# US 2025/0153679 A1 · System and method for verifying proper usage of passenger restraints > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0153679 A1 - Document ID: US20250153679A1 - Status: Published application - Kind: A1 - Application number: 18/507,043 - Filed: 2023-11-11 - Published: 2025-05-15 - Earliest claimed: 2023-11-11 - Assignees: Disney Enterprises, Inc. - Applicants: Disney Enterprises, Inc. - Inventors: Bryant D. BOYLE; Gary D. MARKOWITZ; Clifford Aron WILKINSON; Ching-Chien CHEN; Gregory Brooks HALE; Jeremy EATON - Web page: https://patentgrep.com/patent/US20250153679A1 ## CPC - B60R 22/48: Control systems, alarms, or interlock systems, for the correct application of the belt or harness - 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)} - B60R 2022/4825: {for sensing amount of belt winded on retractor} - B60R 2022/4866: {Displaying or indicating arrangements thereof} - G06V 20/59: inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions - G06V 20/593: {Recognising seat occupancy} - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A restraint verification platform may obtain video data video data of a passenger in a passenger seat. The restraint verification platform may analyze the video data using one or more machine learning models trained to detect passengers in passenger seats and passenger restraints of the passenger seats. The restraint verification platform may detect, using the one or more machine learning models and based on analyzing the video data, the passenger in the passenger seat and a passenger restraint of the passenger seat. The restraint verification platform may determine, based on analyzing the video data, that the passenger restraint is not properly securing the passenger. The restraint verification platform may perform an action based on determining that the passenger restraint is not properly securing the passenger. ## Claims ### Claim 1 A method performed by a restraint verification platform, the method comprising: obtaining video data of a passenger in a passenger seat; analyzing the video data using one or more machine learning models trained to detect passengers in passenger seats and passenger restraints of the passenger seats; detecting, using the one or more machine learning models and based on analyzing the video data, that the passenger is in the passenger seat and a passenger restraint of the passenger seat; determining, based on analyzing the video data, that the passenger restraint is not properly securing the passenger; and performing an action based on determining that the passenger restraint is not properly securing the passenger. ### Claim 2 (depends on 1) The method of claim 1, wherein the passenger restraint is a passenger seat belt, and wherein determining that the passenger restraint is not properly securing the passenger comprises: determining a length of the passenger seat belt that has been extended; and determining that the passenger restraint is not properly securing the passenger based on the length of the passenger seat belt that has been extended. ### Claim 3 (depends on 2) The method of claim 2, wherein determining that the passenger restraint is not properly securing the passenger comprises: determining the length of the passenger seat belt satisfies a length threshold; and determining that the passenger restraint is not properly securing the passenger based on the length of the passenger seat belt satisfies the length threshold. ### Claim 4 (depends on 1) The method of claim 1, wherein performing the action comprises at least one of: preventing movement of a motion base that includes the passenger seat or of a passenger vehicle that includes the passenger seat; and providing a notification that the passenger restraint is not properly securing the passenger. ### Claim 5 (depends on 1) The method of claim 1, further comprising: obtaining rotary data from a rotary encoder device associated with the passenger restraint, wherein the rotary data indicates a measured length of the passenger restraint; determining, based on analyzing the video data, a predicted length of the passenger restraint; comparing the measured length of the passenger restraint and the predicted length of the passenger restraint; and determining that the passenger restraint is not properly securing the passenger based on comparing the measured length of the passenger restraint and the predicted length of the passenger restraint. ### Claim 6 (depends on 1) The method of claim 1, wherein determining that the passenger restraint is not properly securing the passenger comprises: detecting, based on analyzing the video data, a visual indicator on the passenger restraint, wherein the visual indicator being detected indicates that the passenger restraint is not properly securing the passenger; and determining, based on analyzing the video data, that the passenger restraint is not properly securing the passenger. ### Claim 7 (depends on 1) The method of claim 1, further comprising: obtaining data from a sensor device associated with the passenger seat; determining a measure of accuracy of the data based on analyzing the video data; and providing a notification associated with the measure of accuracy of the data. ### Claim 8 A system, comprising: one or more camera devices configured to obtain video data of a passenger in a passenger seat of a passenger vehicle; and a restraint verification platform is configured to: obtain the video data; analyze the video data using one or more machine learning models trained to detect passengers in passenger seats and passenger restraints of the passenger seats; detect, using the one or more