A vehicle high beam and low beam automatic switching method and system based on visual recognition

Abstract

The application relates to a vehicle high-low beam automatic switching method and system based on visual recognition, and relates to the technical field of vehicle lamp control. The method comprises the following steps: acquiring a dual-spectrum image sequence containing a visible light band and a near-infrared band and vehicle motion parameters; extracting a strong light area from the dual-spectrum image sequence and constructing a morphological feature matrix based on the geometric change of the strong light area in continuous frames; performing frequency domain conversion on the strong light area to obtain an edge gradient feature; extracting a halo diffusion contour based on the edge gradient feature and the morphological feature matrix; obtaining a shielding light source probability and a reflected light suppression coefficient for the strong light area based on the reflection response characteristics of the halo diffusion contour in the dual-spectrum image sequence; and obtaining a light beam switching instruction for the vehicle headlamp based on the shielding light source probability and the reflected light suppression coefficient. The application has the effect of improving the safety of night driving.

Images