Quick mapping method and device based on freehand phase boundary recognition

Abstract

The invention relates to the technical field of oil reservoir engineering, in particular to a quick mapping method and device based on freehand facies boundary recognition. The method comprises the following steps: converting a sedimentary facies belt graph scanning image from an RGB space to an HSV space, and extracting a facies boundary coarse contour graph in the scanning image; carrying out connection processing on discontinuous part contour lines by using an image edge expansion algorithm, and carrying out skeletonization processing on the boundary coarse contour map after connection processing to obtain a phase boundary skeleton refined map; and carrying out connected domain analysis on the facies boundary skeleton refined graph, and carrying out error repair on parts which do not meet requirements so as to obtain a final sedimentary facies division result graph. The problems that in the prior art, when a deposition unit phase belt diagram is drawn, the drawing quality and efficiency are low when direct drawing is conducted through computer software, drawing errors are likely to happen, and the investment cost of drawing tools is high are solved; and the description and identification capabilities of a computer on a phase boundary are poor during uploading through hand drawing, so that the final mapping effect is influenced.

Description

Technical Field

[0001] The present invention relates to the technical field of oil reservoir engineering, and in particular to a rapid mapping method and device based on hand-drawn phase boundary recognition. Background Art

[0002] Currently, the main methods for drawing sedimentary unit facies maps in China include: first, drawing sedimentary unit facies maps based on wellpoint facies values ​​in GPTMap software; second, manually sketching after printing the sedimentary unit facies maps, then using GPTMap to depict the manually sketched microfacies boundaries; and third, sketching directly on the touch screen in GPTPlane software using a pen. A survey of the application of these three methods found that the first method has low sketching efficiency and is more suitable for blocks with sparse well networks, simple facies transitions, and small areas; the second method is suitable for blocks with dense well networks, rapid facies transitions, large areas, and a large number of vertically developed layers. Due to its wide sketching field of view, it is not only fast but also generally high-quality. However, its disadvantage is that the hand-drawn drawings need to be scanned and uploaded to a computer, resulting in low description efficiency and poor recognition when the computer is used; the third method simulates manual sketching of sedimentary facies maps, which is relatively efficient but of low quality. The supporting software and hardware equipment require a relatively high one-time investment, and the display window is small when drawing on the computer, which is prone to drawing errors and low efficiency. Over the years, the sedimentary facies maps that need to be drawn not only have many layers and large maps, but also are complex and time-consuming to draw microfacies boundaries, resulting in low mapping efficiency and affecting the timely implementation of work such as reservoir description and perforation plan preparation in production blocks. Summary of the Invention

[0003] The present invention proposes a rapid mapping method and device based on hand-drawn phase boundary identification to solve the problems of low drawing quality and efficiency when drawing sedimentary unit phase belt maps directly through computer software in the past, prone to drawing errors, and high investment costs of drawing tools; and the computer's poor ability to describe and identify phase boundaries when uploading hand-drawn drawings, which affects the final mapping effect.

[0004] According to one aspect of the present invention, a rapid mapping method based on hand-drawn phase boundary recognition is provided, comprising:

[0005] Obtaining a scanned image of a sedimentary facies map to be processed;

[0006] Converting the scanned image from the RGB space to the HSV space, and extracting a rough contour of the phase boundary in the scanned image in the HSV space;

[0007] Using an image edge dilation algorithm to connect the discontinuous contour lines in the phase boundary rough contour image, and then skeletonizing the connected boundary rough contour image to obtain a phase boundary skeleton refinement image;

[0008] A connected domain analysis is performed on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map is error-corrected to obtain a final sedimentary phase division result map.

[0009] Preferably, before converting the scanned image from the RGB space to the HSV space, coordinate conversion and tilt correction processing are performed on the scanned image to obtain a processed scanned image.

[0010] Preferably, the method for performing tilt correction on a scanned image comprises:

[0011] The scanned image is tilt-corrected by using a perspective transformation boundary correction algorithm to obtain a tilt-corrected scanned image.

