Abstract: Techniques for road scene primitive detection using a vehicle camera system are disclosed. In one example implementation, a computer-implemented method includes receiving, by a processing device having at least two parallel processing cores, at least one image from a camera associated with a vehicle on a road. The processing device generates a plurality of views from the at least one image that include a feature primitive. The feature primitive is indicative of a vehicle or other road scene entities of interest. Using each of the parallel processing cores, a set of primitives are identified from one or more of the plurality of views. The feature primitives are identified using one or more of machine learning and classic computer vision techniques. The processing device outputs, based on the plurality of views, result primitives based on the plurality of identified primitives from multiple views based on the plurality of identified entities.

Abstract: A method to equip a vehicle to perform object detection and tracking and a surround view camera system to perform the object detection and tracking involve two or more cameras arranged respectively at two or more locations of the vehicle. The cameras capture images within a field of view of the two or more cameras. A processing system obtains the images from the two or more cameras and performs image processing to detect and track objects in the field of view of the two or more cameras.

Abstract: A system and method for determining whether a driver of a host vehicle intends to make a left or right turn with a certain level of confidence. The method obtains a plurality of turning cues that identify external parameters around the host vehicle and/or define operating conditions of the host vehicle, and determines a confidence level that the host vehicle will make a left or right turn based on the turning cues, where determining the confidence level includes weighting each of the cues based on current vehicle operating conditions.

Abstract: A system and method for predicting whether a driver of a host vehicle or a remote vehicle intends to make a left or right turn or travel straight through an intersection before the host vehicle or remote vehicle reaches the intersection that relies on a probability model that employs a dynamic Bayesian network. The method includes obtaining a plurality of environmental cues that identify external parameters at or around the intersection, where the environmental cues include position and velocity of the remote vehicle, and obtaining a plurality of host vehicle cues that define operation of the host vehicle. The method then predicts the turning intent of the host vehicle and/or remote vehicle at the intersection using the model based on both the external cues and the vehicle cues using the model. The model can use learned information about previous driver turns at the intersection.