Abstract:
A method of lane marker detection and detection fitting is provided for lane tracking. A lane marker is modeled and split into left and right steps. A filter response is calculated from a cumulative row sum, and normalized for filter pixel size, lane marker brightness and road brightness. A lane marker response is peak detected for positive and negative peaks and checked for having a magnitude above a threshold and being a local peak in a five point neighborhood. A Hough transform is extended to multiple planes to use lane marker features to determine a best line. Lane marker features include a mean and variance of lane marker brightness, lane marker width, lane marker parallelism to a host vehicle direction of travel, and consistence with a predicted lane marker characteristic. A closest lane marker line to a host vehicle is identified, and refitted to account for any curvature.
Abstract:
A method of lane marker detection and lane fitting is provided for lane tracking. A lane marker is modeled and split into left and right steps. A filter response is calculated from a cumulative row sum, and normalized for filter pixel size, lane marker brightness and road brightness. A lane marker response is peak detected for positive and negative peaks and checked for having a magnitude above a threshold and being a local peak in a five point neighborhood. A Hough transform is extended to multiple planes to use lane marker features to determine a best line. Lane marker features include a mean and variance of lane marker brightness, lane marker width, lane marker parallelism to a host vehicle direction of travel, and consistence with a predicted lane marker characteristic. A closest lane marker line to a host vehicle is identified, and refitted to account for any curvature.
Abstract:
Lane marker coordinate data obtained from a previous frame of a vehicle vision system is projected into the current video frame based on measured translation and rotation of the host vehicle. The projected lane marker coordinate data is consolidated with lane marker coordinate data from the current video frame for lane detection or display applications.