[0012] Preferably, the perspective transformation boundary correction algorithm is:

[0013]

[0014] Where: (x, y) is the coordinate of the scanned image, (u, v) is the coordinate of the corrected scanned image on the front view, and a, b, c, d, e, f, g, h are distortion parameters.

[0015] Preferably, the method of converting the scanned image from RGB space to HSV space comprises:

[0016]

[0017] Where: R, G, B are the R, G, B values ​​corresponding to the pixels on the scanned image.

[0018] Preferably, before the method of connecting the discontinuous contour lines in the phase boundary rough contour image using the image edge dilation algorithm, the method further comprises:

[0019] The phase boundary contour map is binarized to obtain a binarized phase boundary contour map.

[0020] Preferably, the method of connecting the discontinuous contour lines in the phase boundary rough contour image using an image edge dilation algorithm comprises:

[0021] The imdilate function is used to dilate the phase boundary rough contour image, and the dilated image is the phase boundary rough contour image after the connection processing;

[0022] The imdilate function dilates the image by using a 3*3 structure element to scan each pixel in the phase boundary rough contour image, performing an AND operation with the structure element and the binary image it covers. If the results are both 0, the pixel is 0, otherwise it is 1.

[0023] Preferably, the method of skeletonizing the rough boundary contour map after the connection processing includes:

[0024] The imerode function and the strel function are used to perform skeleton processing on the boundary rough outline map after the connection processing to obtain a phase boundary skeleton refinement map.

[0025] Preferably, the method for determining whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division includes:

[0026] Through connected domain analysis, it is determined whether there are wells in each connected domain in the phase boundary skeleton refinement map and whether they are all wells of the same type. If so, the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map does not meet the accuracy requirements of sedimentary phase division.

[0027] According to one aspect of the present invention, a rapid mapping device based on hand-drawn phase boundary recognition is provided, comprising:

[0028] An acquisition unit, used for acquiring a scanned image of the sedimentary facies map to be processed;

[0029] a coarse contour extraction unit, configured to convert the scanned image from the RGB space to the HSV space, and extract a coarse contour map of the phase boundary in the scanned image in the HSV space;

[0030] an image dilation and refinement unit, configured to connect the discontinuous contour lines in the phase boundary rough contour image using an image edge dilation algorithm, and then perform skeletonization on the connected boundary rough contour image to obtain a phase boundary skeleton refinement image;

[0031] The connected domain analysis unit is used to perform connected domain analysis on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map is error-corrected to obtain the final sedimentary phase division result map.

[0032] The present invention has at least the following beneficial effects:

[0033] The present invention proposes a rapid mapping method and device based on hand-drawn phase boundary recognition. The phase boundary contours are extracted through the HSV technology, and then the continuous sedimentary phase belt contours are obtained through image expansion and edge skeleton refinement image processing technology. Errors are corrected by analyzing the connected domain, which greatly shortens the mapping time, significantly improves work efficiency, reduces labor and equipment costs, and ensures the accuracy and completeness of the final sedimentary phase belt map. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present invention and, together with the specification, are used to explain the technical solutions of the present invention.

[0035] Figure 1 A flowchart of a rapid mapping method and apparatus based on hand-drawn phase boundary recognition according to an embodiment of the present invention is shown;

[0036] Figure 2 A comparison diagram of a scanned image before and after tilt correction according to an embodiment of the present invention is shown;

[0037] Figure 3 shows a rough contour image of phase boundaries extracted according to an embodiment of the present invention;

[0038] Figure 4 The rough outline of the phase boundary after the expansion optimization process according to the embodiment of the present invention is shown. Figure 2 Value image;

[0039] Figure 5 A comparison diagram before and after skeleton thinning processing according to an embodiment of the present invention is shown;

[0040] Figure 6 A diagram showing the connected domain analysis results according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] Various exemplary embodiments, features, and aspects of the present invention will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0042] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0043] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0044] In addition, numerous specific details are provided in the following detailed description to better illustrate the present invention. Those skilled in the art will appreciate that the present invention may be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of the present invention.

