# US 12,182,659 B1 · Object camera > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,659 B1 - Document ID: US12182659B1 - Status: Granted - Kind: B1 - Application number: 17/693,853 - Filed: 2022-03-14 - Granted: 2024-12-31 - Earliest claimed: 2022-03-14 - Assignees: Amazon Technologies, Inc. - Applicants: Amazon Technologies, Inc. - Inventors: Ali Can - Web page: https://patentgrep.com/patent/US12182659B1 ## CPC - G06K 7/1443: {locating of the code in an image} - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes} - H04N 23/58: Means for changing the camera field of view without moving the camera body, e.g. nutating or panning of optics or image sensors - G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A camera device may capture a high-resolution image of a frame and store the high-resolution image in memory. The camera device may down-sample the high-resolution image to a low-resolution image of the frame. The camera device may transmit, to an external compute node, the low-resolution image. The camera device may receive, from the external compute node, a request for a region of interest from the high-resolution image. The camera device may transmit, to the external compute node, the region of interest from the high-resolution image. The camera device may have a captured frame rate at which high-resolution images are captured. The camera device may also have an external frame rate based upon which all, or only some, of the high-resolution images may be down-sampled to low-resolution images that are transmitted to the external compute node. The external frame rate may be decoupled from the captured frame rate. ## Claims ### Claim 1 A camera device comprising: one or more image sensors that capture a high-resolution image of a frame, wherein the high-resolution image has a first resolution; a circular storage buffer that stores the high-resolution image; a plurality of region of interest transmission queues corresponding to a plurality of transmission priorities for regions of interest; and one or more processing components that down-sample the high-resolution image to a low-resolution image of the frame, wherein the low-resolution image has a second resolution that is lower than the first resolution, wherein the camera device performs operations comprising: transmitting, to an external compute node that is external to the camera device, the low-resolution image; receiving, from the external compute node, a request for a region of interest from the high-resolution image; obtaining the region of interest from the high-resolution image; queueing the region of interest in a first region of interest transmission queue of the plurality of region of interest transmission queues within the camera device, the first region of interest transmission queue corresponding to a first transmission priority of the plurality of transmission priorities; and transmitting, to the external compute node, based on the region of interest reaching a front of the first region of interest transmission queue, the region of interest from the high-resolution image. ### Claim 2 (depends on 1) The camera device of claim 1, wherein the region of interest corresponds to one or more objects that are at least partially displayed in the frame. ### Claim 3 (depends on 2) The camera device of claim 2, wherein the one or more objects are detected based on an object detection analysis of the low-resolution image. ### Claim 4 (depends on 2) The camera device of claim 2, wherein the one or more objects comprise a machine-readable data object. ### Claim 5 (depends on 4) The camera device of claim 4, wherein the machine-readable data object is read using the region of interest from the high-resolution image. ### Claim 6 A computer-implemented method comprising: capturing, by a camera device, a high-resolution image of a frame, wherein the high-resolution image has a first resolution; down-sampling, by the camera device, the high-resolution image to a low-resolution image of the frame, wherein the low-resolution image has a second resolution that is lower than the first resolution; transmitting, by the camera device, to an external compute node that is external to the camera device, the low-resolution image; receiving, by the camera device, from the external compute node, a request for a region of interest from the high-resolution image; obtaining, by the camera device, the region of interest from the high-resolution image; queueing the region of interest in a first region of interest transmission queue of a plurality of region of interest transmission queues within the camera device, the plurality of region of interest transmission queues corresponding to a plurality of transmission priorities for regions of interest, the first region of interest transmission queue corresponding to a first transmission priority of the plurality of transmission priorities; and transmitting, by the camera device, to the external compute node, based on the region of interest reaching a front of the first region of interest transmission queue, the region of interest from the high-resolution image. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the region of interest corresponds to one or more objects that are at least partially displayed in the frame. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein the external compute node detects the one or more objects based on an object detection analysis of the low-resolution image. ### Claim 9 (depends on 7) The computer-implemented method of claim 7, wherein the one or more objects comprise a machine-readable data object. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein the machine-readable data object is a barcode or fiducial tag. ### Claim 11 (depends on 9) The computer-implemented method of claim 9, wherein the external compute node reads the machine-readable data object using the region of interest from the high-resolution image. ### Claim 12 (depends on 6) The computer-implemented method of claim 6, further comprising: performing, by the camera device, a geometric transformation on the region of interest including down-sampling a near-field of the region of interest. ### Claim 13 (depends on 6) The computer-implemented method of claim 6, wherein the request for the region of interest comprises two-dimensional coordinate values for the region of interest. ### Claim 14 One or more non-transitory computer-readable storage media having stored thereon computing instructions that, upon execution by one or more computing devices, cause the one or more computing devices to perform operations comprising: capturing, by a camera device, a high-resolution image of a frame, wherein the high-resolution image has a first resolution; down-sampling, by the camera device, the high-resolution image to a low-resolution image of the frame, wherein the low-resolution image has a second resolution that is lower than the first resolution; transmitting, by the camera device, to an external compute node that is external to the camera device, the low-resolution image; receiving, by the camera device, from the external compute node, a request for a region of interest from the high-resolution image; obtaining, by the camera device, the region of interest from the high-resolution image; queueing the region of interest in a first region of interest transmission queue of a plurality of region of interest transmission queues within the camera device, the plurality of region of interest transmission queues corresponding to a plurality of transmission priorities for regions of interest, the first region of interest transmission queue corresponding to a first transmission priority of the plurality of transmission priorities; and transmitting, by the camera device, to the external compute node, based on the region of interest reaching a front of the first region of interest transmission queue, the region of interest from the high-resolution image. ### Claim 15 (depends on 14) The one or more non-transitory computer-readable storage media of claim 14, wherein the region of interest corresponds to one or more objects that are at least partially displayed in the frame. ### Claim 16 (depends on 15) The one or more non-transitory computer-readable storage media of claim 15, wherein the one or more objects comprise a machine-readable data object. ### Claim 17 (depends on 14) The one or more non-transitory computer-readable storage media of claim 14, wherein the operations further comprise: performing, by the camera device, a geometric transformation on the region of interest including down-sampling a near-field of the region of interest. ### Claim 18 (depends on 14) The one or more non-transitory computer-readable storage media of claim 14, wherein the request for the region of interest comprises two-dimensional coordinate values for the region of interest.