Changeset 705

Timestamp:

02/22/10 21:06:48 (2 years ago)

Author:

taborts

Message:

added content to results, accounting for problems in example images

Files:

• branches/2010-image-rec/docs/report.tex (modified) (1 diff)

branches/2010-image-rec/docs/report.tex

@@ -164 +164 @@
 \end{figure}
 
-The next step with our algorithm is to make it work on cases where it fails,
-those with lines appearing within our safe zone.  It is possible that this
+The next step with our algorithm is to make it work on cases where it fails, in \ref{fig:safe-region} 
+there is an example of an image where line pixels appear in the assumed safe zone. Further work will 
+include excluding these pixels from the histogram.  It is possible that this
 could be done by excluding portions of the ``safe zone'' which exceed a
 threshold in brightness, or to apply the previous image's histogram to the safe
-zone and exclude those pixels that fall far outside it. There is also work to
+zone and exclude those pixels that fall far outside it. Another case where our algorithm fails is
+is in \ref{fig:hough-failure}. The obstacle very close to the camera in the image includes more texture than our
+algoristhm expects of an obastacle, and missclassifies it as a set of line pixels. 
+A similar problem occurs where regions further away may have lower texture than grassy regions
+nearer the camera. One solution may be to add to the percieved texture in an image based on height within 
+the image. There is also work to
 be done for it to be run on the robot. The algorithm must be able to run in
 real time to support live decision-making, which means that it must be ported