# US 2023/0057733 A1 · Computer-readable recording medium storing identification program, identification method, and information processing apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0057733 A1 - Document ID: US20230057733A1 - Status: Published application - Kind: A1 - Application number: 17/868,847 - Filed: 2022-07-20 - Published: 2023-02-23 - Earliest claimed: 2021-08-23 - Assignees: Fujitsu Limited - Applicants: Fujitsu Limited - Inventors: Takahiro Yoshioka; Natsuki MIYAHARA; Shuji AWAI; TAKESHI KONNO - Web page: https://patentgrep.com/patent/US20230057733A1 ## CPC - H04N 23/611: where the recognised objects include parts of the human body - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A non-transitory computer-readable recording medium stores an identification program for causing a computer to execute a process including: acquiring image data captured by a camera; generating skeleton information of a person included in an image frame and attribute information of the person included in the image frame by analyzing the image frame that constitutes the acquired image data; setting a first feature amount related to a height of the person for the person in the image frame based on the generated attribute information of the person; setting a second feature amount related to the height of the person for the person in the image frame based on the generated skeleton information; and specifying a parameter of the camera based on a difference between the first feature amount and the second feature amount. ## Claims ### Claim 1 A non-transitory computer-readable recording medium storing an identification program for causing a computer to execute a process comprising: acquiring image data captured by a camera; generating skeleton information of a person included in an image frame and attribute information of the person included in the image frame by analyzing the image frame that constitutes the acquired image data; setting a first feature amount related to a height of the person for the person in the image frame based on the generated attribute information of the person; setting a second feature amount related to the height of the person for the person in the image frame based on the generated skeleton information; and specifying a parameter of the camera based on a difference between the first feature amount and the second feature amount. ### Claim 2 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein the attribute information is statistical information that includes an average height and a variance in accordance with an attribute of the person, and in the setting the first feature amount, a random height is assigned to the person based on the statistical information, and the height of the person in the image frame is set as the first feature amount based on the height assigned to the person. ### Claim 3 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein in the specifying the parameter of the camera, the parameter is set so that the difference between the first feature amount and the second feature amount in the image frame decreases. ### Claim 4 (depends on 2) The non-transitory computer-readable recording medium according to claim 2, wherein in the setting the first feature amount, a plurality of the first feature amounts are set by resetting the random height to the person, and in the specifying the parameter, a plurality of the parameters are generated by using the plurality of first feature amounts, and the process further comprises calculating a feature amount of the person based on any one parameter among the plurality of parameters. ### Claim 5 (depends on 4) The non-transitory computer-readable recording medium according to claim 4, wherein in the specifying the parameter, processing of calculating the difference is executed for each of a plurality of the image frames by using the plurality of parameters, and one parameter is selected from the plurality of parameters based on a variance of the difference. ### Claim 6 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, the process further comprising: calculating a reduction rate of a size of the person due to movement, based on skeleton information and a position of a person included in a first image frame among the plurality of image frames and skeleton information and a position of the person included in a second image frame among the plurality of image frames; and generating skeleton information of the person in a case where the person is disposed at a disposition point, based on the disposition point over a ground different from a position of the person included in the image frame and the reduction rate. ### Claim 7 (depends on 6) The non-transitory computer-readable recording medium according to claim 6, the process further comprising: specifying a region that corresponds to the ground from a region of the image frame, and specifying the disposition point based on an intersection of straight line components in the region that corresponds to the ground. ### Claim 8 (depends on 6) The non-transitory computer-readable recording medium according to claim 6, wherein in the calculating the reduction rate, a first change amount between coordinates of a portion where the person included in the first image frame is in contact with the ground and coordinates of a portion where the person included in the second image frame is in contact with the ground is calculated, a second change amount between a height of the person included in the first image frame and a height of the person included in the second image frame is calculated, and the reduction rate is calculated based on the first change amount and the second change amount. ### Claim 9 (depends on 6) The non-transitory computer-readable recording medium according to claim 6, wherein in the calculating the reduction rate, a third change amount between coordinates of a portion where a right foot region of the person included in the first image frame is in contact with the ground and coordinates of a portion where a left foot region of the person included in the first image frame is in contact with the