Verizon Connect Development Limited

Verizon Connect Ireland Limited

Verizon Patent and Licensing Inc.

Verizon Connect Telo Inc.

Verizon Connect Development Limted

Francesco Sambo

Leonardo Taccari

Luca Bravi

Matteo Simoncini

Samuele Salti

Leonardo Sarti

Douglas Coimbra De Andrade

Alessandro Lori

Stefano Caprasecca

Fabio Schoen

Tommaso Bianconcini

Andrea Benericetti

Luca Kubin

Aurel Pjetri

Jason Mathew Koch

Peter Mitchell

Tommaso Mugnai

Marco Boschi

Nicola Tommasi

Valerio Arena

Simone Magistri

Luca De Luigi

Vidhya Seran

Jerry Gamble, Jr

Luca Noce

Enrico Civitelli

Alex Quintero Garcia

Niccolo Bellaccini

Tomaso Trinci

Andrea Giannoni

S M Murtoza Habib

Francesca Chiti

David Leonardo Spain Contini

John Molamphy

Yaoyang Qian

Wan Luo

Andrew Harbourne-Thomas

A device may receive video data that includes a plurality of video frames, and may utilize a scheduling policy to divide the plurality of video frames into a first set of video frames and a second set of video frames. The device may process the first set of video frames, with a first convolutional neural network (CNN) model that includes one or more saliency gates, to generate first predictions and saliency maps, and may generate a trained first CNN model based on the first predictions and the saliency maps. The device may process the second set of video frames and the saliency maps, with a second CNN model that includes a saliency propagation module, to generate second predictions, and may generate a trained second CNN model based on the second predictions. The device may perform actions based on the trained first CNN model and the trained second CNN model.

Systems and methods for reducing power consumption of executing learning models in vehicle systems

A device may receive video data and corresponding GPS data and IMU data associated with a vehicle, and may process the video data, with an object detector model, to identify objects and to generate a first feature vector. The device may process the GPS data and the IMU data, with a first CNN model, to generate a second feature vector, and may process the objects and the video data, with a tracking model, to identify positions and classes of the objects and to generate a third feature vector. The device may utilize a second CNN model to generate a matrix of object features based on the first, second, and third feature vectors, and may utilize a spatiotemporal attention selector model or a max pooled model with the matrix of object features to identify a classification of a maneuver of the vehicle. The device may perform actions based on the classification.

Systems and methods for classifying a vehicle maneuver using a spatiotemporal attention selector

In some implementations, a video system may capture, from a camera mounted to a vehicle, a video of a portion of a road on which the vehicle is traveling. The video system may detect, in the video, a driving lane associated with the road on which the vehicle is traveling. The video system may detect, in the video, multiple other vehicles within the driving lane. The video system may determine, for each of the multiple other vehicles within the driving lane, a bounding box that substantially surrounds an image of the other vehicle, resulting in a plurality of bounding boxes. The video system may determine a region in the video corresponding to an area to be driven by the vehicle based on the plurality of bounding boxes.

Systems and methods for detecting a driving area in a video

A device may receive a plurality of narratives associated with a plurality of scenes and an image identifying a scene not included in the plurality of scenes, and may process the image, with a classifier model, to detect a plurality of features in the image. The device may replace keywords in the plurality of narratives, with tags, to generate a plurality of sentences, and may group similar sentences of the plurality of sentences, based on a defined measure of dissimilarity, into clusters of templates. The device may select a candidate template from each of the clusters to generate a set of candidate templates, and may select a template from the set of candidate templates. The device may populate tags of the template with the plurality of features detected in the image to generate an image caption, and may provide the image and the image caption for display.

Systems and methods for utilizing a neural network model and templates to generate an image caption

A device may receive video data and corresponding GPS data and IMU data associated with a vehicle, and may remove video frames from the video data to generate modified video data. The device may select objects and image regions of video frames of the modified video data, and may determine a current speed and a current turn angle of the vehicle based on the GPS data, the IMU data, and the modified video data. The device may mask the objects of the video frames of the modified video data to learn first features, and may mask the image regions of the video frames of the modified video data to learn second features. The device may generate a trained neural network model based on the current speed, the current turn angle, the first features, and the second features, and may implement the trained neural network model in the vehicle.

Systems and methods for training a driving agent based on real-world driving data

A device may obtain video data associated with a driving event involving a first vehicle. The device may determine a vanishing point associated with the video data and may construct a cone of impact of the first vehicle based on the vanishing point. The device may detect a second vehicle within the cone of impact and may analyze the subset of video frames to determine a distance between the first vehicle and the second vehicle. The device may determine a speed of the first vehicle during a time period associated with a subset of video frames. The device may determine a headway score, representative of a severity associated with the first vehicle being within a proximity threshold of the second vehicle during the time period, based on the distance and the speed. The device may determine an occurrence of a tailgating event based on the headway score.

