CN112419215B - Image processing method, device, electronic equipment and storage medium - Google Patents
Image processing method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112419215B CN112419215B CN202011256826.6A CN202011256826A CN112419215B CN 112419215 B CN112419215 B CN 112419215B CN 202011256826 A CN202011256826 A CN 202011256826A CN 112419215 B CN112419215 B CN 112419215B
- Authority
- CN
- China
- Prior art keywords
- image
- downsampled
- downsampling
- current
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000003044 adaptive effect Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 241001292396 Cirrhitidae Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses an image processing method, an image processing device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an image to be processed, carrying out downsampling processing on the image to be processed, respectively determining pixel codes of a current downsampled image and an image before downsampling when the downsampled image meets a first layering condition, determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes, carrying out iterative downsampling processing on the current downsampled image when the current downsampled image and the image distance meet a second layering condition, and forming an image set of a pyramid structure based on at least one downsampled image obtained by the image to be processed and the downsampling processing, thereby realizing self-adaptive layering of the image, being applicable to various images and not limited by image characteristics, and being applicable to the fields of image registration and the like, and improving the speed and the precision of image registration.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to an image processing method, an image processing device, electronic equipment and a storage medium.
Background
The image pyramid is an image multi-scale expression, is an effective and conceptual simple data structure for analyzing images with multiple resolutions, can be applied to the field of image registration, and in an image registration algorithm, the number of pyramid layers is a core index, and the size of the pyramid layer directly influences the accuracy and the acceleration effect of the algorithm. More layers may cause errors in the matching results, and fewer layers may reduce the matching speed by a factor of several.
In the prior art, the specification of the pyramid layers is mostly manually selected according to experience. Pyramid layering in OpenCV adopts a manual entry mode. Some scholars propose a method for determining the pyramid layer number according to the loss amount of the feature points between images with different scales. However, this method still requires a large number of experiments to obtain a threshold value of the feature point loss amount as a layering condition, which is not really adaptive per se. The image processing software widely applied in industry, the pyramid in Halcon is layered with auto mode, the layer number of the pyramid can be automatically adjusted, but commercial software is not open source, and the internal algorithm principle can not be obtained.
Disclosure of Invention
The invention provides an image processing method, an image processing device, electronic equipment and a storage medium, which are used for realizing self-adaptive layering of images, are suitable for various images, so that the speed and the accuracy of image registration are improved, and meanwhile, the number of pyramid layers is selected manually, so that the operation is simplified.
In a first aspect, an embodiment of the present invention provides an image processing method, including:
acquiring an image to be processed, and performing downsampling processing on the image to be processed to obtain a downsampled image;
when the downsampled image meets a first layering condition, respectively determining pixel codes of a current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
when the current downsampled image and the image distance meet a second layering condition, performing iterative downsampling processing on the current downsampled image;
and forming an image set with a pyramid structure based on the image to be processed and at least one downsampled image obtained by downsampling.
In a second aspect, an embodiment of the present invention further provides an image processing apparatus, including:
the image processing device comprises a to-be-processed image downsampling module, a sampling module and a sampling module, wherein the to-be-processed image downsampling module is used for acquiring an to-be-processed image and downsampling the to-be-processed image to obtain a downsampled image;
an image distance calculation module, configured to determine pixel codes of a current downsampled image and an image before downsampling respectively when the downsampled image meets a first hierarchical condition, and determine an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
The current image downsampling module is used for performing iterative downsampling processing on the current downsampled image when the current downsampled image and the image distance meet a second layering condition;
and the image set forming module is used for forming a pyramid structured image set based on the image to be processed and at least one downsampled image obtained by downsampling.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement an image processing method as provided by an embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements an image processing method as provided by the embodiment of the present invention.
The embodiments of the above invention have the following advantages or benefits:
the method comprises the steps of obtaining an image to be processed, and carrying out downsampling on the image to be processed to obtain a downsampled image; when the downsampled image meets a first layering condition, respectively determining pixel codes of the current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes; when the current downsampled image and the image distance meet the second layering condition, performing iterative downsampling processing on the current downsampled image; the image collection of the pyramid structure is formed based on the image to be processed and at least one downsampled image obtained by downsampling, so that the self-adaptive layering of the image is realized, the image collection is applicable to various images and is not limited by image characteristics, the pyramid structure of the self-adaptive layering is applicable to the fields of image registration and the like, the speed and the precision of image registration are improved, meanwhile, the number of pyramid layers is selected instead of manual operation, and the operation is simplified.
Drawings
In order to more clearly illustrate the technical solution of the exemplary embodiments of the present invention, a brief description is given below of the drawings required for describing the embodiments. It is obvious that the drawings presented are only drawings of some of the embodiments of the invention to be described, and not all the drawings, and that other drawings can be made according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an image processing method according to an embodiment of the present invention;
FIG. 2 is a view of an image set of template images according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an image set of images to be searched according to an embodiment of the present invention;
fig. 4 is a flowchart of an image processing method according to a second embodiment of the present invention;
fig. 5 is a diagram showing a target registration area according to a second embodiment of the present invention;
FIG. 6 is a schematic diagram of a template image processing and registration process according to a second embodiment of the present invention;
fig. 7 is a schematic structural diagram of an image processing apparatus according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a schematic flow chart of an image processing method according to an embodiment of the present invention, where pyramid adaptive layering is required for images, and a layered image set is used for image registration or image fusion, the method may be performed by an image processing apparatus, and the apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:
s110, acquiring an image to be processed, and performing downsampling on the image to be processed to obtain a downsampled image.
