Abstract: A vehicle dash cam may be configured to execute one or more neural networks (and/or other artificial intelligence), such as based on input from one or more of the cameras and/or other sensors associated with the dash cam, to intelligently detect safety events in real-time. Detection of a safety event may trigger an in-cab alert to make the driver aware of the safety risk. The dash cam may include logic for determining which asset data to transmit to a backend server in response to detection of a safety event, as well as which asset data to transmit to the backend server in response to analysis of sensor data that did not trigger a safety event. The asset data transmitted to the backend server may be further analyzed to determine if further alerts should be provided to the driver and/or to a safety manager.

Abstract: A vehicle dash cam may be configured to execute one or more neural networks (and/or other artificial intelligence), such as based on input from one or more of the cameras and/or other sensors associated with the dash cam, to intelligently detect safety events in real-time. Detection of a safety event may trigger an in-cab alert to make the driver aware of the safety risk. The dash cam may include logic for determining which asset data to transmit to a backend server in response to detection of a safety event, as well as which asset data to transmit to the backend server in response to analysis of sensor data that did not trigger a safety event. The asset data transmitted to the backend server may be further analyzed to determine if further alerts should be provided to the driver and/or to a safety manager.

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 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: A map-based notification system configured to perform operations that include: accessing a base-map that comprises a map-tile, the map-tile defining a speed limit of a location; receiving vehicle data that includes speed data; determining that the speed data from the vehicle data transgresses the speed limit associated with the location defined by the map-tile; and causing display of a notification in response to determining that the speed data from the vehicle data transgresses the speed limit associated with the location defined by the map-tile.

Abstract: A baseline event detection system to detect events by performing operations that include: generating a baseline data set; accessing a data stream; performing a comparison of the baseline data set and the data stream; and detecting an event based on the comparison.

Abstract: Methods for performing improving facial recognition of a driver in a vehicle are disclosed. A set of images is received. Each of the set of images includes a portion that is identified as a face. The identification is based on an application of a first machine-learned model to each of the set of images. The application of the first machine-learned model is performed by an application associated with a client camera device mounted in a vehicle. Based on a determination that the set of images matches one or more reference images stored in a database with a confidence level that is equal to or greater than a confidence threshold, a person corresponding to the one or more reference images is associated as a driver of the vehicle during a time period in which the set of images was captured.

Abstract: A system receives operations data and determines operations indicator(s) from the operations data. An operator on a manufacturing line reports a downtime event via a human machine interface device. The system receives downtime event and uptime information. The system calculates an operations indicator, such as an overall equipment effectiveness indicator, from the downtime event and uptime information. A user interface of the system includes the operations indicator(s) and visualizations. Some visualizations include a timeline indicating downtime events and other operations events. Additional downtime and uptime information is received by the system in substantially real-time. The system dynamically calculates updated operations indicator(s) from the additional downtime and uptime information.

Abstract: A vehicle dash cam may be configured to execute one or more neural networks (and/or other artificial intelligence), such as based on input from one or more of the cameras and/or other sensors associated with the dash cam, to intelligently detect safety events in real-time. Detection of a safety event may trigger an in-cab alert to make the driver aware of the safety risk. The dash cam may include logic for determining which asset data to transmit to a backend server in response to detection of a safety event, as well as which asset data to transmit to the backend server in response to analysis of sensor data that did not trigger a safety event. The asset data transmitted to the backend server may be further analyzed to determine if further alerts should be provided to the driver and/or to a safety manager.

Abstract: A video gateway device at a worksite (or other location) is coupled to multiple cameras on a network, such as multiple cameras at a business site. The gateway device determines video stream capabilities of each camera and, based on the capabilities, determines whether any additional video steams need to be created for particular cameras. For example, for cameras that provide only a high-resolution video stream, the gateway will generate (e.g., via downsampling) a standard-resolution video stream for artificial intelligence (“AI”) analysis and a low-resolution video stream for viewing by a user. However, for cameras that provide both a high and standard-resolution video stream, the gateway device uses the camera-provided standard-resolution video stream for AI analysis, rather than generating a new video stream on the gateway device.