[0045] Figure 1 A flowchart of a rapid mapping method and apparatus based on hand-drawn phase boundary recognition according to an embodiment of the present invention is shown; Figure 2 A comparison diagram of a scanned image before and after tilt correction according to an embodiment of the present invention is shown; Figure 3 shows a rough contour image of phase boundaries extracted according to an embodiment of the present invention; Figure 4 The rough outline of the phase boundary after the expansion optimization process according to the embodiment of the present invention is shown. Figure 2 Value image; Figure 5 A comparison diagram before and after skeleton thinning processing according to an embodiment of the present invention is shown; Figure 6 1 shows the connected domain analysis result diagram according to an embodiment of the present invention. Figure 1-6 As shown, a rapid mapping method based on hand-drawn phase boundary recognition includes: step S01: obtaining a scanned image of a sedimentary phase belt map to be processed; step S02: converting the scanned image from RGB space to HSV space, and extracting a phase boundary coarse contour map in the scanned image in the HSV space; step S03: using an image edge dilation algorithm to connect the discontinuous contour lines in the phase boundary coarse contour map, and then skeletonizing the connected boundary coarse contour map to obtain a phase boundary skeleton refinement map; step S04: performing a connected domain analysis on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the sedimentary phase division accuracy requirement. If not, performing error repair on the phase boundary skeleton refinement map to obtain a final sedimentary phase division result map.

[0046] The rapid mapping method based on hand-drawn phase boundary recognition provided by the embodiment of the present invention specifically includes the following steps:

[0047] Step S01: obtaining a scanned image of a sedimentary facies map to be processed.

[0048] In an embodiment of the present invention, the sedimentary phase zone map to be processed is scanned by a scanner to obtain a sedimentary phase zone map scan image, and the sedimentary phase zone map scan image is imported into drawing software.

[0049] Sedimentary facies maps can show the sedimentary patterns of the target range from a planar perspective. Sedimentary facies maps are mainly drawn manually, and manual operation has two main advantages: the first advantage is that during the drawing process of the map, analysis and understanding can be carried out to correctly judge the details of the map; the second advantage is that the dependence on tools is very low. The manually drawn sedimentary facies map needs to go through multiple processes such as mapping, clearing, and review, especially the clearing step, which is time-consuming and error-prone. The automatic identification technology of microfacies boundaries of the present invention can reduce labor intensity and improve the efficiency and accuracy of dividing sedimentary facies.

[0050] Step S02: converting the scanned image from the RGB space to the HSV space, and extracting a rough contour of the phase boundary in the scanned image in the HSV space.

[0051] In the present invention, before converting the scanned image from the RGB space to the HSV space, coordinate conversion and tilt correction processing are performed on the scanned image to obtain a processed scanned image.

[0052] In the embodiment of the present invention, after the scanned image is imported into the drawing software, there may be differences between the coordinates on the image and the coordinates in the drawing software, and coordinate conversion is required. The coordinate conversion matrix before and after the coordinate deflection is:

[0053]

[0054] From this we can get the relationship between the coordinate deflection before and after:

[0055]

[0056] Where: x, y are the original coordinates of the scanned image, x', y' are the converted coordinates, and φ is the deviation angle.

[0057] After coordinate conversion, the actual coordinate system on the scanned image corresponds to the coordinate system of the drawing software.

[0058] In the present invention, the method for performing tilt correction on a scanned image includes: performing tilt correction on the scanned image using a perspective transformation boundary correction algorithm to obtain a tilt-corrected scanned image.

[0059] In the embodiment of the present invention, perspective transformation is a transformation of three-dimensional space, a nonlinear transformation, and the transformation matrix can be obtained by knowing four pairs of coordinate points.