The image to be processed refers to an image which needs to be subjected to multi-resolution analysis in the image processing process, such as a template image and/or an image to be searched for image registration, and registration of the image is realized by layering the template image and the image to be searched into a multi-scale image structure and carrying out registration analysis on the multi-scale image structure, so that the speed and the accuracy of image registration are improved; or the left viewpoint image and/or the right viewpoint image which are subjected to image fusion are respectively fused under multiple scales by layering two images into an image structure with multiple scales, so that the speed and the accuracy of image fusion are improved.
In this embodiment, the downsampling process is used to reduce the resolution of the image to be processed, where the downsampling process may be implemented by deleting even lines and even columns of the image, or by changing all pixels in the 2×2 window of the image to be the average of all pixels in the window, for example, the size of the image to be processed is m×n, and downsampling is performed 2 times to obtain an image with the size of (M/2) × (N/2), where the resolution of the downsampled image is 1/4 of the image to be processed. By carrying out downsampling on the image to be processed in an iterative manner, an image set with gradually reduced resolution, namely an image set with a pyramid structure, can be obtained, wherein the bottom image of the pyramid is the image to be processed, namely the original image which is not downsampled, and each image on the upper layer is obtained by carrying out downsampling on the previous image layer by layer.
For example, a gaussian pyramid downsampling method may be used for downsampling the layer 1 image (to-be-processed image) to obtain a second layer image, which specifically includes the following steps: (1) Taking the image to be processed as an underlayer L 1 Is stored in a pyramid data structure, corresponding to L 1 Performing Gaussian filtering on the image; (2) Interlaced interval extraction L 1 Pixels of the image, obtaining a second layer L 2 An image. Specifically, from L 1 To L 2 The construction of (2) satisfies the following formula:
wherein G is 2 (i, j) is pyramid L 2 Image, G 1 (i, j) is pyramid L 1 The image, i and j respectively represent the row and the column of pixels, omega (m, n) is a Gaussian kernel function, m and n are the width and the height of a window, and the size of the window is 5 multiplied by 5; m, N is L 1 Rows and columns of the image. It will be appreciated that the construction from the kth layer to the kth+1th layer can also be obtained based on the above formula, k being the middle layer of the pyramid structure.
And S120, when the downsampled image meets the first layering condition, respectively determining pixel codes of the current downsampled image and the image before downsampling, and determining the image distance between the current downsampled image and the image before downsampling based on the pixel codes.
In this embodiment, the first layering condition is a first boundary condition for performing the down-sampling process, and is used to determine the size of the down-sampled image, and the image distance is calculated and the image distance is determined only when the first boundary condition is satisfied. Illustratively, the first layering condition is that the image size is greater than a preset size. Specifically, the preset size may be 8×8, if the downsampled image size is greater than 8×8, determining the pixel codes of the current downsampled image and the image before downsampling, and if the image size of the image to be processed is less than 8×8, stopping the downsampling process. By judging the size of the downsampled image, the calculation and downsampling processing of the image distance are realized only for the image meeting the size condition, and the situation that the image information is seriously lost due to the fact that downsampling is continued for the image with lower resolution is avoided, so that layering precision is improved.
The current downsampled image is obtained through downsampling based on an image before downsampling, and in the pyramid structure, the current downsampled image is a previous layer image of the image before downsampling. The pixel codes represent pixel information of an image, the image distance is used for analyzing information correlation of two images based on the pixel information of the image, the larger the image distance is, the larger the pixel difference between the current downsampled image and the image before downsampling is, the smaller the information correlation between the two images is, the less useful information in the current downsampled image is, and the value of continuous downsampling is smaller; the smaller the image distance is, the smaller the pixel difference between the current downsampled image and the image before downsampling is, the larger the information correlation between the two images is, the more useful information in the current downsampled image is, and the value of continuous downsampling is larger. Specifically, the pixel distance may be a hamming distance, that is, the number of corresponding bits between the pixel codes of the current downsampled image and the image before downsampling is different, and the hamming distance is calculated as follows:
wherein x is k 、y k For the kth code in the pixel codes of the current downsampled image and the image prior to downsampling, The modulo-2 operation is represented, and n is the number of codes in pixel coding of the current downsampled image and the image prior to downsampling. Exemplary, if current downsamplingThe pixel code of the image is 00000100, the pixel code of the image before downsampling is 00000111, the number of the corresponding bit difference between the two pixel codes is 2, and the hamming distance is 2.
Optionally, determining the pixel encoding of the current downsampled image and the image prior to downsampling includes: respectively determining the pixel mean value of the image for the current downsampled image or the image before downsampling; and comparing the pixel value of each pixel point in the current downsampled image or the image before downsampling with the corresponding image pixel average value, and determining the coding of each pixel point according to the comparison result to obtain the pixel coding of the current downsampled image or the image before downsampling.
The pixel mean value is the pixel mean value of all pixel points of the image. Specifically, when the pixel value of the pixel point is greater than or equal to the image pixel mean value, generating a first code of the pixel point; when the pixel value of the pixel point is smaller than the image pixel mean value, generating a second code of the pixel point; and forming a coding matrix by coding each pixel point based on the position of each pixel point in the current downsampled image or the image before downsampling, so as to obtain the pixel coding of the current downsampled image or the image before downsampling.
