# US 12,183,075 B2 · Method and system for alarm verification based on video analytics > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,075 B2 - Document ID: US12183075B2 - Status: Granted - Kind: B2 - Application number: 18/635,260 - Filed: 2024-04-15 - Published: 2024-10-17 - Granted: 2024-12-31 - Earliest claimed: 2023-04-13 - Assignees: Briefcam Ltd. - Applicants: Briefcam Ltd. - Inventors: Igal Dvir; Shmuel Peleg - Web page: https://patentgrep.com/patent/US12183075B2 ## CPC - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - G08B 25/001: {Alarm cancelling procedures or alarm forwarding decisions, e.g. based on absence of alarm confirmation} - G06V 10/993: {Evaluation of the quality of the acquired pattern} - G06V 20/44: {Event detection} - G08B 13/19602: {Image analysis to detect motion of the intruder, e.g. by frame subtraction} - G08B 29/185: {Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system} - G06V 2201/10: Recognition assisted with metadata - G08B 13/19665: {Details related to the storage of video surveillance data (television signal recording H04N5/76)} - G08B 29/24: Self-calibration, e.g. compensating for environmental drift or ageing of components - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS ## Abstract A method and system for alarm verification based on video analytics of a plurality of alerts issued by an alert system, wherein the alert system includes at least one sensor, are provided herein. The system may include: a server comprising a computer processor and an interface for communicating with the alert system, wherein the computer processor is configured to: receive at least one alert issued by the alert system; receive at least one video clip associated with the at least one alert; and analyze, by the computer processor, using video analytics algorithms, the at least one video clip, and determine whether the at least one alert is reliable above a predefined threshold. ## Claims ### Claim 1 A method of alarm verification based on video analytics of alerts issued by an alert system, wherein the alert system comprises at least one sensor, the method comprising: receiving at a computer processor, at least one alert issued by the alert system; receiving, at the computer processor, at least one video clip associated with the at least one alert; analyzing, by the computer processor, using video analytics algorithms, the at least one video clip, and determining, by the computer processor, whether the at least one alert is reliable above a predefined threshold, wherein the at least one sensor comprises a camera producing a camera video and associated with a processing unit and a computer memory having instructions thereon which, when executed, cause the processing unit to analyze the camera video and issue the alert based on the camera video, and wherein the video analytics algorithms are such that executing them by the computer processor on the at least one video clip, results in higher reliability level of the alert, compared with the reliability level of the alert following the execution of the instructions by the processing unit associated with the camera. ### Claim 2 (depends on 1) The method according to claim 1, further comprising receiving at least one video clip associated with the alert, prior to the alert being issued by alert system, wherein the analyzing, by the computer processor, using video analytics algorithms further comprises using the data received from the at least one video clip associated with the alert, prior to the alert being issued by alert system. ### Claim 3 (depends on 1) The method according to claim 1, further comprising receiving metadata from the at least one sensor, and using the metadata to train the video analytics algorithms. ### Claim 4 A non-transitory computer readable medium for alarm verification based on video analytics of a plurality of alerts issued by an alert system wherein the alert system comprises at least one sensor, the computer readable medium comprising a set of instructions that, when executed, cause at least one computer processor to: receive at least one alert issued by the alert system; receive at least one video clip associated with the at least one alert; analyze, using video analytics algorithms, the at least one video clip, and determine whether the at least one alert is reliable above a predefined threshold, wherein the at least one sensor comprises a camera producing a camera video and associated with a processing unit and a computer memory having instructions thereon which, when executed, cause the processing unit to analyze the camera video and issue the alert based on the camera video, and wherein the video analytics algorithms are such that executing them by the computer processor on the at least one video clip, results in higher reliability level of the alert, compared with the reliability level of the alert following the execution of the instructions by the processing unit associated with the camera. ### Claim 5 (depends on 4) The non-transitory computer readable medium according to claim 4, further comprising a set of instructions that, when executed, cause the at least one computer processor to receive at least one video clip associated with the alert, prior to the alert being issued by alert system, wherein the analyzing, by the computer processor, using video analytics algorithms further comprises using the data received from the at least one video clip associated with the alert, prior to the alert being issued by alert system. ### Claim 6 (depends on 4) The non-transitory computer readable medium according to claim 4, further comprising a set of instructions that, when executed, cause the at least one computer processor to receive metadata from the at least one sensor, and using the metadata to train the video analytics algorithms. ### Claim 7 A system for alarm verification based on video analytics of a plurality of alerts issued by an alert system wherein the alert system comprises at least one sensor, the system comprising: a server comprising a computer processor and an interface for communicating with the alert system, wherein the computer processor is configured to: receive at least one alert issued by the alert system; receive at least one video clip associated with the at least one alert; and analyze, by the computer processor, using video analytics algorithms, the at least one video clip, and determine whether the at least one alert is reliable above a predefined threshold, wherein the at least one sensor comprises a camera producing a camera video and associated with a processing unit and a computer memory having instructions thereon which, when executed, cause the processing unit to analyze the camera video and issue the alert based on the camera video, and wherein the video analytics algorithms are such that executing them by the computer processor on the at least one video clip, results in higher reliability level of the alert, compared with the reliability level of the alert following the execution of the instructions by the processing unit associated with the camera. ### Claim 8 (depends on 7) The system according to claim 7, further comprising a set of instructions that, when executed, cause the computer processor to receive at least one video clip associated with the alert, prior to the alert being issued by alert system, wherein the analyzing, by the computer processor, using video analytics algorithms further comprises using the data received from the at least one video clip associated with the alert, prior to the alert being issued by alert system. ### Claim 9 (depends on 7) The system according to claim 7, further comprising a set of instructions that, when executed, cause the computer processor to receive metadata from the at least one sensor, and use the metadata to train the video analytics algorithms.