# US 10,455,144 B2 · Information processing apparatus, information processing method, system, and non-transitory computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,455,144 B2 - Document ID: US10455144B2 - Status: Granted - Kind: B2 - Application number: 15/845,329 - Filed: 2017-12-18 - Published: 2018-07-19 - Granted: 2019-10-22 - Earliest claimed: 2017-01-13 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Kotaro Yano; Tomoaki Kawai - Web page: https://patentgrep.com/patent/US10455144B2 ## CPC - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis - G06V 10/758: {Involving statistics of pixels or of feature values, e.g. histogram matching} - H04N 23/611: where the recognised objects include parts of the human body - H04N 23/62: Control of parameters via user interfaces - H04N 23/69: Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming - H04N 23/695: Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A first control amount of an image capturing device is estimated based on a region of an object detected from a captured image by the image capturing device. A second control amount of the image capturing device instructed in accordance with a user operation is acquired. A parameter required for the estimating is updated based on a difference between the first control amount and the second control amount. ## Claims ### Claim 1 An information processing apparatus, comprising: one or more processors; and a memory coupled to the one or more processors, the memory having stored thereon instructions which, when executed by the one or more processors, cause the apparatus to: obtain an image feature amount in a region of an object detected from a captured image by an image capturing device; estimate a first control amount of the image capturing device based on the image feature amount in the region of the object, image coordinates of the region, and a likelihood of the region; acquire a second control amount of the image capturing device instructed in accordance with a user operation; and update a parameter used for the estimation of the first control amount, based on a difference between the first control amount and the second control amount. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the parameter is a coupling coefficient between neurons in a fully-connected neural network. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein the parameter is updated by using a stochastic gradient descent. ### Claim 4 (depends on 1) The information processing apparatus according to claim 1, the instructions, when executed by the one or more processors, causing the apparatus to control the image capturing device in accordance with the first control amount that is estimated by using the updated parameter. ### Claim 5 (depends on 4) The information processing apparatus according to claim 4, wherein a first value indicating a level of interest with respect to the object based on the region of the object is estimated, a second value indicating a level of interest with respect to the region by a user in the captured image is acquired, and the parameter required for the estimation is updated based on the first value and the second value. ### Claim 6 (depends on 5) The information processing apparatus according to claim 5, wherein the instructions, when executed by the one or more processors, causing the apparatus to decide, out of a plurality of control amounts that are estimated by using the parameter updated, a control amount being estimated based on the region for which the first value is largest as the first control amount. ### Claim 7 (depends on 5) The information processing apparatus according to claim 5, wherein the instructions, when executed by the one or more processors, causing the apparatus to decide a result of performing, on a plurality of control amounts of the image capturing device that are estimated by using the updated parameter, a weighted average taking the first values corresponding to the plurality of control amounts as weights as the first control amount. ### Claim 8 (depends on 1) The information processing apparatus according to claim 1, wherein the first control amount includes at least one of panning, tilting and zooming of the image capturing device. ### Claim 9 A system comprising an image capturing device and an information processing apparatus operable to control the image capturing device, wherein the information processing apparatus comprises: one or more processors; and a memory coupled to the one or more processors, the memory having stored thereon instructions which, when executed by the one or more processors, cause the apparatus to: obtain an image feature amount in a region of an object detected from a captured image by an image capturing device; estimate a first control amount of the image capturing device based on the image feature amount in the region of the object, image coordinates of the region, and a likelihood of the region; acquire a second control amount of the image capturing device instructed in accordance with a user operation; and update a parameter used for the estimation of the first control amount, based on a difference between the first control amount and the second control amount. ### Claim 10 An information processing method, comprising: obtaining an image feature amount in a region of an object detected from a captured image by the image capturing device; estimating a first control amount of an image capturing device based on the image feature amount in the region of the object, image coordinates of the region, and a likelihood of the region; acquiring a second control amount of the image capturing device instructed in accordance with a user operation; and updating a parameter used for the estimating, based on a difference between the first control amount and the second control amount. ### Claim 11 A non-transitory computer-readable storage medium storing a computer program for causing a computer to obtain an image feature amount in a region of an object detected from a captured image by an image capturing device; estimate a first control amount of the image capturing device based on the image feature amount in the region of the object, image coordinates of the region, and a likelihood of the region; acquire a second control amount of the image capturing device instructed in accordance with a user operation; and update a parameter used for the estimation of the first control amount, based on a difference between the first control amount and the second control amount.