Image processing method of vehicle camera and image processing apparatus using the same

摘要

Disclosed herein is an image processing apparatus of a vehicle camera, including a light source extraction unit configured to extract light sources from a first frame exposed to light sources during a first time and to extract light sources including motion blurs from a second frame exposed to the light sources during a second time longer than the first time, a target light source classification unit configured to classify a first target light source that belongs to the light sources of the first frame and that does not move and a second target light source that belongs to the light sources of the second frame and that does not move, and a motion determination unit configured to estimate a first location that is the central point of the first target light source and a second location that is the central line including the central point of the second target light source, compare the first location with the second location, and determine whether or not a pitch motion of the vehicle has occurred.

主权项

1. An image processing apparatus of a vehicle camera, comprising:
a light source extraction unit configured to extract light sources from a first frame exposed to light sources during a first time and to extract light sources generating motion blurs from a second frame exposed to the light sources during a second time longer than the first time; a target light source classification unit configured to classify a first target light source that belongs to the light sources of the first frame and that does not move and a second target light source that belongs to the light sources of the second frame and that does not move; a motion determination unit configured to estimate a first location that is a central point of the first target light source and a second location that is a central line comprising a central point of the second target light source, compare the first location with the second location, determine whether or not a pitch motion of the vehicle has occurred, perform binarization on an image of the first frame or the second frame, and extract coordinates of the center of gravity of pixels having a specific value as the first location or the second location; and a correction unit configured to correct an image of the vehicle camera based on a result of the comparison between the first location and the second location.