preferencesDialog 0 0 1237 765 0 0 Preferences :/images/RTAB-Map.ico:/images/RTAB-Map.ico 0 180 0 QAbstractItemView::NoEditTriggers false 0 true 0 0 939 724 0 0 0 QFrame::Raised 12 General settings (GUI) QFormLayout::AllNonFixedFieldsGrow true Insert new data received in the GUI cache. Used to show the loop closure image and the 3D Map. true Beep! on special events (finished processing the data set, an error has occured, ...). true Image view QFormLayout::AllNonFixedFieldsGrow Flip image (like a mirror). false true Show image when an hypothesis is rejected. true false Show the image of the highest hypothesis. true 0 100 16 Qt::Horizontal Keypoints opacity. true Vertical layout used for the main window. false false Save/load configurations Save all configurations to ... Load all configurations from ... Qt::Vertical 0 0 3D Rendering 3D cloud opacity. true m 1 100.000000000000000 0.100000000000000 0.000000000000000 true Odometry Qt::AlignCenter true m 3 1.000000000000000 0.010000000000000 0.000000000000000 3D cloud decimation (1-2-4-8-...). true 3D cloud maximum depth (0 means no limit). true Map Qt::AlignCenter true 2 1.000000000000000 0.100000000000000 0.600000000000000 Show 3D clouds. true 1 32 4 m 3 1.000000000000000 0.010000000000000 0.000000000000000 1 32 2 m 1 100.000000000000000 0.100000000000000 4.000000000000000 3D cloud voxel size. true 2 1.000000000000000 0.100000000000000 1.000000000000000 2D scan opacity. true 2 1.000000000000000 0.100000000000000 1.000000000000000 2 1.000000000000000 0.100000000000000 1.000000000000000 true Show 2D scans. true true true 3D cloud point size (1..64). true 2D scan point size (1..64). true Saving/ High-res view Qt::AlignCenter true true m 3 1.000000000000000 0.010000000000000 0.010000000000000 1 32 1 m 1 100.000000000000000 0.100000000000000 4.000000000000000 true 1 64 1 64 1 64 1 64 Meshing false Qt::Vertical 20 40 Logging QFormLayout::AllNonFixedFieldsGrow 2 QComboBox::AdjustToContents DEBUG INFO WARNING ERROR Logger level. true 3 QComboBox::AdjustToContents DEBUG INFO WARNING ERROR Logger event sent level (fatal messages are always sent). true 3 QComboBox::AdjustToContents DEBUG INFO WARNING ERROR FATAL Logger level on which the process will automatically pause, showing the log console. A level set under the logger event level will do nothing. true true Logger print time. true 1 QComboBox::AdjustToContents No log Console File Logger type: when using the file type, logs are saved in LogRtabmap.txt (located in the working directory). true Qt::Vertical 20 40 Source Hz 1 100.000000000000000 0.100000000000000 0.000000000000000 Input rate (0 means as fast as possible). Image source true false 0 Usb camera Images Video file Source type. 0-Usb camera (Webcam), 1-Images (directory of images), 2-Video (AVI) true Auto restart. Image width (set to 0 to use the default size of the source). true Image height (set to 0 to use the default size of the source). true 0 999999999 160 0 0 999999999 120 0 Keypoints extraction post threatement. Frames dropped (ignore X frames after each frame acquired, used to decrease source framerate) true 0 999999999 1 0 0 Usb device Usb device. -1 999999999 0 Qt::Vertical 0 0 Images dataset ... false 0 999999999 Start position (default 1, 0=start from the last). Refresh the directory files list after each image loaded. Qt::Vertical 0 0 Video (AVI) ... false Qt::Vertical 0 0 Database source true false ... Start position (index) 0 999999999 Open database viewer :/images/mag_glass.png:/images/mag_glass.png Ignore odometry saved in the database, so if RGB-D SLAM is activated, odometry will be recomputed. true OpenNI camera (RGB-D) true true Grabber for OpenNI devices (i.e., Primesense PSDK, Microsoft Kinect, Asus XTion Pro/Live). true QFormLayout::AllNonFixedFieldsGrow #1 ID of the device, which might be a serial number, bus@address or the index of the device. If empty, the first device found is taken. true 0 0 0 -PI_2 0 -PI_2 Local transform from /base_link to /camera_link. Format (6 values): x y z roll pitch yaw. true Qt::Vertical 0 0 RTAB-Map settings true SLAM mode. If set to false, global localization is performed, so without adding new data to the map. true true Activate metric RGB-D SLAM. If set to false, classic RTAB-Map loop closure detection is done using only images and without any metric information. true true Publish statistics. true Hz 1 1.000000000000000 Detection