Abstract: Systems and methods are provided for distributed video storage and search over edge computing devices having a short-term memory and a long-term memory. The method may comprise caching a first portion of data on a first device. The method may further comprise determining, at a second device, whether the first device has the first portion of data. The determining may be based on whether the first piece of data satisfies a specified criterion. The method may further comprise sending the data, or a portion of the data, and/or a representation of the data from the first device to a third device.

Abstract: Systems and methods for selectively transmitting alerts based on monitored behavior of a driver are disclosed. A system can calculate a driver score for a driver based on a set of driving events detected from sensor data captured while a vehicle was operated by the driver. Each of the set of driving events is associated with a driving behavior in a driving scenario. The driver score is further calculated based on historic driving event data. The system can assign the driver to a category of a number of categories based on the driver score. The system can determine that a change to a habitual driving behavior in a monitored driving scenario would result in reassignment of the driver to another category. The system can transmit an alert to the vehicle based upon a subsequent detection of a driving event that is associated with the monitored driving scenario.

Abstract: Systems and methods are provided for recording video of a driver in a vehicle and a surrounding visual field of the driver. The system includes a detachable body coupled to a windshield of a vehicle. The system further includes three or more cameras coupled to the detachable body. The three or more cameras are configured to capture surrounding views from the detachable body. One of the three or more cameras faces a driver seat of the vehicle in response to the detachable body being coupled to the windshield of the vehicle. The video may be processed by the system, the cloud, or a combination of them.

Abstract: Systems and methods are provided for determining cause of atypical traffic events and/or encouraging good driving behavior. The systems and methods may involve a camera sensor and/or inertial sensors to detect traffic events, as well analytical methods that may attribute a cause to the traffic event. The systems and methods include a processor that is configured to determine an occurrence of an atypical traffic event at or near a monitored vehicle; and determine a cause of the atypical traffic event based on data collected at the monitored vehicle, wherein the cause of the atypical traffic event is at least one of: a driver or control system of the monitored vehicle; a second driver or second control system of a second vehicle; and a road condition.

Abstract: Systems and methods are provided for distributed video storage and search with edge computing. The method may comprise caching a first portion of data on a first device. The method may further comprise determining, at a second device, whether the first device has the first portion of data. The determining may be based on whether the first piece of data satisfies a specified criterion. The method may further comprise sending the data, or a portion of the data, and/or a representation of the data from the first device to a third device.

Abstract: Disclosed herein are systems and methods for classifying traffic indicators to detect intersection crossings by a vehicle. A computing device can receive a sequence of frames captured by a capture device mounted to the vehicle, and generate an intersection status data structure for each frame in the sequence of frames using a full-frame classification model. The computing device can also classify a set of features detected in each frame using an object detection model, and detect an intersection crossing event based on the intersection status data structure of each frame and the classification of each of the set of features detected in each frame. The systems and methods described herein improve upon existing traffic light classification models by using a full-frame intersection classification model in connection with traditional object tracking techniques, thereby reducing false-positive crossing-event detection and improving the accuracy of classification in a variety of environmental conditions.

Abstract: Systems and methods are provided for embedded data inference. The systems and methods may process camera and other sensor data in by leveraging processing and storage capacity of one or more devices nearby or in the cloud to augment or update the sensor processing of an embedded device. The joint processing may be used in stationary cameras or in vehicular systems such as cars and drones, and may improve crop assessments, navigation, and safety.

Abstract: Disclosed herein are systems and methods for tracking objects to detect a potential collision with a vehicle. A computing device can receive a first frame and a second frame captured by a capture device mounted to the vehicle. The computing device can then identify first points of interest corresponding to an object identified in the first frame and second points of interest corresponding to the object identified in the second frame. The computing device can then generate a transformation matrix that specifies a transformation of the first points of interest to the second points of interest. The computing device can then determine, based on the transformation matrix, a score corresponding to a potential collision event, and transmit a collision signal to a collision alert device responsive to the score satisfying a potential collision event threshold.

Abstract: Systems and methods are provided for intelligent driving monitoring systems, advanced driver assistance systems and autonomous driving systems, and providing one-click driver image labeling to facilitate the assignment of drive time to a driver. Various aspects of the driver and/or passengers may be determined, which may include a driver identifier previously associated with the driver, whether the driver is wearing a facial covering, whether an image of the driver is partially occluded, whether the driver is facing in the direction of the camera, and whether an image of the driver is expected to be easily recognizable to a person tasked with assigning representative driver images to driver identifiers. These determinations may be used to improve the efficacy and ease-of-use of a visual login system.

Abstract: Systems and methods are provided for determining cause of atypical traffic events and/or encouraging good driving behavior. The systems and methods may involve a camera sensor and/or inertial sensors to detect traffic events, as well analytical methods that may attribute a cause to the traffic event. The systems and methods include a processor that is configured to determine an occurrence of an atypical traffic event at or near a monitored vehicle; and determine a cause of the atypical traffic event based on data collected at the monitored vehicle, wherein the cause of the atypical traffic event is at least one of: a driver or control system of the monitored vehicle; a second driver or second control system of a second vehicle; and a road condition.

