image of user, the division in the region such as region, foreground target region at the region at corresponding tolerance scope place, distortion range place can also be shown on a display screen, with for reference.
It should be noted that, in other embodiments, the quantity in the foreground target region comprised in target image can be more than one, namely in step s 102, after obtaining the step of the target image of camera collection, obtain at least one the foreground target region in described target image.
Such as, in the application scenarios shown in Fig. 2, described target image includes four foreground target regions that label is 1,2,3,4.
Accordingly, in step S104: obtain in the depth information of foreground target corresponding to described foreground target region, obtain the depth information of foreground target corresponding at least one foreground target region described, that is, the depth information of the foreground target of each acquisition in step s 102 corresponding to foreground target region is obtained.In step S106: according to the linear function preset with the depth information of described foreground target for independent variable calculates in the distortion radius corresponding with described foreground target region, the number of the distortion radius of calculating is also with corresponding to above-mentioned foreground target region.
That is, when foreground target region exists multiple, need respectively for each foreground target region, obtain the depth information of the foreground target of its correspondence, and then calculate distortion radius corresponding to each depth information respectively.
Accordingly, in step S108, also the pixel being greater than described distortion radius in each foreground target region with the distance of the central point of target image is searched respectively, judge whether the distorted region of its correspondence exists respectively for each foreground target region, and show in the process of user follow-up, on displaying interface, all show for multiple distorted region.
For solving the excessive technical problem of the amount of calculation that exists for the processing mode of the lens distortion occurred in the process of taking pictures in the above-mentioned conventional art mentioned, present invention also offers a kind of device searching distorted region in image, this device comprises foreground target region acquisition module 102, Depth Information Acquistion module 104, distortion radius calculation module 106 and distorted region determination module 108, wherein:
Foreground target region acquisition module 102, for obtaining the target image of camera collection, obtains the foreground target region in described target image;
Depth Information Acquistion module 104 is for obtaining the depth information of foreground target corresponding to described foreground target region;
Distortion radius calculation module 106 for according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region;
Distorted region determination module 108 is greater than the pixel of described distortion radius with the distance of the central point of target image in foreground target region for searching, the regional determination formed by the described pixel found is distorted region.
Optionally, Depth Information Acquistion module 104 is also for obtaining the depth information of foreground target corresponding to described foreground target region by dual camera.
Optionally, Depth Information Acquistion module 104 is also for the reference image vegetarian refreshments of choosing predetermined number in described foreground target region, obtain the depth information corresponding with described reference image vegetarian refreshments, and calculate the mean value of the depth information of all reference image vegetarian refreshments, take the mean value of the depth information of described all reference image vegetarian refreshments as the depth information of foreground target corresponding to described foreground target region.
Optionally, foreground target region acquisition module 102 also for: obtain at least two foreground target regions in described target image;
Depth Information Acquistion module 104 is also for the depth information of at least two foreground targets that at least two foreground target regions are corresponding described in obtaining respectively;
Distortion radius calculation module 106 also for: according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described at least two foreground target regions respectively;
Distorted region determination module 108 is also for the pixel being greater than described distortion radius at least two foreground target regions described in searching respectively with the distance of the central point of target image, and the regional determination formed by the described pixel found respectively is the distorted region corresponding with described at least two foreground target regions.
Optionally, the device should searching distorted region in image as Fig. 8 also comprises outstanding display module 110, and for the described distorted region in the described target image of outstanding displaying, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
Implement the embodiment of the present invention, following beneficial effect will be had:
After have employed the method and apparatus of above-mentioned distorted region of searching in image, in the process of taking pictures, for the lens distortion phenomenon that the optics inherent characteristic of camera lens causes, calculate the distance of the foreground target of user's care or the positional distance camera lens at the shooting body place, thus determine the region that there will be distortion phenomenon under this distance and position, if the region at foreground target place and the area coincidence that there will be distortion phenomenon, be then distorted region by this area identification, that is, there is distortion in the foreground target that user is concerned about or the shooting body, need to adjust.Compare with conventional art, the method and apparatus of above-mentioned distorted region of searching in image is in the process of process lens distortion, avoid and carry out a series of distortion correction calculating after imaging, decrease the amount of calculation in imaging process, improve the treatment effeciency of imaging.