Optionally, the first code and the second code are 1 and 0, respectively, when the pixel value of the pixel is greater than or equal to the pixel mean value, the code of the pixel is 1, and when the pixel value of the pixel is less than the pixel mean value, the code of the pixel is 0. Illustratively, each pixel row of the image is traversed, wherein each row traverses each pixel of the image matrix G from left to right, point to point, and if the i-th row j column element G (i, j) > = a, the code value is noted as 1; if the i-th row j column element G (i, j) < a, the encoded value is noted as 0. If the number of pixels in the current downsampled image or the image before downsampling is n, based on the positions of the pixels, the codes of the pixels of each pixel are placed into the coding matrix line by line, so that a 1×n one-dimensional coding matrix can be formed. The current downsampled image or the image before downsampling is typically 2 x 2 in size, 4 in number of pixels, and 1 x 4 in number of pixels. The codes of the pixel points form a one-dimensional coding matrix so as to be convenient for comparing the corresponding positions between the one-dimensional coding matrix of the downsampled image and the one-dimensional coding matrix of the image before downsampling, thereby improving the calculation speed of the Hamming distance of the downsampled image and the image before downsampling.
Optionally, before determining the pixel encoding of the current downsampled image and the image before downsampling, further comprises: respectively carrying out scaling treatment on the current downsampled image and the image before downsampling to obtain the current downsampled image and the image before downsampling with the same size; accordingly, determining the pixel encoding of the current downsampled image and the image prior to downsampling comprises: and carrying out coding processing on the current downsampled image and the image before downsampling of the same size to obtain pixel codes corresponding to the images. The current downsampled image and the image before downsampling are subjected to scaling processing, and the sizes of the current downsampled image and the image before downsampling are unified, so that pixel codes with consistent bit numbers are obtained, and wrong image distances are avoided.
Since the hamming distance is the number of different bits corresponding to two codes of the same length, the number of bits of the pixel codes of the current downsampled image and the image before downsampling must be consistent, the image is scaled before the image calculation region is coded, and the size of the image is fixed to a uniform size, such as 8×8, so as to obtain the pixel codes of the current downsampled image and the image before downsampling, which have the consistent number of bits.
Illustratively, the complete process of calculating the image distance between the current downsampled image and the image before downsampling in this embodiment is as follows: (1) image scaling: scaling the current downsampled image and the image before downsampling, and scaling the current downsampled image and the image before downsampling to 8×8 total 64 pixel points; (2) calculating a pixel mean: calculating the average value of all elements in the matrix according to the 8X 8 integer matrix G obtained in the last step, and enabling the average value to be a; (3) acquiring pixel codes: traversing each pixel of the matrix G row by row from left to right if the ith row, j, column element G (i, j)>=a, the code value is noted as 1; if the ith row and j columns element G (i, j)<a, the coding value is marked as 0, so that the area coding of the current downsampled image and the image before downsampling is obtained; (4) calculating a hamming distance: calculating the timeFront downsampled image [ x ] 1 ,x 2 ,…,x k ,…,x n ]And the image before downsampling [ y ] 1 ,y 2 ,…,y k ,…,y n ]Distance d (x, y).
S130, when the current downsampled image and the image distance meet the second layering condition, performing iterative downsampling processing on the current downsampled image.
The current downsampled image is an image after the first or multiple downsampling of the image to be processed, and the second layering condition is used for further judging whether the current downsampled image is subjected to downsampling processing continuously. If the current downsampled image meets the first layering condition and the current downsampled image and the image distance meet the second layering condition, downsampling the current downsampled image to obtain a downsampled image of the current downsampled image, taking the downsampled image as the current downsampled image, and repeating the iterating condition judging and downsampling steps until the first layering condition or the second layering condition is not met.
Optionally, when any downsampled image does not meet the first layering condition and/or the image distance between any downsampled image and the image before downsampling any downsampled image does not meet the second layering condition, processing of any downsampled image is stopped. By judging the current downsampled image based on the second layering condition, stopping layering when the useful information of the current downsampled image is less, continuing layering when the useful information of the current downsampled image is more, realizing self-adaptive layering based on image information, avoiding the reduction of registration accuracy caused by excessive layering and the slower registration speed caused by too little layering, thereby improving the registration accuracy and speed.
Optionally, the second layering condition includes that the current downsampled image is not the first downsampled image of the image to be processed and the image distance is less than or equal to a preset distance.
As shown in tables 1-3, the hamming distance between each layer of images after downsampling of 6 different images to be processed is shown, wherein the 1 st layer of image is an original non-layered image to be processed, the 2 nd layer to 5 th layer of image after iterative downsampling of the image to be processed is the similarity between two adjacent layers of images, the similarity is evaluated to represent the effective information content contained in the current layer of image, and if the hamming distance between the current layer of image and the image before downsampling is less than 5, the two images are very similar at the moment, and the current layer of image still contains a large amount of effective information content; if the Hamming distance is more than 10, the similarity of the two images is lower, and the loss of the current layer image information is serious.
