Automated method of detecting blurred and saturated pixels in image

Abstract

Systems and methods are provided for analyzing sample images, such as for cuttings obtained during drilling of a geological formation. The system utilizes automated image processing to detect and correct blurred and saturated pixels in a sample image, and controls related devices based on the detection. The system allows high quality logging curves to be obtained for real-time and / or near-real-time geological formation assessment and geosteering.

Description

Cross Reference To Related Applications

[0001] This application claims the benefit of U.S. Provisional Application No. 61 / 081,621, filed August 17, 2023, entitled “METHOD FOR DETERMINING HYDROCARBON IN PRESENCE OF ELECTRON AND CHEMICAL IONIZATION,” the disclosure of which is hereby incorporated by reference herein. BACKGROUND

[0002] The present disclosure relates generally to a method and system for analyzing sample images such as for cuttings obtained during drilling of a geological formation. In particular, the present disclosure relates to utilizing automated image processing to detect blur and saturated pixels in the sample images.

[0003] During the drilling process of an oil well or another well of another outflow, specifically gas, steam, or water, cuttings are brought to the surface after being cut from the geological formation by a drill bit and brought to the surface by mud circulating in the wellbore. Analysis can be performed on the cuttings to enable creation of a detailed record (e.g., a main log) of the geological formation of the wellbore. The detailed record can vary with the depth of the wellbore and can enable determination of various wellbore information, such as the lithology of the geological formation.

[0004] Generally, a geologist would analyze the sample images to determine the properties of the cuttings in order to determine the lithology of the geological formation from which the cuttings were extracted. However, such work takes a significant amount of time and is typically performed in a laboratory that is remote from the drilling rig, which makes it less efficient to control the drilling process based on the results of the analysis. Moreover, such work is highly subjective as it is based on human observation. Thus, it is desirable to have an improved method of analyzing sample images.

[0005] This section is intended to introduce the reader to various aspects of art that can be related to various aspects of the present disclosure and are not necessarily all drawn from a single disclosure. This discussion is intended to provide context for the various aspects of the present disclosure and SUMMARY

[0006] A summary of certain implementations disclosed herein is set forth below. It should be understood that these aspects are presented merely to provide the reader with a brief summary of these certain implementations and that they are not intended to limit the scope of the disclosure. Indeed, the disclosure can encompass a variety of aspects that can not be set forth below.

[0007] Certain embodiments of the present disclosure include a system that can include a processor and a memory storing instructions and the instructions can cause the processor to perform operations including receiving image data of an image of a rock sample from an imaging system and the image data includes a plurality of image pixels associated with a plurality of gray levels, detecting a proportion of image pixels in the image data having a gray level within a particular range, determining whether the image qualifies for an image analysis process by comparing the proportion to a threshold value, in response to determining that the image qualifies for the image analysis process, identifying a lithology of the rock sample, generating a record based on the lithology of the rock sample, and controlling a device associated with obtaining the rock sample based on the record.

[0008] Certain embodiments of the present disclosure include a computer-implemented method that can include receiving image data of an image of a rock sample from an imaging system and the image data includes a plurality of image pixels associated with a plurality of gray levels, detecting a proportion of image pixels in the image data having a gray level within a particular range, determining whether the image qualifies for an image analysis process by comparing the proportion to a threshold value, in response to determining that the image qualifies for the image analysis process, identifying a lithology of the rock sample, generating a record based on the lithology of the rock sample, and controlling a device associated with obtaining the rock sample based on the record.

[0009] Certain embodiments of the present disclosure include a system that can include a drilling system for obtaining a rock sample from a wellbore and a geologic analysis system for identifying a lithology of the rock sample. The geologic analysis system can include a preparation device configured to prepare the rock sample, an imaging system configured to take an image of the rock sample, and an analysis system configured to analyze an image quality of the image and identify the lithology of the rock sample.

[0010] Various improvements to the above-mentioned features can exist with respect to the various aspects of the present disclosure. Additional features can likewise be incorporated into these various aspects. These improvements and additional features can exist individually or in any combination. For example, various features discussed below with respect to one or more of the illustrated embodiments can be incorporated into any of the above-mentioned aspects of the present disclosure, either individually or in any combination. The brief summary presented above is intended only to familiarize the reader with certain aspects and context of implementations of the present disclosure, without limitation to the claimed subject matter. BRIEF DESCRIPTION OF DRAWINGS

[0011] Various aspects of the present disclosure can be better understood after a reading of the following detailed description with reference to the drawings, in which: Figure 1is a schematic diagram of a drilling rig including a geological analysis system according to aspects of the present disclosure; Figure 2 is a graphical representation of a two-dimensional image according to aspects of the present disclosure; Figure 1 is a flowchart of a method of generating a detailed record for a system according to aspects of the present disclosure; Figure 3 is a graphical representation of a portion of a detailed record generated by a method according to aspects of the present disclosure; Figure 2 Figure 4 is a flowchart of a method of analyzing image quality according to aspects of the present disclosure; Figure 5 is a comparison of image saturation for two images according to aspects of the present disclosure; and Figure 6 is a comparison of blurriness for two images according to aspects of the present disclosure. DETAILED DESCRIPTION

[0012] One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which can vary from one implementation to another. Moreover, it should be appreciated that such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure.