[0060] During the acquisition process, scanned images can experience varying degrees of geometric distortion due to factors such as precision, imaging system nonlinearity, and scanning angle. In practical applications, the goal is often to obtain an orthographic view of the image, so distortion correction (tilt correction) is necessary. A perspective transformation uses the collinearity of the perspective center, image point, and target point to determine four points as the vertices of a rectangle. Tilt correction is then performed on the image based on these four points, transforming the tilted image into an orthographic view.

[0061] Perspective projection is essentially the process of projecting every point on plane P' onto plane P under the influence of the viewing angle. If plane P is defined as the front view plane of an object, then perspective transformation is the process of transforming every pixel on the perspective projection plane to the corresponding pixel on the front view. To correct perspective distortion, it is only necessary to find the transformation formula between the points on plane P and the corresponding points on the front view of the object. The perspective transformation formula for a two-dimensional image, that is, the perspective transformation boundary correction algorithm, can be expressed as:

[0062] In the present invention, the perspective transformation boundary correction algorithm is:

[0063]

[0064] Where: (x, y) is the coordinate of the scanned image (projected image), (u, v) is the coordinate of the corrected scanned image on the front view, and a, b, c, d, e, f, g, h are distortion parameters.

[0065] like Figure 2 As shown, Figure 2 Figure a is the scanned image before tilt correction, and Figure b is the scanned image after tilt correction according to formula (3).

[0066] In the present invention, the method of converting the scanned image from the RGB space to the HSV space includes:

[0067]

[0068] Where: R, G, B are the R, G, B values ​​corresponding to the pixels on the scanned image.

[0069] In the embodiments of the present invention, the RGB color space is the most common color space and a typical additive model. In the RGB space, each color is composed of red (R), green (G), and blue (B) in proportion. The RGB color space is consistent with the fact that the human eye perceives the three primary colors of red, green, and blue, and can be well applied to display devices. However, it cannot fully explain the actual process of color perception by the human eye. When the human eye discerns a color image, it never considers the amount and proportion of red, green, and blue contained in the color, but instead observes it from the perspective of hue, saturation, and brightness.

[0070] In the HSV color space, H represents the hue of a pixel, that is, the color attribute it represents when describing a pure color. It is measured by angle and its value ranges from 0° to 360°. S represents the saturation of the pixel, which is proportional to its value. Its value ranges from 0 to 255. V represents the brightness of the pixel, reflecting the concept of colorless intensity, and its value ranges from 0.0 to 1.0, with 0.0 representing black and 1.0 representing white. The visual perception-oriented nature of the HSV space makes it a commonly used system model, and it allows color images to eliminate the influence of the intensity component from the color information they carry.

[0071] The HSV color model (space) describes color from a perspective consistent with human visual perception of color. The hue and saturation components are independent of each other and do not affect each other. Furthermore, the brightness and hue components are also independent of each other. Therefore, the brightness component is unrelated to the color information of the image, removing color correlation and making it easier to process the brightness and color information of the image. These features make the HSV model very natural and intuitive, and it is also very suitable for processing color information in situations based on visual perception.

[0072] As mentioned above, the HSV color model evolved from the RGB cube model, so it is possible to convert from the RGB color space to the HSV color space. According to its evolution principle, the conversion formula can be obtained as shown in formula (4). Therefore, using formula (4) can convert the image from the RGB color space to the HSV color space.

[0073] When the image needs to be converted from HSV space back to RGB space, use formulas (4-1) and (4-2) for the conversion.

[0074]

[0075] For each color vector (R, G, B) we have:

[0076]

[0077] Where: v is a specific component of V.

