ICP 1.2

An algorithm for registering a camera image with a database image
ICP stands for Iterative Closest Point algorithm. ICP algorithms are used to register two data sets (meaning making one data set spatially congruent with the other data set) by applying iteratively a rotation and translation to one data set until it is congruent with the other data set.
In the domain of image processing, ICP can be used to register a data image recorded through a sensor against a model image that may be produced by a geographic information system (GIS). A typical application would be a UAV recording images as it flies over a terrain; a successful registration between such sensor images and the the model images produced by an on-board or satellite-connected GIS system would enable precise computation of the position and the orientation of the UAV vis-a-vis the terrain.
The main goal of the pure-Python implementation of ICP presented here is to make it easier to experiment with the different aspects of such algorithms.

Documentation: http://cobweb.ecn.purdue.edu/~kak/distICP/ICP-1.0.html

last updated on:
September 13th, 2011, 5:23 GMT
license type:
Python License 
developed by:
Avinash Kak
ROOT \ Science and Engineering \ Image Recognition
Download Button

In a hurry? Add it to your Download Basket!

user rating



Rate it!

Add your review!