rate (0 means inf). RTAB-Map will filter input images to satisfy this rate. true 999 1 Images buffer size (0 means inf). true ms 0 10000.000000000000000 50.000000000000000 700.000000000000000 T_time : Max time (ms) allowed (0 means inf). true 1.000000000000000 0.010000000000000 0.950000000000000 T_loop : Loop closure threshold. true 1.000000000000000 0.200000000000000 T_similarity : Similarity threshold (for Rehearsal/Weight Update). true 1 9999 15 STM size : Short-term memory size. true Database path. true ... true Qt::Vertical 0 0 RTAB-Map settings QFormLayout::AllNonFixedFieldsGrow true SLAM mode. If set to false, global localization is performed, so without adding new data to the map. true Hz 1 1.000000000000000 Detection rate (0 means inf). RTAB-Map will filter input data to satisfy this rate. If you want to process all data, consider set "Detection rate" to 0 and "Data buffer size" to 0. true Data buffer size (0 means inf). true 999 1 Thresholds QFormLayout::AllNonFixedFieldsGrow ms 0 10000.000000000000000 50.000000000000000 700.000000000000000 T_time : Max time (ms) allowed (0 means inf). true 99999 0 Maximum signatures allowed in Working Memory (0 means inf). true 1.000000000000000 0.010000000000000 0.950000000000000 T_loop : Loop closure threshold. Setting to 0 means that the new place hypothesis is used as threshold. true 1.000000000000000 0.010000000000000 0.700000000000000 T_ratio : The loop closure hypothesis must be over T_ratio x lastHypothesisValue. true Publishing (stuff to be shown in the GUI) QFormLayout::AllNonFixedFieldsGrow true Publish statistics (when false, this disables other "Publish *"). true true Publish raw sensor data. true Publish pdf. See the probability density function true Publish likelihood. Statistics QFormLayout::AllNonFixedFieldsGrow true Statistics logs buffered in RAM and written to hard drive on exit (otherwise logs are written at each iteration on hard drive). true Log statistics (in LogI.txt and LogF.txt in the working directory). true true Database path. true ... true Working directory (where to put logs/dump stuff). true ... true Qt::Vertical 0 0 Bayes filter Prediction probabilities for each loop closure event: We can edit how will like the prediction used in the Bayes filter when there is a loop closure hypothesis. Format is [VP LC N1 N2 N3...]. LC is the loop closure event and N# are its neighbors. VP (virtual place) is the probability to be in a new place when a loop closure was found on the last iteration. true Prediction Sum false Preview 1.000000000000000 0.010000000000000 0.900000000000000 The VP here is the probability to be in a new place since no loop closure was found on the last iteration. true Regenerate all the prediction matrix on each iteration (otherwise only removed/added ids are updated). true Qt::Vertical 0 0 Memory QFormLayout::AllNonFixedFieldsGrow 1 9999 15 STM size : Short-term memory size. false 50 0 1.000000000000000 0.010000000000000 0.200000000000000 T_recent : Ratio of locations after the last loop closure in WM that cannot be transferred. true 999 1 2 Maximum locations retrieved at the same time from LTM to WM. true true True=Generate location Ids, False=use input image ids. true Bad signatures are ignored. true true Rehearsal / Weight Update T_similarity : Similarity threshold. Values must be >=0.0 ans <=1.0. true 1.000000000000000 0.200000000000000 On merging, update to new id. true Qt::Vertical 0 0 Database true Keep raw sensor data. true 10 999999 100 2000 Sqlite3 cache size, see Sqlite3 doc 'PRAGMA cache_size'. true DELETE TRUNCATE PERSIST MEMORY OFF Sqlite3 journal mode, see Sqlite3 doc 'PRAGMA journal_mode'. true Using database in the memory instead of a file on the hard disk (this greatly improve database access performance but it requires more RAM memory). true Sqlite3 synchronous, see Sqlite3 doc 'PRAGMA synchronous'. true Sqlite3 temp store, see Sqlite3 doc 'PRAGMA temp_store'. true 2 OFF NORMAL FULL DEFAULT FILE MEMORY Keep rehearsed locations. true true Qt::Vertical 0 0 Visual Word QFormLayout::AllNonFixedFieldsGrow true Publish visual words. true 0 2000 150 0 means that the response (hessian) threshold used for the detector will not be adapted. Otherwise, the threshold is modified to generate the number of words requested. Maximum words per image. true 2 0.000000000000000 1.000000000000000 0.050000000000000 0.250000000000000 0 means that the