[0013] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that there are one or more of the elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there can be additional elements other than the listed elements. Additionally, it should be understood that references to "one embodiment" or "an embodiment" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

[0014] ​As used herein, the terms “connect,” “connection,” “connected,” “in connection with,” and “connecting” are used in the sense of “directly connected to” or “connected to via one or more elements”; and the term “set” is used in the sense of “one element” or “more than one element.” Furthermore, the terms “couple,” “coupling,” “coupled,” “coupled together,” and “coupled with” are used in the sense of “directly coupled together” or “coupled together via one or more elements.”

[0015] Additionally, as used herein, the terms “real-time,” “in real-time,” or “substantially real-time” are used interchangeably and are intended to describe operations (e.g., computational operations) performed in a manner that does not have any human perceptible operational interruption. For example, data related to the systems described herein can be collected, transmitted, and / or used for control computations “substantially in real-time” such that data reading, data transfer, and / or data processing steps can occur every second, every 0.1 seconds, every 0.01 seconds, or even more frequently during system operation (e.g., while the system is operating). Additionally, as used herein, the terms “automatic” and “automated” are intended to describe operations performed by the analytical system alone, e.g., without human intervention.

[0016] The present disclosure relates to a system and method for analyzing images of a cuttings sample acquired by a drilling system from a geological formation. The cuttings sample is cut down from the geological formation during drilling and can be used to evaluate the geological formation and characterize one or more properties thereof, such as its mineralogy, lithology, porosity, density, etc., based on a location (e.g., X, Y, Z coordinates and / or depth) in the geological formation. For example, the images of the cuttings sample can be used to identify a lithology of a rock in the cuttings sample and predict characteristics and parameters of the geological formation. The lithology of the rock sample can be used to generate a detailed record (e.g., a main log) of the geological formation. The detailed record can include information about geological properties (e.g., lithology, beds, depositional environment) and petrophysical characteristics (e.g., water saturation, porosity, permeability, shale volume) of the geological formation, which can be used to control the drilling system or a drilling plan of the drilling system. The quality of the images can vary (e.g., brightness, blurriness, etc.), and some of the images can not have an image quality suitable for image analysis, which can result in reduced efficiency of the image analysis process and / or reduced accuracy of the results. Therefore, it is desirable to detect the image quality before sending the images to an analysis system for detailed analysis.

[0017] An image can be divided into small geometric subunits called image pixels, which include image data corresponding to the image content. Depending on the content of the image, the image data can include different color channels, such as red channel image data indicating a target luminance of red, blue channel image data indicating a target luminance of blue, green channel image data indicating a target luminance of green, or grayscale image data indicating a target luminance of gray. The image data corresponding to the image content indicates a target visual property (e.g., luminance and / or color) at one or more specific points (e.g., image pixels) in the image content, for example, by indicating a color channel intensity level (e.g., a grayscale level).

[0018] A grayscale level is a discrete level (e.g., 0, 1,... 255) corresponding to a quantized light luminance (e.g., of a color channel, of gray) at an image pixel. For example, when the value of the grayscale level is 255, the luminance level can be the maximum, and when the value of the grayscale level is 0, the luminance level can be the minimum. The relationship between the grayscale level of an image pixel and the corresponding luminance at the image pixel is associated with the imaging system used to capture the image. For example, the grayscale level and the luminance of an image pixel can generally have a non-linear relationship, especially at the minimum or maximum values of the grayscale level in their neighborhood. For example, when the grayscale level is in a range close to the maximum value (e.g., a first or near-maximum range), changes in the grayscale level can not correspond to changes in the luminance of the image pixel, which corresponds to image saturation. When an image pixel is saturated, the luminance difference of the image pixel can be difficult to detect. On the other hand, when the grayscale level is in a range close to the minimum value (e.g., a second or near-minimum range), changes in the grayscale level can also not correspond to changes in the luminance of the image pixel. To improve the efficiency of image processing / analysis and obtain more accurate results, the quality of the image can be defined such that the grayscale levels used in the image generally avoid these two ranges. In some embodiments, images with grayscale levels in the two ranges (e.g., the first and second ranges) can be processed such that the quality of the image can be improved to meet the requirements of the analysis system.

[0019] Another factor of image quality is image blur, which can be caused by a variety of reasons, such as improper focusing on the photographed object, motion of the camera during exposure, and / or motion of the photographed object, etc. A blur index can be used to describe the degree of blur. For example, when the value of the blur index is less than a predefined value (which can be associated with the image processing system), it can be difficult to detect visual characteristics (e.g., brightness and / or color) in the image. To improve the efficiency of image processing / analysis and obtain more accurate results, the quality of the image can be defined such that the blur index used in the image is generally greater than the predefined value. In some embodiments, images with local blur indices less than the predefined value can be processed such that the quality of the image can be improved to meet the requirements of the analysis system.

