Iterative Closest Point (ICP) is an algorithm employed to minimize the difference between two clouds of points. ICP is often used to reconstruct 2D or 3D surfaces from different scans, to localize robots and achieve optimal path planning (especially when wheel odometry is unreliable due to slippery terrain), to co-register bone models, etc.
The algorithm is conceptually simple and is commonly used in real-time. It iteratively revises the transformation (translation, rotation) needed to minimize the distance between the points of two raw scans.
Inputs: points from two raw scans, initial estimation of the transformation, criteria for stopping the iteration.
Output: refined transformation.
Essentially the algorithm steps are :
- Associate points by the nearest neighbor criteria.
- Estimate transformation parameters using a mean square cost function.
- Transform the points using the estimated parameters.
- Iterate (re-associate the points and so on).
In, a modified K-D tree algorithm is proposed for efficient closest point computation, and a statistical method based on the distance distribution is used to deal with outliers, occlusion, appearance and disappearance, which enables subset-subset matching.
Famous quotes containing the words closest and/or point:
“... a business career for a woman and her need for a woman’s life as wife and mother, are not enemies at all, unless we make them so, but may be the closest and most co-operative friends and supporter of each other.”
—Hortense Odlum (1892–?)
“The success of a party means little more than that the Nation is using the party for a large and definite purpose.... It seeks to use and interpret a change in its own plans and point of view.”
—Woodrow Wilson (1856–1924)