Abstract: The disclosed systems and techniques are directed to computationally efficient detection and tracking of objects in driving environments. The techniques include generating a set of auto-labeled training data using a first autonomous vehicle (AV) system having multiple sensor modalities. The auto-labeled training data includes a first set of non-lidar data associated with the first AV system, and one or more target predictions for the first set of non-lidar data, said predictions generated based at least on lidar data associated with the first AV system. The techniques further include training, by the processing device and using the auto-labeled training data, an end-to-end perception model of a second AV system lacking a lidar sensor to predict presence of one or more objects in a driving environment of the second AV system.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps for receiving an image comprising a first image object and a second image object, processing the image to place a bounding box around the first image object and the second image object, and processing an image area within the bounding box to identify a first image mask corresponding with a first pixel region of the first image object and a second image mask corresponding with a second pixel region of the second image object. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps for receiving an image comprising a first image object and a second image object, processing the image to place a bounding box around the first image object and the second image object, and processing an image area within the bounding box to identify a first image mask corresponding with a first pixel region of the first image object and a second image mask corresponding with a second pixel region of the second image object. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps receiving an image data comprising an image object comprised of a plurality of image pixels, calculating a number of image pixels corresponding with the image object, receiving Light Detection and Ranging (LiDAR) point cloud data comprising a plurality of LiDAR data points corresponding with the image data collected from the camera sensor, and calculating a number of LiDAR data points corresponding with the image object. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps receiving an image data comprising an image object comprised of a plurality of image pixels, calculating a number of image pixels corresponding with the image object, receiving Light Detection and Ranging (LiDAR) point cloud data comprising a plurality of LiDAR data points corresponding with the image data collected from the camera sensor, and calculating a number of LiDAR data points corresponding with the image object. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for selecting points of an image for processing with LiDAR data. A process of the disclosed technology can include steps for receiving an image comprising a first image object and a second image object, processing the image to place a bounding box around the first image object and the second image object, and processing an image area within the bounding box to identify a first image mask corresponding with a first pixel region of the first image object and a second image mask corresponding with a second pixel region of the second image object. Systems and machine-readable media are also provided.

Abstract: A fast response, upright sprinkler head includes a body having a central orifice through which fire extinguishing fluid is expelled through an outlet end. A yoke, attached to the exterior surface of the sprinkler body, extends beyond the outlet end of the sprinkler body and is connected at its apex to a deflector. A fusible trigger assembly is coupled to the yoke and the outlet end of the sprinkler head. The deflector is formed with a planar member having a skirt depending therefrom and an annular ledge extending horizontally from the skirt. The skirt depends from the planar member in an outward direction at a pre-selected angle from the vertical, and is formed with a plurality of through-holes. The fast response upright sprinkler head is configured to have a K value of at least 13.5, while the fusible trigger assembly has a fusing temperature between approximately 155° F. and 175° F.