# US 12,725,264 B2 · Masking a detected object in a video stream > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,725,264 B2 - Document ID: US12725264B2 - Status: Granted - Kind: B2 - Application number: 18/613,890 - Filed: 2024-03-22 - Published: 2024-10-03 - Granted: 2026-09-01 - Earliest claimed: 2023-03-30 - Assignees: Axis AB - Applicants: Axis AB - Inventors: Axel Keskikangas; Song Yuan; Viktor Edpalm - Web page: https://patentgrep.com/patent/US12725264B2 ## CPC - G06T 7/11: Region-based segmentation - G06V 10/80: Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level (multimodal speaker identification or verification G10L17/10) - G06T 7/136: involving thresholding - G06T 7/194: involving foreground-background segmentation - G06T 2207/10016: Video; Image sequence - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A device and a method mask an object in a video stream. The camera is arranged in a system including the camera and another device. A location and field of view is known for the device and the camera. Furthermore, the field of view of the device and the camera are non-overlapping. Information indicating that an object is approaching the field of view of the camera is obtained. The obtained information is determined from the device indicating a location and a direction of movement of the object and the known locations and fields of view of the camera and the device. In response to the information, a threshold for detecting objects to be masked in the video stream captured by the camera is reduced. An object to be masked in the video stream is detected using the reduced threshold, and masking of the object in the video stream is inserted. ## Claims ### Claim 1 A method for masking a detected object in a video stream captured by a camera, wherein the camera is arranged in a camera system including the camera and at least a further device, wherein a location and field of view is known for the further device and a location and a field of view is known for the camera, and wherein the field of view of the further device and the field of view of the camera are non-overlapping, the method comprising: obtaining, in the camera, information indicating that an object is approaching the field of view of the camera, wherein the obtained information is determined from information from the further device indicating a location and a direction of movement of the object and the known locations and fields of view of the camera and the further device; in response to the obtained information, reducing a threshold on a confidence level over which an object is determined to belong to an object class which is to be masked in the video stream; detecting an object and determining that the object belongs to the object class that is to be masked in the video stream in response to a confidence level of the object belonging to the object class that is to be masked being over the reduced threshold; and inserting masking of the detected object in the video stream, wherein the masking is such that the object can no longer be identified after masking. ### Claim 2 (depends on 1) The method according to claim 1, wherein the obtained information further indicates a subarea of the field of view of the camera in which the object is expected to first appear, and wherein, in the act of reducing, the threshold is reduced only in the indicated subarea. ### Claim 3 (depends on 1) The method according to claim 1, wherein the obtained information further indicates at which point in time the object will first appear in the field of view of the camera, and wherein the threshold is reduced starting from the indicated point in time. ### Claim 4 (depends on 1) The method according to claim 1, wherein the obtained information from the further device further indicates that the object is masked by the further device. ### Claim 5 (depends on 1) The method according to claim 1, wherein the obtained information from the further device further indicates an object class of the object. ### Claim 6 (depends on 5) The method according to claim 5, wherein the obtained information from the further device further indicates a confidence in relation to the object class. ### Claim 7 (depends on 1) The method according to claim 1, wherein, in the act of reducing, the threshold is reduced in an area along a periphery of the field of view. ### Claim 8 (depends on 1) The method according to claim 1, wherein the further device is one of: a further camera, an IR camera, a thermal camera, a radar, a sonar, and a lidar. ### Claim 9 (depends on 1) The method according claim 1, further comprising: after detecting the object in the camera field of view, increasing the threshold; and on condition that the object is detected and determined to belong to the object class using the increased threshold: maintaining masking of the detected object in the video stream; on condition that the object is not detected or not determined to the object class using the increased threshold: discontinuing masking of the detected object in the video stream. ### Claim 10 (depends on 9) The method according to claim 9, wherein the act of increasing the threshold is performed a predetermined time after detecting the object. ### Claim 11 (depends on 1) A non-transitory computer-readable storage medium having stored thereon instructions for implementing the method according to claim 1 when executed in a camera having a processor. ### Claim 12 A camera for masking a detected object in a video stream captured by the camera, the camera comprising: circuitry configured to execute, when the camera is arranged in a camera system including the camera and at least a further device, wherein a location and field of view is known for the further device and a location and a field of view is known for the camera, and wherein the field of view of the further device and the field of view of the camera are non-overlapping; an obtaining function configured to obtain information indicating that an object is approaching the field of view of the camera, wherein the obtained information is determined from information from the further device indicating a location and a direction of movement of the object and the known locations and fields of view of the camera and the further device; a reducing function configured to, in response to the obtained information, reduce a threshold on a confidence level over which an object is determined to belong to an object class which is to be masked in the video stream; a detecting function configured to detect an object and determining that the object belongs to the object class that is to be masked in the video stream in response to a confidence level of the object belonging to the object class that is to be masked being over the reduced threshold; and an inserting function configured to insert masking of the detected object in the video stream, wherein the masking is such that the object can no longer be identified after masking.