Kimera Semantics not generating 3D mesh with RealSense D455
shabpompeiano opened this issue · 6 comments
shabpompeiano commented
Description:
I am trying to obtain a 3D mesh of an entire room using Kimera Vio and Kimera Semantics in conjunction with a RealSense D455 camera. Although Kimera Semantics is designed to produce this, I am not able to see the 3D mesh. In rviz, the display shows only black (refer to attached images).
I am attaching the launch files and the output to rqt_graph too.
Commands:
roslaunch realsense2_camera rs_camera.launch \
unite_imu_method:=linear_interpolation \
align_depth:=true \
enable_accel:=true \
enable_gyro:=true \
enable_imu:=true \
enable_color:=true \
enable_depth:=true \
enable_infra1:=true \
enable_infra2:=true \
infra_width:=640 \
infra_height:=480 \
infra_fps:=15 \
depth_width:=640 \
depth_height:=480 \
depth_fps:=15 \
color_width:=1280 \
color_height:=720 \
color_fps:=15 \
initial_reset:=true
rosrun dynamic_reconfigure dynparam set /camera/stereo_module emitter_enabled 0
roslaunch kimera_vio_ros kimera_vio_ros_realsense_IR.launch
rviz -d $(rospack find kimera_vio_ros)/rviz/kimera_vio_euroc.rviz
roslaunch kimera_semantics_ros kimera_metric_realsense.launch register_depth:=true
rviz -d $(rospack find kimera_semantics_ros)/rviz/kimera_realsense_metric.rviz
Console output:
* /kimera_vio_ros/kimera_vio_ros_node/position_det_threshold: 0.3
* /kimera_vio_ros/kimera_vio_ros_node/right_cam_frame_id: right_cam
* /kimera_vio_ros/kimera_vio_ros_node/stereo_ransac_threshold: 20
* /kimera_vio_ros/kimera_vio_ros_node/use_lcd: False
* /kimera_vio_ros/kimera_vio_ros_node/use_online_cam_params: False
* /kimera_vio_ros/kimera_vio_ros_node/velocity_det_threshold: 0.1
* /kimera_vio_ros/kimera_vio_ros_node/world_frame_id: world
* /kimera_vio_ros/posegraph_viewer/frame_id: world
* /rosdistro: melodic
* /rosversion: 1.14.13
* /use_sim_time: False
NODES
/
velo_link_broadcaster (tf/static_transform_publisher)
/kimera_vio_ros/
kimera_vio_ros_node (kimera_vio_ros/kimera_vio_ros_node)
posegraph_viewer (pose_graph_tools/visualizer_node)
ROS_MASTER_URI=http://localhost:11311
process[kimera_vio_ros/kimera_vio_ros_node-1]: started with pid [3994]
process[kimera_vio_ros/posegraph_viewer-2]: started with pid [3995]
process[velo_link_broadcaster-3]: started with pid [3996]
[ INFO] [1694179178.729510298]: Initializing pose graph visualizer
I0908 15:19:38.830406 3994 RegularVioBackend.cpp:114] Using Regular VIO Backend.
I0908 15:19:38.830544 3994 PipelineModule.h:449] MISO Pipeline Module: Display has no output queue registered.
I0908 15:19:38.830662 3994 Pipeline.cpp:296] Pipeline Modules launched (parallel_run set to 1).
I0908 15:19:38.830775 3994 KimeraVioRos.cpp:137] Statistics
----------- # Log Hz {avg +- std } [min,max]
Display [ms] 0
Mesher [ms] 0
VioBackend [ms] 0
VioFrontend [ms] 0
backend_input_queue Size [#] 0
data_provider_left_frame_queue Size [#] 0
data_provider_right_frame_queue Size [#] 0
display_input_queue Size [#] 0
frontend_input_queue Size [#] 0
mesher_backend Size [#] 0
mesher_frontend Size [#] 0
visualizer_backend_queue Size [#] 0
visualizer_frontend_queue Size [#] 0
visualizer_mesher_queue Size [#] 0
I0908 15:19:38.830880 4030 Pipeline.cpp:89] Spinning Kimera-VIO.
I0908 15:19:39.168602 4025 VioBackend.h:167] ------------------- Initialize Pipeline: timestamp = 1694179179131177425--------------------
W0908 15:19:39.168617 4025 InitializationFromImu.cpp:25] InitializationFromImu: assumes that the vehicle is stationary and upright along some axis,and gravity vector is along a single axis!
