Primitive fitting apparatus and method using point cloud
A primitive fitting apparatus is provided. The primitive fitting apparatus may include a selecting unit to receive, from a user, a selection of points used to fit a primitive a user desires to fit from a point cloud, an identifying unit to receive a selection of the primitive from the user and to identify the selected primitive, and a fitting unit to fit the primitive to correspond to the points, using the points and primitive.
1. A primitive fitting apparatus, comprising:
one or more processors configured to:
receive, from a user, a selection of points from a point cloud, the points being used to fit a primitive a user desires to fit;
receive a selection of the primitive from the user, and to identify the selected primitive; and
fit the identified primitive to correspond to the points, using the points and primitive,
wherein the processor compares an area of a primitive optimized for inliers by removing outliers with an area of a region corresponding to a mesh formed by connecting points corresponding to the inliers, and fit the primitive based on a ratio of the areas.
2. The primitive fitting apparatus of claim 1 , wherein the processor provides the user with a user interface enabling the selection of the points, and receives the selection of the points.
3. The primitive fitting apparatus of claim 1 , wherein the processor receives a selection of a point with a normal vector in a point cloud extracted to be provided to the user.
4. The primitive fitting apparatus of claim 1 , wherein the processor hierarchically receives the selection of the points from the user through a node of a hierarchical tree structure.
5. The primitive fitting apparatus of claim 1 , wherein the processor identifies a primitive of an object that is three-dimensionally represented.
6. The primitive fitting apparatus of claim 1 , wherein the processor removes outliers, based on a difference in a distance between a point selected by the user and points located neighboring the selected point.
7. The primitive fitting apparatus of claim 1 , wherein the processor removes outliers, based on a difference in a normal vector between a normal angle of a point selected from the identified primitive and a normal angle of a point selected from a primitive extracted based on the points.
8. The primitive fitting apparatus of claim 1 , wherein the processor compares the area of the primitive with the area of the region, based on a threshold associated with a difference in a preset area ratio.
9. A primitive fitting apparatus, comprising:
one or more processors configured to:
extract a normal vector of a point, using a point cloud to be provided to a user;
provide the user with a point corresponding to the extracted normal vector, and to determine a primitive the user desires to fit, and points selected by the user, the points being used to fit the primitive based on the normal vector; and
fit the primitive to correspond to the points, using the points and the primitive,
wherein the processor compares an area of a primitive optimized for inliers by removing outliers with an area of a region corresponding to a mesh formed by connecting points corresponding to the inliers, and fit the primitive based on a ratio of the areas.
10. A primitive fitting method, comprising:
receiving, from a user, a selection of points from a point cloud, the points being used to fit a primitive a user desires to fit;
receiving a selection of the primitive from the user, and identifying the selected primitive; and
fitting the identified primitive to correspond to the points, using the points and primitive,
wherein the fitting compares an area of a primitive optimized for inliers by removing outliers with an area of a region corresponding to a mesh formed by connecting points corresponding to the inliers, and fitting the primitive based on a ratio of the areas.
11. The primitive fitting method of claim 10 , wherein the receiving of the selection of the points comprises providing the user with a user interface enabling the selection of the points, and receiving the selection of the points.
12. The primitive fitting method of claim 10 , wherein the receiving of the selection of the points comprises receiving a selection of a point with a normal vector in a point cloud extracted to be provided to the user.
13. The primitive fitting method of claim 10 , wherein the receiving of the selection of the points comprises hierarchically receiving the selection of the points from the user through a node of a hierarchical tree structure.
14. The primitive fitting method of claim 10 , wherein the receiving of the selection of the primitive comprises identifying a primitive of an object that is three-dimensionally represented.
15. The primitive fitting method of claim 10 , wherein the fitting comprises removing outliers, based on a difference in a distance between a point selected by the user and points located neighboring the selected point.
16. The primitive fitting method of claim 10 , wherein the fitting comprises removing outliers, based on a difference in a normal vector between a normal angle of a point selected from the identified primitive and a normal angle of a point selected from a primitive extracted based on the points.
17. The primitive fitting method of claim 10 , wherein the fitting comprises comparing the area of the primitive with the area of the region, based on a threshold associated with a difference in a preset area ratio.