# US 12,223,013 B2 · Systems, methods, and devices for automated meter reading for smart field patrol > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,013 B2 - Document ID: US12223013B2 - Status: Granted - Kind: B2 - Application number: 17/406,825 - Filed: 2021-08-19 - Published: 2023-02-23 - Granted: 2025-02-11 - Earliest claimed: 2021-08-19 - Assignees: Yokogawa Electric Corporation - Applicants: Yokogawa Electric Corporation - Inventors: Aparnadevi Minisankar; Saurabh Bhandari; Jia Xuan Koh; Gokula Krishnan Sivaprakasam - Web page: https://patentgrep.com/patent/US12223013B2 ## CPC - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06T 7/0004: {Industrial image inspection} - G06T 5/60: using machine learning, e.g. neural networks - G06T 5/90: Dynamic range modification of images or parts thereof - G06T 7/215: Motion-based segmentation - G06T 7/60: Analysis of geometric attributes - G06T 7/62: of area, perimeter, diameter or volume - G06T 7/74: {involving reference images or patches} - G06V 10/243: {by compensating for image skew or non-uniform image deformations} - G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes} - G06V 10/42: Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation - G06V 10/82: using neural networks - G06T 2207/10016: Video; Image sequence - G06T 2207/10024: Color image - G06T 2207/20032: Median filtering - G06T 2207/20056: Discrete and fast Fourier transform, [DFT, FFT] - G06T 2207/20061: Hough transform - G06T 2207/20064: Wavelet transform [DWT] - G06T 2207/20072: Graph-based image processing - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20132: Image cropping - G06V 2201/02: Recognising information on displays, dials, clocks - G06V 2201/07: Target detection - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods, systems, and devices for equipment reading in a factory or plant environment are described, including: capturing an image of an environment including a measurement device; detecting a target region included in the image, the target region including at least a portion of the measurement device; determining identification information associated with the measurement device based on detecting the target region; and extracting measurement information associated with the measurement device based on detecting the target region. In some aspects, detecting the target region may include: providing the image to a machine learning network; and receiving an output from the machine learning network in response to the machine learning network processing the image based on a detection model, the output including the target region. ## Claims ### Claim 1 A method comprising: capturing an image of an environment comprising a first measurement device by an image capture device; detecting a target region included in the image, the target region comprising at least a portion of the first measurement device, wherein detecting the target region comprises: providing the image to a machine learning network; and receiving an output from the machine learning network in response to the machine learning network processing the image based at least in part on a detection model, the output comprising the target region; identifying the first measurement device from among a set of measurement devices based on detecting the target region, wherein identifying the first measurement device from among the set of measurement devices includes: detecting whether the image comprises an identification tag that identifies the first measurement device, the identification tag being associated with identification information of the first measurement device; and when the identification tag is not detected in the image, determining a current location of the image capture device within the environment and using the current location of the image capture device to lookup the identification tag in a database to identify the first measurement device; and extracting measurement information associated with the identified first measurement device based at least in part on detecting the target region, wherein the detection model comprises an object detection model trained based at least in part on a set of reference images associated with the set of measurement devices. ### Claim 2 (depends on 1) The method of claim 1, further comprising: determining a center point associated with an object included in the image, a radius associated with the object, or both, based at least in part on one or more dimensions of the image. ### Claim 3 (depends on 1) The method of claim 1, further comprising at least one of: modifying a brightness level of the image based at least in part on a brightness threshold; and modifying a contrast level of the image based at least in part on a contrast threshold. ### Claim 4 (depends on 1) The method of claim 1, further comprising: comparing at least one feature included in the image to at least one feature included in one or more registered images of the set of measurement devices; and outputting a result of the comparison. ### Claim 5 (depends on 1) The method of claim 1, further comprising: detecting a set of linear features included in the target region, wherein the set of linear features are of the same type; identifying coordinate values respectively associated with the set of linear features; and determining, based at least in part on the coordinate values, at least one of: a first coordinate value associated with at least one linear feature of the set of features and a first reference axis; and a second coordinate value associated with the at least one linear feature and a second reference axis, wherein extracting the measurement information associated with the first measurement device is based at least in part on the first coordinate value, the second coordinate value, or both. ### Claim 6 (depends on 1) The method of claim 1, further comprising: processing textual information included on the identification tag using one or more optical character recognition operations, and identifying the first measurement device based on the processing of the textual information. ### Claim 7 (depends on 1) The method of claim 1, wherein: the target region comprises a measurement indicator associated with