# US 11,440,555 B2 · Systems and methods for detecting and classifying an unsafe maneuver of a vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,440,555 B2 - Document ID: US11440555B2 - Status: Granted - Kind: B2 - Application number: 16/947,918 - Filed: 2020-08-24 - Published: 2021-11-18 - Granted: 2022-09-13 - Earliest claimed: 2020-05-18 - Assignees: Verizon Connect Development Limited - Applicants: Verizon Connect Development Limited - Inventors: Matteo Simoncini; Douglas Coimbra De Andrade; Samuele Salti; Leonardo Taccari; Fabio Schoen; Francesco Sambo; Leonardo Sarti - Web page: https://patentgrep.com/patent/US11440555B2 ## CPC - B60W 40/09: Driving style or behaviour - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06F 21/35: communicating wirelessly - G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road} - G07C 5/008: {communicating information to a remotely located station (transmission systems for measured values G08C)} - G07C 5/0891: {Video recorder in combination with video camera} - G08G 1/20: {Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles} - B60W 2540/30: Driving style - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) ## Abstract A maneuver classification platform may obtain video data and telematic data that are associated with a driving event involving a vehicle. The maneuver classification platform may analyze the video data to identify a path of the vehicle along a roadway during the driving event, and based on markings of a plurality of roadways. The maneuver classification platform may analyze the video data to determine a type of a vehicle maneuver performed by the vehicle during the driving event. The maneuver classification platform may determine a maneuver score of the driving event based on the type of the vehicle maneuver, the path of the vehicle, and the telematic data. The maneuver classification platform may send a message associated with the maneuver score and a vehicle identifier of the vehicle to a client device to permit the client device to use the maneuver score. ## Claims ### Claim 1 A method, comprising: obtaining, by a device, video data and telematic data that are associated with a driving event involving a vehicle; analyzing, by the device, the video data to identify a path of the vehicle along a roadway during the driving event based on markings of a plurality of roadways; analyzing, by the device, the video data to determine a type of a vehicle maneuver performed by the vehicle during the driving event, wherein the type of the vehicle maneuver indicates whether the vehicle maneuver was performed by the vehicle in association with an obstruction depicted in the video data; determining, by the device, a maneuver score of the driving event based on the type of the vehicle maneuver, the path of the vehicle, and the telematic data, wherein the maneuver score is representative of a level of safety associated with the vehicle maneuver, and wherein determining the maneuver score comprises: determining, from the type of the vehicle maneuver, that the obstruction is depicted in the video data, and determining the maneuver score based on at least one of: a type of the obstruction depicted in the video, a probability that the vehicle maneuver was performed to avoid the obstruction, or a probability that a different vehicle maneuver would have avoided the obstruction; and sending, by the device, a message associated with the maneuver score and a vehicle identifier of the vehicle to a client device to permit the client device to use the maneuver score. ### Claim 2 (depends on 1) The method of claim 1, wherein at least one of: the telematic data, the video data, a user input to a user interface, or sensor data from another device indicates a harsh driving event that triggers acquisition of the video data and the telematic data, wherein the vehicle maneuver is associated with the harsh driving event. ### Claim 3 (depends on 1) The method of claim 1, wherein the telematic data indicates that the vehicle maneuver triggered the driving event. ### Claim 4 (depends on 1) The method of claim 1, wherein determining the maneuver score comprises: determining, based on movement of the obstruction relative to the roadway, that the vehicle maneuver was performed to avoid the obstruction; determining, based on the movement of the obstruction and the telematic data, the probability that the different vehicle maneuver would have avoided the obstruction; and determining the maneuver score based on the probability. ### Claim 5 (depends on 1) The method of claim 1, wherein determining the maneuver score comprises: determining, from the type of the vehicle maneuver, that another obstruction is not depicted in the video data; and generating the maneuver score to represent that the vehicle maneuver did not satisfy a threshold level of safety. ### Claim 6 (depends on 1) The method of claim 1, wherein the client device is one of a plurality of client devices, the method further comprising: prior to sending the message, identifying the vehicle identifier based on an identifier associated with the video data or the telematic data; and selecting, based on the vehicle identifier being mapped to the client device, the client device from the plurality of client devices, wherein the message is sent to the client device based on selecting the client device. ### Claim 7 A device, comprising: one or more processors configured to: receive information associated with a driving event involving a vehicle, wherein the information includes a vehicle identifier of the vehicle; obtain, based on the information, video data and telematic data that are associated with the driving event; analyze the video data to identify a path of the vehicle along a roadway during the driving event; determine a maneuver score, of a vehicle maneuver performed during the driving event, based on the path of the vehicle, the telematic data, and obstruction information associated with the video data, and wherein the obstruction information indicates whether an obstruction triggered the vehicle maneuver, and wherein the one or more processors, to determine the maneuver score, are to: determine, from a type of the vehicle maneuver, that the obstruction is depicted in the