# US 2022/0044064 A1 · Aggregating sensor profiles of objects > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0044064 A1 - Document ID: US20220044064A1 - Status: Published application - Kind: A1 - Application number: 17/130,653 - Filed: 2020-12-22 - Published: 2022-02-10 - Earliest claimed: 2020-08-08 - Assignees: Analog Devices International Unlimited Company - Applicants: Analog Devices International Unlimited Company - Inventors: Qian Zhang; Sudong Shu; Rajesh Mahapatra; Raka Singh; Michael L. Long - Web page: https://patentgrep.com/patent/US20220044064A1 ## CPC - G06F 18/22: Matching criteria, e.g. proximity measures - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06F 16/285: {Clustering or classification} - G06F 16/55: Clustering; Classification - G06F 16/583: using metadata automatically derived from the content - G06F 16/587: using geographical or spatial information, e.g. location - G06V 10/16: {using multiple overlapping images; Image stitching} - G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking - G06V 20/44: {Event detection} - G06V 20/48: {Matching video sequences} - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion} - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract This disclosure describes techniques to aggregate sensor data. The techniques perform operations comprising: receiving, from a first sensor, a first profile representing a first set of movement attributes detected by the first sensor in an area at a given point in time; receiving, from a second sensor, a second profile representing a second set of movement attributes detected by the second sensor in the area at the given point in time; computing a similarity measure between the first and second sets of movement attributes of the first and second profiles; determining that the similarity measure exceeds a threshold value; and in response to determining that the similarity measure exceeds the threshold value, associating the first and second profiles with a same first object that is in the area at the given point in time. ## Claims ### Claim 1 A system for detecting an object using multiple sensors, the system comprising: a processor; and a memory for storing one or more instructions that, when executed by the processor, configure the processor to perform operations comprising: receiving, from a first sensor, a first profile representing a first set of movement attributes detected by the first sensor in an area at a given point in time; receiving, from a second sensor, a second profile representing a second set of movement attributes detected by the second sensor in the area at the given point in time; computing a similarity measure between the first and second sets of movement attributes of the first and second profiles; determining that the similarity measure exceeds a threshold value; and in response to determining that the similarity measure exceeds the threshold value, associating the first and second profiles with a same first object that is in the area at the given point in time. ### Claim 2 (depends on 1) The system of claim 1, wherein the first and second sensors comprise image sensors. ### Claim 3 (depends on 1) The system of claim 1, wherein the operations further comprise aggregating the first profile with the second profile to generate a global profile that represents movement of the first object in the area, the global profile comprising a subset of features from the first profile and the second profile. ### Claim 4 (depends on 3) The system of claim 3, wherein the operations further comprise computing a count value indicating how many objects are present in the area at the given point in time based on the global profile. ### Claim 5 (depends on 1) The system of claim 1, wherein the first object is visible by both the first and second sensors. ### Claim 6 (depends on 1) The system of claim 1, wherein the first set of movement attributes includes a time series vector comprising at least one of a timestamp, a motion vector, activity information, color distribution, luminance intensity, or one or more shape measurements comprising an area-to-perimeter ratio. ### Claim 7 (depends on 6) The system of claim 6, wherein the time series vector further includes one or more location coordinates. ### Claim 8 (depends on 1) The system of claim 1, wherein the similarity measure is computed in accordance with an information theoretic metric. ### Claim 9 (depends on 1) The system of claim 1, wherein the first sensor generates the first profile by: obtaining an image of the area at the given point in time; extracting one or more features from the image of the area; and determining a location coordinate, a timestamp, a motion vector, activity information, color distribution, luminance intensity, and one or more shape measurements for one or more objects depicted in the image. ### Claim 10 (depends on 1) The system of claim 1, wherein the operations further comprise: determining a first track representing movement of the first object in the area based on the first profile; determining a second track representing movement of the first object in the area based on the second profile; and fusing the first and second tracks to generate a third track representing movement of the first object in the area. ### Claim 11 (depends on 1) The system of claim 1, wherein the operations further comprise: receiving, from the first sensor, a third profile representing a third set of movement attributes detected by the first sensor in the area at the given point in time; receiving, from a second sensor, a fourth profile representing a fourth set of movement attributes detected by the second sensor in the area at the given point in time; computing a plurality of similarity measures between the first, second, third and fourth profiles; and selecting the first and second profiles to be associated with the first object and selecting the third and fourth profiles to be associated with a same second object based on the plurality of similarity measures. ### Claim 12 (depends on 1) The system of claim 1, wherein the operations further comprise estimating linear displacement or angular rotation errors based on the first and second profiles. ### Claim 13 (depends on 12) The system of claim 12, wherein the operations further comprise: determining, at a subsequent point in time, that only a single object exists in the area that is visible to the first and second sensors; receiving updated first and second profiles representing updated sets of movement attributes within the area at the subsequent point in time from the first and second sensors; and updating the linear displacement or angular rotation errors based on the updated first and second profiles. ### Claim 14 A method comprising: receiving, from a first sensor, a first profile representing a first set of movement attributes detected by the first sensor in an area at a given point in time; receiving, from a second sensor, a second profile representing a second set of movement attributes detected by the second sensor in the area at the given point in time; computing a similarity measure between the first and second sets of movement attributes of the first and second profiles; determining that the similarity measure exceeds a threshold value; and. in response to determining that the similarity measure exceeds the threshold value, associating the first and second profiles with a same first object that is in the area at the given point in time. ### Claim 15 (depends on 14) The method of claim 14, wherein the first and second sensors comprise image sensors. ### Claim 16 (depends on 14) The method of claim 14, further comprising aggregating the first profile with the second profile to generate a global profile that represents movement of the first object in the area, the global profile comprising a subset of features from the first profile and the second profile. ### Claim 17 (depends on 16) The method of claim 16, further comprising computing a count value indicating how many objects are present in the area at the given point in time based on the global profile. ### Claim 18 An apparatus comprising: means for receiving, from a first sensor, a first profile representing a first set of movement attributes detected by the first sensor in an area at a given point in time; means for receiving, from a second sensor, a second profile representing a second set of movement attributes detected by the second sensor in the area at the given point in time; means for computing a similarity measure between the first and second sets of movement attributes of the first and second profiles; means for determining that the similarity measure exceeds a threshold value; and means for, in response to determining that the similarity measure exceeds the threshold value, associating the first and second profiles with a same first object that is in the area at the given point in time. ### Claim 19 (depends on 18) The apparatus of claim 18, further comprising means for aggregating the first profile with the second profile to generate a global profile that represents movement of the first object in the area, the global profile comprising a subset of features from the first profile and the second profile. ### Claim 20 (depends on 19) The apparatus of claim 19, further comprising means for computing a count value indicating how many objects are present in the area at the given point in time based on the global profile.