[0078] After converting the scanned image from RGB space to HSV space, image threshold segmentation is performed in HSV space to extract the rough outline of the phase boundary in the scanned image. The image threshold segmentation is specifically performed by adjusting the thresholds of the three channels to debug the color range that can most clearly display the pencil outline, retaining the H, S, V (h, s, v) color values ​​of the pencil color lines of the sedimentary phase belt and filtering out the noise; the specific threshold selection range is:

[0079] h∈[0.55,0.75]∪[1],s∈[0,0.03],v∈[0.6,0.95];

[0080] In this way, the rough outline of the threshold segmentation map (phase boundary rough outline map) is extracted, and the result is as follows Figure 3 shown.

[0081] Step S03: using an image edge dilation algorithm to connect the discontinuous contour lines in the phase boundary rough contour image, and then performing skeleton processing on the connected boundary rough contour image to obtain a phase boundary skeleton refinement image.

[0082] In the present invention, before the image edge dilation algorithm is used to connect the discontinuous contour lines in the phase boundary rough contour map, the method further includes: binarizing the phase boundary contour map to obtain a binarized phase boundary contour map.

[0083] In the embodiments of the present invention, in most images, the color (grayscale) of the object is generally darker than that of the background. After binarization, the object becomes black and the background becomes white. Therefore, we are usually accustomed to representing the object with black (grayscale value 0) and the background with white (grayscale value 255). However, in Matlab's two-dimensional image morphological processing, by default, white (pixels with a grayscale value of 1 in a two-dimensional image, or pixels with a grayscale value of 255 in a grayscale image) are foreground (objects) and black is the background. Therefore, this embodiment complies with Matlab's own foreground identification habit.

[0084] No matter what grayscale value is used for foreground and background, it is just a processing habit and has nothing to do with the morphological algorithm itself. You only need to invert the image before morphological processing to switch freely between the two recognition habits.

[0085] In the present invention, the method of connecting the discontinuous contour lines in the phase boundary rough contour image using the image edge dilation algorithm includes: using the imdilate function to dilate the image in the phase boundary rough contour image, and the expanded image is the phase boundary rough contour image after the connection processing; wherein the method of dilating the image by the imdilate function is: using a 3*3 structural element, scanning each pixel in the phase boundary rough contour image, and performing an AND operation with the structural element and the binary image covered by it. If the results are all 0, then the pixel is 0, otherwise it is 1.

[0086] In an embodiment of the present invention, the imdilate function is used to perform image dilation, and its common calling form is: I2=imdilate(I, SE); I is the original image, which can be a two-bit or grayscale image (corresponding to grayscale dilation), and SE is a custom or preset structuring element object returned by the strel function.

[0087] Dilation has the opposite effect of erosion, expanding the boundaries of objects. The specific results depend on the image itself and the shape of the structuring elements. Dilation is often used to bridge previously separated objects in an image. Binarization can easily split a connected object into two parts, complicating subsequent image analysis (such as counting objects based on connected regions). Image edge dilation optimization algorithms can be used to bridge these gaps.

[0088] In order to solve the problem of some discontinuous points in the threshold segmentation image (phase boundary rough outline image), the image edge dilation optimization algorithm is used to deal with it. Dilation is the process of merging all background points that are in contact with the object into the object, so that the boundary expands outward, which can be used to fill the holes in the object. The processing process of the imdilate function is: use the preset 3*3 structure element to scan each pixel of the image (binarized phase boundary rough outline image), and use the structure element SE to perform an "and" operation with the binary image it covers. If both are 0, the pixel of the result image is 0, otherwise it is 1. The final processed result makes the binary image expand one circle. Phase boundary rough outline after edge dilation optimization processing Figure 2 Value image such as Figure 4 shown.

[0089] In the present invention, the method of skeletonizing the coarse boundary contour map after the connection processing includes: using an imerode function to skeletonize the coarse boundary contour map after the connection processing to obtain a phase boundary skeleton refinement map.

[0090] In an embodiment of the present invention, for the problem that thick border is difficult to vectorize, the mode of morphological operation is adopted, obtains " skeleton " of border, i.e. borderline.Two commonly used functions relevant to corrosion among Matlab are imerode and strel.The imerode function is used to complete image corrosion, and its commonly used calling form is: I2=imrode(I, SE), I is the original image, can be two-bit or grayscale image (corresponding to grayscale corrosion).SE is the self-defined or preset structuring element object returned by the strel function.The strel function can generate structuring element SE for various common morphological operations, and when generating the structuring element elbow for binary morphology use, its calling form is: SE=strl(shape, parameter), and shape has specified the shape of structuring element.

[0091] The function of corrosion is to dissolve the boundary of an object, and the specific corrosion result is related to the image itself and the shape of the structural element. If the object is larger than the structural element as a whole, the structure of the corrosion is to make the object "thinner", and how big this circle is is determined by the structural element. If the object itself is smaller than the structural element, the object will completely disappear in the image after corrosion; if only part of the object is smaller than the structural element, as the corroded structural element gradually increases, the objects smaller than the structural element will disappear one after another. Since the corrosion operation has the above characteristics, it can be used for filtering. Selecting a structural element of appropriate size and shape can filter out all noise points that cannot completely contain the structural element. However, there is a disadvantage in using corrosion to filter out noise, that is, while removing noise points, it will also affect the shape of the foreground objects in the image, but when we only care about the position or number of objects, the effect is not significant. By calling the imerode function, the rough outline of the phase boundary after connection processing, that is, after expansion, is removed. Figure 2 The boundary skeleton of the image is refined, and the final image after boundary skeleton refinement is as follows Figure 5 As shown, Figure 5 Figure a is the image before skeleton refinement, and figure b is the image after skeleton refinement.

[0092] According to the skeletonized boundary lines, the skeletonized image is vectorized, that is, the boundary lines are sorted in a clockwise order to obtain vectorized boundary coordinates.

[0093] Step S04: performing a connected domain analysis on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, performing error repair on the phase boundary skeleton refinement map to obtain a final sedimentary phase division result map.

[0094] In the present invention, the method for judging whether the phase boundary skeleton refinement map meets the requirements for the accuracy of sedimentary phase division includes: determining through connected domain analysis whether there are wells in each connected domain in the phase boundary skeleton refinement map and whether they are all wells of the same type; if so, the phase boundary skeleton refinement map meets the requirements for the accuracy of sedimentary phase division; if not, the phase boundary skeleton refinement map does not meet the requirements for the accuracy of sedimentary phase division.

[0095] In the embodiment of the present invention, the phase boundary skeleton refinement map is a binary image, and the brightness value of the binary image has only two states: black (0) and white (255). Binary images play an important role in image analysis and recognition because they have a simple pattern and have a strong expressive power for the spatial relationship between pixels. In practical applications, many image analyses are ultimately converted into binary image analyses. The most important method for binary image analysis is connected region labeling, which is the basis of all binary image analysis. It labels the white pixels (targets) in the binary image so that each individual connected region forms a marked block. Further, we can obtain the geometric parameters of these blocks, such as the outline, circumscribed rectangle, centroid, and invariant moment.

[0096] In the phase boundary skeleton refinement map, the smallest unit is the pixel. Each pixel is surrounded by eight adjacent pixels. There are two common adjacency relationships: 4-adjacency and 8-adjacency. 4-adjacency has four points, namely, up, down, left, and right. 8-adjacency has eight points, including those located diagonally. If pixels A and B are adjacent, we say A and B are connected. If B and C are connected, then A and C are connected. Visually, connected points form a region, while disconnected points form different regions. A set of all connected points is called a connected region.

[0097] A connected component generally refers to an image region (or blob) consisting of adjacent foreground pixels with the same pixel value. Connected component analysis (connected component labeling) involves identifying and labeling connected regions within an image. Connected component analysis typically involves processing a binary image. The accuracy of sedimentary facies delineation is analyzed by analyzing the relationships between and within these connected regions.

[0098] Refinement of the skeleton by analyzing phase boundaries Figure 2 Whether there are wells in the connected domains formed by the sedimentary facies belts of the value image, and whether there are only wells of a single category in each connected domain, the quality of the places where the sedimentary facies division is wrong is monitored, and these wrong directions are marked. That is, if there are no wells in a connected domain, or there are two or more categories of wells in the connected domain, it means that the drawing is wrong and it needs to be marked. If there are two or more categories of wells in a connected domain, when marking, the wells of other categories except the wells of the most categories in the connected domain will be marked; the final connected domain analysis results are as follows Figure 6 As shown, in Figure 6In the figure, all the wells marked with circles are wells with different categories from other wells in their connected domain. Errors of these wells are corrected, and finally a clear and accurate sedimentary facies division result map is obtained.

[0099] It can be understood that the above-mentioned various method embodiments mentioned in the present invention can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, the present invention will not elaborate on them.

[0100] The execution subject of the rapid mapping method based on hand-drawn phase boundary recognition may be a rapid mapping device based on hand-drawn phase boundary recognition. For example, the rapid mapping method based on hand-drawn phase boundary recognition may be executed by a terminal device, a server, or other processing device, wherein the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc. In some possible implementations, the rapid mapping method based on hand-drawn phase boundary recognition may be implemented by a processor calling computer-readable instructions stored in a memory.

[0101] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0102] In the present invention, a rapid mapping device based on hand-drawn phase boundary recognition includes: an acquisition unit for acquiring a scanned image of a sedimentary phase belt map to be processed; a coarse contour extraction unit for converting the scanned image from RGB space to HSV space, performing image threshold segmentation in the HSV space, and extracting a coarse contour map of the phase boundary in the scanned image; an image expansion and refinement unit for connecting the discontinuous contour lines in the coarse contour map of the phase boundary using an image edge expansion algorithm, and then performing skeletonization on the connected boundary coarse contour map to obtain a skeleton refinement map of the phase boundary; a connected domain analysis unit for performing connected domain analysis on the skeleton refinement map of the phase boundary to determine whether the skeleton refinement map of the phase boundary meets the accuracy requirements of the sedimentary phase division. If not, the skeleton refinement map of the phase boundary meets the accuracy requirements of the sedimentary phase division, thereby obtaining a final sedimentary phase division result map.

[0103] In some embodiments, the functions or modules and units included in the device provided by the embodiment of the present invention can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0104] The present invention scans a manually drawn sedimentary facies map to form a scanned image, and uses techniques such as coordinate transformation and perspective transformation to correct the scanned image, thereby correcting errors caused by manual operation and improving the accuracy of the final result. Based on the HSV color recognition technology and related morphological processing in image processing, the color gamut of the pencil line is determined, image contour extraction is completed, and a better segmentation result map is obtained, thereby accurately identifying different microfacies boundaries in the scanned image, greatly saving subsequent operation time. In the threshold segmentation map (coarse contour), an image edge expansion algorithm is used to solve the problem of discontinuous edge contours. Then, by using edge skeletonization and boundary vectorization image processing techniques, a continuous and vectorized pencil line is obtained. Based on the closed characteristics of the boundaries of different sedimentary microfacies, the accuracy of sedimentary facies division is improved through related algorithms such as connected domain analysis. According to different well point phase distinction values ​​(categories), different microfacies boundaries are automatically tracked and characterized, reducing most subjective and objective errors and improving recognition accuracy. The present invention can be integrated into oil enterprise software, such as GPTMap, to achieve automatic recognition of microfacies boundaries.

[0105] The results of this invention have been applied to the mapping of a certain sedimentary facies belt. Compared with the traditional mapping process, it has significantly improved work efficiency. The old mapping process required approximately 12 people to complete 96 maps within a month, while the new process only requires one person to complete 96 maps within a day. The microfacies boundary recognition rate is greater than 97%, and the microfacies boundary positioning error is less than 3m. Replacing traditional manual mapping with a machine can improve work efficiency by more than 450 times, thereby achieving the goal of optimizing job staffing and improving mapping efficiency. The technology of this invention can be widely promoted and applied in various oil production plants, playing a positive role in improving work efficiency, shortening mapping time, and reducing labor costs.

