Abstract: An Internet of Things (IoT) or vehicle dash cam may store both a high-resolution and low-resolution video stream on a device. The video streams are selectively accessible by remote devices. Because of the relatively smaller storage requirements of low-resolution video files, retaining of additional video data on the vehicle device (beyond what would be possible with only high-resolution video) is possible. The user may be provided an option to adjust the amount of low-resolution and high-resolution video to store on the device. A combined media file may be generated by a device to include time-synced high-resolution video, low-resolution video, and/or metadata for a particular time period.

Abstract: A management server in communication with one or more object tracking devices is disclosed. The management server may receive location information, configuration information, and orientation information associated with the one or more object tracking devices. Based at least in part on the location information, the management server may receive weather information associated with the locations of the one or more object tracking devices. Based at least in part on the location information, the weather information, the configuration information, and the orientation information, the management server can determine power generated and power consumed by the one or more object tracking devices, which then can be used to determine estimated operation time for the one or more object tracking devices.

Abstract: An analytics reporting system to perform operations that include: aggregating sensor data collected from a plurality of sensor devices within a database, the sensor data comprising a set of values that correspond with a metric; generating a threshold value based on the set of values that correspond with the metric; accessing a portion of the sensor data based on an identifier associated with the portion of the sensor data; determining the portion of the sensor data transgresses the threshold value; and generating a report that comprises a display of the portion of the sensor data based on the determining that the portion of the sensor data transgresses the threshold value.

Abstract: A method performed by an asset tracking device is disclosed to track an asset. The method comprises receiving, while operating in an extended discontinuous reception mode, a carrier messaging service message from a carrier network, transmitting a connection request to a management server to establish a connection with the management server in response to receiving the carrier messaging service message, receiving, from the management server over the connection, an instruction to use a specified backend check-in schedule until a specified condition is met, and responsive to receiving the instruction, using the specified backend check-in schedule to check in with the management server until the specified condition is met. The method further comprises reverting back to using a default backend check-in schedule to check in with the management server after the specified condition has been met.

Abstract: Techniques are presented for detecting when drivers drive while drowsy. In some implementations, a drowsiness model is trained with data associated with inward videos and outward videos captured during a trip. The inward videos capture the inside of the cabin with the driver, and the outward videos capture the view in front of the vehicle in the direction of travel. Further, a device at the vehicle periodically calculates a drowsiness scale index value that indicates the level of drowsiness of the driver. Calculating the drowsiness scale index value includes obtaining a set of inward frames from the inward videos; for each inward frame, creating a face image by cropping the inward frame; obtaining a set of outward frames from the outward videos; calculating inward embeddings of the face images and outward embeddings of the outward frames; and calculating, by the drowsiness model, the drowsiness scale index value.

Abstract: Methods, systems, and programs are presented for detecting impaired views in monitoring cameras. One method includes training a rotation classifier with unsupervised learning utilizing a first set of images. The rotation classifier is configured to receive an input image and generate a rotation feature embedding for the input image. In addition, the method includes training an impairment classifier with supervised learning utilizing a second set of images, impairment labels for each of the second set of images, and the rotation feature embedding, generated by the rotation classifier, for each of the second set of images. The method further includes accessing a vehicle image captured by a camera on a vehicle, and providing the vehicle image to the impairment classifier as input, and the impairment classifier outputs a camera impairment from a set of camera impairment categories. Further, the vehicle image and the camera impairment are presented on a user interface.

Abstract: An intraocular assembly includes a sulcus fixation frame including at least one anterior haptic restraint member to which a posterior intraocular device receiving member is coupled by means of coupling members. The at least one anterior haptic restraint member includes a sulcus support portion, configured to be received in a sulcus of an eye, and haptic support portions, configured to block anterior movement of haptics of an intraocular device mounted in the sulcus fixation frame or fixate an IOL in the sulcus.

Abstract: An improved system and method of selectively transmitting asset data from one or more sensors associated with the vehicle to a backend server, which is configured to analyze the asset data and, if necessary for further analysis of the asset data (e.g., to determine whether a safety event has occurred) and/or to provide actionable data for review by a safety analyst, requests further asset data from a vehicle device.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for previewing assigned routes. A route management system provides for accessing a route tracking report associated with a vehicle to identify a plurality of routes associated with the vehicle; generating, for display, a graphical user interface (GUI) for navigating through the plurality of routes associated with the vehicle, the graphical user interface comprising a plurality of time period options; receiving input that selects a first time period option from the plurality of time period options; in response to receiving the input, retrieving a first set of routes from the plurality of routes that corresponds to the first time period option; and updating the GUI to display a first portion of the first set of routes in response to receiving the input.

