# US 12,217,590 B2 · Shadow-based fall detection > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,590 B2 - Document ID: US12217590B2 - Status: Granted - Kind: B2 - Application number: 18/105,960 - Filed: 2023-02-06 - Published: 2023-08-10 - Granted: 2025-02-04 - Earliest claimed: 2022-02-08 - Assignees: Alarm.com Incorporated - Applicants: Alarm.com Incorporated - Inventors: Ramy Samir Aziz ElDelgawy; William Wireko Mensah; Andrew Or; Jinfei Yin - Web page: https://patentgrep.com/patent/US12217590B2 ## CPC - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G08B 21/043: {detecting an emergency event, e.g. a fall} - G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model - G06V 10/82: using neural networks - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G08B 21/0476: {Cameras to detect unsafe condition, e.g. video cameras} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS ## Abstract Methods, systems, and apparatus, including computer programs encoded on computer storage media, for fall detection using data for a person's shadow. One of the methods includes obtaining, from a camera, an image of a portion of a property; determining whether a shadow is likely depicted in the image; in response to determining that a shadow is likely depicted in the image, determining whether the shadow in the image likely represents a potentially falling person; and in response to determining that the shadow in the image likely represents a potentially falling person, performing one or more actions for the potentially falling person. ## Claims ### Claim 1 A computer-implemented method comprising: obtaining, from a camera, an image of a portion of a property; determining whether a shadow is likely depicted in the image; in response to determining that a shadow is likely depicted in the image, determining whether the shadow in the image likely represents a potentially falling person; and in response to determining that the shadow in the image likely represents a potentially falling person, performing one or more actions for the potentially falling person. ### Claim 2 (depends on 1) The method of claim 1, wherein determining whether the shadow in the image likely represents a falling person comprises: determining a time of day when the image was captured by the camera; and determining, using data for the time of day when the image was captured by the camera, whether the shadow in the image likely represents a falling person. ### Claim 3 (depends on 2) The method of claim 2, comprising selecting, using the time of day when the image was captured, a model trained to detect shadows of falling people as the data for the time of day when the image was captured by the camera. ### Claim 4 (depends on 1) The method of claim 1, wherein determining whether the shadow in the image likely represents a falling person comprises: determining one or more light sources for the image; and determining, using data for the one or more light sources for the image, whether the shadow in the image likely represents a falling person. ### Claim 5 (depends on 4) The method of claim 4, wherein determining the one or more light sources for the image comprises: determining, for one or more potential light sources of multiple potential light sources for an area surrounding content depicted in the image, a status of the corresponding potential light source; and determining, using the statuses of the one or more potential light sources, the one or more light sources for the image. ### Claim 6 (depends on 4) The method of claim 4, wherein determining the one or more light sources for the image comprises detecting one or more of a fixed light source or a moveable light source as a source of light for the image. ### Claim 7 (depends on 6) The method of claim 6, wherein detecting the one or more of a fixed light source or a moveable light source comprises detecting a lamp or a light fixture as a fixed light source for the image. ### Claim 8 (depends on 6) The method of claim 6, wherein detecting the one or more of a fixed light source or a moveable light source comprises detecting a flashlight, a light on a mobile device, or the sun as a moveable light source for the image. ### Claim 9 (depends on 1) The method of claim 1, wherein performing the one or more actions for the potentially falling person comprises: determining, using data for the camera, a predicted location of the potentially falling person; and providing, to a computing device, instructions to cause the computing device to present an interface that indicates that the potentially falling person has potentially fallen and the predicted location of the potentially falling person. ### Claim 10 (depends on 9) The method of claim 9, comprising: determining whether a number of occupants of the property satisfies an occupancy threshold; and in response to determining that the number of occupants of the property satisfies the occupancy threshold, selecting, from a plurality of computing devices at the property, the computing device as a device to provide the instructions to, wherein providing the instructions is responsive to selecting the computing device. ### Claim 11 (depends on 9) The method of claim 9, comprising: determining, using sensor data for the property, whether a likelihood that an identity of the potentially falling person satisfies a likelihood threshold; and in response to determining whether the likelihood that an identity of the potentially falling person satisfies the likelihood threshold, selecting, from a plurality of computing devices at the property, the computing device as a device to provide the instructions to, wherein providing the instructions is responsive to selecting the computing device. ### Claim 12 A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: obtaining, from a camera, an image of a portion of a property; determining whether a shadow is likely depicted in the image; in response to determining that a shadow is likely depicted in the image, determining whether the shadow in the image likely represents a potentially falling person; and in response to determining that the shadow in the image likely represents a potentially falling person, performing one or more actions for the potentially falling person. ### Claim 13 (depends on 12) The system of claim 12, wherein determining whether the shadow in the image likely represents a falling person comprises: determining a time of day when the image was captured by the camera; and determining, using data for the time of day when the image was captured by the camera, whether the shadow in the image likely represents a falling person. ### Claim 14 (depends on 13) The system of claim 13, the operations comprising selecting, using the time of day when the image was captured, a model trained to detect shadows of falling people as the data for the time of day when the image was captured by the camera. ### Claim 15 (depends on 12) The system of claim 12, wherein determining whether the shadow in the image likely represents a falling person comprises: determining one or more light sources for the image; and determining, using data for the one or more light sources for the image, whether the shadow in the image likely represents a falling person. ### Claim 16 (depends on 15) The system of claim 15, wherein determining the one or more light sources for the image comprises: determining, for one or more potential light sources of multiple potential light sources for an area surrounding content depicted in the image, a status of the corresponding potential light source; and determining, using the statuses of the one or more potential light sources, the one or more light sources for the image. ### Claim 17 (depends on 15) The system of claim 15, wherein determining the one or more light sources for the image comprises detecting one or more of a fixed light source or a moveable light source as a source of light for the image. ### Claim 18 (depends on 17) The system of claim 17, wherein detecting the one or more of a fixed light source or a moveable light source comprises detecting a lamp or a light fixture as a fixed light source for the image. ### Claim 19 (depends on 17) The system of claim 17, wherein detecting the one or more of a fixed light source or a moveable light source comprises detecting a flashlight, a light on a mobile device, or the sun as a moveable light source for the image. ### Claim 20 One or more non-transitory computer storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising: obtaining, from a camera, an image of a portion of a property; determining whether a first likelihood that a shadow is depicted in the image satisfies a first likelihood threshold; in response to determining that the first likelihood that a shadow is depicted in the image satisfies the first likelihood threshold, determining whether a second likelihood that the shadow in the image represents a potentially falling person satisfies a second likelihood threshold; and in response to determining that the second likelihood that the shadow in the image represents a potentially falling person satisfies the second likelihood threshold, performing one or more actions for the potentially falling person.