User:Aeh84 - Revision history

Aeh84: /* Do something new */

2012-06-15T20:16:36Z

Do something new

Aeh84: /* Registering pointclouds in ROS with PCL for Robot_Lab_(Spring_2012) */

2012-06-15T20:14:55Z

Registering pointclouds in ROS with PCL for Robot_Lab_(Spring_2012)

Aeh84 at 20:13, 15 June 2012

2012-06-15T20:13:51Z

Aeh84: /* Learn about registration */

2012-06-15T20:09:18Z

Learn about registration

Aeh84: /* register_pointclouds/registration.cpp */

2012-06-15T20:07:36Z

register_pointclouds/registration.cpp

Aeh84: /* Try my scripts */

2012-06-15T20:07:24Z

Try my scripts

Aeh84: /* Try my scripts */

2012-06-15T20:01:22Z

Try my scripts

Aeh84: /* Do something new */

2012-06-15T19:53:34Z

Do something new

Aeh84: /* View results */

2012-06-15T19:52:41Z

View results

Aeh84 at 19:51, 15 June 2012

2012-06-15T19:51:16Z

@@ Line 61: / Line 61: @@
 Things I would do if I were to keep working on this project.
 * Working odometry into the registration process appears to be key.  It would be nice to figure out the best way to do it.
 ** A new version of pcl should be coming out any day now as I finish this quarter.  A new registration algorithm will take odometry data with each pointcloud; it's called Normal Distributions Transform.  That would be worth trying out.
-** Further research on Euler angles and rotations in 3d space could be useful.  There may be mathematical errors in the script I wrote to do this.
+** I don't know whether / how it's possible to send odometry and pointclouds over the ROS bus and correlate them on the other side.  Do they need to be combined into a single message?  Can the callbacks on the two topics be tied together somehow?  It would be easier to start by skipping the ROS bus altogether and just reading in the pointcloud and omdometry data from file.
 * Cleaning noise from the data could be helpful.  I believe the circular artifacts in my images come from noise in the pointclouds.  Without them, registration could be more accurate.
-* Experiment more with max correspondence and epsilon parameters to registration algorithms.
+* Experiment more with max correspondence and epsilon parameters to registration algorithms.  These are highly dependent on the data set you use, and it seems they need to be discovered via trial-and-error, and then re-discovered if you use a different data set.

@@ Line 1: / Line 1: @@
 = Registering pointclouds in ROS with PCL for [[Robot_Lab_(Spring_2012)]] =
-Paths followed, lessons learned, code shared.
+Paths followed, lessons learned, code shared, next steps.
 == Find some data ==

@@ Line 15: / Line 15: @@
 == Try my scripts ==
-Download a tgz of my scripts.
+Download a tgz of my scripts: [[File:Registration_code.tar.gz]]
 === pose_registration.py ===

@@ Line 12: / Line 12: @@
 == Learn about registration ==
-The pcl site has a lot of information.  I would recommend reading the introductory material on
+The pcl site has a lot of information.  I would recommend reading the introductory material on a number of pcl modules, including registration, keypoint estimation, features, and correspondence.  There are a number of ways to do this and it would be helpful to get a sense of some of them before starting on one.
 == Try my scripts ==

@@ Line 36: / Line 36: @@
 Reads a pointcloud off the ROS bus (the topic name is set to the same one public_from_file.py writes to).  Runs Iterative Closest Point on each pair of pointclouds.
   $ rosmake register_pointclouds
   $ rosrun register_pointclouds register

@@ Line 33: / Line 33: @@
   $ rosrun pointclouds_ah public_from_file.py
-=== pointcloud registration ===
+=== register_pointclouds/registration.cpp ===
-$ rosmake register_pointclouds
+Reads a pointcloud off the ROS bus (the topic name is set to the same one public_from_file.py writes to).  Runs Iterative Closest Point on each pair of pointclouds.
 $ rosrun register_pointclouds register
 == View results ==

@@ Line 35: / Line 35: @@
 Pointclouds registered by translating them according to odometry data:
 [[File:RegistrationOdometry|500px]]
 Running the data set through odometry translation and then pointcloud registration:

@@ Line 34: / Line 34: @@
 [[File:RegistrationOriginal.png|500px]]
-Running the data set through pose registration only:
+Pointclouds registered by translating them according to odometry data:
-Running the data set through pose registration and then pointcloud registration:
+Running the data set through odometry translation and then pointcloud registration:
 [[File:RegistrationPrecomputed.png|500px]]
@@ Line 44: / Line 45: @@
 == Do something new ==
 * Working odometry into the registration process appears to be key.  It would be nice to figure out the best way to do it.
 ** I don't know whether / how it's possible to send odometry and pointclouds over the ROS bus and correlate them on the other side.  Do they need to be combined into a single message?  Can the callbacks on the two topics be tied together somehow?  It would be easier to start by skipping the ROS bus altogether and just reading in the pointcloud and omdometry data from file.
@@ Line 49: / Line 51: @@
 ** Further research on Euler angles and rotations in 3d space could be useful.  I'm not certain that what I did in my python script is without error.
 * Cleaning noise from the data could be helpful.  I believe the circular artifacts in my images come from noise in the pointclouds.  Without them, registration could be more accurate.