Abstract: A device may receive, from a first vehicle, video data for video captured of a location associated with an accident for a second vehicle, and may process the video data, with a first model, to generate a sparse point cloud of the location associated with the accident. The device may process the video data, with a second model, to generate depth maps for frames of the video data, and may utilize the depth maps with the sparse point cloud to generate a dense point cloud. The device may process the video data, with a third model, to generate a dense semantic point cloud, and may process the dense semantic point cloud, with a fourth model, to determine a dense semantic overhead view of the location associated with the accident. The device may perform actions based on the dense semantic overhead view.

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.

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.

Abstract: A method and system for identifying recurrent stops of a vehicle fleet having a plurality of vehicles. The method comprises retrieving historical GPS tracks of the vehicle fleet over a period of time; detecting stops made by the vehicle fleet along travelled routes that are associated with the historical GPS tracks; constructing a coverage area that covers the travelled routes; discretizing the coverage area into a plurality of cells; determining whether a cell is a recurrent stop based on a fleet stay period associated with that cell; and classifying a determined recurrent stop into a plurality of categories.

Abstract: A device may receive, from a first vehicle, video data for video captured of a location associated with an accident for a second vehicle, and may process the video data, with a first model, to generate a sparse point cloud of the location associated with the accident. The device may process the video data, with a second model, to generate depth maps for frames of the video data, and may utilize the depth maps with the sparse point cloud to generate a dense point cloud. The device may process the video data, with a third model, to generate a dense semantic point cloud, and may process the dense semantic point cloud, with a fourth model, to determine a dense semantic overhead view of the location associated with the accident. The device may perform actions based on the dense semantic overhead view.

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.

Abstract: A device may receive, from a first vehicle, video data for video captured of a location associated with an accident for a second vehicle, and may process the video data, with a first model, to generate a sparse point cloud of the location associated with the accident. The device may process the video data, with a second model, to generate depth maps for frames of the video data, and may utilize the depth maps with the sparse point cloud to generate a dense point cloud. The device may process the video data, with a third model, to generate a dense semantic point cloud, and may process the dense semantic point cloud, with a fourth model, to determine a dense semantic overhead view of the location associated with the accident. The device may perform actions based on the dense semantic overhead view.

Abstract: A method and system for classifying a vehicle based on low frequency GPS tracks. The method and system comprise retrieving a low frequency GPS track having a sampling interval of at least 20 seconds; deriving additional data from the low frequency GPS track, the additional data including interval speed and instantaneous acceleration of the vehicle; extracting a plurality of data sets from the low frequency GPS track and the additional data; generating a plurality of features from the extracted data sets; and providing the plurality of generated features to a classifier that classifies the vehicle into a predetermined class.

Abstract: A device may receive, from a first vehicle, video data for video captured of a location associated with an accident for a second vehicle, and may process the video data, with a first model, to generate a sparse point cloud of the location associated with the accident. The device may process the video data, with a second model, to generate depth maps for frames of the video data, and may utilize the depth maps with the sparse point cloud to generate a dense point cloud. The device may process the video data, with a third model, to generate a dense semantic point cloud, and may process the dense semantic point cloud, with a fourth model, to determine a dense semantic overhead view of the location associated with the accident. The device may perform actions based on the dense semantic overhead view.

Abstract: A method and system for classifying a vehicle based on low frequency GPS tracks. The method and system comprise retrieving a low frequency GPS track having a sampling interval of at least 20 seconds; deriving additional data from the low frequency GPS track, the additional data including interval speed and instantaneous acceleration of the vehicle; extracting a plurality of data sets from the low frequency GPS track and the additional data; generating a plurality of features from the extracted data sets; and providing the plurality of generated features to a classifier that classifies the vehicle into a predetermined class.

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.

Abstract: A device receives location information and work order information associated with multiple vehicles, and groups the location information into engine off information, idling information, and journey information. The device combines, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles, and matches corresponding work order information with the vehicle stop information to generate matched information. The device extracts stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information, and utilizes the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the multiple vehicles. The device provides information associated with the work order stops and the non-work order stops for the multiple vehicles.