As can be seen from Table 1, the L < th > of the first image to be processed 2 Layer to L 4 The Hamming distance of the layer is less than 10, from L 4 The Hamming distance from layer to topmost layer is greater than 10, indicating from L 4 The loss of image information after the layer is serious, at this time, L 4 The layer is the top layer and meets the cut-off condition, namely from L 3 Layer and L 3 The hamming distance is calculated for the first time in the upper layer of the layer to be more than 10, and layering is stopped; l of the second image to be processed 2 Layer to L 4 The Hamming distance of the layer is greater than 10, L 5 The Hamming distance of the layers is less than 10, and for the abnormal cases that the Hamming distance of the first layers is more than 10, L is used 3 The layer is the top layer and meets the cut-off condition, namely from L 3 Layer and L 3 The hamming distance is calculated for the first time in the upper layer of the layer to be more than 10, and layering is stopped. As can be seen from Table 2, the L-th image of the third image to be processed 2 The Hamming distance of the layer is greater than 10, L 3 Layer to L 5 The Hamming distance of the layer is smaller than 10, and for the abnormal situation that the Hamming distance of the first layered image is larger than 10, but the Hamming distance of the subsequent layered image is smaller than 10, the first layered condition is taken as a cut-off condition; l of fourth image to be processed 2 The Hamming distance of the layer is greater than 10, L 3 The Hamming distance of the layer is less than 10L 4 The layer is again greater than 10, at this point L 4 The layer is the top layer and meets the cut-off condition, namely from L 3 Layer and L 3 The hamming distance is calculated for the first time in the upper layer of the layer to be more than 10, and layering is stopped. As can be seen from Table 3, the fifth image to be processed is from L 2 Layer to L 5 The Hamming distance of the layers is less than or equal to 10, which indicates that the information quantity of each layer of image meets the requirement at the moment, and the first layering condition is taken as a cut-off condition at the moment; sixth stepL of the image to be processed 2 The Hamming distance of the layer is 10 or less from L 3 The Hamming distance from layer to topmost layer is greater than 10, indicating from L 3 The loss of image information after the layer is serious, which is L 3 The layer is the top layer and meets the cut-off condition, namely from L 3 Layer and L 3 The hamming distance is calculated for the first time in the upper layer of the layer to be more than 10, and layering is stopped.
TABLE 1
TABLE 2
TABLE 3 Table 3
In conclusion, no matter L 2 Whether the Hamming distance of the layer pyramid image is less than 10 is selected as L 2 The number of layers with the hamming distance larger than 10 appearing for the first time after the layers is a cut-off condition, namely, determining the downsampled images with the hamming distance larger than 10 except the first downsampled image as top-layer images; if a hamming distance greater than 10 does not occur, the topmost image is determined based on the first layering condition. It will be appreciated that, according to the above second layering condition, the image distance of the downsampled image of the image to be processed other than the first downsampled image is determined, the corresponding layer of the downsampled image having the image distance greater than the preset distance is used as the cut-off layer, and the downsampling process is stopped, that is, no matter what value the image distance of the first downsampled image of the image to be processed is, only the first downsampled image is determined The image distance of the subsequent downsampled image. In this embodiment, by judging the image distance after the second downsampling, adaptive layering of the images to be layered is achieved, so that the information amount of each layer of image meets the requirements.
S140, forming an image set with a pyramid structure based on the image to be processed and at least one downsampled image obtained by downsampling.
The image to be processed is an original image which is not subjected to downsampling processing, and at least one downsampled image can be obtained through continuous downsampling processing of one image to be processed. The pyramid structure is an image structure with gradually reduced resolution, the bottom layer is an image to be processed, and the images of other layers are obtained by iterative downsampling of the images of the bottom layer by layer. As shown in fig. 2 and 3, are respectively a set of images of a downsampled pyramid structure of the template image and the image to be searched.
The pyramid structure of the adaptive hierarchical structure obtained in this embodiment may be applied to image registration, as shown in table 4, and is a comparison of accuracy of image registration under the adaptive hierarchical pyramid and manual hierarchical structure. The figure shows that the number of layers of the pyramid self-adaptive layering is 3, and the matching result is accurate. If the number of layers is manually set to 3, the same result can be obtained, and if the number of layers is manually set to 4, errors occur in the matching result, but the matching speed is relatively improved. Thus, pyramid adaptive layering can achieve the same matching effect with ensured accuracy.
TABLE 4 Table 4
Table 5 shows that the pyramid self-adaptive layering method provided by the embodiment can effectively improve the matching speed and realize the improvement of the speed magnitude under the condition of ensuring the same registration accuracy compared with the effect of image registration without using the pyramid self-adaptive layering method, and the embodiment has good application advantages for image registration.
TABLE 5
Table 6 shows the calculation result of FAST feature points of the pyramid image, "lena. Jpg", and as can be seen from table 6, the application of the FAST feature point method to pyramid image detection shows that: (1) The threshold t is required to be manually specified, the influence of the threshold t on the number of the feature points is large, and the optimal value cannot be accurately judged; (2) The feature point number is fast reduced when the scale is changed, and the fluctuation between layers is large, so that the problem that 25% -30% of the fuzzy image information of the first layer of the image pyramid is difficult to meet as the threshold value of the number of the matching points in the paper self-adaptive variable scale feature point extraction method is solved, the reliability of the result can be ensured, and the rationality of the matching time can be ensured; (3) There are few feature points in the smoothed region of the image, and this method may fail if there are more smoothed regions in the input image. Therefore, the FAST feature point method cannot be well applied to pyramid self-adaptive layering tasks, and the scheme of the embodiment can be applied to various images without being limited by image features.