Abstract: An improved system and method of determining presence of stop signs at intersection based on multiple types of data including ground truth data, telemetry data, and/or trip stills gathered from vehicle devices. The data may be analyzed and aggregated by one or more models and/or neural networks to develop a prediction regarding presence of stop signs at individual intersections.

Abstract: A vehicle dash cam may be configured to execute one or more neural networks (and/or other artificial intelligence), such as based on input from one or more of the cameras and/or other sensors associated with the dash cam, to intelligently detect safety events in real-time. Detection of a safety event may trigger an in-cab alert to make the driver aware of the safety risk. The dash cam may include logic for determining which asset data to transmit to a backend server in response to detection of a safety event, as well as which asset data to transmit to the backend server in response to analysis of sensor data that did not trigger a safety event. The asset data transmitted to the backend server may be further analyzed to determine if further alerts should be provided to the driver and/or to a safety manager.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for configuration of optical sensor devices in vehicles based on thermal data. To manage the temperature of an optical sensor device, temperature data describing the current temperature of the optical sensor is used to determine whether the current temperature meets or exceeds a predetermined threshold temperature. If the current temperature meets or exceeds the threshold temperature, the optical sensor device may be configured into a modified operating mode to reduce the current temperature of the optical sensor device. For example, the operating mode of the optical sensor device may be modified to terminate one or more processes, reduce a frame rate at which image/video data is captured, and the like.

Abstract: A video gateway device at a worksite (or other location) automatically locates cameras on the network, authenticates the gateway device with the cameras, and initiates streaming of a video stream (and/or other camera sensor data) from the cameras. For example, a worksite with existing cameras from multiple manufacturers, models, and/or capabilities may all be automatically registered with the video gateway devices through a series of automated communication and authentication attempts.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for configuration of optical sensor devices in vehicles based on thermal data. To manage the temperature of an optical sensor device, temperature data describing the current temperature of the optical sensor is used to determine whether the current temperature meets or exceeds a predetermined threshold temperature. If the current temperature meets or exceeds the threshold temperature, the optical sensor device may be configured into a modified operating mode to reduce the current temperature of the optical sensor device. For example, the operating mode of the optical sensor device may be modified to terminate one or more processes, reduce a frame rate at which image/video data is captured, and the like.

Abstract: Methods for performing improving facial recognition of a driver in a vehicle are disclosed. A set of images is received. Each of the set of images includes a portion that is identified as a face. The identification is based on an application of a first machine-learned model to each of the set of images. The application of the first machine-learned model is performed by an application associated with a client camera device mounted in a vehicle. Based on a determination that the set of images matches one or more reference images stored in a database with a confidence level that is equal to or greater than a confidence threshold, a person corresponding to the one or more reference images is associated as a driver of the vehicle during a time period in which the set of images was captured.

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 map-based notification system configured to perform operations that include: accessing a base-map that comprises a map-tile, the map-tile defining a speed limit of a location; receiving vehicle data that includes speed data; determining that the speed data from the vehicle data transgresses the speed limit associated with the location defined by the map-tile; and causing display of a notification in response to determining that the speed data from the vehicle data transgresses the speed limit associated with the location defined by the map-tile.

Abstract: Methods for performing improving facial recognition of a driver in a vehicle are disclosed. A set of images is received. Each of the set of images includes a portion that is identified as a face. The identification is based on an application of a first machine-learned model to each of the set of images. The application of the first machine-learned model is performed by an application associated with a client camera device mounted in a vehicle. Based on a determination that the set of images matches one or more reference images stored in a database with a confidence level that is equal to or greater than a confidence threshold, a person corresponding to the one or more reference images is associated as a driver of the vehicle during a time period in which the set of images was captured.