video data, and determine the maneuver score based on at least one of: a type of the obstruction depicted in the video, a probability that the vehicle maneuver was performed to avoid the obstruction, or a probability that a different vehicle maneuver would have avoided the obstruction; store, in a data structure, the maneuver score in association with the vehicle identifier; and provide, to a client device, an indication that the maneuver score is stored in the data structure in association with the vehicle identifier. ### Claim 8 (depends on 7) The device of claim 7, wherein the one or more processors, when determining the maneuver score, are configured to: determine the maneuver score based on a timestamp of the vehicle maneuver according to the telematic data and a timestamp of the obstruction being depicted nearest the vehicle in the video data. ### Claim 9 (depends on 7) The device of claim 7, wherein the one or more processors, when determining the maneuver score, are configured to: determine, based on movement of the obstruction relative to the roadway, that the vehicle maneuver was performed to avoid the obstruction; determine, based on the movement and the telematic data, the probability that the different vehicle maneuver would have avoided the obstruction; and determine the maneuver score based on the probability. ### Claim 10 (depends on 7) The device of claim 7, wherein the one or more processors, when determining the maneuver score, are configured to: determine that another obstruction is not depicted in the video data; and generate the maneuver score to represent that the vehicle maneuver did not satisfy a safety threshold. ### Claim 11 (depends on 7) The device of claim 7, wherein the vehicle is one of a plurality of vehicles of a fleet and the client device is associated with managing the fleet, and wherein the data structure includes a plurality of maneuver scores that are associated with the plurality of vehicles. ### Claim 12 (depends on 7) The device of claim 7, wherein the one or more processors are further configured to: send, to the client device, a request for an authentication of the maneuver score; receive, from the client device, a response associated with the authentication; and retrain a vehicle maneuver classification model associated with determining maneuver scores based on the response. ### Claim 13 (depends on 7) The device of claim 7, wherein the video data and the telematic data were obtained, from a storage device, via a link associated with the storage device, and wherein the indication is provided in association with the link to permit the client device to access the video data and the telematic data. ### Claim 14 A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by one or more processors, cause the one or more processors to: receive video data and telematic data that are associated with a driving event involving a vehicle, wherein the telematic data indicates that the driving event included a harsh driving event; analyze the video data to identify a path of the vehicle along a roadway during the driving event; determine a maneuver score of the driving event based on the path of the vehicle and a subset of the telematic data that is associated with the harsh driving event, and wherein the maneuver score is associated with a vehicle maneuver performed by the vehicle during the driving event; and perform an action associated with the maneuver score and a vehicle identifier of the vehicle, wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to: identify the vehicle identifier based on an identifier that is associated with the video data or the telematic data, and select, based on the vehicle identifier, a client device from a plurality of client devices, wherein a message is sent to the client device based on selecting the client device. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the maneuver score is representative of a level of safety associated with the vehicle maneuver. ### Claim 16 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to: identify the vehicle identifier based on an identifier that is associated with the video data or the telematic data; store, in a data structure, the maneuver score in association with the vehicle identifier; and send, to the client device, the message to indicate that the maneuver score is stored in the data structure in association with the vehicle identifier. ### Claim 17 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to: send, to the client device, a request for an authentication of the maneuver score; receive, from the client device, a response associated with the authentication; and retrain a vehicle maneuver classification model associated with determining maneuver scores based on the response. ### Claim 18 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the video data and the telematic data are obtained from a storage device based on receiving, from a vehicle monitoring system of the vehicle, a link to the storage device, and wherein the one or more instructions, that cause the one or more processors to perform the action, cause the one or more processors to: provide, to the client device, the maneuver score, the vehicle identifier, and the link to permit the client device to access the video data and the telematic data. ### Claim 19 (depends on 1) the method of claim 1, further comprising sending, to the client device, a request for an authentication of the maneuver score; receiving, from the client device, a response associated with the authentication; and retraining a vehicle maneuver classification model associated with determining maneuver scores based on the response. ### Claim 20 (depends on 14) The non-transitory computer-readable medium of claim 14, wherein the one or more instructions, cause the one or more processors to determine the maneuver score, cause the one or more processors to: determine, from a type of the vehicle maneuver, that an obstruction is depicted in the video data; and determine the maneuver score based on at least one of: a type of the obstruction depicted in the video, a probability that the vehicle maneuver was performed to avoid the obstruction, or a probability that a different vehicle maneuver would have avoided the obstruction.