Systems and methods for detecting vehicle tailgating

A device may receive driver facing video data associated with a driver of a vehicle and forward facing video data associated with the vehicle, and may process the driver facing video data, with a face model, to identify driver head orientation and driver gaze. The device may generate a first transformation matrix mapping the driver facing video data, the driver head orientation, and the driver gaze, and may generate a second transformation matrix mapping the driver facing video data and the forward facing video data. The device may utilize the first transformation matrix and the second transformation matrix to estimate image coordinates, and may aggregate the image coordinates to generate aggregated coordinates. The device may generate heat maps based on the aggregated coordinates, may train machine learning model, with the heat maps, to generate a trained machine learning model, and may perform actions based on the trained machine learning model.

Systems and methods for determining road object importance based on forward facing and driver facing video data

A system may determine, for each frame of a plurality of frames of image data associated with a vehicle, a probability that each frame of the plurality of frames that includes an image of a stop sign is relevant to the vehicle. The system may determine a longest sequence of consecutive frames of the plurality of frames for which the probability satisfies a probability threshold. The system may determine a maximum probability associated with a frame included in the longest sequence of consecutive frames. The system may determine a time window based on a time associated with the frame associated with the maximum probability. The system may determine location data and sensor data for the vehicle based on the time window. The system may determine an occurrence of a stop sign violation based on the location data and the sensor data.

System for automatic stop sign violation identification

A device may process the video data, with a first machine learning model, to identify a driver of a vehicle and may process the video data associated with the driver, with a second machine learning model, to detect behavior data identifying a behavior of the driver. The device may process the behavior data, with a third machine learning model, to determine distraction data identifying whether the behavior is classified as a distracted behavior. The device may process the behavior data, with a fourth machine learning model, to determine policy compliance data identifying whether the behavior satisfies one or more policies. The device may calculate a distraction score based on the distraction data and the video data, and may calculate a policy compliance score based on the policy compliance data and vehicle data. The device may perform one or more actions based on the distraction score and the policy compliance score.

Systems and methods for identifying distracted driver behavior from video

In some implementations, an adverse environment detection system may receive an image of a road scene associated with a vehicle. The adverse environment detection system may determine a set of features associated with the image based on providing the image to an initial portion of a model. The adverse environment detection system may determine a first condition associated with the image based on providing the set of features to a first processing layer of the model, a second condition associated with the image based on providing the set of features to a second processing layer of the model, and a third condition associated with the image based on providing the set of features to a third processing layer of the model. The first processing layer, the second processing layer, and the third processing layer may process the set of features in parallel.

Systems and methods for utilizing machine learning for vehicle detection of adverse conditions

A device can receive a request for a schedule that assigns a fleet of vehicles to a set of deliveries. The device can determine that a parameter is not included in the request that is needed to generate a new schedule or that is needed to generate an existing schedule. The device can obtain the parameter using a historical user request, a historical schedule, or a scheduling template. The device can generate or obtain the schedule based on information included in the request and the obtained parameter. The device can provide the schedule to a user device and/or to one or more devices associated with the fleet of vehicles carrying out the set of deliveries. The device can modify the schedule based on a trigger. The device can provide the modified schedule to the user device and/or to the one or more devices associated with the fleet of vehicles.

Scheduling and management of deliveries via a virtual agent

In some implementations, a device may receive video data associated with video frames that depict an environment of a vehicle. The device may identify an object depicted in the video frames, wherein an object detection model indicates bounding boxes associated with the object. The device may determine, based on the bounding boxes, a configuration of the bounding boxes within the video frames. The device may determine, based on the configuration of the bounding boxes, that the object is a vulnerable road user (VRU) that is in the environment. The device may determine a trajectory of the VRU based on a change in the configuration between video frames of a set of the video frames. The device may determine, based on the trajectory, a probability of a collision between the VRU and the vehicle. The device may perform, based on the probability, an action associated with the vehicle.

Systems and methods for detecting a vulnerable road user in an environment of a vehicle

A device may receive a first image. The device may process the first image to identify an object in the first image and a location of the object within the first image. The device may extract a second image from the first image based on the location of the object within the first image. The device may process the second image to determine at least one of a coarse-grained viewpoint estimate or a fine-grained viewpoint estimate associated with the object. The device may determine an object viewpoint associated with the second vehicle based on the at least one of the coarse-grained viewpoint estimate or the fine-grained viewpoint estimate. The device may perform one or more actions based on the object viewpoint.

Systems and methods for utilizing a deep learning model to determine vehicle viewpoint estimations

A violation detection platform may obtain image data, location data, and sensor data associated with a vehicle. The violation detection platform may determine a probability that a frame of the image data includes an image of a stop sign. The violation detection platform may determine that the probability satisfies a probability threshold. The violation detection platform may identify location data and sensor data associated with the frame of the image data based on the probability satisfying the probability threshold. The violation detection platform may determine an occurrence of a type of a stop sign violation based on the probability, the location data, and the sensor data. The violation detection platform may perform one or more actions based on determining the occurrence of the type of the stop sign violation.

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.

Growing community of inventors

Padua, Italy

Francesco Sambo