response (hessian) threshold used for the detector will not be adapted. Otherwise, the threshold is modified to generate the number of words requested. Bad signature ratio (less than Ratio x AverageWordsPerImage = bad). true true Use the tf-idf method to compute the likelihood. true true If the dictionary update and signature creation were parallelized. true true ROI ratios [left, right, top, bottom]. true % 0 Left ROI ratio (0 = no change). true % 0 Right ROI ratio (0 = no change). true % 0 Top ROI ratio (0 = no change). true % 0 Bottom ROI ratio (0 = no change). true Visual word type. true SURF SIFT 0 SURF 0 50000.000000000000000 500.000000000000000 Hessian threshold. 1 100000 4 Octaves. 1 100000 2 Octave layers. U-SURF used. true Descriptor extended (true=128, false=64). true true true GPU version (as well for descriptor). true SIFT Sigma. 6 0.000000000000000 50000.000000000000000 0.001000000000000 0.006667000000000 Contrast threshold. Edge threshold. 0.100000000000000 10.000000000000000 0.100000000000000 10.000000000000000 nOctaveLayers. nFeatures. Qt::Vertical 0 0 Dictionary 1024 64 Maximum number of leafs checked (when using kd-trees). true true Path to a pre-computed dictionary (when "Use an incremental dictionary" is not set). true ... true Use an incremental dictionary. When set to false, no new words are added to dictionary, so no more updates are required after each detection, which greatly increases time performance at the cost of lower adaptation to new environments. true true 999.990000000000009 0.010000000000000 0.160000000000000 Use a minimum distance for the nearest neighbor. true Minimum distance (for the nearest neighbor) Lower the distance -> higher the precision. false Use nearest neighbor distance ratio approach (NNDR). true 999.990000000000009 0.010000000000000 0.700000000000000 NNDR ratio (A matching pair is accepted, if its distance is closer than X times the distance of the second nearest neighbor) Lower the ratio -> higher the precision. true Nearest neighbor strategy. QComboBox::AdjustToContents Naive KdForest FLANN Qt::Vertical 0 0 0 0 Hypotheses verification QComboBox::AdjustToContents No verification Epipolar constraints Hypotheses verification. Epipolar constraints 8 100000 11 Minimum match count to accept a loop closure. true 1 10.000000000000000 0.100000000000000 3.000000000000000 Fundamental Matrix : Distance (pixels) for inliers. true 2 0.990000000000000 0.010000000000000 0.990000000000000 Fundamental Matrix : Ransac performance. true Qt::Vertical 0 0 RGB-D SLAM false Activate metric RGB-D SLAM. If set to false, classic RTAB-Map loop closure detection is done using only images and without any metric information. true This module enables 6d metric SLAM directly in RTAB-Map. Rigid transformations between nodes are saved on the neighbor links of the RTAB-Map's graph. On loop closures, a new constraint is added to the graph and TORO optimizes the graph. Loop closure constraints are computed using SIFT/SURF features extracted by RTAB-Map. RGB-D images must be sent to work (see Source->Openni). true QFormLayout::AllNonFixedFieldsGrow Laser scan matching history size for odometry correction (laser scans are required). Set to 0 to disable odometry correction. true rad 2 3.140000000000000 0.100000000000000 m 2 0.100000000000000 Angular update: Minimum angular displacement to update the map. Note that Weight Update is done prior to this, so weights are still updated. true Linear update: Minimum linear displacement to update the map. Note that Weight Update is done prior to this, so weights are still updated. true Local loop closure detection Local detection is done using two modalities: Time and Space. In the two cases, if a transform can be computed using the loop closure constraints, a local loop closure is added. The Bayes filter is not used here, so it may result in more false detections. true QFormLayout::AllNonFixedFieldsGrow Time Activate local detection over all locations in STM. Space Activate local detection over locations (in Working Memory or STM) near in space. Laser scans required. true m 1.000000000000000 Maximum radius for space detection. Maximum nearest neighbors for space detection. 