Meanwhile, user can also be informed in the distortion phenomenon that may occur in the process of taking pictures, and further adjusts, thus can initiatively go to avoid distortion phenomenon to appear on the shot object of user's care, improves Consumer's Experience.
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (10)
1. search a method for distorted region in image, it is characterized in that, comprising:
Obtain the target image of camera collection, obtain the foreground target region in described target image;
Obtain the depth information of foreground target corresponding to described foreground target region;
According to preset linear function with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region;
Search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is distorted region.
2. method of searching distorted region in image according to claim 1, is characterized in that, the step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises:
The depth information of foreground target corresponding to described foreground target region is obtained by dual camera.
3. method of searching distorted region in image according to claim 1, is characterized in that, the step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises:
Choose the reference image vegetarian refreshments of predetermined number in described foreground target region, obtain the depth information corresponding with described reference image vegetarian refreshments, and calculate the mean value of the depth information of all reference image vegetarian refreshments, take the mean value of the depth information of described all reference image vegetarian refreshments as the depth information of foreground target corresponding to described foreground target region.
4. method of searching distorted region in image according to claim 1, is characterized in that, the step in the foreground target region in the described target image of described acquisition also comprises:
Obtain at least two foreground target regions in described target image;
The step of the depth information of the foreground target that described acquisition described foreground target region is corresponding also comprises: the depth information of at least two foreground targets that at least two foreground target regions are corresponding described in obtaining respectively;
The linear function that described basis is preset with the depth information of described foreground target for independent variable, the step calculating the distortion radius corresponding with described foreground target region also comprises: according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described at least two foreground target regions respectively;
Describedly search the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the step being distorted region by the regional determination that the described pixel found is formed also comprises:
Be greater than the pixel of described distortion radius at least two foreground target regions described in searching respectively with the distance of the central point of target image, the regional determination formed by the described pixel found respectively is the distorted region corresponding with described at least two foreground target regions.
5. method of searching distorted region in image according to claim 1, is characterized in that, the described regional determination by the described pixel formation found also comprises after being the step of distorted region:
The outstanding described distorted region shown in described target image, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
6. search a device for distorted region in image, it is characterized in that, comprising:
Foreground target region acquisition module, for obtaining the target image of camera collection, obtains the foreground target region in described target image;
Depth Information Acquistion module, for obtaining the depth information of foreground target corresponding to described foreground target region;
Distortion radius calculation module, for according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described foreground target region;
Distorted region determination module, for searching the pixel being greater than described distortion radius in foreground target region with the distance of the central point of target image, the regional determination formed by the described pixel found is distorted region.
7. the device searching distorted region in image according to claim 6, is characterized in that, described Depth Information Acquistion module is also for the depth information that obtained foreground target corresponding to described foreground target region by dual camera.
8. the device searching distorted region in image according to claim 6, is characterized in that, described Depth Information Acquistion module also for:
Choose the reference image vegetarian refreshments of predetermined number in described foreground target region, obtain the depth information corresponding with described reference image vegetarian refreshments, and calculate the mean value of the depth information of all reference image vegetarian refreshments, take the mean value of the depth information of described all reference image vegetarian refreshments as the depth information of foreground target corresponding to described foreground target region.
9. the device searching distorted region in image according to claim 6, is characterized in that, described foreground target region acquisition module also for: obtain at least two foreground target regions in described target image;
Described Depth Information Acquistion module is also for the depth information of at least two foreground targets that at least two foreground target regions are corresponding described in obtaining respectively;
Described distortion radius calculation module also for: according to the linear function preset with the depth information of described foreground target for independent variable, calculate the distortion radius corresponding with described at least two foreground target regions respectively;
Described distorted region determination module is also for the pixel being greater than described distortion radius at least two foreground target regions described in searching respectively with the distance of the central point of target image, and the regional determination formed by the described pixel found respectively is the distorted region corresponding with described at least two foreground target regions.
