Abstract: A system, including a processor and a memory, the memory including instructions to be executed by the processor to determine camera calibration parameters including camera focal distance, camera height and camera tilt based on a two-dimensional calibration pattern located parallel to and coincident with a ground plane determined by a roadway surface and determine object data including object location, object speed and object direction for one or more objects in a field of view of the video camera.

Abstract: A sensor device includes a multi-part retainable shell, including an exterior outward facing wall and an interior wall shaped in accordance with a mounting element about which the shell is to be secured. The apparatus includes one or more processors provided to the hollow interior and one or more heat sinks provided on the outer wall, capable of carrying heat away from the hollow interior. The apparatus also includes a plurality of sensors provided to the outer wall to create a sensor field-of-view in a direction facing outward from the outer wall, the sensors each in communication with a processor. The parts of the shell are securable to each other in a manner that causes friction inducing material provided to the inner wall to substantially contact a mounting pole with sufficient force to prevent vertical slippage of the apparatus when the parts are secured to each other.

Abstract: Neural networks and learning algorithms can use a variance of gradients to provide a heuristic understanding of the model. The variance of gradients can be used in active learning techniques to train a neural network. Techniques include receiving a dataset with a vector. The dataset can be annotated and a loss calculated. The loss value can be used to update the neural network through backpropagation. An updated dataset can be used to calculate additional losses. The loss values can be added to a pool of gradients. A variance of gradients can be calculated from the pool of gradient vectors. The variance of gradients can be used to update a neural network.

Abstract: A system, including a processor and a memory, the memory including instructions to be executed by the processor to determine camera calibration parameters including camera focal distance, camera height and camera tilt based on a two-dimensional calibration pattern located parallel to and coincident with a ground plane determined by a roadway surface and determine object data including object location, object speed and object direction for one or more objects in a field of view of the video camera.