Abstract: A system having a camera assembly and a communication coupling extending from the camera assembly is provided. The camera assembly can include a first enclosure having a first window and a second enclosure having a second window. The second enclosure can be opposite the first enclosure and couple with the first enclosure to form a cavity. The camera assembly can include a port disposed in one of the first enclosure and the second enclosure and a dual-facing camera disposed within the cavity. The dual facing camera can have a first camera facing a first direction and a second camera facing a second direction opposite the first direction. The first camera can align with the first window and the second camera can align with the second window when the dual-facing camera is disposed within the cavity. The communication coupling can couple with the dual-facing camera and extend through the port.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for a variable multiplexer for vehicle communication bus compatibility. A device includes a variable multiplexer that can be electronically configured to a desired pinout configuration to provide compatibility with multiple vehicles. For example, the variable multiplexer may be electronically configured based on a pinout configuration used by the vehicle to connect pins in the device to the corresponding pins on the data link connector that provide the same specified function. The device may therefore use a single standardized cable with vehicles using a variety of pinout configurations.

Abstract: Methods and systems for offload of data from a wireless sensing device to a gateway device. A certificate that is generated by the management server in response to a determination that the gateway device is associated with a wireless sensing device is received during an initial connection with the management server. In response to confirming, based on the certificate, that the gateway device is authorized to connect to the wireless sensing device, the certificate is transmitted to the wireless sensing device; and data is received from the wireless sensing device in response to confirming that the wireless sensing device is authorized to connect with the gateway device based on the certificate.

Abstract: A device orientation calibration system to perform operations that include: accessing inertial measurement unit (IMU) data generated by an IMU mounted upon an object that corresponds with a first reference frame, the IMU data indicating a second reference frame that comprises a Z-axis, a Y-axis, and an X-axis; performing a calibration of the IMU data to align the second reference frame of the IMU with the first reference frame of the object, the performing the calibration comprising: determining a gravitational vector based on a first portion of the IMU data; applying a first rotation to the IMU data to align the Z-axis of the second reference frame with the gravitational vector; determining a forward motion vector based on a second portion of the IMU data; and applying a second rotation to the IMU data to align the X-axis of the second reference frame with the forward motion vector.

Abstract: An event detection system to operations that include: detecting an event based on at least a portion of the sensor data, the event comprising a plurality of event attributes; determining one or more event attributes from the plurality of event attributes of the event transgress a threshold value; and causing display of a notification that includes a presentation of at least the portion of the sensor data in response to the determining that the one or more event attributes from among the plurality of event attributes of the event transgress the threshold value.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for vehicle rider behavioral monitoring. A behavioral monitoring system uses sensor data received from vehicles to monitor the behavior of the vehicle riders (e.g., vehicle operator and/or vehicle passengers) and performs predetermined actions if undesirable behavior is detected. For example, the behavioral monitoring system can transmit a notification or generate a record if inappropriate language or actions are detected.

Abstract: A management server in communication with one or more object tracking devices is disclosed. The management server may receive location information, configuration information, and orientation information associated with the one or more object tracking devices. Based at least in part on the location information, the management server may receive weather information associated with the locations of the one or more object tracking devices. Based at least in part on the location information, the weather information, the configuration information, and the orientation information, the management server can determine power generated and power consumed by the one or more object tracking devices, which then can be used to determine estimated operation time for the one or more object tracking devices.

Abstract: Methods for performing operations for improving driver safety across a fleet of vehicles are disclosed. A plurality of safety events pertaining to a driving of a fleet of vehicles by a plurality of drivers are detected. A subset of the events is identified. The subset corresponds to one or more safety events of the plurality of safety events involving one or more vehicles of the fleet of vehicles to which drivers have not been assigned. A user interface is generated for presentation on a client device, the user interface including an interactive user interface element for accessing the subset of the events. One or more user interface elements are provided for accepting or rejecting recommendations for assignments of one of the plurality of drivers to each of the vehicles. The recommendations are generated based on an application of a machine-learned model to images of faces captured.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for a device arrangement to derive unknown portions of a communication data scheme. A proxy node is established in a communication path between two nodes configured to transmit communications according to a communication bus standard. The communication data included in the communications transmitted between the nodes conforms to a communication data scheme. The proxy node logs communications transmitted between the nodes via the communication path, resulting in a communication log. The communication log can then be used to derive unknown portion of the communication data scheme, such as commands for requesting specified data types and the data format for transmitting data of specified data types.

Abstract: A vehicle device may execute one or more neural networks (and/or other artificial intelligence), based on input from one or more of the cameras and/or other sensors, to intelligently detect safety events in real-time. The one or more neural networks may be an ensemble neural network that includes neural networks for detecting a head and hand of a user, neural networks for detecting hand actions of the user, neural networks for detecting the head pose of the user, neural networks for predicting an occurrence of an event, and neural networks for predicting a start time and end time of the event. Further, the neural networks can be segmented into a modular neural network based on metadata. The segmentation of the neural network can define a thin layer of the modular neural network to enable independent tuning of the thin layer of the modular neural network.

Abstract: One or more video gateway devices configured to: access pre-configured criteria including at least a first condition, a second condition, and a first event; access video content captured by cameras configured to capture video of areas of a manufacturing facility; determine, based on an analysis of the video content, that the first condition is satisfied; access sensor data from one or more sensors; determine, based on an analysis of the sensor data, that the second condition is satisfied; and based on determining that the first and second conditions are satisfied, cause the first event to be executed.