Apparatus and method for generating around view
Provided is an apparatus for generating an around view. The apparatus includes a capture unit configured to capture images in front of, behind, to the left of, and to the right of a vehicle using cameras, a mask generation unit configured to set a region ranging a predetermined distance from the vehicle in the captured image as a mask region, a feature point extraction unit configured to extract ground feature points from the mask region of each of the captured images; a camera attitude angle estimation unit configured to generate a rotation matrix including a rotation angle of the camera using the extracted feature points; and an around view generation unit configured to rotationally convert the captured images to a top-view image using the rotation matrix.
1. An apparatus for generating an around view, the apparatus comprising:
a plurality of cameras configured to capture images in front of, behind, to the left of, and to the right of a vehicle; and
one or more processors configured to:
set a region ranging a predetermined distance from the vehicle in each of the captured images as a mask region,
extract ground feature points from the mask region of each of the captured images,
generate a rotation matrix including a rotation angle of each camera using the extracted feature points, and
rotationally convert the captured images to a top-view image using the rotation matrix,
wherein the one or more processors are configured to detect a traffic line in each of the captured images and set a region between the detected traffic line and the vehicle as the mask region.
2. The apparatus of claim 1 , wherein the one or more processors are further configured to generate a virtual traffic line with a predetermined width in each of the captured images when a traffic line is not detected, and set a region between the generated virtual traffic line and the vehicle as the mask region.
3. The apparatus of claim 1 , wherein:
the one or more processors are further configured to calculate a slope of a ground surface using a rotation matrix indicating the attitude angle of the camera and a rotation matrix calculated using the feature points extracted from the captured images, the rotation matrices being prestored; and
wherein the one or more processors are configured to set an entirety of each of the captured images as the mask region when the slope of the ground surface is less than or equal to a predetermined threshold value.
4. A method of generating an around view which is performed by an apparatus that includes one or more processors and generates an around view, the method comprising:
acquiring images by performing capturing in four directions, i.e., in front of, behind, to a left side of, and to a right side, of a vehicle using a plurality of cameras;
setting a region ranging a predetermined distance from the vehicle in each of the captured images as a mask region;
extracting ground feature points from the mask region;
generating a rotation matrix including a rotation angle of each camera using the extracted feature points; and
rotationally converting the images captured in the four directions to a top-view image using the rotation matrix,
wherein the setting comprises detecting a traffic line in each of the captured images and setting a region between the detected traffic line and the vehicle as the mask region.
5. The method of claim 4 , wherein the setting comprises detecting a traffic line in each of the captured images, generating a virtual traffic line with a predetermined width in each of the captured images when a traffic line is not detected, and setting a region between the generated virtual traffic line and the vehicle as the mask region.
6. A method of generating an around view which is performed by an apparatus that includes one or more processors and generates an around view, the method comprising:
acquiring images by performing capturing in four directions, i.e., in front of, behind, to a left side of, and to a right side, of a vehicle using a plurality of cameras;
setting a region ranging a predetermined distance from the vehicle in each of the acquired images as a mask region;
extracting ground feature points from the mask region;
generating a rotation matrix including a rotation angle of each camera using the extracted feature points; and
rotationally converting the images captured in the four directions to a top-view image using the rotation matrix,
wherein the generating of a rotation matrix comprises calculating a slope of a ground surface using a rotation matrix indicating the attitude angle of the camera and a rotation matrix calculated using the feature points extracted from the captured images, the rotation matrices being prestored; and
wherein the setting comprises setting an entirety of each of the captured images as the mask region when the ground slope is less than or equal to a predetermined threshold value.