# US 12,008,881 B1 · Water safety device, system, and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,881 B1 - Document ID: US12008881B1 - Status: Granted - Kind: B1 - Application number: 17/719,612 - Filed: 2022-04-13 - Granted: 2024-06-11 - Earliest claimed: 2021-05-28 - Assignees: Swamcam LLC - Applicants: Swamcam LLC - Inventors: Asher Brand; Gang Bi - Web page: https://patentgrep.com/patent/US12008881B1 ## CPC - G08B 21/08: responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water - G06V 10/82: using neural networks - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G08B 21/084: {by monitoring physical movement characteristics of the water} - G08B 21/086: {by monitoring a perimeter outside the body of the water} - G08B 25/008: {Alarm setting and unsetting, i.e. arming or disarming of the security system} - G08B 25/009: {Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range} - G08B 29/186: {Fuzzy logic; neural networks} - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems and methods for improving water safety are provided. The methods include various features based on monitoring the area around a pool. Benefits are gained by applying artificial intelligence algorithms, as well as various techniques for improving processing speed and eliminating false alarms. A method for promoting water safety includes the steps of: video monitoring an area including around a body of water, and above or at a top surface of the water; detecting a presence of a human suspect in the monitored area through processing images of the video with computer implemented artificial intelligence; storing an image upon detection of the human suspect in the monitored area; processing the stored image to determine if the detection was a false alarm; and if the human suspect is determined to be a human in the monitored area, then transmitting an alert, either to a device in the area being monitored, to a mobile device, or both. ## Claims ### Claim 1 A method for promoting water safety comprising the steps of: video monitoring an area including around a body of water, and above or at a top surface of the water; detecting a presence of a human suspect in the monitored area through processing images of the video with computer implemented artificial intelligence; storing an image upon detection of the human suspect in the monitored area; processing the stored image to determine if the detection was a false alarm; and if the human suspect is determined to be a human in the monitored area, then transmitting an alert, either to a device in the area being monitored, to a device inside a home, to a mobile device, or any combination of these; wherein the processing of the stored image to determine if the detection was the false alarm includes processing the stored image including the human suspect to determine the false alarm by one or more of the following false alarm detection steps: comparing the stored image including the human suspect and a second subsequent image of a same view to determine if a threshold level of pixels have changed; scanning multiple areas of the stored image including the human suspect for a human suspect meeting a threshold pixel height, the threshold pixel height being different in each area; or comparing the stored image including the human suspect and a second subsequent image of the same view, and determining if a threshold number of pixels in an area around coordinates corresponding to a detection event have changed, if a false alarm is not detected, then transmitting an alert, either to a device in the area around the body of water, to a mobile device, or both. ### Claim 2 (depends on 1) The method of claim 1, wherein the step of comparing first and second images to determine if a threshold level of pixels have changed is performed. ### Claim 3 (depends on 2) The method of claim 2, wherein the step of scanning multiple areas of the image in which motion was detected for a human suspect meeting a threshold pixel height, the threshold pixel height being different in each area is performed. ### Claim 4 (depends on 3) The method of claim 3, wherein the step of comparing the stored image including the human suspect and a second subsequent image of the same view, and determining if a threshold number of pixels in an area around coordinates corresponding to a detection event have changed is performed. ### Claim 5 (depends on 4) The method of claim 4, further comprising formatting the images to eliminate an upper portion and side portion of the image and storing a formatted image for use in the step of processing the images to determine the presence of a human suspect by utilizing artificial intelligence. ### Claim 6 (depends on 1) The method of claim 1, wherein the step of scanning multiple areas of the image in which motion was detected for a human suspect meeting a threshold pixel height, the threshold pixel height being different in each area is performed. ### Claim 7 (depends on 1) The method of claim 1, wherein the step of comparing the stored image including the human suspect and a second subsequent image of the same view, and determining if a threshold number of pixels in an area around coordinates corresponding to a detection event have changed is performed. ### Claim 8 (depends on 1) The method of claim 1, further comprising formatting the images to eliminate an upper portion and