US 12,249,094 B2
Inter-device positional relationship estimation device, inter-device positional relationship estimation method, and program
Misao Kataoka, Musashino (JP); Hirofumi Noguchi, Musashino (JP); Takuma Isoda, Musashino (JP); and Kyota Hattori, Musashino (JP)
Assigned to Nippon Telegraph and Telephone Corporation, Tokyo (JP)
Appl. No. 17/799,963
Filed by Nippon Telegraph and Telephone Corporation, Tokyo (JP)
PCT Filed Feb. 17, 2020, PCT No. PCT/JP2020/006067
§ 371(c)(1), (2) Date Aug. 16, 2022,
PCT Pub. No. WO2021/166032, PCT Pub. Date Aug. 26, 2021.
Prior Publication US 2023/0067207 A1, Mar. 2, 2023
Int. Cl. G06T 7/73 (2017.01)
CPC G06T 7/73 (2017.01) [G06T 2207/10016 (2013.01)] 6 Claims
OG exemplary drawing
 
1. An inter-device positional relationship estimation apparatus comprising:
an analysis information acquisition unit, including one or more processors, configured to acquire time-series analysis information of a target to be photographed obtained by each device, as time-series analysis information;
a recommendation processing unit, including one or more processors, configured to, when detailed information indicating features of the target is not analyzed at a certain time in the time-series analysis information, by using detailed information of another time of the same device and detailed information of another device different from the device, estimate unanalyzed detailed information applying a predetermined recommendation algorithm, and generate time-series analysis information including the estimated detailed information;
an initial map creation unit, including one or more processors, configured to, by referring to the time-series analysis information including the estimated detailed information, calculate a neighborhood determination point indicating a degree of correlation of the detailed information between fixed devices among the devices, extract the devices of which the calculated neighborhood determination point is equal to or larger than a predetermined first threshold value as neighboring device candidates, and calculate a detection probability between the devices and a movement time between the devices based on time-series target detection information indicated by the detailed information of the extracted neighboring device candidates to create an initial map; and
a device relationship map creation unit, including one or more processors, configured to, by referring to the time-series analysis information including the estimated detailed information, set and calculate neighborhood points indicating a degree of correlation of detailed information between the devices including a moving device or/and a new fixed device to be higher when a time is closer to a current time as compared with the past and to be imparted to the device present in a narrower range when a distance to a device to be calculated obtained from a movement time of the target of the initial map is closer to a current distance, determine the device of which the calculated neighborhood points are equal to or larger than a predetermined second threshold value to be a neighboring device, and calculate a detection probability between the devices and a movement time between the devices based on time-series target detection information indicated by the detailed information of the determined neighboring device to create a device relationship map.