10 Qt::Vertical 20 40 Odometry Odometry is computed as fast as possible up to "Source->Input rate" parameter. Odometry is not computed if already provided by the source. true QFormLayout::AllNonFixedFieldsGrow m 3 0.100000000000000 0.015000000000000 Linear update: minimum linear distance to update the odometry. true m 3 0.100000000000000 0.015000000000000 Angular update: minimum angular distance to update the odometry. true QComboBox::AdjustToContents Bag-of-words (SURF/SIFT) Binary (FAST+BRIEF) Iterative closest point (ICP) Type Max features extracted from the images (0 means inf). Not used for ICP. true 999999 Maximum distance for visual word correspondences. Not used for ICP. true Minimum visual word correspondences to compute geometry transform. Not used for ICP. true m 3 0.001000000000000 0.010000000000000 0.005000000000000 8 1000 10 Maximum iterations to compute the transform from visual words. Not used for ICP. true 1 10000 1 100 Max feature depth. For ICP, it is the max cloud depth. true m 2 0.000000000000000 1.000000000000000 5.000000000000000 Automatically reset odometry after X consecutive images on which odometry cannot be computed (value=0 disables auto-reset). true 999999 2 Bag-of-words odometry (SIFT/SURF) SIFT or SURF features extracted/descriptors with the depth images (making 3d visual words) are used to compute the odometry. The transformation is estimated using RANSAC between 3D correspondences. Parameters about SIFT or SURF can be found under RTAB-Map->"Visual Word". The nearest neighbor parameters are the same as in RTAB-Map->"Visual Word"->Dictionary (so a FLANN kd-tree is used with euclidian distance). true Qt::Vertical 20 40 Binary odometry (FAST+BRIEF) false Odometry is computed using BRIEF binary descriptors computed from FAST features. The transformation is estimated using RANSAC between 3D correspondences. Nearest neigbor is computed with Hamming distance. true QFormLayout::AllNonFixedFieldsGrow 1 1000 32 BRIEF bytes. true 1 9999 50 FAST Threshold. true true FAST Non max suppression. true true Brute force nerarest neighbor matching. If false, FLANN LSH index is used. true Qt::Vertical 20 40 ICP odometry false Only geometric information is used here. Iterative closest point (ICP) is done with the 3D point clouds. true QFormLayout::AllNonFixedFieldsGrow 1 32 Depth image decimation. true 0 999999 100 5000 Random samples to be used for ICP computation. Not used if Voxel size is not null. true 0.010000000000000 0.010000000000000 0.100000000000000 Max distance for point correspondences. true 1 1000 10 Max iterations. true 0.010000000000000 30.000000000000000 Maximum fitness to accept the computed transform. true Voxel size to be used for ICP computation. true m 3 0.000000000000000 0.010000000000000 0.005000000000000 Qt::Vertical 20 0 Test selected odometry Qt::Horizontal 40 20 Qt::Vertical 20 40 Loop closure constraints Step 1: Compute guess transform from 3D visual words. Guess transform QFormLayout::AllNonFixedFieldsGrow 8 1000 10 Minimum visual word correspondences to compute geometry transform. m 3 0.001000000000000 0.010000000000000 0.020000000000000 Maximum distance for visual word correspondences. 1 10000 1 100 Maximum iterations to compute the transform from visual words. m 0.000000000000000 5.000000000000000 Max feature depth. Step 2: Optimize guess transform with ICP. true QComboBox::AdjustToContents 3D (e.g. Kinect depth) 2D (e.g. Laser scan) Qt::Horizontal 40 20 1 ICP 3D (e.g. Kinect depth) QFormLayout::AllNonFixedFieldsGrow 1 32 Depth image decimation. m 0.000000000000000 5.000000000000000 Max cloud depth. 0 999999 100 5000 Random samples to be used for ICP computation. Not used if Voxel size is null. 0.010000000000000 0.010000000000000 0.100000000000000 Max distance for point correspondences. 1 1000 10 Max iterations. 0.010000000000000 30.000000000000000 Maximum fitness to accept the computed transform. Voxel size to be used for ICP computation. m 3 0.000000000000000 0.010000000000000 0.005000000000000 ICP 2P (e.g. Laser scan) QFormLayout::AllNonFixedFieldsGrow 0.010000000000000 0.010000000000000 0.100000000000000 Max distance for point correspondences. 1 1000 10 Max iterations. 0.010000000000000 30.000000000000000 Maximum fitness to accept the computed transform. 0.000000000000000 1.000000000000000 0.010000000000000 0.900000000000000 Ratio of matching correspondences to accept the transform. Qt::Vertical 20 40 12 12 Qt::Horizontal QDialogButtonBox::Apply|QDialogButtonBox::RestoreDefaults Basic true Advanced Qt::Horizontal QDialogButtonBox::Cancel|QDialogButtonBox::Ok UPlot QWidget

utilite/UPlot.h

1