[0020] In view of the above, Figure 1 An example oil and gas operation site 10 is shown with a geological analysis system 11 for analysis and control and a drilling system 12. The drilling system 12 includes a rotary drilling tool 14 that drills a cavity 16; a surface rig 18 in which a drill string is placed in the cavity 16. A wellbore 20 (e.g., a well bore) that defines the cavity 16 is formed in a subterranean formation 21 by the rotary drilling tool 14. At a surface 22, a wellhead 23 with a discharge pipe 25 closes the wellbore 20. The drilling tool 14 includes a drill bit assembly 27, a drill string 29, and a liquid injection head 31. The drill bit assembly 27 includes a drill bit 33 for drilling through rock of the subterranean formation 21. The drill bit assembly 27 is mounted on a lower portion of the drill string 29 and positioned in a bottom of the wellbore 20. The drill string 29 includes a set of hollow drill pipes. The drill pipes define an interior space 35 that enables drilling fluid to be brought from the surface 22 to the drill bit assembly 27. The liquid injection head 31 is mounted (e.g., threaded, bolted, etc.) to an upper portion of the drill string 29. The drilling fluid includes a drilling mud, such as a water-based or oil-based drilling mud.

[0021] The surface rig 18 includes a support 41 for supporting and driving rotation of the drilling tool 14, an injector 43 for injecting drilling fluid, and a shale shaker 45. The injector 43 is hydraulically connected to the injection head 31 to introduce and circulate drilling fluid in the interior space 35 of the drill string 29. The shale shaker 45 collects drilling fluid that flows from the discharge pipe 25. The drilling fluid contains drilling residue, referred to as cuttings. The shale shaker 45 includes a screen 46 that allows separation of solid drilling cuttings, such as rock samples 47, from the drilling mud. The shale shaker 45 also includes an outlet 48 for discharging the rock samples 47. The rock samples 47 obtained at the outlet 48 are cut from the geological formation during drilling and can be used to evaluate the geological formation and characterize one or more properties thereof, such as its mineralogy, lithology, porosity, density, etc.

[0022] In Figure 1In the illustrated embodiment, the rock samples 47 can be automatically or manually sampled and transferred to a conveyor 50, which can transfer the rock samples 47 to a preparation device 52. The preparation device 52 can prepare the rock samples before manually or automatically (e.g., via a transport device) sending the rock samples 47 to an imaging system 54. The geological analysis system 11 can include all equipment associated with acquiring, preparing, imaging, and analyzing the rock samples 47. For example, the geological analysis system 11 can include the shale shaker 45, the conveyor 50, the preparation device 52, the imaging system 54, the analysis system 60, and the image processing system 78. Preparation can include washing, rinsing, drying, or sieving the rock samples, among others. The imaging system 54 can include an imaging device 56 to take images of the rock samples 47. The imaging device 56 can be any type of optical or electronic microscope, camera, or the like. The images obtained by the imaging device 56 can be digital images, which, as discussed in further detail below, can be automatically analyzed. The following examples are given in the case of a camera that detects the visible spectrum, but the same methods can also be applied to images taken with IR or UV cameras that detect light in the ultraviolet (UV) or infrared (IR) domains. The imaging system 54 can also include a control device 58 (e.g., a processor-based controller) to control the imaging device 56 and operating conditions (e.g., illumination, temperature, humidity) associated with the image taking process inside the imaging system 54. For example, the control device 58 can adjust parameters of the imaging device 56 (e.g., focus, exposure, shutter speed, brightness and color, contrast, filters, resolution, zoom). The preparation device 52 and / or the imaging system 54 can be located at the oil and gas operation site 10 or at one or more remote locations.

[0023] Analysis system 60 can be used to receive and analyze image data (e.g., digital images) from imaging system 54, directly or via network 61. Analysis system 60 may be located at oil and gas operation site 10 or at one or more remote locations. Analysis system 60 may include communication components 62, processor 64, memory 66, data storage device 68, input / output (I / O) ports 70, display 72, prediction engine 74, etc. Network 61 may include transceivers, receivers, and / or transmitters to facilitate data communication with analysis system 60. For example, image data from imaging system 54 can be transmitted to analysis system 60 via network 61. Furthermore, external data (e.g., data on geological formations) can be collected from remote systems and transmitted to analysis system 60 via network 61. However, in some embodiments, data may be transmitted directly from the device (e.g., imaging system 54) to analysis system 60. In fact, according to this embodiment, analysis system 60 may communicate directly with the device and / or communicate with the device via network 61. In some implementations, data (e.g., image data) can be automatically transmitted from imaging system 54 to analysis system 60 for real-time analysis, thereby enabling real-time responses to information obtained from data analysis (e.g., adjusting imaging system 54, retaking unacceptable images, adjusting drilling system 12, etc.).

[0024] Communication component 62 can be a wireless or wired communication component (e.g., a circuit) that facilitates communication between analysis system 60, various types of devices, network 61, etc. Additionally, communication component 62 facilitates data transmission to analysis system 60, enabling analysis system 60 to... Figure 1 Other components depicted herein receive data. Communication component 62 may use various communication protocols, such as Open Database Connectivity (ODBC), TCP / IP, Distributed Relational Database Architecture (DRDA), Database Change Protocol (DCP), HTTP, other suitable current or future protocols, or combinations thereof.