the first measurement device; and extracting the measurement information associated with the first measurement device is based at least in part on the measurement indicator. ### Claim 8 (depends on 1) The method of claim 1, further comprising: comparing the current location of the image capture device to locations of the set of measurement devices recorded in the database; and identifying the first measurement device is based at least in part on a result of the comparison. ### Claim 9 A system comprising: a transport instrument for patrolling an environment comprising a plurality of measurement devices; an image capture device located on the transport instrument and that supports capture of images of the environment; a processor that processes an image captured by the image capture device, the image including a first measurement device of the plurality of measurement devices; and a memory coupled with the processor, wherein the memory stores data that, when executed by the processor, enables the processor to: detect a target region included in the image, the target region comprising at least a portion of the first measurement device, wherein detecting the target region comprises: providing the image to a machine learning network; and receiving an output from the machine learning network in response to the machine learning network processing the image based at least in part on a detection model, the output comprising the target region; identify the first measurement device from among the plurality of measurement devices based on detecting the target region, wherein identifying the first measurement device from among the plurality of measurement devices includes: detecting whether the image comprises an identification tag that identifies the first measurement device, the identification tag being associated with identification information of the first measurement device; and when the identification tag is not detected in the image, adjusting one or more characteristics of the image to yield a modified image and detecting whether the modified image comprises the identification tag; and extract measurement information associated with the identified first measurement device based at least in part on detecting the target region. ### Claim 10 (depends on 9) The system of claim 9, wherein the processor is configured to adjust a parameter associated with a patrol of the transport instrument based on one or more characteristics of the image. ### Claim 11 (depends on 10) The system of claim 10, wherein the parameter being adjusted includes a patrol route of the transport instrument. ### Claim 12 (depends on 10) The system of claim 10, wherein the parameter being adjusted includes a patrol schedule of the transport instrument. ### Claim 13 (depends on 10) The system of claim 10, wherein the one or more characteristics of the image comprises image quality. ### Claim 14 (depends on 9) The system of claim 9, wherein the processor is configured to access configuration information associated with the environment, and process the image based on the configuration information. ### Claim 15 (depends on 14) The system of claim 14, wherein the configuration information includes a configuration profile for the plurality of measurement devices, a configuration profile for equipment associated with the plurality of measurement devices, a configuration profile for the transport instrument, or any combination thereof. ### Claim 16 (depends on 9) The system of claim 9, wherein the measurement information is indicative of a measurement value of the first measurement device, and wherein the processor is configured to compare the measurement value to a range of expected values and determine whether to generate an alert based on the comparison. ### Claim 17 (depends on 9) The system of claim 9, wherein the processor is configured to communicate with at least one other transport instrument in the environment to share data associated with processing the image. ### Claim 18 A system comprising: a machine learning network; a processor; and a memory coupled with the processor, wherein the memory stores data that, when executed by the processor, enables the processor to: receive an image of an environment comprising a measurement device, wherein the image is captured by an image capture device; detect a target region included in the image, the target region comprising at least a portion of the measurement device, wherein detecting the target region comprises: providing the image to the machine learning network; and receiving an output from the machine learning network in response to the machine learning network processing the image based at least in part on a detection model, the output comprising the target region, wherein the detection model comprises an object detection model trained based at least in part on a set of reference images associated with a set of measurement devices, and wherein the set of measurement devices comprises at least the measurement device; identify the measurement device from among the set of measurement devices by: detecting whether the image comprises a tag that identifies the measurement device; when the tag is not detected in the image, adjusting one or more characteristics of the image to yield a modified image and detecting whether the modified image comprises the tag; when the tag is detected in the image or the modified image, accessing a database containing a plurality of tags associated to the set of measurement devices to identify the measurement device using the detected tag; and when the tag is not detected in the image or the modified image, determining a current location of the image capture device within the environment and using the current location of the image capture device to lookup the tag in the database to identify the measurement device; and extract measurement information from the target region of the image based on the identified measurement device. ### Claim 19 (depends on 18) The system of claim 18, wherein adjusting one or more characteristics of the image to yield the modified image includes adjusting one of a brightness level of the image, a contrast level of the image, and an orientation of the image.