Monocular 3D Reconstruction by Applying a Clustering Algorithm to the Hough Parameter Space

C. Torre Ferrero, J.R. Llata García, and A. González Saro (Spain)


Stereo Vision, 3D Reconstruction, clustering, Hough transform.


This paper describes a 3D vision system that reconstructs objects by using a sequence of images acquired with only one CCD camera placed in a fixed position. These images are obtained by turning the object with the help of a rotary platform and then, processed by the `Reconstruction Software'. After performing an image processing that includes filtering and edge detection, it is applied a clustering algorithm to the Hough parameter space in order to extract lines from the images. Following that, the data of each consecutive pair of images are matched and later reconstructed by using techniques based on stereo vision.

Important Links:

Go Back