[0025] Processor 64 may include a single-threaded processor, a multi-threaded processor, or both. Processor 64 may process instructions stored in memory 66. Processor 64 may also include hardware-based processors, each including one or more cores. Processor 64 may include a general-purpose processor, a special-purpose processor, or both. Processor 64 may be communicatively coupled to other internal components, such as communication component 62, data storage device 68, I / O port 70, and display 72.

[0026] Memory 66 and data storage 68 can be any suitable article that is usable as a medium to store processor-executable code, data, etc. These articles can represent computer-readable media (e.g., any suitable form of memory or storage) that can store processor-executable code used by processor 64 to perform the presently disclosed technology. As used herein, an application can include any suitable computer software or program that can be installed onto analysis system 60 and executed by processor 64. Memory 66 and data storage 68 can represent non-transitory computer-readable media (e.g., any suitable form of memory or storage) that can store processor-executable code used by processor 64 to perform the various technologies described herein. It is noted that non-transitory merely indicates that the media is tangible, as opposed to a signal.

[0027] I / O ports 70 can be interfaces that can be coupled to other peripheral components, such as input devices (e.g., keyboard, mouse), sensors, input / output (I / O) modules, etc. Display 72 can operate as a human-machine interface (HMI) to depict visualizations associated with software or executable code that processor 64 is processing. Display 72 can display maps of geologic formation data (e.g., images and information derived from images) corresponding to locations on a map, alerts / alarm when image data is not acceptable, suggestions associated with alerts / alarm, etc. In one embodiment, display 72 can be a touch display capable of receiving input from an operator of analysis system 60. For example, display 72 can be any suitable type of display, such as a liquid crystal display (LCD), a plasma display, or an organic light-emitting diode (OLED) display. Additionally, in one embodiment, display 72 can be provided in conjunction with a touch-sensitive mechanism (e.g., a touchscreen) that can operate as part of a control interface of analysis system 60.

[0028] The prediction engine 74 can use various machine learning algorithms to analyze images obtained for the rock samples 47 to identify the lithology of the rock samples. The prediction engine 74 can utilize one or more prediction models to analyze various data received by the analysis system 60. Various types of prediction models can be used to analyze data from various sources and generate prediction outputs. For example, the prediction engine 74 can be trained using supervised machine learning techniques, i.e., training the prediction model with training data that includes input data and desired prediction outputs (e.g., labeled data sets). The prediction engine 74 can also be trained using unsupervised machine learning techniques, i.e., training the prediction model with training data that includes input data but without desired prediction outputs (e.g., unlabeled data sets). The prediction engine 74 can include various types of artificial neural networks (ANN), such as convolutional neural networks (CNN), recurrent neural networks (RNN), etc. The analysis system 60 can also be in communication with a database 76, which can store information associated with the oil and gas worksite 10, the drilling system 12, related external resources (e.g., geologic formation history), etc.

[0029] It is noted that the components described above with respect to the analysis system 60 are example components, and the analysis system 60 can include more or fewer components than shown in the figures. Additionally, although these components are described as part of the analysis system 60, these components can also be part of any suitable computing device described herein, such as the sieve 46, the conveyor 50, the preparation device 52, the imaging device 56, the control device 58, an image processing system 78 coupled to the imaging system 54 and the analysis system 60, etc., to perform various operations described herein.

[0030] The image processing system 78 can be used to receive and analyze image data from the imaging system 54 or the analysis system 60, either directly or via the network 61. In some embodiments, the image processing system 78 can be included in the analysis system 60 or the imaging system 54, or both. The image processing system 78 can apply various image processing algorithms (e.g., fast Fourier transform (FFT), singular value decomposition (SVD) transform, discrete cosine transform (DCT)) or software to modify visual characteristics (e.g., brightness, color, contrast, sharpness) of an image, or to recognize certain characteristics (e.g., shape, texture, color, size) in an image, or to modify an image to obtain a target visual effect, etc. The characteristics in the image can be used to identify the lithology of the rock samples 47. For example, different rock classes of the rock samples 47 can exhibit different characteristics (e.g., shape, texture, color, size) on the images, and the image processing system 78 can analyze the images to identify these characteristics to determine the rock class of the rock samples 47.