ground is calculated, a fourth change amount between an area of the right foot region and an area of the left foot region is calculated, and the reduction rate is calculated based on the third change amount and the fourth change amount. ### Claim 10 An identification method comprising: acquiring image data captured by a camera; generating skeleton information of a person included in an image frame and attribute information of the person included in the image frame by analyzing the image frame that constitutes the acquired image data; setting a first feature amount related to a height of the person for the person in the image frame based on the generated attribute information of the person; setting a second feature amount related to the height of the person for the person in the image frame based on the generated skeleton information; and specifying a parameter of the camera based on a difference between the first feature amount and the second feature amount. ### Claim 11 (depends on 10) The identification method according to claim 10, wherein the attribute information is statistical information that includes an average height and a variance in accordance with an attribute of the person, and in the setting the first feature amount, a random height is assigned to the person based on the statistical information, and the height of the person in the image frame is set as the first feature amount based on the height assigned to the person. ### Claim 12 (depends on 10) The identification method according to claim 10, wherein in the specifying the parameter of the camera, the parameter is set so that the difference between the first feature amount and the second feature amount in the image frame decreases. ### Claim 13 (depends on 11) The identification method according to claim 11, wherein in the setting the first feature amount, a plurality of the first feature amounts are set by resetting the random height to the person, and in the specifying the parameter, a plurality of the parameters are generated by using the plurality of first feature amounts, and the process further comprises calculating a feature amount of the person based on any one parameter among the plurality of parameters. ### Claim 14 (depends on 13) The identification method according to claim 13, wherein in the specifying the parameter, processing of calculating the difference is executed for each of a plurality of the image frames by using the plurality of parameters, and one parameter is selected from the plurality of parameters based on a variance of the difference. ### Claim 15 (depends on 10) The identification method according to claim 10, the process further comprising: calculating a reduction rate of a size of the person due to movement, based on skeleton information and a position of a person included in a first image frame among the plurality of image frames and skeleton information and a position of the person included in a second image frame among the plurality of image frames; and generating skeleton information of the person in a case where the person is disposed at a disposition point, based on the disposition point over a ground different from a position of the person included in the image frame and the reduction rate. ### Claim 16 (depends on 15) The identification method according to claim 15, the process further comprising: specifying a region that corresponds to the ground from a region of the image frame, and specifying the disposition point based on an intersection of straight line components in the region that corresponds to the ground. ### Claim 17 (depends on 15) The identification method according to claim 15, wherein in the calculating the reduction rate, a first change amount between coordinates of a portion where the person included in the first image frame is in contact with the ground and coordinates of a portion where the person included in the second image frame is in contact with the ground is calculated, a second change amount between a height of the person included in the first image frame and a height of the person included in the second image frame is calculated, and the reduction rate is calculated based on the first change amount and the second change amount. ### Claim 18 (depends on 15) The identification method according to claim 15, wherein in the calculating the reduction rate, a third change amount between coordinates of a portion where a right foot region of the person included in the first image frame is in contact with the ground and coordinates of a portion where a left foot region of the person included in the first image frame is in contact with the ground is calculated, a fourth change amount between an area of the right foot region and an area of the left foot region is calculated, and the reduction rate is calculated based on the third change amount and the fourth change amount. ### Claim 19 An information processing apparatus comprising: a memory; and a processor coupled to the memory and configured to: acquire image data captured by a camera; generate skeleton information of a person included in an image frame and attribute information of the person included in the image frame by analyzing the image frame that constitutes the acquired image data; set a first feature amount related to a height of the person for the person in the image frame based on the generated attribute information of the person; set a second feature amount related to the height of the person for the person in the image frame based on the generated skeleton information; and specify a parameter of the camera based on a difference between the first feature amount and the second feature amount. ### Claim 20 (depends on 19) The information processing apparatus according to claim 19, wherein the attribute information is statistical information that includes an average height and a variance in accordance with an attribute of the person, and the processor assigns a random height to the person based on the statistical information, and sets the height of the person in the image frame as the first feature amount based on the height assigned to the person.