TABLE 6
According to the technical scheme, the image to be processed is obtained, and downsampling is carried out on the image to be processed to obtain a downsampled image; when the downsampled image meets a first layering condition, respectively determining pixel codes of the current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes; performing iterative downsampling processing on the current downsampled image when the current downsampled image and the image distance meet the second layering condition; the image collection of the pyramid structure is formed based on the image to be processed and at least one downsampled image obtained by downsampling, so that the self-adaptive layering of the image is realized, the image collection is applicable to various images and is not limited by image characteristics, the pyramid structure of the self-adaptive layering is applicable to the fields of image registration and the like, the speed and the precision of image registration are improved, meanwhile, the number of pyramid layers is selected instead of manual operation, and the operation is simplified.
Example two
Fig. 4 is a flowchart of an image processing method according to a second embodiment of the present invention, where, based on the above embodiment, when an image to be processed is a template image to be registered, a registration step with the template image and a image to be searched is added. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.
Referring to fig. 4, the image processing method provided in the present embodiment includes:
s410, acquiring a template image, and performing downsampling processing on the template image to obtain a downsampled image.
The template image and the image to be searched are images acquired under different conditions for the same object, such as a plurality of images shot under different acquisition equipment, acquisition time, shooting distance or shooting visual angle and the like, and the template image can be mapped onto the image to be searched so that the template image corresponds to the points of the image to be searched in the same position in space one by one, wherein the template image refers to a local image used for searching in a corresponding area of the image to be searched.
S420, when the downsampled image meets the first layering condition, respectively determining pixel codes of the current downsampled image and the image before downsampling, and determining the image distance between the current downsampled image and the image before downsampling based on the pixel codes.
S430, when the current downsampled image and the image distance meet the second layering condition, performing iterative downsampling processing on the current downsampled image.
S440, forming an image set of a pyramid structure based on the template image and at least one downsampled image obtained by downsampling.
S450, determining the layer number in the pyramid structure image set, and layering the image to be searched registered with the template image based on the layer number to obtain the pyramid structure image set of the image to be searched.
The layer number of the image set of the pyramid structure of the template image is used for specifying the layer number of the image to be searched, so that the pyramid structure of the image to be searched is consistent with the layer number of the pyramid structure of the template image.
S460, performing rotation processing on each image in the image set corresponding to the template image to obtain at least one image to be registered corresponding to each pyramid layering.
The images to be registered refer to images of the template image after corresponding rotation of each layer of images in the image set, and a plurality of rotation images can be generated by each layer of images in the image set according to different rotation angles. Optionally, after rotation processing is performed on each image in the image set corresponding to the template image, filling processing is performed on the rotated image, and accordingly, the image after filling processing is used as the image to be registered.
And S470, performing correlation registration on at least one image to be registered with the same layer number and a corresponding image in an image set of the pyramid structure of the image to be searched layer by layer based on the pyramid structure to obtain a target registration area matched with the template image in the image to be searched.
Specifically, a registration angle range of the current layer number is obtained, and at least one target registration image used for matching is determined based on the registration angle range in the image to be registered of the current layer number, wherein the target registration image refers to an image which is subjected to correlation registration with the image to be searched of the current layer number. The current layer number can be any layer in the pyramid structure, if the current layer number is the top layer in the pyramid structure, the registration angle range is full-range angle registration, namely, all the rotating images of the top layer are used as target registration images and are registered with the top layer images in the target image set one by one; if the current layer number is not the top layer, i.e. the bottom layer or the middle layer, the registration angle range is determined by the registration angle acquired by the previous layer and the preset range, specifically, the registration angle range=the registration angle of the previous layer± (preset range/2), and if the current layer is the 4 th layer, the registration angle acquired by the 3 rd layer is 90 degrees, the preset range is 10 degrees, the registration angle range of the 3 rd layer is 85 degrees to 95 degrees, and an image in a range of 85 degrees to 95 degrees is selected from images to be registered of the 4 th layer as a target registration image.
After determining the target registration images, determining correlation coefficients of at least one target registration image and corresponding images in an image set of the image to be searched, determining a registration angle and a registration coordinate corresponding to the target registration image with the largest correlation coefficient, judging whether the current layer number is the bottom layer of the pyramid structure, if not, iteratively executing the operation of mapping the registration angle range downwards, if so, determining a target registration area matched with the template image based on the registration coordinate and the registration angle obtained by bottom layer registration, wherein the area displayed in a frame is the target registration area in the image to be searched as shown in fig. 5.
Exemplary, the complete steps of processing and registration of the template image are as follows, as shown in fig. 6: (1) inputting a template image; (2) Taking the input template image as L 1 Layering into pyramid structures; (3) For L k (k=1, 2,) layer image downsampling to obtain L k+1 A layer image; (4) Judgment of L k+1 Whether the layer image meets the size boundary or not, if yes, executing the step (5), and if not, executing the step (8); the method comprises the steps of carrying out a first treatment on the surface of the (5) Acquisition of L k Layer and L k+1 Image coding of layers, calculating their hamming distances; (6) Judging whether the Hamming distance boundary is met, if yes, executing the step (7), otherwise, executing the step (8); (7) Will L k+1 The layer images are stored in a pyramid structure, k++, and the step (3) is executed; (8) Finishing downsampling, and recording the number of layers k+1, namely the number of layers of the self-adaptive layering; (9) downsampling the image to be searched according to k+1; (10) The template image is matched on the image to be searched from coarse to fine, namely from top to bottom.
According to the technical scheme, the pyramid self-adaptive layering method is applied to two images participating in image registration, so that layer-by-layer registration from top to bottom is realized, the speed and the accuracy of image registration are improved, and the method is also applicable to registration of images with smooth areas occupying more areas.