Abstract: A method and system for identifying recurrent stops of a vehicle fleet having a plurality of vehicles. The method comprises retrieving historical GPS tracks of the vehicle fleet over a period of time; detecting stops made by the vehicle fleet along travelled routes that are associated with the historical GPS tracks; constructing a coverage area that covers the travelled routes; discretizing the coverage area into a plurality of cells; determining whether a cell is a recurrent stop based on a fleet stay period associated with that cell; and classifying a determined recurrent stop into a plurality of categories.

Abstract: A method and system for identifying recurrent stops of a vehicle fleet having a plurality of vehicles. The method comprises retrieving historical GPS tracks of the vehicle fleet over a period of time; detecting stops made by the vehicle fleet along travelled routes that are associated with the historical GPS tracks; constructing a coverage area that covers the travelled routes; discretizing the coverage area into a plurality of cells; determining whether a cell is a recurrent stop based on a fleet stay period associated with that cell; and classifying a determined recurrent stop into a plurality of categories.

Abstract: A device receives location information and work order information associated with multiple vehicles, and groups the location information into engine off information, idling information, and journey information. The device combines, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles, and matches corresponding work order information with the vehicle stop information to generate matched information. The device extracts stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information, and utilizes the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the multiple vehicles. The device provides information associated with the work order stops and the non-work order stops for the multiple vehicles.

Abstract: A system and method for optimizing traveled routes of a fleet. The method comprises reconstructing routes traveled by vehicles of the fleet based on historical GPS traces of the fleet; determining stops made by the vehicles along the traveled routes; and classifying the stops into work stops and non-work stops; and optimizing routes for the work stops.

Abstract: A device receives location information and work order information associated with multiple vehicles, and groups the location information into engine off information, idling information, and journey information. The device combines, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles, and matches corresponding work order information with the vehicle stop information to generate matched information. The device extracts stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information, and utilizes the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the multiple vehicles. The device provides information associated with the work order stops and the non-work order stops for the multiple vehicles.

Abstract: A device can obtain acceleration data and GPS location data. The GPS location data can include a plurality of GPS location data samples relating to vehicles. The acceleration data can include a plurality of acceleration data samples relating to one or more of the vehicles. The device can determine, using the plurality of acceleration data samples or the plurality of GPS location data samples, a potential wrong-way travel event associated with a vehicle, determine whether the vehicle is associated with an industry in which vehicles legitimately engage in wrong-way travel after determining the potential wrong-way travel event, and perform one or more actions to cause information regarding the potential wrong-way travel event to be provided to a user device based on determining the potential wrong-way travel event and determining whether the vehicle is associated with an industry in which vehicles legitimately engage in wrong-way travel.

Abstract: A device can receive message data associated with a vehicle tracking unit (VTU). The device can identify, based on the message data, the VTU as an inactive VTU. The device can compute a feature vector, associated with the VTU, based on the message data and on environmental data associated with the VTU. The feature vector can be computed based on identifying the VTU as an inactive VTU. The device can determine, using an inactivity classification model, an inactivity classification associated with the VTU. The inactivity classification can be determined based on providing the feature vector, associated with the VTU, as an input to the inactivity classification model. The device can cause an inactivity action to be performed based on the inactivity classification.

Abstract: A device can receive message data associated with a vehicle tracking unit (VTU). The device can identify, based on the message data, the VTU as an inactive VTU. The device can compute a feature vector, associated with the VTU, based on the message data and on environmental data associated with the VTU. The feature vector can be computed based on identifying the VTU as an inactive VTU. The device can determine, using an inactivity classification model, an inactivity classification associated with the VTU. The inactivity classification can be determined based on providing the feature vector, associated with the VTU, as an input to the inactivity classification model. The device can cause an inactivity action to be performed based on the inactivity classification.