[0031] Figure 2 is for use in providing Figure 1A flowchart of a computer-implemented method 100 of system generating detailed records (e.g., a master log) is shown. For example, the method 100 can be implemented using one or more processor-based systems (e.g., a processor-based controller) configured to control the drilling system 12, the imaging system 54, the analysis system 60, the image processing system 78, and the associated equipment of the oil and gas worksite 10. At block 102, a sample of cuttings at a certain depth of the wellbore 20 can be received from the drilling system 12. At block 104, the shale shaker 45 can separate the solid sample of cuttings from the drilling mud via the screen 46 to obtain the rock sample 47, as described above. The rock sample 47 can be delivered (e.g., via the conveyor 50) to the preparation device 52, which can prepare the rock sample 47 before sending it to the imaging system 54. The preparation can include washing, rinsing, drying, or sieving the rock sample, etc. At block 106, the imaging system 54 can take an optical image of the rock sample 47 by using the control device 58 to control the imaging device 56. At block 108, the analysis system 60 can receive the image of the rock sample from the imaging system 54. At block 110, the analysis system 60 can analyze the image of the rock sample by calculating a plurality of parameters (e.g., image saturation, image blur) associated with the image to check the image quality, as described in detail in Figure 4

[0032] If the image quality of the image is not qualified (e.g., the parameters associated with the image do not satisfy the threshold values), at block 114, the analysis system 60 can output a notification (e.g., an audio and / or visual alarm) and send instructions to the imaging system 54 to calibrate the imaging system based on the deviation of the parameters of the image from their corresponding threshold values. The analysis system 60 can send instructions to the control device 58 to adjust the operating parameters of the imaging device 56, such as focus, exposure, shutter speed, brightness and color, contrast, filter, resolution, zoom, etc. For example, when the parameter indicates that the image is out of focus, the analysis system 60 can send instructions to the control device 58 to adjust the focal length of the imaging device 56, and the adjustment can vary based on the deviation of the parameter from the corresponding threshold value. When the parameter indicates that the image is saturated or too dark, the analysis system 60 can send instructions to the control device 58 to adjust the exposure, shutter, brightness and color, contrast, filter, etc. of the imaging device 56. In addition, the control device 58 can also adjust the operating conditions of the imaging device 56, such as the ambient light, temperature, humidity of the imaging device 56. After the imaging system 54 is calibrated, the imaging system 54 can take another image of the rock sample. Thus, blocks 106-112 can be repeated until the image quality is qualified.​

[0033] If the image quality of the image is qualified (e.g., the parameters associated with the image meet the threshold), at block 116, the analysis system 60 can use the image to identify the lithology of the rock sample. The analysis system 60 can utilize the image processing system 78 to process the image to identify the lithology of the rock sample. The analysis system 60 can also utilize the prediction engine 74 to identify the lithology of the rock sample. For example, the prediction engine 74 can use a convolutional neural network (CNN) to detect characteristics of the image of the rock sample to identify the lithology of the rock sample. The characteristics in the image can be associated with the lithology of the rock sample 47. For example, different rock classes of rock samples 47 can exhibit different characteristics (e.g., shape, texture, color, size) on the image, and the prediction engine 74 can analyze the image to identify these characteristics to determine the rock class of the rock sample 47. The prediction engine 74 can also compare the image to baseline images and / or images of known rock formations to better identify the rock class. The images can be compared by identifying colors, patterns, textures, etc. to more accurately identify the lithology. The prediction engine 74 can also use historical wellbore formation data (e.g., data from other locations in the geologic region) to identify the lithology of the rock sample and predict the geologic formation of the wellbore 20.

[0034] At block 118, the analysis system 60 can generate a detailed record (e.g., a main log) based on the lithology of the rock of the cuttings samples from various locations indicated by corresponding coordinates (e.g., XYZ coordinates) in the wellbore 20. An example of a detailed record (e.g., from various depths along the Z direction) is shown in FIG. 150. Figure 3 The detailed record includes information of the geologic formation, which can be used at block 120 to control the drilling system 12 and / or the drilling plan of the drilling system 12. To obtain accurate results, a large number of images of the rock sample can be analyzed, and it is desirable to control the image quality of the images fed to the image processing system 78 or the prediction engine 74 to save cost and save time.

[0035] Figure 3 FIG. 150 is a graph 150 that is part of a detailed record (such as a main log) generated by using the method 100. As shown in FIG. 150, the main log can include one or more curves to provide a record of one or more physical measurements (e.g., lithology) according to the depth in the wellbore 20 of Figure 1 The main log can include drilling information and drilling parameters that are related to the geologic and rock property interpretation of the wellbore data.

[0036] As Figure 3As shown, Figure 150 represents the lithology as a function of depth along direction 152 (e.g., the Z-axis), and the corresponding lithology quantification along direction 154. The gray scale regions of the figure represent the class of rock that has been detected on the image of the rock sample at the corresponding depth. Legend 155 indicates which gray scale is associated with which rock class. For example, Figure 150 illustrates 4 rock classes, namely sandstone (e.g., located in region 156), siltstone (e.g., located in region 158), shale (e.g., located in region 160), and the "mismatch" class (e.g., located in region 162) indicating an unknown class.

[0037] Figure 150 can also include a confidence level plot 170 corresponding to the predicted confidence of each rock class as a function of depth. Generally, in a wellbore, the lithology is continuously changing. Thus, based on the confidence level at each depth, depths with a lower confidence level can be corrected by comparing to adjacent depths associated with a higher confidence level. For example, at depth 172, the confidence level can have a relatively low value with a discrete change relative to its adjacent confidence levels (above and below). As shown in Figure 150, the rock class at depth 172 is predicted to be "mismatch" at a relatively high proportion. Thus, the predicted rock class at depth 172 can be corrected so that it matches the adjacent results with a higher confidence level, such as at depth 174 with a confidence level of 84%. The above correction can be applied to depths with a confidence level below a predetermined threshold and / or depths with a relatively low confidence level in terms of the average confidence level for the entire well.