[0106] While various embodiments of the present invention have been described above, the above descriptions are intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A rapid mapping method based on hand-drawn phase boundary recognition, characterized in that: include: Obtaining a scanned image of a sedimentary facies map to be processed; Converting the scanned image from the RGB space to the HSV space, and extracting a rough contour of the phase boundary in the scanned image in the HSV space; Using an image edge dilation algorithm to connect the discontinuous contour lines in the phase boundary rough contour image, and then skeletonizing the connected boundary rough contour image to obtain a phase boundary skeleton refinement image; A connected domain analysis is performed on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map is error-corrected to obtain a final sedimentary phase division result map.

2. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 1 is characterized in that: Before converting the scanned image from the RGB space to the HSV space, coordinate conversion and tilt correction processing are performed on the scanned image to obtain a processed scanned image.

3. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 2 is characterized in that: The method for performing tilt correction on a scanned image comprises: The scanned image is tilt-corrected by using a perspective transformation boundary correction algorithm to obtain a tilt-corrected scanned image.

4. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 3 is characterized in that: The perspective transformation boundary correction algorithm is: Where: (x, y) is the coordinate of the scanned image, (u, v) is the coordinate of the corrected scanned image on the front view, and a, b, c, d, e, f, g, h are distortion parameters.

5. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 1 is characterized in that: The method for converting the scanned image from the RGB space to the HSV space comprises: Where: R, G, B are the R, G, B values ​​corresponding to the pixels on the scanned image.

6. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 1 is characterized in that: Before the image edge dilation algorithm is used to connect the discontinuous contour lines in the phase boundary rough contour image, the method further includes: The phase boundary contour map is binarized to obtain a binarized phase boundary contour map.

7. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 6 is characterized in that: The method of connecting the discontinuous contour lines in the phase boundary rough contour image using an image edge dilation algorithm includes: The imdilate function is used to dilate the phase boundary rough contour image, and the dilated image is the phase boundary rough contour image after the connection processing; The imdilate function dilates the image by using a 3*3 structure element to scan each pixel in the phase boundary rough contour image, performing an AND operation with the structure element and the binary image it covers. If the results are both 0, the pixel is 0, otherwise it is 1.

8. The rapid mapping method based on hand-drawn phase boundary recognition according to claim 1 is characterized in that: The method of skeletonizing the rough boundary contour image after the connection processing includes: The imerode function and the strel function are used to perform skeleton processing on the boundary rough outline map after the connection processing to obtain a phase boundary skeleton refinement map.

9. The rapid mapping method based on hand-drawn phase boundary recognition according to any one of claims 1 to 8, characterized in that: The method for determining whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division includes: Through connected domain analysis, it is determined whether there are wells in each connected domain in the phase boundary skeleton refinement map and whether they are all wells of the same type. If so, the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map does not meet the accuracy requirements of sedimentary phase division.

10. A rapid mapping device based on hand-drawn phase boundary recognition, characterized in that: include: An acquisition unit, used for acquiring a scanned image of the sedimentary facies map to be processed; a coarse contour extraction unit, configured to convert the scanned image from the RGB space to the HSV space, and extract a coarse contour map of the phase boundary in the scanned image in the HSV space; an image dilation and refinement unit, configured to connect the discontinuous contour lines in the phase boundary rough contour image using an image edge dilation algorithm, and then perform skeletonization on the connected boundary rough contour image to obtain a phase boundary skeleton refinement image; The connected domain analysis unit is used to perform connected domain analysis on the phase boundary skeleton refinement map to determine whether the phase boundary skeleton refinement map meets the accuracy requirements of sedimentary phase division. If not, the phase boundary skeleton refinement map is error-corrected to obtain the final sedimentary phase division result map.

Images