# US 11,908,197 B2 · Information processing apparatus, information processing method, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,197 B2 - Document ID: US11908197B2 - Status: Granted - Kind: B2 - Application number: 17/370,974 - Filed: 2021-07-08 - Published: 2022-01-20 - Granted: 2024-02-20 - Earliest claimed: 2020-07-20 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Shunsuke Sato - Web page: https://patentgrep.com/patent/US11908197B2 ## CPC - G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion} - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06V 40/23: {Recognition of whole body movements, e.g. for sport training} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An information processing apparatus that detects an object from an image, includes a determination unit configured to determine a boundary at which a movement of the object between partial regions in the image is estimated, the partial regions each including a plurality of objects, and an estimation unit configured to estimate movement information indicating a number of objects that have passed the boundary determined by the determination unit. ## Claims ### Claim 1 An information processing apparatus that detects an object from an image, comprising: one or more processors; and one or more memories storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions to: determine a boundary at which a movement of the object between partial regions in the image is estimated, the partial regions being specified based on positions of a plurality of objects; and estimate movement information indicating a number of objects that have passed the determined boundary, wherein the boundary at which the movement of the object is estimated is determined based on a partial image out of a plurality of partial images obtained by dividing the image including objects, a number of which is larger than a predetermined value. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more programs include further instructions to detect a congestion region including more objects than other partial regions based on the estimated movement information. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein, in a case where a density of objects in proximity to the boundary is higher than a predetermined threshold, the congestion region is detected. ### Claim 4 (depends on 2) The information processing apparatus according to claim 2, wherein, in a case where a number of objects in a region in proximity to the boundary is larger than a predetermined threshold, the congestion region is detected. ### Claim 5 (depends on 2) The information processing apparatus according to claim 2, wherein, in a case where a total of the number of objects that have passed the determined boundary and have flowed into a region of interest and a number of objects detected from the image is larger than a second threshold indicating a congestion state, the congestion region is detected. ### Claim 6 (depends on 2) The information processing apparatus according to claim 2, wherein the one or more programs include further instructions to notify a user of occurrence of a congestion state in a case where the congestion region is detected. ### Claim 7 (depends on 2) The information processing apparatus according to claim 2, wherein, in a case where the number of objects is larger than a predetermined value, the congestion region is detected based on the estimated movement information. ### Claim 8 (depends on 1) The information processing apparatus according to claim 1, wherein the boundary at which the movement of the object is estimated is determined based on a partial region out of the partial regions, the partial region including objects in the image, a number of which per region is larger than that of the other partial regions. ### Claim 9 (depends on 1) The information processing apparatus according to claim 1, wherein the boundary at which the movement of the object is estimated is determined based on a partial region out of the partial regions, the partial region including objects in the image, a number of which per region is larger than a first threshold. ### Claim 10 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more programs include further instructions to extract partial regions each including a plurality of objects, based on a position of the object in the image, wherein the boundary at which the movement of the object is estimated is determined based on a region of interest out of the extracted partial regions, the region of interest including objects, a number of which is larger than that of the other regions. ### Claim 11 (depends on 10) The information processing apparatus according to claim 10, wherein the partial regions are extracted based on a position of the object in a real space, the object being detected from the image. ### Claim 12 (depends on 1) The information processing apparatus according to claim 1, wherein a line segment connecting two regions acquired from the partial regions is determined as the boundary at which the movement of the object is estimated. ### Claim 13 (depends on 12) The information processing apparatus according to claim 12, wherein a line segment not including a position of a known obstacle out of line segments each connecting two regions acquired from the partial regions is determined as the boundary at which the movement of the object is estimated. ### Claim 14 (depends on 12) The information processing apparatus according to claim 12, wherein a line segment connecting regions of interest out of the partial regions, each region of interest including objects, a number of which is larger than a first threshold, is determined as the boundary at which the movement of the object is estimated. ### Claim 15 (depends on 12) The information processing apparatus according to claim 12, wherein the line segment connecting the two regions acquired from the partial regions is determined as the boundary at which the movement of the object is estimated such that a length of the line segment is smaller than a predetermined length. ### Claim 16 (depends on 1) The information processing apparatus according to claim 1, wherein the movement of the object is estimated by tracking a feature of the object in proximity to the determined boundary. ### Claim 17 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more programs include further instructions to: identify, in a case where a number of objects in a partial region constituting the image is larger than a first threshold indicating a small-scale congestion state and is larger than a second threshold indicating an abnormal congestion state, the partial region as a region of interest; and hold a number of objects in the region of interest by detecting a feature of each object from the region of interest, wherein, in a case where the region of interest is identified, whether the number of objects in the region of interest is larger than a predetermined threshold is detected, and wherein, in a case where the number of objects in the region of interest is smaller than the second threshold, the region of interest is canceled. ### Claim 18 A non-transitory computer readable storage medium that stores a program that causes a computer to execute an information processing method of detecting an object from an image, the method comprising: determining a boundary at which a movement of the object between partial regions in the image is estimated, the partial regions being specified based on positions of a plurality of objects; and estimating movement information indicating a number of objects that have passed the determined boundary, wherein the boundary at which the movement of the object is estimated is determined based on a partial image out of a plurality of partial images obtained by dividing the image including objects, a number of which is larger than a predetermined value. ### Claim 19 An information processing method for detecting an object from an image, the method comprising: determining a boundary at which a movement of the object between partial regions in the image is estimated, the partial regions being specified based on positions of a plurality of objects; and estimating movement information indicating a number of objects that have passed the determined boundary, wherein the boundary at which the movement of the object is estimated is determined based on a partial image out of a plurality of partial images obtained by dividing the image including objects, a number of which is larger than a predetermined value.