# US 2019/0172219 A1 · 3d image processing and visualization with anomalous identification and predictive auto-annotation generation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0172219 A1 - Document ID: US20190172219A1 - Status: Published application - Kind: A1 - Application number: 15/828,676 - Filed: 2017-12-01 - Published: 2019-06-06 - Earliest claimed: 2017-12-01 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Aavishkar Bharara - Web page: https://patentgrep.com/patent/US20190172219A1 ## CPC - G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics - G06F 17/153: {Multidimensional correlation or convolution} - G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection - G06T 1/0007: {Image acquisition} - G06T 7/001: {using an image reference approach} - G06T 7/149: involving deformable models, e.g. active contour models - G06T 7/73: using feature-based methods - G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts - G06T 2207/30108: Industrial image inspection - G06T 2219/004: Annotating, labelling - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for three dimensional image processing with predictive auto-annotation generation including receiving sensor raw data captured by an image acquisition system, identifying parameters within the sensor raw data using historical data, creating a union set of the historical data and the sensor raw data, identifying patterns within the union set by comparing data points of the union set, classifying the identified patterns as usual patterns or unusual patterns, creating a visual image from the received sensor raw data, annotating a location of any identified unusual patterns in the visual image, and providing the visual image to a display device. A system and a non-transitory computer-readable medium are also disclosed. ## Claims ### Claim 1 A method of three-dimensional image processing with predictive auto-annotation generation, the method comprising: receiving sensor raw data, the sensor raw data captured by an image acquisition system; identifying parameters within the sensor raw data using historical data; creating a union set of the historical data and the sensor raw data; identifying patterns within the union set by comparing data points of the union set; classifying the identified patterns as usual patterns or unusual patterns; creating a visual image from the received sensor raw data; annotating a location of any identified unusual patterns in the visual image; and providing the visual image to a display device. ### Claim 2 (depends on 1) The method of claim 1, the received sensor raw data including one of raw captured image data and formatted image data. ### Claim 3 (depends on 1) The method of claim 1, including: identifying one or more object contours in the sensor raw data; and creating the union set only using historical data and sensor raw data to a region local to the one or more object contours. ### Claim 4 (depends on 1) The method of claim 1, the image parameters including at least one of signal intensity change between object contours and between object contours groupings. ### Claim 5 (depends on 1) The method of claim 1, including comparing periods of historical data to create the historical mathematical data. ### Claim 6 (depends on 1) The method of claim 1, including providing the union set data points to augment the historical data. ### Claim 7 (depends on 1) The method of claim 1, the classifying identified patterns including comparing the identified patterns to patterns within the historical data. ### Claim 8 (depends on 1) The method of claim 1, classifying the identified patterns including comparing an intensity change between object contours with a predetermined threshold. ### Claim 9 A non-transitory computer-readable medium having stored thereon instructions which when executed by a control processor cause the control processor to perform a method of three-dimensional image processing with predictive auto-annotation generation, the method comprising: receiving sensor raw data, the sensor raw data captured by an image acquisition system; identifying parameters within the sensor raw data using historical data; creating a union set of the historical mathematical data and the sensor raw data; identifying patterns within the union set by comparing data points of the union set; classifying the identified patterns as usual patterns or unusual patterns; creating a visual image from the received sensor raw data; annotating a location of any identified unusual patterns in the visual image; and providing the visual image to a display device. ### Claim 10 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the method, including the received sensor raw data including one of raw captured image data and formatted image data. ### Claim 11 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the method, including: identifying one or more object contours in the sensor raw data; and creating the union set only using historical data and sensor raw data to a region local to the one or more object contours. ### Claim 12 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the method, the image parameters including at least one of signal intensity change between object contours and between object contours groupings. ### Claim 13 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the method, including comparing periods of historical data to create the historical mathematical data. ### Claim 14 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the method, including providing the union set data points to augment the historical data. ### Claim 15 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the classifying identified patterns by including comparing the identified patterns to patterns within the historical data. ### Claim 16 (depends on 9) The non-transitory computer-readable medium of claim 9, the instructions further configured to cause the control processor to perform the classifying the identified patterns by including comparing an intensity change between object contours with a predetermined threshold. ### Claim 17 A system for three-dimensional image processing with predictive auto-annotation generation, the system comprising: an anomalous identification and annotation unit including a control processor, the control processor configured to access computer executable instructions that cause the control processor to perform a method, the method comprising: receiving sensor raw data, the sensor raw data captured by an image acquisition system; identifying parameters within the sensor raw data using historical data; creating a union set of the historical data and the sensor raw data; identifying patterns within the union set by comparing data points of the union set; classifying the identified patterns as usual patterns or unusual patterns; creating a visual image from the received sensor raw data; annotating a location of any identified unusual patterns in the visual image; and providing the visual image to a display device. ### Claim 18 (depends on 17) The system of claim 17, the received sensor raw data including one of raw captured image data and formatted image data, the control processor configured to access computer executable instructions that cause the control processor to perform a method, the method including: identifying one or more object contours in the sensor raw data; and creating the union set only using historical data and sensor raw data to a region local to the one or more object contours. ### Claim 19 (depends on 17) The system of claim 17, the control processor configured to access computer executable instructions that cause the control processor to perform a method, the method including classifying identified patterns by including comparing the identified patterns to patterns within the historical data. ### Claim 20 (depends on 17) The system of claim 17, the control processor configured to access computer executable instructions that cause the control processor to perform a method, the method including classifying the identified patterns by including comparing an intensity change between object contours with a predetermined threshold.