machine learning models and based on analyzing the video data, the passenger in the passenger seat and a passenger restraint of the passenger seat; determine, based on analyzing the video data, that the passenger restraint is not properly securing the passenger; and perform an action based on determining that the passenger restraint is not properly securing the passenger. ### Claim 9 (depends on 8) The system of claim 8, wherein the one or more camera devices include at least one of: a first camera device located onboard the passenger vehicle, or a second camera device located offboard the passenger vehicle. ### Claim 10 (depends on 8) The system of claim 8, wherein, to perform the action, the restraint verification platform is configured to: prevent movement of the passenger vehicle; or provide a notification that the passenger restraint is not properly securing the passenger. ### Claim 11 (depends on 8) The system of claim 8, wherein the passenger restraint is a passenger seat belt, and wherein, to determine that the passenger restraint is not properly securing the passenger, the restraint verification platform is configured to: determine a length of the passenger seat belt that has been extended; and determine that the passenger restraint is not properly securing the passenger based on the length of the passenger seat belt that has been extended. ### Claim 12 (depends on 11) The system of claim 11, wherein, to determine that the passenger restraint is not properly securing the passenger, the restraint verification platform is configured to: determine the length of the passenger seat belt satisfies a length threshold; and determine that the passenger restraint is not properly securing the passenger based on the length of the passenger seat belt satisfies the length threshold. ### Claim 13 (depends on 9) The system of claim 9, wherein the restraint verification platform is further configured to: obtain rotary data from a rotary encoder device associated with the passenger restraint, wherein the rotary data indicates a measured length of the passenger restraint; determine, based on analyzing the video data, a predicted length of the passenger restraint; compare the measured length of the passenger restraint and the predicted length of the passenger restraint; and determine that the passenger restraint is not properly securing the passenger based on comparing the measured length of the passenger restraint and the predicted length of the passenger restraint. ### Claim 14 (depends on 9) The system of claim 9, wherein, to determine that the passenger restraint is not properly securing the passenger, the restraint verification platform is configured to: detect, based on analyzing the video data, a visual indicator on the passenger restraint, wherein the visual indicator indicates that the passenger restraint is not properly securing the passenger; and determine, based on analyzing the video data, that the passenger restraint is not properly securing the passenger. ### Claim 15 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: obtain video data of a passenger in a passenger seat; analyze the video data using one or more machine learning models trained to detect passengers in passenger seats and passenger restraints of the passenger seats; detect, using the one or more machine learning models and based on analyzing the video data, the passenger in the passenger seat and a passenger restraint of the passenger seat; determine, based on analyzing the video data, that the passenger restraint is not properly securing the passenger; and perform an action based on determining that the passenger restraint is not properly securing the passenger. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the device to perform the action, cause the device to: provide a notification that the passenger restraint is not properly securing the passenger. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the passenger restraint is a passenger seat belt, and wherein the one or more instructions, that cause the device to determine that the passenger restraint is not properly securing the passenger, cause the device to: determine a length of the passenger seat belt that has been extended; and determine that the passenger restraint is not properly securing the passenger based on the length of the passenger seat belt that has been extended. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: train the one or more machine learning models with training data that includes historical video data of passengers onboard passenger vehicles or motion bases, wherein the video data identifies different types of passengers, wherein the video data identifies a first type of passengers that are properly secured by passenger restraints of the passenger vehicles or of the motion bases, and wherein the video data identifies a second type of passengers that are not properly secured by the passenger restraints of the passenger vehicles or of the motion bases. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: obtain data from a sensor device associated with the passenger seat; determine a measure of accuracy of the data based on analyzing the video data; and provide a notification associated with the measure of accuracy of the data. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein the one or more instructions further cause the device to: determine that the data, from the sensor device, does not correspond to the video data based on the measure of accuracy of the data based on analyzing the video data, wherein the notification indicates that the data, from the sensor device, does not correspond to the video data.