Example III
Fig. 7 is a schematic structural diagram of an image processing apparatus according to a third embodiment of the present invention, where pyramid adaptive layering is required for images, and a layered image set is used for image registration or image fusion, the apparatus specifically includes: a pending image downsampling module 710, an image distance calculation module 720, a current image downsampling module 730, and an image collection formation module 740.
The image to be processed downsampling module 710 is configured to obtain an image to be processed, and downsample the image to be processed to obtain a downsampled image;
an image distance calculating module 720, configured to determine pixel codes of the current downsampled image and the image before downsampling, respectively, when the downsampled image satisfies a first hierarchical condition, and determine an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
the current image downsampling module 730 is configured to iteratively downsample the current downsampled image when the current downsampled image and the image distance satisfy the second layering condition;
an image set forming module 740 is configured to form a pyramid-structured image set based on the image to be processed and at least one downsampled image obtained by the downsampling process.
In the embodiment, an image to be processed is obtained through an image downsampling module to be processed, and downsampling processing is carried out on the image to be processed to obtain a downsampled image; based on an image distance calculation module, when the downsampled image meets a first layering condition, respectively determining pixel codes of a current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes; performing iterative downsampling processing on the current downsampled image based on the fact that the current downsampled image and the image distance meet a second layering condition by the current image downsampling module; the image collection forming module is used for forming the image collection of the pyramid structure based on the image to be processed and at least one downsampled image obtained through downsampling, so that the self-adaptive layering of the image is realized, the image collection forming module is applicable to various images and is not limited by image characteristics, the pyramid structure of the self-adaptive layering is applicable to the fields of image registration and the like, the speed and the precision of image registration are improved, meanwhile, the number of pyramid layers is selected instead of manual operation, and the operation is simplified.
Optionally, the current image downsampling module 730 is further configured to stop processing any downsampled image when any downsampled image does not meet the first layering condition and/or an image distance between any downsampled image and an image before downsampling any downsampled image does not meet the second layering condition.
Optionally, the first layering condition is that the image size is larger than a preset size, the second layering condition includes that the current downsampled image is not the first downsampled image of the image to be processed, and the image distance is smaller than or equal to the preset distance.
Optionally, the image distance calculating module 720 includes:
the pixel mean value calculation unit is used for respectively determining the pixel mean value of the image for the current downsampled image or the image before downsampling;
and the pixel coding calculation unit is used for comparing the pixel value of each pixel point in the current downsampled image or the image before downsampling with the corresponding image pixel average value, determining the coding of each pixel point according to the comparison result, and obtaining the pixel coding of the current downsampled image or the image before downsampling.
Optionally, the pixel coding calculation unit is specifically configured to generate a first code of the pixel point when the pixel value of the pixel point is greater than or equal to the average value of the pixels of the image; when the pixel value of the pixel point is smaller than the image pixel mean value, generating a second code of the pixel point; and forming a coding matrix by coding each pixel point based on the position of each pixel point in the current downsampled image or the image before downsampling, so as to obtain the pixel coding of the current downsampled image or the image before downsampling.
Optionally, the image distance calculating module 720 further includes:
the scaling processing unit is used for respectively scaling the current downsampled image and the image before downsampling to obtain the current downsampled image and the image before downsampling with the same size before determining pixel codes of the current downsampled image and the image before downsampling;
correspondingly, the pixel mean value calculation unit and the pixel coding calculation unit are also used for carrying out coding processing on the current downsampled image and the image before downsampling of the same size to obtain pixel codes corresponding to the images.
Optionally, on the basis of the image processing apparatus, the image processing apparatus further includes an image registration module, where the image registration module includes:
the image layering unit to be searched is used for determining the number of layers in the pyramid structure image set when the image to be processed is the template image to be registered, and layering the image to be searched registered with the template image based on the number of layers to obtain the pyramid structure image set of the image to be searched;
the rotation unit is used for carrying out rotation processing on each image in the image set corresponding to the template image to obtain at least one image to be registered corresponding to each pyramid layering;
And the registration unit is used for carrying out correlation registration on at least one image to be registered with the same layer number and a corresponding image in the pyramid structure image set of the image to be searched layer by layer based on the pyramid structure to obtain a target registration area matched with the template image in the image to be searched.
The image processing device provided by the embodiment of the invention can execute the image processing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that, the units and modules included in the above system are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present invention.
Example IV
Fig. 8 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. Fig. 8 shows a block diagram of an exemplary electronic device 80 suitable for use in implementing the embodiments of the present invention. The electronic device 80 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in FIG. 8, the electronic device 80 is in the form of a general purpose computing device. Components of the electronic device 80 may include, but are not limited to: one or more processors or processing units 801, a system memory 802, and a bus 803 that connects the various system components (including the system memory 802 and processing units 801).
Bus 803 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 80 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 80 and includes both volatile and non-volatile media, removable and non-removable media.
The system memory 802 may include computer-system-readable media in the form of volatile memory, such as Random Access Memory (RAM) 804 and/or cache memory 805. The electronic device 80 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 806 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, commonly referred to as a "hard disk drive"). Although not shown in fig. 8, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 803 via one or more data medium interfaces. Memory 802 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 808 having a set (at least one) of program modules 807 may be stored in, for example, memory 802, such program modules 807 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 807 typically carry out the functions and/or methods of the described embodiments of the invention.