[0038] The confidence level is closely related to the image quality of the rock sample. In order to obtain a higher confidence level for a certain depth, a high image quality of the rock sample at that depth can be required. In addition, using high quality images can improve the accuracy of the rock class prediction, which can reduce the "mismatch" class. Overall, using high quality images to identify the lithology of the rock sample can greatly improve the accuracy of the lithology prediction. Moreover, using high quality images to identify the lithology of the rock sample can greatly reduce the processing time, as less time is used to process the images and correct the prediction of the rock class.

[0039] Figure 4 is for analyzing images of rock samples taken at various depths along a wellbore to determine the lithology of the rock at each depth. Figure 2A flowchart of a computer-implemented method 200 of calculating image quality used at blocks 110 and 112 of the method 100 in FIG. 1. For example, the method 200 can be implemented using one or more processor-based systems (e.g., processor-based controllers) configured to control the drilling system 12, the imaging system 54, the analysis system 60, the image processing system 78, or any combination thereof. At block 202, the analysis system 60 can receive an image (e.g., a digital image) of a rock sample from the imaging system 54. At block 204, the analysis system 60 can analyze the image of the rock sample to check image quality by calculating a plurality of parameters associated with the image. The analysis system 60 can utilize the image processing system 78 to analyze the image of the rock sample. As described above, one of the parameters associated with image quality is image saturation. When image pixels are saturated, the differences in light intensity of the image pixels can be difficult to detect. On the other hand, when the gray scale levels are in a range close to the minimum value, the changes in the gray scale levels can also not correspond to changes in light intensity of the image pixels. The analysis system 60 can analyze the image pixels in the image data of the image to detect image pixels having a gray scale level in a particular range close to a maximum value (e.g., 250-255) or a minimum value (e.g., 0-10). For image data including different color channels (e.g., red, green, blue, gray), the particular range can be determined for each color channel or one or more combinations of color channels. When the proportion of image pixels having a gray scale level in the particular range (e.g., 250-255, 0-10) is greater than a threshold value, the image can not include enough information to identify the lithology of the rock sample. Figure 5 An example image having a portion of saturated image pixels is shown in FIG. 3.

[0040] Figure 5 An image 300 without image saturation and an image 320 with a portion of saturated image pixels are shown. In the image 320, a plurality of regions 322 correspond to regions of image pixels having a gray scale level in a range close to a maximum value (e.g., 250-255). As described above, the image 320 can not include enough information to identify the lithology of the rock sample. Figure 5As shown, because the changes in the gray levels of the image pixels in the region 322 do not correspond to changes in the lightness of the image pixels, less information (e.g., color, brightness, texture) can be retrieved from the image pixels in the region 322. The proportion of saturated image pixels can be determined by calculating the ratio of the total number of image pixels in the plurality of regions 322 to the total number of image pixels of the image 320. For example, a higher ratio indicates that there are more saturated image pixels in the image 320, while a lower ratio indicates that there are fewer saturated image pixels in the image 320. When the proportion of saturated image pixels is greater than a threshold value (e.g., 40%, 50%), the image can not provide enough information to identify the lithology of the rock sample. The same method can also be used to determine the proportion of image pixels having a gray level in a range close to a minimum value (e.g., 0-10).

[0041] Referring back to Figure 4 At block 206, the analysis system 60 can compare the detected proportion of image pixels having a gray level in a particular range (e.g., 250-255, 0-10) to a corresponding threshold value. The threshold value for the particular range can be predetermined (e.g., based on the operational requirements of the analysis system 60 or the drilling objectives). If the detected proportion of image pixels having a gray level in the particular range (e.g., 250-255, 0-10) is not less than the threshold value, the analysis system 60 can output a notification (e.g., an audio and / or visual alert) at block 208 indicating that the detected gray levels of the image are not acceptable. The notification can be output to various systems (e.g., the preparation device 52, the imaging system 54, the image processing system 78, the prediction engine 74) to alert that the gray levels of the image are not acceptable. For example, based on the notification, the rock sample preparation in the preparation device 52 can be adjusted, the image processing system 78 can also adjust parameters associated with the image processing, and the prediction engine 74 can determine not to use the image to identify the lithology of the rock sample.

[0042] At block 210, the analysis system 60 can send instructions to the imaging system 54 to calibrate the imaging system 54. The calibration can be determined based on the detected proportion of the range of gray levels. For example, the analysis system 60 can send instructions to the control device 58 to calibrate / adjust the illumination of the imaging system 54. For example, the control device 58 can adjust the shutter of the imaging device 56 to increase / decrease the exposure of the image, or adjust the light source in the imaging system 54 to increase / decrease the ambient light of the imaging device 56, etc. If the detected proportion corresponds to a gray level within a range (e.g., 250-255) close to the maximum gray level, the control device 58 can decrease the shutter of the imaging device 56 to decrease the exposure of the image, and / or decrease the intensity of the light source in the imaging system 54 to decrease the ambient light of the imaging device 56, such that the detected proportion of the image can be reduced or eliminated. If the detected proportion has a gray level within a range (e.g., 0-10) close to the minimum gray level, the control device 58 can increase the shutter of the imaging device 56 to increase the exposure of the image, and / or increase the intensity of the light source in the imaging system 54 to increase the ambient light of the imaging device 56, such that the detected proportion of the image can be reduced or eliminated. After the imaging system 54 is calibrated / adjusted, the imaging system 54 can take another image of the rock sample. Thus, blocks 202-210 can be repeated.

[0043] If the detected proportion of image pixels having a gray level within a particular range (e.g., 250-255, 0-10) is less than a threshold (e.g., indicative of acceptable gray levels), the analysis system 60 can analyze the image data of the image at block 212 to detect image blur. As described above, another factor of image quality is image blur, which can be caused by a variety of reasons such as improper focusing on the subject being photographed, motion of the camera during exposure, and / or motion of the subject being photographed, etc. A blur index can be used to describe the degree of blur. Various algorithms (e.g., Fast Fourier Transform (FFT), Singular Value Decomposition (SVD) transform, Discrete Cosine Transform (DCT)) or software can be used to determine the degree of blur of an image.

[0044] For example, a Laplacian operator can be used to determine the local differences in gray levels. Thus, the Laplacian operator can be applied to the image, and the results (e.g., statistical values) of the image can be used to determine the blur index of the image. For example, as shown in Figure 6 the local differences in gray levels are lower, the sharpness of the image is lower, indicating that the image is blurrier, and the blur index is smaller; when the local differences in gray levels are larger, the sharpness of the image is larger, indicating that the image is less blurry, and the blur index is larger. Other methods can also be used to detect the degree of blur, such as applying a blur filter (e.g., a Gaussian filter) to the image.

[0045] Figure 6Image 350 is shown with an acceptable blur index (e.g., 565.491) that is greater than a threshold (e.g., 500) and image 370 is shown with an unacceptable blur index (e.g., 246.104) that is less than the threshold. It can be difficult to detect visual characteristics (e.g., brightness and / or color) of image 370 with a relatively lower blur index compared to image 350 because local differences in gray scale are less apparent.

[0046] Referring back to Figure 4 At block 214, analysis system 60 can compare the blur index of the image to a first threshold. For example, the first threshold can be a minimum blur index of an image that will be used by analysis system 60 (e.g., prediction engine 74) to identify the lithology of the rock sample.

[0047] If the blur index is less than or equal to (e.g., not greater than) the first threshold, analysis system 60 can compare the blur index of the image to a second threshold at block 216. For example, the second threshold can be a minimum blur index of an image that will be corrected by image processing system 78. If the blur index is less than or equal to (e.g., not greater than) the second threshold, analysis system 60 can proceed to block 208 (e.g., output a notification) and block 210 (e.g., calibrate the imaging system). Analysis system 60 can repeat the process of blocks 202-216 until the blur index is greater than the second threshold, otherwise, analysis system 60 can exclude using the image to identify the lithology of the rock sample.

[0048] If the blur index is greater than the second threshold, analysis system 60 can send the image to image processing system 78 for correction at block 218. The blur index of the corrected image can be compared to the first threshold at block 214 and the process of blocks 214-218 can be repeated until the blur index is greater than the first threshold. If the blur index is greater than the first threshold, analysis can use it to identify the lithology of the rock sample at block 220. As previously described, analysis system 60 can utilize image processing system 78 to process the image to identify the lithology of the rock sample. As previously described, analysis system 60 can also utilize prediction engine 74 to identify the lithology of the rock sample.

[0049] It is noted that the above examples are for illustration only. While certain specific values or ranges (e.g., gray scale 255, 250-255, 0-10) are used to describe the disclosed embodiments, they are to be understood as approximations and can differ in different systems.

[0050] The technology and systems disclosed herein relate to utilizing automated image processing to detect and correct for blur and saturated pixels in sample images, such as for cuttings obtained during drilling of a geologic formation. The results can be used to control related devices, such as the drilling system 12 and / or a drilling plan for the drilling system 12, based on the lithology of the rock sample 47. The technology and methods disclosed herein can allow for high quality well logs to be acquired for real-time and / or near real-time geologic formation evaluation and geosteering, which can be used to more efficiently and accurately control the drilling process. While the examples described above are illustrated for wellbores on land, similar methods can be applied to any acquisition configuration.

[0051] The foregoing description has been presented for the purpose of illustration. It is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Many modifications and variations are possible in light of the above teaching. Further, the order in which elements are shown and described in the figures can be rearranged, and / or two or more elements can be performed at the same time. These embodiments are chosen and described to best explain the principles of the disclosure and its practical application, to thereby enable others skilled in the art to best utilize the disclosure and various embodiments with various modifications as are suited to the particular use contemplated.