Abstract: Systems and methods are provided for intelligent driving monitoring systems, advanced driver assistance systems and autonomous driving systems, and providing alerts to the driver of a vehicle, based on anomalies detected between driver behavior and environment captured by the outward facing camera. Various aspects of the driver, which may include his direction of sight, point of focus, posture, gaze, is determined by image processing of the upper visible body of the driver, by a driver facing camera in the vehicle. Other aspects of environment around the vehicle captured by the multitude of cameras in the vehicle are used to correlate driver behavior and actions with what is happening outside to detect and warn on anomalies, prevent accidents, provide feedback to the driver, and in general provide a safer driver experience.

Abstract: Disclosed herein are systems and methods for classifying traffic indicators to detect intersection crossings by a vehicle. A computing device can receive a sequence of frames captured by a capture device mounted to the vehicle, and generate an intersection status data structure for each frame in the sequence of frames using a full-frame classification model. The computing device can also classify a set of features detected in each frame using an object detection model, and detect an intersection crossing event based on the intersection status data structure of each frame and the classification of each of the set of features detected in each frame. The systems and methods described herein improve upon existing traffic light classification models by using a full-frame intersection classification model in connection with traditional object tracking techniques, thereby reducing false-positive crossing-event detection and improving the accuracy of classification in a variety of environmental conditions.

Abstract: Systems and methods are provided for distributed video storage and search with edge computing. The method may comprise caching a first portion of data on a first device. The method may further comprise determining, at a second device, whether the first device has the first portion of data. The determining may be based on whether the first piece of data satisfies a specified criterion. The method may further comprise sending the data, or a portion of the data, and/or a representation of the data from the first device to a third device.

Abstract: Systems and methods provide, implement, and use using a computer-vision based methods of context-sensitive monitoring and characterization of driver behavior. Additional systems and methods are provided for unsupervised learning of action values, monitoring of a driver's environment, and transmitting visual information from a client to a server.

Abstract: Systems and methods are provided for classifying one or more images of video data captured by a camera in a vehicle. The classification involves a detection of a traffic control device, such as a U-Turn sign, in image data. The classification further involves querying a database with a location of the vehicle from which the traffic control device was observed. In some embodiments, the database contains entries for various types of traffic control devices from a family of traffic control devices, where each type of traffic control device in the family has a similar visual appearance. The database query may therefore help disambiguate the visually perceived traffic control device at a particular location. Embodiments may be incorporated into navigation or driver safety systems.

Abstract: Methods and systems for joint processing for data inference in a vehicle-to-cloud communication system are provided. The method includes processing sensor data from a first sensor in a first vehicle using a first model at a first device, resulting in a first inference data. The first communication data derived from the first sensor data is sent to a cloud device, where it undergoes further processing using a second model to generate cloud inference data. Subsequently, the cloud communication data based on the cloud inference data is sent to a second device in a second vehicle from the cloud device.

Abstract: Systems and methods for curating video and other driving-related data for use in driver coaching, which may include selecting or ranking driving behaviors for coaching, selecting or ranking drivers for coaching, selecting or ranking video and other data to be used in coaching, preparing for, scheduling, and summarizing coaching sessions, matching the format of coaching to the behavior or person being coached, preventing unsafe driving situations, influencing job dispatch decisions based on safety scores, and/or reducing data bandwidth usage based on a determined coaching effectiveness of video data.

Abstract: Systems and methods are provided for intelligent driving monitoring systems, advanced driver assistance systems and autonomous driving systems, and providing one-click driver image labeling to facilitate the assignment of drive time to a driver. Various aspects of the driver and/or passengers may be determined, which may include a driver identifier previously associated with the driver, whether the driver is wearing a facial covering, whether an image of the driver is partially occluded, whether the driver is facing in the direction of the camera, and whether an image of the driver is expected to be easily recognizable to a person tasked with assigning representative driver images to driver identifiers. These determinations may be used to improve the efficacy and ease-of-use of a visual login system.

Abstract: Systems and methods for selectively transmitting alerts based on monitored behavior of a driver are disclosed. A system can calculate a driver score for a driver based on a set of driving events detected from sensor data captured while a vehicle was operated by the driver. Each of the set of driving events is associated with a driving behavior in a driving scenario. The driver score is further calculated based on historic driving event data. The system can assign the driver to a category of a number of categories based on the driver score. The system can determine that a change to a habitual driving behavior in a monitored driving scenario would result in reassignment of the driver to another category. The system can transmit an alert to the vehicle based upon a subsequent detection of a driving event that is associated with the monitored driving scenario.

Abstract: Disclosed herein are systems and methods for classifying traffic indicators to detect intersection crossings by a vehicle. A computing device can receive a sequence of frames captured by a capture device mounted to the vehicle, and generate an intersection status data structure for each frame in the sequence of frames using a full-frame classification model. The computing device can also classify a set of features detected in each frame using an object detection model, and detect an intersection crossing event based on the intersection status data structure of each frame and the classification of each of the set of features detected in each frame. The systems and methods described herein improve upon existing traffic light classification models by using a full-frame intersection classification model in connection with traditional object tracking techniques, thereby reducing false-positive crossing-event detection and improving the accuracy of classification in a variety of environmental conditions.