Abstract: An method for automatically panning a view for a commercial vehicle includes analyzing a portion of a first view at a first time to determine a position of a vehicle feature within the first view, wherein the first view is a subset of a second view, estimating an expected position of the vehicle feature in the first view at a second time subsequent to the first time, defining a region of interest centered on the expected position of the vehicle feature in the second view and analyzing the region of interest to determine an exact position of the vehicle feature at the second time, and determining a current trailer angle based on a position of the vehicle feature within the second view.

Abstract: An method for automatically panning a view for a commercial vehicle includes analyzing a portion of a first view at a first time to determine a position of a vehicle feature within the first view, wherein the first view is a subset of a second view, estimating an expected position of the vehicle feature in the first view at a second time subsequent to the first time, defining a region of interest centered on the expected position of the vehicle feature in the second view and analyzing the region of interest to determine an exact position of the vehicle feature at the second time, and determining a current trailer angle based on a position of the vehicle feature within the second view.

Abstract: A method for automatically panning a view for a commercial vehicle includes receiving a video feed from at least one camera defining a field of view. A plurality of objects in the video feed, includes at least one wheel and at least one line, are identified. A path of each object in the plurality of objects is tracked through an image plane of the video feed. A trailer angle corresponding to each path is identified, the identified trailer angle is associated with the corresponding path, thereby generating a plurality of trailer angle measurements. The plurality of paths are down selected to a single path and identifying a single trailer angle measurement corresponding to the single path.

Abstract: A method for determining a trailer detection parameter of a trailer including receiving an image from at least one camera at a controller. The at least one camera defines a field of view including at least a portion of a vehicle trailer. The method determines a trailer angle of the vehicle trailer relative to a tractor, identifies at least one feature in an image of the trailer, determines a two-dimensional distance from the at least one feature to a predefined position on the image, and converts the two-dimensional distance to a three-dimensional distance based at least in part on the determined angle. The three-dimensional distance is a trailer detection parameter of the trailer.

Abstract: An method for automatically panning a view for a commercial vehicle includes analyzing a portion of a first view at a first time to determine a position of a vehicle feature within the first view, wherein the first view is a subset of a second view, estimating an expected position of the vehicle feature in the first view at a second time subsequent to the first time, defining a region of interest centered on the expected position of the vehicle feature in the second view and analyzing the region of interest to determine an exact position of the vehicle feature at the second time, and determining a current trailer angle based on a position of the vehicle feature within the second view.

Abstract: A system and related method for monitoring an occupant within a vehicle using a plurality of convolutional neural networks includes a processor, a sensor having a field of view that includes at least a portion of the occupant, and a memory. The memory may include a feature map module, a key point head module, a part affinity field head module, and a seatbelt head module. The modules include instructions that cause the processor to generate a key point heat map indicating a probability that a pixel is a joint of a plurality of joints of the occupant, a part affinity field heat map indicating a pairwise relationship between at least two joints of the plurality of joints of the occupant, and a seatbelt heat map indicating a likelihood that a pixel of the input image is a seatbelt.