Advanced driver assistance system and vehicle

An advanced driver assistance system (ADAS), comprising:

• a communicator configured to communicate with a camera;
• and
• a processor operatively connected to the communicator and configured to:
• receive a first image and a second image obtained by the camera,
• obtain a plurality of first feature points based on the received first image,
• obtain a plurality of second feature points based on the received second image,
• obtain a plurality of first and second feature points matching each other among the plurality of first feature points and the plurality of second feature points,
• obtain an optical flow and a vanishing point based on the plurality of first and second feature points matching each other,
• recognize a pose of the camera based on the optical flow and the vanishing point, and
• correct a distance to an object in the second image based on the recognized pose of the camera,
• wherein the processor is further configured to:
• obtain relative pose data of the camera based on location information of the obtained vanishing point,
• obtain a trajectory data of the camera based on the obtained optical flow,
• obtain a plurality of cross points where a plurality of lines cross, the plurality of lines defined by the plurality of first and second feature points that match each other,
• identify a density of the plurality of cross points,
• perform a Gaussian fitting for the plurality of cross points,
• obtain a Gaussian coefficient corresponding to the Gaussian fitting,
• obtain a reliability determination value based on the obtained Gaussian coefficient,
• obtain a weight of the relative pose data based on the obtained reliability determination value, and
• obtain a weight of the trajectory data based on the obtained weight of the relative pose data.

A vehicle, comprising:

• a vehicle body;
• a camera provided on the vehicle body;
• and
• a processor configured to recognize an object and a distance to the object based on images obtained by the camera,
• wherein the processor is configured to:
• obtain a plurality of first feature points based on a first image among the images,
• obtain a plurality of second feature points based on a second image among the images,
• obtain a plurality of first and second feature points matching each other among the plurality of first feature points and the plurality of second feature points,
• obtain a plurality of optical flows and a vanishing point based on the plurality of first and second feature points matching each other,
• recognize a pose of the camera based on the plurality of optical flows and the vanishing point,
• obtain a distance error to an object in the second image based on the recognized pose of the camera, and
• correct a distance to the object based on the obtained distance error, wherein the processor is further configured to:
• obtain relative pose data of the camera based on location information of the obtained vanishing point,
• obtain a trajectory data of the camera based on the obtained optical flows,
• obtain a plurality of cross points where a plurality of lines cross, the plurality of lines being defined by the plurality of first and second feature points that match each other,
• identify a density of the plurality of cross points,
• obtain a weight of the relative pose data of the camera and a weight of the trajectory data of the camera based on the identified density, and
• recognize the pose of the camera based on the obtained weight of the relative pose data of the camera and the obtained weight of the trajectory data of the camera.