[0052] The technology presented and claimed herein are related to a tangible, concrete, and useful improvement in the field of technology and, thus, the elements recited in the claims are intentionally set forth with precision in order to best explain the technology in a manner that enables others skilled in the art to best utilize the technology and various embodiments. There is no intention to voluntarily disclose any aspect of the claimed technology or to dedicate anything to the public, including without limitation any subcombinations (including all subcombinations) of any hardware disclosures recited in the specification or claims herein unless otherwise expressly indicated by the language used in the specification or claims. Thus, the claimed technology is not abstract, intangible or purely theoretical. Furthermore, to the extent that any claim recites a "means" or "step-plus-function" clause, it is intended that the disclosure encompass both the specific embodiments and equivalents thereof, including the structures specifically recited in the specification and claims. Furthermore, if any part of the specification or claims shall be determined to be invalid or otherwise unenforceable under any single jurisdiction's patent law, such determination shall have no validity or effect on the enforceability of the specification or claims under the patent laws of any other single jurisdiction.

Claims

1. A system comprising: processor; as well as A memory accessible to the processor and storing instructions that, when executed by the processor, cause the processor to perform operations, including: Image data of an image of a rock sample received from an imaging system, wherein the image data includes multiple image pixels associated with multiple gray levels; Detect the proportion of image pixels in the image data that have gray levels within a specific range; Whether an image is eligible for image analysis is determined by comparing the ratio to a threshold. In response to determining that the image is eligible for the image analysis process, the lithology of the rock sample is identified; A record is generated based on the lithology of the rock sample; and The device associated with acquiring the rock sample is controlled based on the records.

2. The system of claim 1, wherein the operation further comprises: In response to determining that the image is not eligible for the image analysis process, a notification is output indicating that the image quality of the image is unacceptable. as well as The imaging system is calibrated.

3. The system of claim 2, wherein calibrating the imaging system includes adjusting parameters of the camera of the imaging system used to capture the image, the operating conditions of the camera, or both.

4. The system of claim 1, wherein the apparatus includes components used by the drilling system, and wherein the rock sample is obtained by the drilling system from multiple depths in the wellbore.

5. The system of claim 1, wherein the operation further comprises: The image data is used to calculate the blur index of the image; The fuzziness index is compared with a first threshold. as well as In response to the fuzziness index being greater than the first threshold, the lithology of the rock sample is identified.

6. The system of claim 5, wherein the operation further comprises: The Laplacian operator is applied to the plurality of image pixels of the image data to calculate the blur index of the image.

7. The system of claim 5, wherein the operation further comprises: In response to the fuzziness index being less than or equal to the first threshold, the fuzziness index is compared with a second threshold; as well as In response to the blur index being greater than the second threshold, the image is corrected via an image processing system to make the blur index greater than the first threshold.

8. The system of claim 1, wherein a machine learning algorithm is used to identify the lithology of the rock sample.

9. The system of claim 8, wherein the machine learning algorithm uses historical wellbore formation data to identify the lithology of the rock sample.

10. A computer-implemented method, comprising: Image data of an image of a rock sample received from an imaging system, wherein the image data includes multiple image pixels associated with multiple gray levels; Detect the proportion of image pixels in the image data that have gray levels within a specific range; Whether an image is eligible for image analysis is determined by comparing the ratio to a threshold. In response to determining that the image is eligible for the image analysis process, the lithology of the rock sample is identified; A record is generated based on the lithology of the rock sample; as well as The device associated with acquiring the rock sample is controlled based on the records.

11. The method of claim 10, further comprising: In response to determining that the image is not eligible for the image analysis process, a notification is output indicating that the image quality of the image is unacceptable. as well as The imaging system is calibrated.

12. The method of claim 11, wherein calibrating the imaging system comprises: Adjust the parameters of the camera of the imaging system used to capture the image, the operating conditions of the camera, or both.

13. The method of claim 10, further comprising: The image data is used to calculate the blur index of the image; The fuzziness index is compared with a first threshold. as well as In response to the fuzziness index being greater than the first threshold, the lithology of the rock sample is identified.

14. The method of claim 13, further comprising: The Laplacian operator is applied to the plurality of image pixels of the image data to calculate the blur index of the image.

15. The method of claim 13, further comprising: In response to the fuzziness index being less than or equal to the first threshold, the fuzziness index is compared with a second threshold; as well as In response to the blur index being greater than the second threshold, the image is corrected via an image processing system to make the blur index greater than the first threshold.

16. The method of claim 10, further comprising: Machine learning algorithms are used to identify the lithology of the rock samples.

17. A system comprising: A drilling system configured to obtain rock samples from a wellbore; as well as A geological analysis system configured to identify the lithology of the rock sample, wherein the geological analysis system includes: A preparation apparatus configured to prepare the rock sample; An imaging system configured to capture images of the rock sample; and An analysis system configured to analyze the image quality of the image and identify the lithology of the rock sample.

18. The system of claim 17, wherein the analysis system is further configured to adjust the imaging system based on the image quality of the image.

19. The system of claim 17, wherein the analysis system is configured to analyze the image quality of the image by using a convolutional neural network incorporating historical wellbore formation data associated with the wellbore.

20. The system of claim 17, wherein the analysis system is further configured to adjust the drilling system based on the lithology of the rock sample.

Images