10. the device searching distorted region in image according to claim 6, it is characterized in that, described device also comprises outstanding display module, and for the described distorted region in the described target image of outstanding displaying, the mode of described outstanding displaying comprises highlighted, at least one added in frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510598683.XA CN105227948B (en) | 2015-09-18 | 2015-09-18 | The method and device of distorted region in a kind of lookup image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510598683.XA CN105227948B (en) | 2015-09-18 | 2015-09-18 | The method and device of distorted region in a kind of lookup image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105227948A true CN105227948A (en) | 2016-01-06 |
| CN105227948B CN105227948B (en) | 2017-10-27 |
Family
ID=54996591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510598683.XA Expired - Fee Related CN105227948B (en) | 2015-09-18 | 2015-09-18 | The method and device of distorted region in a kind of lookup image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105227948B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025638A (en) * | 2017-03-28 | 2017-08-08 | 北京小米移动软件有限公司 | The method and device of image procossing |
| CN110135382A (en) * | 2019-05-22 | 2019-08-16 | 北京华捷艾米科技有限公司 | A kind of human body detecting method and device |
| CN110971827A (en) * | 2019-12-09 | 2020-04-07 | Oppo广东移动通信有限公司 | Portrait mode shooting method and device, terminal equipment and storage medium |
| CN113222862A (en) * | 2021-06-04 | 2021-08-06 | 黑芝麻智能科技(上海)有限公司 | Image distortion correction method, device, electronic equipment and storage medium |
| CN113808053A (en) * | 2021-09-29 | 2021-12-17 | 华北电力大学（保定） | Infrared imager and signal correction method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1507407A2 (en) * | 2003-08-13 | 2005-02-16 | Topcon Corporation | Electronic image pickup apparatus with image correction function and method thereof |
| CN1582459A (en) * | 2001-06-12 | 2005-02-16 | 奥普提克斯晶硅有限公司 | System and method for correcting keystone distortion |
| CN101661162A (en) * | 2009-09-09 | 2010-03-03 | 谭洪舟 | Distortion compensation method based on wide-angle lens |
| CN101673043A (en) * | 2008-09-10 | 2010-03-17 | 鸿富锦精密工业（深圳）有限公司 | Wide-angle distortion testing system and method |
| CN101930111A (en) * | 2009-06-20 | 2010-12-29 | 凤凰光学(广东)有限公司 | Wide-angle lens |
| CN103124334A (en) * | 2012-12-19 | 2013-05-29 | 四川九洲电器集团有限责任公司 | Lens distortion correction method |
| CN103824303A (en) * | 2014-03-14 | 2014-05-28 | 格科微电子（上海）有限公司 | Image perspective distortion adjusting method and device based on position and direction of photographed object |
| CN104200468A (en) * | 2014-08-28 | 2014-12-10 | 中国矿业大学 | Method for obtaining correction parameter of spherical perspective projection model |
| CN104657940A (en) * | 2013-11-22 | 2015-05-27 | 中兴通讯股份有限公司 | Method and device for correction remediation and analysis alarm of distorted image |
-
2015
- 2015-09-18 CN CN201510598683.XA patent/CN105227948B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1582459A (en) * | 2001-06-12 | 2005-02-16 | 奥普提克斯晶硅有限公司 | System and method for correcting keystone distortion |
| EP1507407A2 (en) * | 2003-08-13 | 2005-02-16 | Topcon Corporation | Electronic image pickup apparatus with image correction function and method thereof |
| EP1507407A3 (en) * | 2003-08-13 | 2011-05-11 | Topcon Corporation | Electronic image pickup apparatus with image correction function and method thereof |
| CN101673043A (en) * | 2008-09-10 | 2010-03-17 | 鸿富锦精密工业（深圳）有限公司 | Wide-angle distortion testing system and method |
| CN101930111A (en) * | 2009-06-20 | 2010-12-29 | 凤凰光学(广东)有限公司 | Wide-angle lens |
| CN101661162A (en) * | 2009-09-09 | 2010-03-03 | 谭洪舟 | Distortion compensation method based on wide-angle lens |
| CN103124334A (en) * | 2012-12-19 | 2013-05-29 | 四川九洲电器集团有限责任公司 | Lens distortion correction method |