The electronic device 80 may also communicate with one or more external devices 809 (e.g., keyboard, pointing device, display 810, etc.), one or more devices that enable a user to interact with the electronic device 80, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 80 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 811. Also, the electronic device 80 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 812. As shown, network adapter 812 communicates with other modules of electronic device 80 over bus 803. It should be appreciated that although not shown in fig. 8, other hardware and/or software modules may be used in connection with electronic device 80, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 801 executes various functional applications and data processing by running a program stored in the system memory 802, for example, implements an image processing method step provided by the present embodiment, and the method includes:
acquiring an image to be processed, and performing downsampling on the image to be processed to obtain a downsampled image;
when the downsampled image meets a first layering condition, respectively determining pixel codes of a current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
when the current downsampled image and the image distance meet the second layering condition, performing iterative downsampling processing on the current downsampled image;
an image set of the pyramid structure is formed based on the image to be processed and at least one downsampled image resulting from the downsampling process.
Of course, those skilled in the art will understand that the processor may also implement the technical solution of the image processing method provided in any embodiment of the present invention.
Example five
A fifth embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the image processing method as provided in any embodiment of the present invention, the method comprising:
Acquiring an image to be processed, and performing downsampling on the image to be processed to obtain a downsampled image;
when the downsampled image meets a first layering condition, respectively determining pixel codes of a current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
when the current downsampled image and the image distance meet the second layering condition, performing iterative downsampling processing on the current downsampled image;
an image set of the pyramid structure is formed based on the image to be processed and at least one downsampled image resulting from the downsampling process.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. An image processing method, comprising:
acquiring an image to be processed, and performing downsampling processing on the image to be processed to obtain a downsampled image;
when the downsampled image meets a first layering condition, respectively determining pixel codes of a current downsampled image and an image before downsampling, and determining an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
when the current downsampled image meets a first layering condition and the current downsampled image and the image distance meet a second layering condition, downsampling the current downsampled image to obtain a downsampled image of the current downsampled image, taking the downsampled image as the current downsampled image, and repeating the iterative condition judging and downsampling steps until the first layering condition or the second layering condition is not met; the second layering condition is used for further judging whether the current downsampled image is subjected to downsampling processing continuously or not;
And forming an image set with a pyramid structure based on the image to be processed and at least one downsampled image obtained by downsampling.
2. The method according to claim 1, wherein the method further comprises:
and stopping processing any downsampled image when any downsampled image does not meet the first layering condition and/or an image distance between the any downsampled image and an image between the any downsampled image and the any downsampled image does not meet the second layering condition.
3. The method according to claim 1 or 2, wherein the first hierarchical condition is that an image size is larger than a preset size, the second hierarchical condition comprises that the current downsampled image is not the first downsampled image of the image to be processed, and the image distance is smaller than or equal to a preset distance.
4. The method of claim 1, wherein determining the pixel encoding of the current downsampled image and the image prior to downsampling comprises:
respectively determining the pixel mean value of the image for the current downsampled image or the image before downsampling;
and comparing the pixel value of each pixel point in the current downsampled image or the image before downsampling with the corresponding image pixel average value, and determining the coding of each pixel point according to the comparison result to obtain the pixel coding of the current downsampled image or the image before downsampling.
5. The method of claim 4, wherein determining the pixel codes for each pixel based on the comparison results to obtain the pixel codes for the current downsampled image or the image prior to downsampling comprises:
when the pixel value of the pixel point is larger than or equal to the image pixel mean value, generating a first code of the pixel point;
when the pixel value of the pixel point is smaller than the image pixel mean value, generating a second code of the pixel point;
and forming a coding matrix by coding each pixel point based on the position of each pixel point in the current downsampled image or the image before downsampling, so as to obtain the pixel coding of the current downsampled image or the image before downsampling.
6. The method of claim 4, further comprising, prior to determining the pixel encoding of the current downsampled image and the image prior to downsampling:
scaling the current downsampled image and the image before downsampling respectively to obtain the current downsampled image and the image before downsampling with the same size;
accordingly, the determining pixel codes of the current downsampled image and the image before downsampling includes:
and carrying out coding processing on the current downsampled image and the image before downsampling in the same size to obtain pixel codes corresponding to the images.
7. The method according to claim 1, wherein the image to be processed is a template image to be registered;
the method further comprises the steps of:
determining the layer number in the pyramid structure image set, and layering the image to be searched registered with the template image based on the layer number to obtain the pyramid structure image set of the image to be searched;
performing rotation processing on each image in the image set corresponding to the template image to obtain at least one image to be registered corresponding to each pyramid layering;
and carrying out correlation registration on at least one image to be registered with the same layer number and a corresponding image in an image set of the pyramid structure of the image to be searched layer by layer based on the pyramid structure to obtain a target registration area matched with the template image in the image to be searched.
8. An image processing apparatus, comprising:
the image processing device comprises a to-be-processed image downsampling module, a sampling module and a sampling module, wherein the to-be-processed image downsampling module is used for acquiring an to-be-processed image and downsampling the to-be-processed image to obtain a downsampled image;
an image distance calculation module, configured to determine pixel codes of a current downsampled image and an image before downsampling respectively when the downsampled image meets a first hierarchical condition, and determine an image distance between the current downsampled image and the image before downsampling based on the pixel codes;
The current image downsampling module is used for performing downsampling processing on the current downsampled image to obtain a downsampled image of the current downsampled image when the current downsampled image meets a first layering condition and the current downsampled image and the image distance meet a second layering condition, taking the downsampled image as the current downsampled image, and repeating the iterative condition judgment and downsampling steps until the first layering condition or the second layering condition is not met; the second layering condition is used for further judging whether the current downsampled image is subjected to downsampling processing continuously or not;
and the image set forming module is used for forming a pyramid structured image set based on the image to be processed and at least one downsampled image obtained by downsampling.
9. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the image processing method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the image processing method according to any one of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256826.6A CN112419215B (en) | 2020-11-11 | 2020-11-11 | Image processing method, device, electronic equipment and storage medium |
| PCT/CN2021/097085 WO2022100068A1 (en) | 2020-11-11 | 2021-05-31 | Image processing method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256826.6A CN112419215B (en) | 2020-11-11 | 2020-11-11 | Image processing method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112419215A CN112419215A (en) | 2021-02-26 |
| CN112419215B true CN112419215B (en) | 2024-04-09 |
Family
ID=74781131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011256826.6A Active CN112419215B (en) | 2020-11-11 | 2020-11-11 | Image processing method, device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112419215B (en) |
| WO (1) | WO2022100068A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419215B (en) * | 2020-11-11 | 2024-04-09 | 广东拓斯达科技股份有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN113592831B (en) * | 2021-08-05 | 2024-03-19 | 北京方正印捷数码技术有限公司 | Printing error detection method, device and storage medium |
| CN115600619B (en) * | 2022-12-13 | 2023-04-07 | 深圳思谋信息科技有限公司 | Dot matrix two-dimensional code identification method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228577A (en) * | 2016-07-28 | 2016-12-14 | 西华大学 | A kind of dynamic background modeling method and device, foreground detection method and device |
| CN111260580A (en) * | 2020-01-17 | 2020-06-09 | 珠海全志科技股份有限公司 | Image denoising method based on image pyramid, computer device and computer readable storage medium |
| CN111652818A (en) * | 2020-05-29 | 2020-09-11 | 浙江大华技术股份有限公司 | Image filtering method and device based on pyramid and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8547389B2 (en) * | 2010-04-05 | 2013-10-01 | Microsoft Corporation | Capturing image structure detail from a first image and color from a second image |
| CN104484866A (en) * | 2014-12-15 | 2015-04-01 | 天津大学 | Image inpainting method based on rotation and scale space expansion |
| CN110705457B (en) * | 2019-09-29 | 2024-01-19 | 核工业北京地质研究院 | Remote sensing image building change detection method |
| CN112419215B (en) * | 2020-11-11 | 2024-04-09 | 广东拓斯达科技股份有限公司 | Image processing method, device, electronic equipment and storage medium |
-
2020
- 2020-11-11 CN CN202011256826.6A patent/CN112419215B/en active Active
-
2021
- 2021-05-31 WO PCT/CN2021/097085 patent/WO2022100068A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228577A (en) * | 2016-07-28 | 2016-12-14 | 西华大学 | A kind of dynamic background modeling method and device, foreground detection method and device |
| CN111260580A (en) * | 2020-01-17 | 2020-06-09 | 珠海全志科技股份有限公司 | Image denoising method based on image pyramid, computer device and computer readable storage medium |
| CN111652818A (en) * | 2020-05-29 | 2020-09-11 | 浙江大华技术股份有限公司 | Image filtering method and device based on pyramid and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| TDFA:一种生成空间影像金字塔的方法;张云舟;张陌;王晋年;张刚;;中国图象图形学报(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022100068A1 (en) | 2022-05-19 |
| CN112419215A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112419215B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN112102411B (en) | Visual positioning method and device based on semantic error image | |
| CN111523414B (en) | Face recognition method, device, computer equipment and storage medium | |
| CN112132959B (en) | Digital rock core image processing method and device, computer equipment and storage medium | |
| CN113111212B (en) | Image matching method, device, equipment and storage medium | |
| US20190361972A1 (en) | Method, apparatus, device for table extraction based on a richly formatted document and medium | |
| WO2022100065A1 (en) | Image registration method and apparatus, electronic device and storage medium | |
| CN112419372B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN111523447B (en) | Vehicle tracking method, device, electronic equipment and storage medium | |
| CN110222703B (en) | Image contour recognition method, device, equipment and medium | |
| CN111191649A (en) | Method and equipment for identifying bent multi-line text image | |
| US20210097648A1 (en) | Multi-image-based image enhancement method and device | |
| CN112800955A (en) | Remote sensing image rotating target detection method and system based on weighted bidirectional feature pyramid | |
| CN110796108B (en) | Method, device and equipment for detecting face quality and storage medium | |
| CN114266860A (en) | Three-dimensional face model establishing method and device, electronic equipment and storage medium | |
| CN109934283B (en) | Self-adaptive moving object detection method integrating CNN and SIFT optical flows | |
| CN113159103A (en) | Image matching method, image matching device, electronic equipment and storage medium | |
| CN117634556A (en) | Training method and device for semantic segmentation neural network based on water surface data | |
| WO2023109086A1 (en) | Character recognition method, apparatus and device, and storage medium | |
| CN114758123A (en) | Remote sensing image target sample enhancement method | |
| CN113129299A (en) | Template determination method and device, computer equipment and storage medium | |
| CN111856618A (en) | Meteorological element prediction method and equipment | |
| CN108986135B (en) | Target tracking method and device based on LLC and frequency domain residual error significance | |
| CN111310824A (en) | Multi-angle dense target detection inhibition optimization method and equipment | |
| CN114443708A (en) | Pathological section interpretation result display method and system and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |