WO2018214151A1

WO2018214151A1 - Image processing method, terminal device and computer storage medium

Info

Publication number: WO2018214151A1
Application number: PCT/CN2017/086100
Authority: WO
Inventors: 阳光
Original assignee: 深圳配天智能技术研究院有限公司
Priority date: 2017-05-26
Filing date: 2017-05-26
Publication date: 2018-11-29
Also published as: CN109478326B; CN109478326A

Abstract

An image processing method, a terminal device and a computer storage medium. The method comprises: acquiring a first image and a second image (S11), wherein the first image has a correlation with the second image; respectively performing edge calculation on the first image and the second image, so as to obtain a first contour line in the first image and a second contour line in the second image (S12); determining pixels in the second contour line corresponding to pixels in the first contour line, so as to determine a correlation between the first contour line and the second contour line (S13); and determining, by using the correlation, pixels in the second image corresponding to pixels in a region outside the first contour line in the first image (S14). By means of the implementation of the method, the speed of image processing can be greatly improved.

Description

Image processing method, terminal device and computer storage medium

[Technical Field]

The present invention relates to the field of computer vision, and in particular to an image processing method, a terminal device, and a computer storage medium.

【Background technique】

The recognition of the corresponding points on the two images is an important form of machine vision. It is based on the principle of parallax and uses the imaging device to acquire two images of the measured object from different positions. By calculating the positional deviation between the corresponding points of the image, A method for obtaining three-dimensional geometric information of an object. Among them, binocular stereo vision has been widely used in robot navigation, precision industrial measurement, object recognition, virtual reality, scene reconstruction and surveying.

Generally, when performing image corresponding recognition, each pixel in one image and each pixel in another image are separately calculated for each other. This method is feasible, but due to the large amount of computation. Greatly reduced image processing speed.

[Summary of the Invention]

The technical problem to be solved by the present invention is to provide an image processing method, a terminal device and a computer storage medium, which can greatly improve the speed of image processing.

In order to solve the above technical problem, the technical solution adopted by the present invention is to provide an image processing method, including: acquiring a first image and a second image, wherein a first image and a second image have a corresponding relationship; Performing an edge calculation on the second image to determine a first contour line in the first image, a second contour line in the second image, and determining a pixel in the second contour line corresponding to the pixel in the first contour line to Determining a correspondence relationship between the first contour line and the second contour line; using the correspondence relationship to determine pixels in the second image corresponding to pixels in a region other than the first contour line in the first image.

In order to solve the above technical problem, the technical solution adopted by the present invention is: providing a terminal device, the terminal device comprising: a processor, a memory, a computer operation instruction and data stored in the memory, and the processor executing the computer operation instruction, for: Acquiring a first image and a second image from the memory, wherein the first image has a corresponding relationship with the second image; performing edge calculation on the first image and the second image respectively to determine a first contour line in the first image, a second contour line in the second image; determining the second contour line a pixel corresponding to a pixel in the first contour line to determine a correspondence relationship between the first contour line and the second contour line; using the correspondence relationship to determine the second image and the first contour line in the first image The pixel corresponding to the pixel in the area.

In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a computer storage medium, the device stores program data, and the program data can be executed to implement the corresponding method as above.

The invention has the beneficial effects that, in the image processing process, the corresponding relationship between the second contour line and the first contour line is first determined, and the corresponding relationship is used to determine the second image and A pixel corresponding to a pixel in a region other than the first contour line in the first image. The technical solution of the present invention utilizes the correspondence between the first contour line and the second contour line, thereby reducing the number of pixel points that need to be aligned when calculating corresponding pixels of pixels other than the first contour line. In turn, the amount of calculation is reduced, and the speed of image processing is improved.

[Description of the Drawings]

1 is a schematic flow chart of an embodiment of an image processing method according to the present invention;

2 is a schematic flowchart of step S13 in an embodiment of an image processing method according to the present invention;

3 is a schematic diagram showing an example of acquiring an epipolar line in an embodiment of an image processing method according to the present invention;

4 is a schematic flowchart of step S14 in an embodiment of an image processing method according to the present invention;

FIG. 5 is a schematic diagram of an example of step S14 in an embodiment of the image processing method of the present invention; FIG.

6 is a schematic flowchart of step S132 in an embodiment of an image processing method according to the present invention;

FIG. 7 is a schematic flowchart of step S132 in an embodiment of an image processing method according to the present invention; FIG.

FIG. 8 is a schematic diagram showing an example of entropy calculation in an embodiment of an image processing method according to the present invention; FIG.

9 is a schematic flowchart of step S132 in an embodiment of an image processing method according to the present invention;

FIG. 10 is a schematic flowchart of step S143 in an embodiment of an image processing method according to the present invention; FIG.

11 is a schematic flowchart of step S143 in an embodiment of an image processing method according to the present invention;

12 is a schematic flowchart of step S143 in an embodiment of an image processing method according to the present invention;

13 is a schematic diagram of a frame of an embodiment of a terminal device of the present invention;

Figure 14 is a schematic diagram of a frame of another embodiment of the terminal device of the present invention.

【detailed description】

Please refer to FIG. 1. FIG. 1 is an embodiment of an image processing method according to the present invention, including:

Step S11: acquiring a first image and a second image;

It should be noted that there is a correspondence between the first image and the second image.

In an application scenario, the first image and the second image are two images respectively acquired by two cameras of the binocular camera, and the two images have both differences and corresponding relationships, based on the correspondence relationship. The image is subjected to operations such as matching processing. At this time, the binocular camera can be used for direct shooting acquisition when acquiring the two images.

Of course, in other application scenarios, the two images may not be two images corresponding to the dual purpose, but two images of the same or similar relationship may exist, for example, the user may separately use the terminal device having the camera function. To take images of the same object at different angles, it should be noted that the scenes in the two images need to have overlapping parts. At this time, the user may photograph the same object, the scene, and the like from different angles by using a camera or the like, thereby obtaining the first image and the second image having the corresponding relationship to perform image processing.

Step S12: Perform edge calculation on the first image and the second image respectively to obtain a first contour line in the first image and a second contour line in the second image;

Wherein, the edge calculation of the image is performed to detect the edge contour of the object in the image to obtain the contour of the object in the image, and then the contour is used to divide the image into different regions. In this embodiment, the first contour line and the second contour line obtained may be one, or multiple, and the area enclosed by the contour line may be a closed area or an open area. It is not specifically limited.

Among them, there are many types of methods for edge detection, such as differential operator method, template matching method, wavelet detection method, neural network method, etc. Each type of detection method has different specific methods. Edge recognition based on differential operators is currently a more common method, usually using first or second derivatives to detect edges. In the differential operator method, there are detection methods such as Roberts, Sobel, Prewitt, Canny, Laplacian, Log and MATLAB simulation. In the application, different operators can be selected according to the actual situation. The specific algorithm is not limited in the present invention.

Step S13: determining pixels in the second contour line corresponding to pixels in the first contour line to determine a correspondence relationship between the first contour line and the second contour line;

In an application scenario, the first contour line is a line having a width of a first preset value, and the second contour line is a line having a width of a second preset value. The width of the first preset value refers to a width that can cover a certain number of pixels, for example, 5 pixels, 10 pixels, and the like, and is not limited thereto; similarly, the width is the second preset value.

The second preset value may be the same as or different from the first preset value; in an application scenario, The second preset value is greater than the first preset value, such that when determining the correspondence between the first contour line and the second contour line, the determination can be made by using pixels in a relatively larger range in the second image, thereby improving the above The accuracy of the correspondence.

It should be noted that any image corresponding recognition technology may be adopted when determining the pixels in the second contour line corresponding to the pixels in the first contour line, which is not limited herein.

Step S14: Using the correspondence relationship to determine pixels in the second image corresponding to pixels in a region other than the first contour line in the first image.

In the image processing process, the corresponding relationship between the second contour line and the first contour line is first determined, and the corresponding relationship is used to determine the area in the second image and the area other than the first contour line in the first image. The pixel corresponding to the pixel. The technical solution of the present invention utilizes the correspondence between the first contour line and the second contour line, thereby reducing the number of pixel points that need to be aligned when calculating corresponding pixels of pixels other than the first contour line. In turn, the amount of calculation is reduced, and the speed of image processing is improved.

Referring to FIG. 2, in an embodiment, step S13 includes: sub-step S131 and sub-step S132.

Sub-step S131, acquiring a first constraint line of the first pixel of the first contour line in the first image, and a second constraint line corresponding to the second image, and obtaining the second constraint line and the second contour line Intersection point

In this embodiment, the constraint line may specifically be a polar line, where the polar line refers to the intersection of the pole face in the opposite pole geometry and the plane of the two images.

Referring to FIG. 3, in the embodiment, one of the first pixels J is randomly set in the first image, and the projection centers corresponding to the first image and the second image are respectively known as C ₁ and C ₂ , and then the plane JC ₁ The intersection lines x and y of C ₂ and the planes γ and σ of the first image and the second image respectively are the polar lines corresponding to the first pixel J in the first image and the second image, that is, the first constraint line and the second line. Constraint line.

After obtaining the first constraint line, the second constraint line, and the first contour line and the second contour line, the intersection of the second constraint line and the second contour line in the second image can be simply obtained.

Sub-step S132, searching for the mutual information of the pixel of the first pixel and the intersection point one by one, and determining the second pixel of the second contour line corresponding to the first pixel in the second image to determine the first contour line and the second The correspondence of the outlines.

It should be noted that since the second contour line has a certain line width, the intersection point of the second constraint line and the second contour line is, to some extent, a small line segment having a certain length. At this time, mutual information is obtained for the first pixel and the pixel located at the intersection point, that is, mutual information is obtained for the first pixel and the pixel located on the small line segment.

In this embodiment, the mutual information indicates the degree of correlation between a certain pixel in the first image and a certain pixel in the second image, wherein the greater the mutual information, the greater the degree of correlation between the two pixels.

Since the first pixel is located on the first contour line, it is easy to understand that the first pixel is necessarily located at an intersection of the first contour line and the first constraint line, and corresponding to the first pixel in the second image according to the correspondence relationship The two pixels also correspond to the intersection of the second contour line and the second constraint line, that is, a certain pixel in the small line segment. In this case, it is only necessary to obtain mutual information for the pixels at the intersection of the first pixel and the second constraint line and the second contour line, and determine the pixels in the second image corresponding to the obtained maximum mutual information value. It is a second pixel corresponding to the first pixel.

In this embodiment, when determining a pixel in the second image corresponding to the pixel of the first contour line in the first image, according to the polar line constraint, only the first pixel and the second constraint line and the second contour are needed. The intersection of the lines, that is, the pixels covered by the small line segments described above, can obtain mutual information, which greatly reduces the amount of calculation, thereby improving the speed of image processing.

Referring to FIG. 4, in an embodiment, step S14 includes: sub-step S141, sub-step S142, and sub-step S143.

Sub-step S141, acquiring a third constraint line of the third pixel of the area outside the first contour line in the first image, and a fourth constraint line corresponding to the second image, to obtain the first contour line and the third constraint line All first intersecting line segments obtained by intersecting, and all second intersecting line segments obtained by intersecting the second contour line with the fourth constraint line;

Sub-step S142, acquiring a second intersecting line segment corresponding to the first intersecting line segment where the third pixel is located according to the correspondence relationship, and acquiring an end point of the second intersecting line segment;

The correspondence relationship refers to a correspondence relationship between the first contour line in the first image and the second contour line in the second image. Since the correspondence relationship between the first contour line and the second contour line is determined, the positional relationship between the first intersecting line segment and the first contour line and the positional relationship between the second intersecting line segment and the second contour line can be determined and the first a second intersecting line segment in the second image corresponding to the first intersecting line segment where the first pixel is located in the image.

Sub-step S143, searching for the mutual information of the third pixel and the pixel corresponding to the second intersecting line segment after the endpoint is removed, and obtaining a fourth pixel corresponding to the third pixel in the second image to obtain the second image. a pixel corresponding to a pixel in a region other than the first contour line in the first image.

Since the end point of the second intersecting line segment is located on the second contour line, according to the constraint principle, the pixels on the second contour line correspond to the pixels on the first contour line in the first image, and therefore, the first contour line is acquired When the pixels corresponding to the pixels in the area other than the pixels do not need to consider the pixels on the second contour line, That is, there is no need to consider the pixels on the endpoints of the second intersecting line segment.

For example, referring to FIG. 5, the first constraint line 212 of the first pixel M in the first image 21 and the second constraint line 222 corresponding to the second image 22 are obtained by the method for calculating the polar line in the prior art. . Then, according to the above steps S131 and S132, all the pixels on the first contour line 211 in the first image 21 are uniformly found in the corresponding pixels in the second image 22, and obtained in the second image 22, and the first image. The first contour line 211 in the image 21 corresponds to the contour line 223. Wherein, the first intersecting line segment wired segments K ₁ G ₁ , G ₁ H ₁ , H ₁ I ₁ , I ₁ E ₁ , E ₁ F ₁ , F ₁ L ₁ , the second intersecting line segment wired segments K ₂ G ₂ , G ₂ H ₂ , H ₂ I ₂ , I ₂ E ₂ , E ₂ F ₂ , F ₂ L ₂ . At this time, since the orientation of the first pixel M in the first image 21 has been determined to be on the first intersecting line segment E ₁ F ₁ between the

first contour lines

211a and 211b in the present embodiment, correspondingly, The second pixel in the second image corresponding to one pixel M is also correspondingly defined in a second intersection between the

contour lines

223a and 223b corresponding to the first intersecting line segment E ₁ F ₁ in the first image 21 in the second image 22 . On the line segment E ₂ F ₂ , then, at this time, when acquiring the second pixel corresponding to the first pixel M in the second image 22, only the second intersecting line segment of the first pixel M and the second image 22 is needed. It is sufficient to remove the pixel of the endpoint from the E ₂ F ₂ to obtain mutual information, and it is not necessary to obtain mutual information for all the pixels on the first pixel M and the corresponding second intersecting line segment E ₂ F ₂ .

In the above manner, when the pixel corresponding to the third pixel in the region other than the first contour line in the first image is acquired in the second image, the pixel in the second image can be further limited to be located at the third pixel The first intersecting line segment corresponding to the second intersecting line segment after the end point is removed, thereby greatly reducing the amount of calculation, and can significantly improve the speed of image processing.

Referring to FIG. 6, in an embodiment, step S132 includes: sub-step S1321, sub-step S1322:

Sub-step S1321, using all pixels in the first image and all pixels in the second image, calculating a first edge entropy of the first pixel, a first edge entropy of the fifth pixel of the intersection, and the first pixel and the fifth The first joint entropy of the pixel;

Sub-step S1322, calculating mutual information between the first pixel and the fifth pixel according to the first edge entropy of the first pixel, the first edge entropy of the fifth pixel, and the first joint entropy of the first pixel and the fifth pixel, a second pixel of the second contour line in the second image corresponding to the first pixel to obtain a correspondence relationship between the first contour line and the second contour line.

The operation for obtaining mutual information for the pixels x and y is I(x, y) = H(x) + H(y) - H(x, y).

Where I(x, y) is the mutual information of pixel x and pixel y, H(x), H(y) represent the edge entropy of pixel x, y, respectively, and H(x, y) represents pixel x and pixel y. Joint entropy. The entropy referred to here is information entropy, variable The greater the uncertainty, the greater the entropy.

