Page 255 -

234 4 Feature detection and matching

mean or centroid of the edgels and then use eigenvalue analysis to find the dominant
orientation.
2. Compute the perpendicular errors (deviations) to the line and robustly estimate the
variance of the fitting noise using an estimator such as MAD (Appendix B.3).

3. (Optional) re-fit the line parameters by throwing away outliers or using a robust norm
or influence function.

4. Estimate the error in the perpendicular location of the line segment and its orientation.

Ex 4.14: Vanishing points Compute the vanishing points in an image using one of the tech-
niques described in Section 4.3.3 and optionally refine the original line equations associated
with each vanishing point. Your results can be used later to track a target (Exercise 6.5)or
reconstruct architecture (Section 12.6.1).

Ex 4.15: Vanishing point uncertainty Perform an uncertainty analysis on your estimated
vanishing points. You will need to decide how to represent your vanishing point, e.g., homo-
geneous coordinates on a sphere, to handle vanishing points near infinity.
See the discussion of Bingham distributions by Collins and Weiss (1990) for some ideas.