GUI: Support Optimizer/Robust with RGBD/OptimizeMaxError at the same time. DBReader: fixed repeated odom covariance when Mem/ReduceGraph is used. Memory: avoid error msg when receiving frames without features while we expect odometry features. See also #1573

This commit is contained in:
matlabbe
2025-09-24 23:24:32 -07:00
parent c774ef641a
commit a552bdfb2f
7 changed files with 71 additions and 42 deletions
+4 -4
View File
@@ -95,7 +95,7 @@
<enum>QFrame::Raised</enum>
</property>
<property name="currentIndex">
<number>5</number>
<number>8</number>
</property>
<widget class="QWidget" name="page_22">
<layout class="QVBoxLayout" name="verticalLayout_29" stretch="0,0">
@@ -10409,7 +10409,7 @@ If set to false, classic RTAB-Map loop closure detection is done using only imag
<item row="7" column="1">
<widget class="QLabel" name="label_retrieved_10">
<property name="text">
<string>Reduce graph. Merge nodes when loop closures are added (ignoring those with user data set).</string>
<string>Reduce graph. Merge nodes when loop closures are added (ignoring those with user data). Note that this approach assumes that 100% of the loop closures accepted are good, so it is highly recommended to enable optimization error ratio at the same time.</string>
</property>
<property name="wordWrap">
<bool>true</bool>
@@ -13433,7 +13433,7 @@ If set to false, classic RTAB-Map loop closure detection is done using only imag
<item row="1" column="1">
<widget class="QLabel" name="label_258">
<property name="text">
<string>Robust graph optimization using Vertigo (only for g2o and GTSAM optimization strategies). This approach can filter wrong loop closure detections.</string>
<string>Robust graph optimization using Vertigo (only work for g2o and GTSAM optimization strategies).</string>
</property>
<property name="wordWrap">
<bool>true</bool>
@@ -13468,7 +13468,7 @@ If set to false, classic RTAB-Map loop closure detection is done using only imag
<item row="2" column="1">
<widget class="QLabel" name="label_259">
<property name="text">
<string>Reject loop closures if optimization error ratio is greater than this value (0=disabled). Ratio is computed as absolute error over standard deviation of each link. This will help to detect when a wrong loop closure is added to the graph. It should not be used at the same time than Vertigo above.</string>
<string>Reject loop closures if optimization error ratio is greater than this value (0=disabled). Ratio is computed as absolute error over standard deviation of each link. This will help to detect when a wrong loop closure is added to the graph. If used with robust graph optimization, the disabled loop closure links will be removed.</string>
</property>
<property name="wordWrap">
<bool>true</bool>