In this embodiment, for example, when edge entropy is obtained for the first pixel in the first image, all pixels in the first image need to participate in the operation; similarly, in the first pixel and the second image When a pixel finds joint entropy, all pixels in the first image and the second image need to participate in the operation.

According to the above method, after the mutual information is calculated for the pixel covered by the intersection of the first pixel and the second image in the first image, the pixel having the largest mutual information value is the second pixel corresponding to the first pixel.

Referring to FIG. 7, in an embodiment, step S132 includes: sub-step S1323, sub-step S1324;

Sub-step S1323: calculating a second edge entropy of the first pixel, a second edge entropy of the sixth pixel of the intersection, and using a first contour line pixel in the first image and a second contour line pixel in the second image a second joint entropy of the first pixel and the sixth pixel;

Sub-step S1324: calculating mutual information between the first pixel and the sixth pixel according to the second edge entropy of the first pixel, the second edge entropy of the sixth pixel, and the second joint entropy of the first pixel and the sixth pixel, a second pixel of the second contour line in the second image corresponding to the first pixel to obtain a correspondence relationship between the first contour line and the second contour line.

It is easy to understand that the edge contour of an object refers to the most significant part of the image local intensity change in the image, that is, the region where the pixel value abruptly changes. Then, the pixel value in other regions except the contour line changes very little. Uniform, to some extent even negligible.

In the present embodiment, in the process of seeking mutual information, when calculating the edge entropy and the joint entropy, the area enclosed by the contour line is regarded as a blank, that is, the pixels therein are ignored. Referring to FIG. 8 , for example, the regions i′, j′′, k′ enclosed by the first contour line in the first image 21 and the second contour line in the second image 22 may be included. As a blank, for example, when the edge entropy of the first pixel N in the first image is obtained, only the pixels of the first contour line in the first image are used for calculation, regardless of the pixels of the area enclosed by the contour line, because the other Since the number of pixels included in the region is very large, calculation in this case can greatly reduce the amount of computation for entropy, thereby indirectly reducing the amount of computation for mutual information, thereby further increasing the speed of image processing.

Referring to FIG. 9, in an embodiment, step S132 includes: sub-step S1325, sub-step S1326, sub-step S1327;

Sub-step S1325, respectively obtaining the respective mean values of the pixels surrounding the first contour line and the second contour line in the first image and the second contour line, respectively, and enclosing the first contour line and the second contour line respectively All pixels of each region are set to a single pixel having respective mean values;

Sub-step S1326, using a first contour line pixel in the first image, a single pixel having a respective mean value of a region surrounded by all the first contour lines, a second contour line pixel in the second image, and all second contour lines a single pixel having respective mean values of the enclosed regions, calculating a third edge entropy of the first pixel, a third edge entropy of the seventh pixel of the intersection, and a third joint entropy of the first pixel and the seventh pixel;

Sub-step S1327, calculating mutual information of the first pixel and the seventh pixel according to the third edge entropy of the first pixel, the third edge entropy of the seventh pixel, and the third joint entropy of the first pixel and the seventh pixel, a second pixel in the second image corresponding to the first pixel to obtain a correspondence relationship between the first contour line and the second contour line.

The respective mean values of the pixels surrounding the first contour line and the second contour line respectively mean that the pixel values of all the pixels in the region surrounded by the contour lines are averaged, and the obtained average values are The respective mean values of the pixels that surround each region.

A single pixel refers to a region surrounded by a first contour line and a second contour line as a pixel, and the pixel value of the pixel is the mean value of the enclosed region.

In the above embodiment, the pixel values of the pixels in other regions than the contour line change very little and are relatively uniform, and can be considered to be a plurality of pixels having the same pixel value to some extent.

Therefore, in the present embodiment, by considering the pixels of the area surrounded by the contour lines as individual pixels, it is only necessary to use the pixels of the contour line and the above-mentioned individual pixels when performing entropy calculation in the process of seeking mutual information, and thus The amount of computation is reduced. At the same time, since the pixel value of a single pixel is an average value of the pixel values of all the pixels in the contoured area, the calculation of the mutual information does not bring too much error, that is, the present embodiment guarantees mutual The accuracy of information calculation greatly reduces the amount of calculation and improves the speed of image processing.

Referring to FIG. 10, in an embodiment, step S143 includes: sub-step S1431, sub-step S1432:

Sub-step S1431, using all the pixels in the first image and all the pixels in the second image, calculating the fourth edge entropy of the third pixel, and removing the fourth edge of the eighth pixel of the corresponding second intersecting line segment after the endpoint is removed Edge entropy and fourth joint entropy of the third pixel and the prime eighth pixel;

Sub-step S1432, calculating mutual information between the third pixel and the eighth pixel according to the fourth edge entropy of the third pixel, the fourth edge entropy of the eighth pixel, and the fourth joint entropy of the third pixel and the eighth pixel. And a fourth pixel in the second image corresponding to the third pixel to acquire a pixel in the second image corresponding to a pixel in a region other than the first contour line in the first image.

In the present embodiment, the method for calculating mutual information and the relationship between edge entropy and joint entropy are The beneficial effects and the like of the present embodiment are similar to those in the above embodiment. For details, refer to the above embodiment, and details are not described herein again.

Referring to FIG. 11, in an embodiment, step S143 includes: sub-step S1433, sub-step S1434;

Sub-step S1433: calculating the fifth edge entropy of the third pixel and the corresponding second intersecting line segment after removing the endpoint by using the first contour line pixel in the first image and the second contour line pixel in the second image a fifth edge entropy of nine pixels and a fifth joint entropy of the third pixel and the ninth pixel;

Sub-step S1434: calculating the mutual information of the third pixel and the ninth pixel according to the fifth edge entropy of the third pixel, the fifth edge entropy of the ninth pixel, and the fifth joint entropy of the third pixel and the ninth pixel. And a fourth pixel in the second image corresponding to the third pixel to acquire a pixel in the second image corresponding to a pixel in a region other than the first contour line in the first image.

Referring to FIG. 12, in an embodiment, step S143 includes: sub-step S1435, sub-step S1435, sub-step S1437;

Sub-step S1435, respectively obtaining the respective mean values of the pixels surrounding the first contour line and the second contour line in the first image and the second contour line, respectively, and enclosing the first contour line and the second contour line respectively All pixels of each region are set to a single pixel having respective mean values;

Sub-step S1436, using a first contour line pixel in the first image, a single pixel having a respective mean value of a region surrounded by all the first contour lines, a second contour line pixel in the second image, and all second contour lines a single pixel having respective mean values of the enclosed regions, calculating a sixth edge entropy of the third pixel, a sixth edge entropy of the tenth pixel of the corresponding second intersecting line segment after removing the endpoint, and the third pixel and the third pixel Sixth joint entropy of ten pixels;

Sub-step S1437, calculating mutual information between the third pixel and the tenth pixel according to the sixth edge entropy of the third pixel, the sixth edge entropy of the tenth pixel, and the sixth joint entropy of the third pixel and the tenth pixel. And a fourth pixel in the second image corresponding to the third pixel to acquire a pixel in the second image corresponding to a pixel in a region other than the first contour line in the first image.

Referring to FIG. 13 , an embodiment of the terminal device of the present invention includes a processor 31 and a memory 32 , wherein the memory 32 is coupled to the processor 31 .

The computer 32 stores the computer operation instructions and data, and the processor 31 executes the computer operation instructions for: acquiring the first image and the second image from the memory 32, wherein the first image and the second image have a corresponding relationship; An image and a second image respectively perform edge calculation to determine a first contour line in the first image and a second contour line in the second image; and determine the first contour line and the first contour line a pixel corresponding to the pixel, determining a correspondence relationship between the first contour line and the second contour line; using a correspondence relationship to determine a pixel in the second image corresponding to a region other than the first contour line in the first image Pixels.

In an embodiment, the processor 31 executes a computer operation instruction, and is further configured to: acquire a first constraint line of the first pixel of the first contour line in the first image, and a second corresponding to the second image Constraining the line, and obtaining an intersection of the second constraint line and the second contour line; obtaining mutual information for the pixels of the first pixel and the intersection point, and determining the second contour line corresponding to the first pixel in the second image a second pixel to determine a correspondence between the first contour line and the second contour line.

In one embodiment, the processor 31 determines pixels in the second contour line corresponding to the first contour line pixels to determine a correspondence between the first contour line and the second contour line. The method includes: acquiring a third constraint line of the third pixel of the area outside the first contour line in the first image, and corresponding to the fourth constraint line in the second image, to obtain the first contour line intersecting the third constraint line Obtaining all the first intersecting line segments, and all the second intersecting line segments obtained by intersecting the second contour line and the fourth constraint line; acquiring a second intersecting line segment corresponding to the first intersecting line segment where the third pixel is located according to the correspondence relationship, and Obtaining an endpoint of the second intersecting line segment; searching for the mutual information of the third pixel and the pixel corresponding to the second intersecting line segment after removing the end point, and obtaining a fourth pixel corresponding to the third pixel in the second image, Pixels in the second image corresponding to pixels in a region other than the first contour line in the first image are acquired.

Wherein, in an embodiment, the processor 31 uses the correspondence to determine pixels in the second image that correspond to pixels in a region other than the first contour in the first image, including: utilizing Calculating a first edge entropy of the first pixel, a first edge entropy of the fifth pixel of the intersection, and a first of the first pixel and the fifth pixel, all pixels in the first image and all pixels in the second image Joint entropy; calculating mutual information of the first pixel and the fifth pixel according to the first edge entropy of the first pixel, the first edge entropy of the fifth pixel, and the first joint entropy of the first pixel and the fifth pixel.

In one embodiment, the processor 31 obtains mutual information for the first pixel and the pixels of the intersection point, including: utilizing a first contour line pixel in the first image and a second contour in the second image a line pixel, calculating a second edge entropy of the first pixel, a second edge entropy of the sixth pixel of the intersection, and a second joint entropy of the first pixel and the sixth pixel; according to the second edge entropy of the first pixel, The second edge entropy of the sixth pixel and the second joint entropy of the first pixel and the sixth pixel calculate mutual information of the first pixel and the sixth pixel.

In one embodiment, the processor 31 obtains mutual information for the first pixel and the pixels of the intersection point, including: obtaining a first contour, a first contour, and a second contour in the second image, respectively. Line Separating the respective mean values of the pixels of the region, and setting all the pixels of each region surrounded by the first contour line and the second contour line into individual pixels each having a respective mean value; using the first image a first contour line pixel, a single pixel having a respective mean value of a region surrounded by all first contour lines, a second contour line pixel in the second image, and a region surrounded by all the second contour lines having respective mean values a single pixel, calculating a third edge entropy of the first pixel, a third edge entropy of the seventh pixel of the intersection, and a third joint entropy of the first pixel and the seventh pixel; according to the third edge entropy of the first pixel, The third edge entropy of the seventh pixel and the third joint entropy of the first pixel and the seventh pixel calculate a mutual information system of the first pixel and the seventh pixel.

In one embodiment, the processor 31 obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the endpoint, including: utilizing all the first images a pixel and all pixels in the second image, calculating a fourth edge entropy of the third pixel, removing a fourth edge entropy of the eighth pixel of the corresponding second intersecting line segment after the endpoint, and the third pixel and a fourth joint entropy of the eighth pixel; calculating a mutual relationship between the third pixel and the eighth pixel according to the fourth edge entropy of the third pixel, the fourth edge entropy, and the fourth joint entropy of the third pixel and the eighth pixel information.

In one embodiment, the processor 31 obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the endpoint, including: using the first image a contour line pixel and a second contour line pixel in the second image, calculating a fifth edge entropy of the third pixel, and a fifth of the ninth pixel of the corresponding second intersecting line segment after the end point is removed Edge entropy and fifth joint entropy of the third pixel and the ninth pixel; calculating according to the fifth edge entropy of the third pixel, the fifth edge entropy of the ninth pixel, and the fifth joint entropy of the third pixel and the ninth pixel Mutual information between three pixels and ninth pixels.

In one embodiment, the processor 31 obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after the endpoint is removed, including: obtaining the first image, respectively The first contour line and the second contour line in the two images respectively represent the respective mean values of the pixels of the region, and all the pixels of each region surrounded by the first contour line and the second contour line are respectively set to respectively a single pixel having a respective mean value; utilizing a first contour line pixel in the first image, a single pixel having a respective mean of the regions enclosed by all of the first contour lines, a second contour line pixel in the second image, and all of a single pixel having a respective mean value of a region enclosed by the two contour lines, calculating a sixth edge entropy of the third pixel, and a tenth pixel of the corresponding second intersecting line segment after the end point is removed Six edge entropy and a sixth joint entropy of the third pixel and the tenth pixel; calculating according to the sixth edge entropy of the third pixel, the sixth edge entropy of the tenth pixel, and the sixth joint entropy of the third pixel and the tenth pixel First The first pixel Ten-pixel mutual information.

Referring to FIG. 14 , in an embodiment, the terminal device further includes: a first camera 33 and a second camera 34; the first camera 33 and the second camera 34 are respectively configured to acquire the first image and the second image, and The first image and the second image are stored in the memory 32.

In an embodiment of the computer storage medium of the present invention, the apparatus stores program data, and the program data can be executed to implement the method in the image processing method embodiment of the present invention.

The computer storage medium may be at least one of a floppy disk drive, a hard disk drive, a CD-ROM reader, a magneto-optical disk reader, a CPU (for RAM), and the like.

For details of other related content, please refer to the above method section, which will not be described here.

The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformation made by the specification and the drawings of the present invention may be directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims

An image processing method, comprising:

Obtaining a first image and a second image, wherein the first image has a corresponding relationship with the second image;

Performing edge calculation on the first image and the second image respectively to determine a first contour line in the first image and a second contour line in the second image;

Determining pixels of the second contour line corresponding to pixels in the first contour line to determine a correspondence relationship between the first contour line and the second contour line;

The correspondence is used to determine pixels in the second image that correspond to pixels in a region other than the first contour in the first image.
The method of claim 1 wherein said determining a pixel of said second contour line corresponding to said first contour line pixel to determine said first contour line and said second contour line Correspondence of lines, including:

Obtaining a first constraint line of the first pixel of the first contour line in the first image, and a second constraint line corresponding to the second image, and obtaining the second constraint line The intersection of the second contour line;

Mutual information is obtained for the first pixel and the pixel of the intersection point, and a second pixel of the second contour line corresponding to the first pixel is determined in the second image to determine Corresponding relationship between the first contour line and the second contour line.
The method according to claim 1, wherein said utilizing said correspondence relationship determines pixels in said second image corresponding to pixels in a region other than said first contour line in said first image ,include:

Obtaining a third constraint line of the third pixel of the region outside the first contour line in the first image, and a fourth constraint line corresponding to the second image to obtain the first contour line All first intersecting line segments obtained by intersecting the third constraint line, and all second intersecting line segments obtained by intersecting the second contour line with the fourth constraint line;

Acquiring, according to the correspondence, the second intersecting line segment corresponding to the first intersecting line segment where the third pixel is located, and acquiring an end point of the second intersecting line segment;

Pixel to the third pixel and the corresponding second intersecting line segment after the end point is removed Obtaining a mutual information, obtaining a fourth pixel corresponding to the third pixel in the second image, to acquire pixels in the second image and a region other than the first contour line in the first image Corresponding pixels.
The method according to claim 2, wherein the mutual information of the first pixel and the pixel of the intersection point comprises:

Calculating a first edge entropy of the first pixel, a first edge entropy of a fifth pixel of the intersection, and the first using all pixels in the first image and all pixels in the second image a first joint entropy of a pixel and the fifth pixel;

Calculating the first pixel and the first according to a first edge entropy of the first pixel, a first edge entropy of the fifth pixel, and a first joint entropy of the first pixel and the fifth pixel Five-pixel mutual information.
The method according to claim 2, wherein the mutual information of the first pixel and the pixel of the intersection point comprises:

Calculating a second edge entropy of the first pixel and a sixth pixel of the intersection by using the first contour line pixel in the first image and the second contour line pixel in the second image a second edge entropy and a second joint entropy of the first pixel and the sixth pixel;

Calculating the first pixel and the first according to a second edge entropy of the first pixel, a second edge entropy of the sixth pixel, and a second joint entropy of the first pixel and the sixth pixel Six-pixel mutual information.
The method according to claim 2, wherein the mutual information of the pixels of the first pixel and the intersection point comprises:

Obtaining, respectively, respective mean values of pixels of the first image, the first contour line, and the second contour line in the second image, and the first contour line, the first contour line All pixels of each region surrounded by the second contour line are set as individual pixels each having the respective mean values;

Using the first contour line pixel in the first image, the single pixel having the respective mean values of the area enclosed by all the first contour lines, and the second of the second image a single pixel having the respective mean values of the contour pixels and a region surrounded by all of the second contour lines, calculating a third edge entropy of the first pixel, and a seventh pixel of the intersection a third edge entropy and a third joint entropy of the first pixel and the seventh pixel;

Calculating the first pixel and the first according to a third edge entropy of the first pixel, a third edge entropy of the seventh pixel, and a third joint entropy of the first pixel and the seventh pixel Seven-pixel mutual trust interest.
The method according to claim 3, wherein the mutual information is obtained by the pixel of the third pixel and the corresponding second intersecting line segment after the endpoint is removed, including:

Calculating a fourth edge entropy of the third pixel, and a corresponding second intersection after removing the endpoint by using all pixels in the first image and all pixels in the second image a fourth edge entropy of the eighth pixel of the line segment and a fourth joint entropy of the third pixel and the eighth pixel;

Calculating the third pixel and the fourth pixel according to a fourth edge entropy of the third pixel, a fourth edge entropy of the eighth pixel, and a fourth joint entropy of the third pixel and the eighth pixel The mutual information of the eighth pixel.
The method according to claim 3, wherein the mutual information is obtained by the pixel of the third pixel and the corresponding second intersecting line segment after the endpoint is removed, including:

Calculating a fifth edge entropy of the third pixel by using the first contour line pixel in the first image and the second contour line pixel in the second image, after removing the endpoint a fifth edge entropy of a ninth pixel of the corresponding second intersecting line segment and a fifth joint entropy of the third pixel and the ninth pixel;

Calculating the third pixel and the first according to a fifth edge entropy of the third pixel, a fifth edge entropy of the ninth pixel, and a fifth joint entropy of the third pixel and the ninth pixel Nine-pixel mutual information.
The method according to claim 3, wherein the mutual information is obtained by the pixel of the third pixel and the corresponding second intersecting line segment after the endpoint is removed, including:

Obtaining, respectively, respective mean values of pixels of the first image, the first contour line, and the second contour line in the second image, and the first contour line, the first contour line All pixels of each region surrounded by the second contour line are set as individual pixels each having the respective mean values;

Using the first contour line pixel in the first image, the single pixel having the respective mean values of the area enclosed by all the first contour lines, and the second of the second image a single pixel having the respective mean values of the contour pixels and a region surrounded by all of the second contour lines, calculating a sixth edge entropy of the third pixel, the removing the endpoint a sixth edge entropy of the tenth pixel of the corresponding second intersecting line segment and a sixth joint entropy of the third pixel and the tenth pixel;

a sixth edge entropy of the third pixel, a sixth edge entropy of the tenth pixel, and the The sixth joint entropy of the three pixels and the tenth pixel calculates the mutual information of the third pixel and the tenth pixel.
The image processing method according to any one of claims 1 to 9, wherein the first contour line is a line having a width of a first preset value, and the second contour line is a width of a second preset. The line of values.
A terminal device, comprising: a processor, a memory, wherein the memory is stored in a computer operation instruction and data, and the processor executes the computer operation instruction for:

Obtaining a first image and a second image from a memory, wherein the first image has a corresponding relationship with the second image;

Performing edge calculation on the first image and the second image respectively to determine a first contour line in the first image and a second contour line in the second image;

Determining pixels of the second contour line corresponding to pixels in the first contour line to determine a correspondence relationship between the first contour line and the second contour line;

The correspondence is used to determine pixels in the second image that correspond to pixels in a region other than the first contour in the first image.
The terminal device according to claim 11, wherein said processor determines pixels of said second contour line corresponding to said first contour line pixels to determine said first contour line and said Correspondence of the second contour line, including:

Obtaining a first constraint line of the first pixel of the first contour line in the first image, and a second constraint line corresponding to the second image, and obtaining the second constraint line The intersection of the second contour line;

Mutual information is obtained for the first pixel and the pixel of the intersection point, and a second pixel of the second contour line corresponding to the first pixel is determined in the second image to determine Corresponding relationship between the first contour line and the second contour line.
The terminal device according to claim 11, wherein said processor uses said correspondence relationship to determine pixels in said second image that are outside a first contour line in said first image Corresponding pixels, including:

Obtaining a third constraint line of the third pixel of the region outside the first contour line in the first image, and a fourth constraint line corresponding to the second image to obtain the first contour line All first intersecting line segments obtained by intersecting the third constraint line, and all second intersecting line segments obtained by intersecting the second contour line with the fourth constraint line;

Acquiring, according to the correspondence, the second intersecting line segment corresponding to the first intersecting line segment where the third pixel is located, and acquiring an end point of the second intersecting line segment;

Obtaining mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the end point, and obtaining a fourth pixel corresponding to the third pixel in the second image, to Pixels in the second image corresponding to pixels in a region other than the first contour line in the first image are acquired.
The terminal device according to claim 12, wherein the processor seeks mutual information for the pixels of the first pixel and the intersection point, including:

Calculating a first edge entropy of the first pixel, a first edge entropy of a fifth pixel of the intersection, and the first using all pixels in the first image and all pixels in the second image a first joint entropy of a pixel and the fifth pixel;

Calculating the first pixel and the first according to a first edge entropy of the first pixel, a first edge entropy of the fifth pixel, and a first joint entropy of the first pixel and the fifth pixel Five-pixel mutual information.
The terminal device according to claim 12, wherein the processor seeks mutual information for the pixels of the first pixel and the intersection point, including:

Calculating a second edge entropy of the first pixel and a sixth pixel of the intersection by using the first contour line pixel in the first image and the second contour line pixel in the second image a second edge entropy and a second joint entropy of the first pixel and the sixth pixel;

Calculating the first pixel and the first according to a second edge entropy of the first pixel, a second edge entropy of the sixth pixel, and a second joint entropy of the first pixel and the sixth pixel Six-pixel mutual information.
The terminal device according to claim 12, wherein the determining, by the processor, the mutual information of the first pixel and the pixel of the intersection includes:

Obtaining, respectively, respective mean values of pixels of the first image, the first contour line, and the second contour line in the second image, and the first contour line, the first contour line All pixels of each region surrounded by the second contour line are set as individual pixels each having the respective mean values;

Using the first contour line pixel in the first image, the single pixel having the respective mean values of the area enclosed by all the first contour lines, and the second of the second image a single pixel having the respective mean values of the contour pixels and a region surrounded by all of the second contour lines, calculating a third edge entropy of the first pixel, and a seventh pixel of the intersection Third edge entropy And a third joint entropy of the first pixel and the seventh pixel;

Calculating the first pixel and the first according to a third edge entropy of the first pixel, a third edge entropy of the seventh pixel, and a third joint entropy of the first pixel and the seventh pixel Seven-pixel mutual information.
The terminal device according to claim 13, wherein the processor obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the endpoint, including:

Calculating a fourth edge entropy of the third pixel, and a corresponding second intersection after removing the endpoint by using all pixels in the first image and all pixels in the second image a fourth edge entropy of the eighth pixel of the line segment and a fourth joint entropy of the third pixel and the eighth pixel;

Calculating the third pixel and the first according to a fourth edge entropy of the third pixel, a fourth edge entropy of the eighth pixel, and a fourth joint entropy of the third pixel and the eighth pixel Eight-pixel mutual information.
The terminal device according to claim 13, wherein the processor obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the endpoint, including:

Calculating a fifth edge entropy of the third pixel by using the first contour line pixel in the first image and the second contour line pixel in the second image, after removing the endpoint a fifth edge entropy of a ninth pixel of the corresponding second intersecting line segment and a fifth joint entropy of the third pixel and the ninth pixel;

Calculating the third pixel and the first according to a fifth edge entropy of the third pixel, a fifth edge entropy of the ninth pixel, and a fifth joint entropy of the third pixel and the ninth pixel Nine-pixel mutual information.
The terminal device according to claim 13, wherein the processor obtains mutual information for the pixels of the third pixel and the corresponding second intersecting line segment after removing the endpoint, including:

Obtaining, respectively, respective mean values of pixels of the first image, the first contour line, and the second contour line in the second image, and the first contour line, the first contour line All pixels of each region surrounded by the second contour line are set as individual pixels each having the respective mean values;

Enclosing the first contour line pixel in the first image, all the first contour lines The individual pixels of the region having the respective mean values, the second contour line pixels in the second image, and the regions surrounded by all of the second contour lines having the respective mean values Calculating a sixth edge entropy of the third pixel, a sixth edge entropy of a tenth pixel of the corresponding second intersecting line segment after removing the endpoint, and the third pixel and the a sixth joint entropy of the tenth pixel;

Calculating the third pixel and the first according to a sixth edge entropy of the third pixel, a sixth edge entropy of the tenth pixel, and a sixth joint entropy of the third pixel and the tenth pixel Ten-pixel mutual information.
A computer storage medium, characterized in that program data is stored in the computer storage medium, the program data being executable to implement the method of any of claims 1-10.