# US 2015/0178293 A1 · Change invariant scene recognition by an agent > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2015/0178293 A1 - Document ID: US20150178293A1 - Status: Published application - Kind: A1 - Application number: 14/537,802 - Filed: 2014-11-10 - Published: 2015-06-25 - Earliest claimed: 2011-02-14 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Georgios CHRYSANTHAKOPOULOS - Web page: https://patentgrep.com/patent/US20150178293A1 ## CPC - G06F 16/7837: {using objects detected or recognised in the video content} - G06V 20/20: in augmented reality scenes - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A technology can be provided for change invariant scene recognition of an environment by an agent that uses image sensors to capture images. An example method can include grouping the images into situation image sets to form an image database. A navigation image can be captured by the agent at the agent's current location. Another operation can be searching through images by separately loaded situation image set to identify images that are a probable match for the navigation image. Error values can be computed between the navigation image and situation image sets. A probability can be calculated that situation image sets are to be used as a relevant situation image set based on the error values. Then the relevant situation image set can be searched for matching purposes with the navigation image while the error value is below a defined threshold. ## Claims ### Claim at position 1 1-20. (canceled) ### Claim 21 A system comprising: an image database configured to store situation image sets of an environment; a probability module configured to identify a selected situation image set from the image database based on a probability that the selected situation image set has an individual image that matches a navigation image of the environment; and at least one processor configured to execute the probability module. ### Claim 22 (depends on 21) The system of claim 21, further comprising an image camera configured to capture images to be grouped into the situation image sets. ### Claim 23 (depends on 22) The system of claim 22, further comprising a grouping module configured to group the images of the environment into the situation image sets. ### Claim 24 (depends on 21) The system of claim 21, further comprising a query module configured to query the image database by comparing a first image signature of the navigation image with second image signatures of the situation image sets. ### Claim 25 (depends on 24) The system of claim 24, wherein the situation image sets are loaded as separate sets from the image database. ### Claim 26 (depends on 21) The system of claim 21, further comprising a feature matching module configured to identify one or more matching images in the selected situation image set that match the navigation image. ### Claim 27 (depends on 26) The system of claim 26, wherein the feature matching module is further configured to provide a navigation location for an agent based on the one or more matching images. ### Claim 28 A method implemented by one or more computer processing devices, the method comprising: comparing situation image signatures of situation image sets to one or more navigation image signatures of a navigation image; and identifying a selected situation image set based on a corresponding probability that the selected situation image set has an individual image that matches the navigation image. ### Claim 29 (depends on 28) The method of claim 28, further comprising grouping images of an environment into the situation image sets. ### Claim 30 (depends on 28) The method of claim 28, further comprising determining the corresponding probability. ### Claim 31 (depends on 30) The method of claim 30, wherein the determining the corresponding probability further comprises computing an error value between particular situation image signatures of the selected situation image set and the one or more navigation image signatures of the navigation image and basing the corresponding probability on the error value. ### Claim 32 (depends on 28) The method of claim 28, further comprising tracking a transition probability that determines whether to search a different situation image set for different situation image signatures. ### Claim 33 (depends on 32) The method of claim 32, wherein the transition probability has a threshold that indicates searching the different situation image set. ### Claim 34 (depends on 28) The method of claim 28, further comprising: identifying one or more matching images in the selected situation image set that match the navigation image; and providing a navigation location based on the one or more matching images, wherein the situation image sets and the navigation image are captured in an environment, and the navigation location is provided for an agent in the environment. ### Claim 35 A system comprising: a computer processing device; and a storage device storing computer readable instructions which, when executed by the computer processing device, cause the computer processing device to: perform a comparison between situation image signatures of situation image sets and one or more navigation image signatures of a navigation image; and based on the comparison, identify one or more matching images in a selected situation image set that match the navigation image. ### Claim 36 (depends on 35) The system of claim 35, wherein the situation image sets include images captured in an environment and grouped according to locations in the environment. ### Claim 37 (depends on 36) The system of claim 36, wherein the computer readable instructions further cause the computer processing device to determine a navigation location in the environment based on the one or more matching images. ### Claim 38 (depends on 37) The system of claim 37, wherein the computer readable instructions further cause the computer processing device to provide the navigation location to an agent in the environment. ### Claim 39 (depends on 38) The system of claim 38, further comprising the agent. ### Claim 40 (depends on 39) The system of claim 39, wherein the computer readable instructions further cause the computer processing device to capture the images with a camera of the agent.