| CN104657940A (en) * | 2013-11-22 | 2015-05-27 | 中兴通讯股份有限公司 | Method and device for correction remediation and analysis alarm of distorted image |
| CN103824303A (en) * | 2014-03-14 | 2014-05-28 | 格科微电子（上海）有限公司 | Image perspective distortion adjusting method and device based on position and direction of photographed object |
| CN104200468A (en) * | 2014-08-28 | 2014-12-10 | 中国矿业大学 | Method for obtaining correction parameter of spherical perspective projection model |
Non-Patent Citations (2)
| Title |
|---|
| 王会峰等: "移动特征靶标的摄像机径向畸变标定", 《光学学报》 * |
| 艾莉莉等: "照相物镜径向畸变模型的再商讨", 《光学学报 》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025638A (en) * | 2017-03-28 | 2017-08-08 | 北京小米移动软件有限公司 | The method and device of image procossing |
| CN107025638B (en) * | 2017-03-28 | 2020-02-07 | 北京小米移动软件有限公司 | Image processing method and device |
| CN110135382A (en) * | 2019-05-22 | 2019-08-16 | 北京华捷艾米科技有限公司 | A kind of human body detecting method and device |
| CN110971827A (en) * | 2019-12-09 | 2020-04-07 | Oppo广东移动通信有限公司 | Portrait mode shooting method and device, terminal equipment and storage medium |
| CN113222862A (en) * | 2021-06-04 | 2021-08-06 | 黑芝麻智能科技(上海)有限公司 | Image distortion correction method, device, electronic equipment and storage medium |
| CN113808053A (en) * | 2021-09-29 | 2021-12-17 | 华北电力大学（保定） | Infrared imager and signal correction method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105227948B (en) | 2017-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961406B (en) | Image processing method and device and terminal equipment | |
| KR101612727B1 (en) | Method and electronic device for implementing refocusing | |
| CN105453136B (en) | The three-dimensional system for rolling correction, method and apparatus are carried out using automatic focus feedback | |
| CN105227948A (en) | A kind of method and device searching distorted region in image | |
| CN103207664B (en) | A kind of image processing method and equipment | |
| CN107665483B (en) | Calibration-free convenient monocular head fisheye image distortion correction method | |
| CN103776419B (en) | A kind of binocular distance measurement method improving measurement range | |
| EP3163535A1 (en) | Wide-area image acquisition method and device | |
| CN108154058B (en) | Graphic code display and position area determination method and device | |
| RU2017139576A (en) | DEVICE, SYSTEM AND METHOD FOR DETERMINING ONE OR MORE OPTICAL PARAMETERS OF THE LENS | |
| CA2776881A1 (en) | Image processing device, image processing method, image processing program, and recording medium | |
| KR20170005009A (en) | Generation and use of a 3d radon image | |
| CN105578019A (en) | Image extraction system capable of obtaining depth information and focusing method | |
| CN109255808B (en) | Building texture extraction method and device based on oblique images | |
| EP3005286B1 (en) | Image refocusing | |
| Wang et al. | Out-of-focus color camera calibration with one normal-sized color-coded pattern | |
| CN107409205A (en) | The apparatus and method determined for focus adjustment and depth map | |
| US20180213156A1 (en) | Method for displaying on a screen at least one representation of an object, related computer program, electronic display device and apparatus | |
| WO2017133160A1 (en) | Smart eyeglass perspective method and system | |
| US9769379B2 (en) | Method and apparatus for selecting target image | |
| CN103253193A (en) | Method and system of calibration of panoramic parking based on touch screen operation | |
| CN103377470A (en) | Image stitching method for vehicle-mounted panoramic video system | |
| CN114788254A (en) | Auxiliary focusing method, device and system | |
| US20110182470A1 (en) | Mobile communication terminal having image conversion function and method | |
| CN104506768A (en) | Method and device for image selection as well as terminal |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171027 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |