A method of diagnosing a state of health of a vision-based lane sensing system. A first misalignment factor is calculated as a function of a vehicle lateral offset and a vehicle heading. A second misalignment factor is calculated as a function of a vehicle speed, an estimated curvature of an expected path of travel, a lane curvature, and the vehicle heading. Histograms are generated for the first and second misalignment factors. A probability of a state of health is determined. A determination is made whether the probability of the state of health is within a predetermined threshold. An angle misalignment of the vision system is estimated. The angle misalignment of the vision system is corrected in response to the determination that the probability of the state of health is within the predetermined threshold; otherwise a warning of a faulty lane sensing system is actuated.