side portion of the image and storing a formatted image for use in the step of processing the images to determine the presence of a human suspect by utilizing artificial intelligence. ### Claim 9 (depends on 1) The method of claim 1, further comprising transmitting a video feed of the monitored area to the mobile device. ### Claim 10 (depends on 1) The method of claim 1, further comprising, receiving audio input from the mobile device and transmitting it to a speaker in audible range of the monitored area. ### Claim 11 (depends on 1) The method of claim 1, further comprising receiving input to enable or disable the monitoring through a keypad in a vicinity of the body of water, through a mobile device, or both. ### Claim 12 A method for promoting water safety comprising the steps of: video monitoring an area including around a body of water, and above or at a top surface of the water; detecting a presence of a human suspect in the monitored area through processing images of the video with computer implemented artificial intelligence; storing an image upon detection of the human suspect in the monitored area; processing the stored image to determine if the detection was a false alarm; and, if the false alarm is not determined to be present or if the processing the stored image to determine if the detection was a false alarm is not performed, then transmitting an alert, either to a device in the area being monitored, to a mobile device, or both; wherein a camera device performing the video monitoring is in communication with a WiFi network through an extender; and the extender is in communication with the camera device through the WiFi network and a Zigbee network; wherein the processing of the stored image to determine if the detection was the false alarm includes processing the stored image including the human suspect to determine the false alarm by one or more of the following false alarm detection steps: comparing the stored image including the human suspect and a second subsequent image of a same view to determine if a threshold level of pixels have changed; scanning multiple areas of the stored image including the human suspect for a human suspect meeting a threshold pixel height, the threshold pixel height being different in each area; or comparing the stored image including the human suspect and a second subsequent image of the same view, and determining if a threshold number of pixels in an area around coordinates corresponding to a detection event have changed; if a false alarm is not detected, then transmitting an alert, either to a device in the area around the body of water, to a mobile device, or both. ### Claim 13 (depends on 12) The method of claim 12, wherein the alert is transmitted from the camera device via the extender to the WiFi network, then to the mobile device via the Internet; and further transmitting a redundant notification from the camera device to the extender through the Zigbee network, and then to the mobile device via the Internet. ### Claim 14 (depends on 12) The method of claim 12, wherein the extender is coupled to a device capable of emitting an audible alarm, and sounding an alarm when the alert is received at the extender. ### Claim 15 (depends on 12) The method of claim 12, further comprising automatically connecting the extender to the WiFi network using a WiFi network ID and password transmitted from the camera device over the Zigbee network. ### Claim 16 A method for promoting water safety comprising the steps of: capturing multiple images including an area around a body of water and the body of water; monitoring for a human presence in the area around the body of water and the body of water by cyclically scanning multiple portions of the images for a human suspect, the multiple portions including: front left, front right, back left, back right, and back center; wherein the multiple portions are scanned in the following scanning order: cycle 1, front left or front right, front right or front left, back left or back right, back right or back left; and then cycle 2, front left or front right, front right or front left, back center; wherein if front left or back left is scanned, then front right or back right is scanned in the same cycle; the scanning order is then repeated at least until a human suspect is detected. ### Claim 17 (depends on 16) The method of claim 16, further comprising transmitting an alert, either to a device in the area around the body of water, to a mobile device, or both. ### Claim 18 (depends on 16) The method of claim 16, wherein the multiple images are processed to determine the presence of a human suspect by utilizing artificial intelligence instructions loaded onboard a camera device performing the monitoring step. ### Claim 19 (depends on 16) The method of claim 16, further comprising storing the image with the human suspect, performing one or more false alarm detection processes on the image, and transmitting an alert, either to a device in the area around the body of water, to a mobile device, or both if no false alarms are determined to be present. ### Claim 20 (depends on 16) The method of claim 16, further comprising formatting the multiple images to eliminate an upper portion and side portion of the multiple images and storing a resulting formatted image for use in the step of cyclically scanning for multiple portions of the images.