Archive for April, 2009

Beginings of a proof that only 4 regions can come together at a point

Wednesday, April 22nd, 2009

It can be shown geometrically that the sum of the angles of all lines meeting at a point must be 360 degrees.  I can show that every exposed corner in my application is either 90 degrees, or in the case of edge following regions will when added to the angle of the edge they are following be 180 degrees.  This means I can prove an upper limit for regions coming together at a point of 4.

Posted in CGUL Tools, PhD Thesis | Comments Off

Weekly Report 16

Monday, April 20th, 2009

Engineering:

Fixing remaining bugs outstanding in DEACCON 3D

Produced images of 3D decomposition.

Performed comparison between multiple decomposition techniques.

Got dynamic creation of controls in wxPython working

Science:

Produced AIIDE paper.  Trimmed AIIDE paper.

Started reading for second half of qualifying exam.

Other:

Demo’ed for the friday speaker.

Took Qualifying exam written component

Posted in CGUL Tools, DASSIEs, Uncategorized, Weekly Report | Comments Off

Week 15 Report

Sunday, April 12th, 2009

Science:

DEACCON 3D algorithm work

DEACCON 3D paper work

Found study participants to hit 80% target

Regenerated all study statistics to accommodate new users.

Tried to get CGAL to work – the directions on it are sub-optimal.

Engineering

Improved DEACCON 3D.

Now testing and debugging with actual level data

Implemented gravity based seeding.

Succesfully seeding a stair case using gravity dropped seeds.

Filling negative space via drop seeding.


Other:

Demo

Qualifying Exam Paperwork and studying

To Do:

Iron out remaining bugs in DEACCON.

Survive Qualifying Exam



Posted in CGUL Tools, PhD Thesis, Weekly Report | Comments Off

Week 14 Report

Monday, April 6th, 2009

Science:

DEACCON 3D algorithm work

Engineering

Implemented DEACCON 3D.  It still isn’t perfect but it works.

To Do:

Generate a paper draft by Wednesday.

Currently – seeding – should be in before meeting

Integrate Keith’s code for better seed dropping and to pull the building geometry once a level is created

Bring up python CGAL for the delauney triangulation library

Also the CGAL library will be needed for its fast convex3D checks to ensure edge growth doesn’t extend to far and render object concave as can currently happen

Clean up any lingering issues in DEACCON 3D – I am sure some more issues will become apparent while building a comparision between DEACCON and the other 3D algorithms.

Do metric based comparision.

Posted in CGUL Tools, PhD Thesis, Weekly Report | Comments Off