From ad1005e65b754dafda91e8275044c7c1fe185bf9 Mon Sep 17 00:00:00 2001 From: matlabbe Date: Mon, 22 Oct 2018 15:02:08 -0400 Subject: [PATCH] Updated Robust Graph Optimization (markdown) --- Robust-Graph-Optimization.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Robust-Graph-Optimization.md b/Robust-Graph-Optimization.md index 526b763..c55be2e 100644 --- a/Robust-Graph-Optimization.md +++ b/Robust-Graph-Optimization.md @@ -92,11 +92,11 @@ $ g2o_viewer -typeslib libvertigo-g2o.so with_vertigo_constaints_identity_cov.g2 Screenshot of the correct one after optimization: [[doc/Tutorials/RobustGraphOptimization/g2o_viewer.png]] # Multi Session -In previous section, two approaches have been presented to be more robust to bad loop closures. We will test them again in a multi session experiment with this database: [loop_3it_gps.db](https://raw.githubusercontent.com/wiki/introlab/rtabmap/doc/Tutorials/RobustGraphOptimization/loop_3it_gps.db). This database was captured with [RTAB-Map Tango](https://play.google.com/store/apps/details?id=com.introlab.rtabmap) with GPS enabled: +In previous section, two approaches have been presented to be more robust to bad loop closures. We will test them again in a multi session experiment with this database: [loop_3it_gps.db](https://raw.githubusercontent.com/wiki/introlab/rtabmap/doc/Tutorials/RobustGraphOptimization/loop_3it_gps.db). This database was captured with [RTAB-Map Tango](https://play.google.com/store/apps/details?id=com.introlab.rtabmap) with GPS enabled. In the picture below, the blue path is the trajectory from Tango and the yellow path is the corresponding GPS trajectory. Note that I walked directly in the middle of the sidewalk, so the GPS recorded seems to have an offset with the map from Google Earth. [[doc/Tutorials/RobustGraphOptimization/loop_3it_gps.jpg]] -The same box has been placed at two different locations. We oriented the camera at those locations to see only the box, so that images are identical. First, we will see how the robust approaches perform on this new database in a single session, then we will test again by splitting the database into two sessions. +The same box has been placed at two different locations (see green and red rectangles above). We oriented the camera at those locations to see only the box, so that images are identical. First, we will see how the robust approaches perform on this new database in a single session, then we will test again by splitting the database into two sessions. ## On same session * Without robust approaches (`RGBD/OptimizeRobust=false` and `RGBD/OptimizeMaxError=0`):