W0908 15:19:39.169299 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
E0908 15:19:39.169550 4026 Mesher.cpp:1729] Delaunay Triangle out of image (size: x: 0, y: 0, height: 480, width 640
Triangle: x, y:
1920, 0
0, 1920
631.922, 388.018
W0908 15:19:39.328872 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.328891 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.340059 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.340517 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:39.407665 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:39.440079 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.440104 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.452549 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.453209 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:39.474189 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:39.591810 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.591830 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.602816 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.603260 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:39.607173 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:39.705420 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.705441 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.717381 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.717795 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
I0908 15:19:39.830916 3994 KimeraVioRos.cpp:137] Statistics
----------- # Log Hz {avg +- std } [min,max]
Display [ms] 9 10.0844 {0.111111 +- 0.333333} [0,1]
Mesher [ms] 5 5.60383 {4.60000 +- 0.894427} [3,5]
Stereo Data Provider [ms] 0
VioBackend [ms] 5 5.63654 {0.00000 +- 0.00000} [0,0]
VioFrontend Frame Rate [ms] 5 9.34364 {1.20000 +- 0.447214} [1,2]
VioFrontend Keyframe Rate [ms] 4 7.84869 {51.5000 +- 11.0905} [42,63]
VioFrontend [ms] 10 10.9635 {23.8000 +- 25.7889} [1,63]
Visualizer [ms] 5 5.60369 {0.00000 +- 0.00000} [0,0]
backend_input_queue Size [#] 5 5.62232 {1.00000 +- 0.00000} [1,1]
data_provider_left_frame_queue Size [#] 12 12.2644 {1.00000 +- 0.00000} [1,1]
data_provider_right_frame_queue Size [#] 12 12.2635 {1.00000 +- 0.00000} [1,1]
display_input_queue Size [#] 9 10.0534 {1.00000 +- 0.00000} [1,1]
frontend_input_queue Size [#] 11 11.2146 {1.00000 +- 0.00000} [1,1]
mesher_backend Size [#] 5 5.63578 {1.00000 +- 0.00000} [1,1]
mesher_frontend Size [#] 10 10.9620 {1.40000 +- 0.516398} [1,2]
visualizer_backend_queue Size [#] 5 5.63583 {1.00000 +- 0.00000} [1,1]
visualizer_frontend_queue Size [#] 10 10.9621 {1.40000 +- 0.516398} [1,2]
visualizer_mesher_queue Size [#] 5 5.60302 {1.00000 +- 0.00000} [1,1]
W0908 15:19:39.860337 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.860354 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.871870 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.872303 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
E0908 15:19:39.872656 4026 Mesher.cpp:1729] Delaunay Triangle out of image (size: x: 0, y: 0, height: 480, width 640
Triangle: x, y:
84, 145
-1920, -1920
137.193, 75.1869
W0908 15:19:39.940984 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:39.983759 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:39.983780 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:39.997138 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:39.997563 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.127099 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.127120 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.139950 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.140501 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.140631 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:40.236294 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.236315 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.249401 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.249851 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.341473 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:40.400185 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.400202 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.411280 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.411703 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.499318 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.499338 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.510834 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.511270 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
E0908 15:19:40.511652 4026 Mesher.cpp:1729] Delaunay Triangle out of image (size: x: 0, y: 0, height: 480, width 640
Triangle: x, y:
0, 1920
-1920, -1920
146.25, 462.11
W0908 15:19:40.609467 4030 DataProviderModule.cpp:68] Waiting for IMU data...
W0908 15:19:40.631736 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.631750 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.640388 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.640902 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.793686 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.793707 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.804924 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.805425 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
W0908 15:19:40.807183 4030 DataProviderModule.cpp:68] Waiting for IMU data...
I0908 15:19:40.831172 3994 KimeraVioRos.cpp:137] Statistics
----------- # Log Hz {avg +- std } [min,max]
Display [ms] 25 12.6260 {0.0400000 +- 0.200000} [0,1]
Mesher [ms] 13 6.56623 {4.92308 +- 0.759555} [3,6]
Stereo Data Provider [ms] 0
VioBackend [ms] 13 6.58327 {0.00000 +- 0.00000} [0,0]
VioFrontend Frame Rate [ms] 13 8.11166 {1.69231 +- 1.37747} [1,6]
VioFrontend Keyframe Rate [ms] 12 7.51328 {51.6667 +- 13.1725} [29,69]
VioFrontend [ms] 26 13.1338 {25.7308 +- 26.4659} [1,69]
Visualizer [ms] 13 6.56616 {0.00000 +- 0.00000} [0,0]
backend_input_queue Size [#] 13 6.57613 {1.00000 +- 0.00000} [1,1]
data_provider_left_frame_queue Size [#] 27 13.6580 {1.00000 +- 0.00000} [1,1]
data_provider_right_frame_queue Size [#] 27 13.6578 {1.00000 +- 0.00000} [1,1]
display_input_queue Size [#] 25 12.6084 {1.00000 +- 0.00000} [1,1]
frontend_input_queue Size [#] 26 13.1288 {1.00000 +- 0.00000} [1,1]
mesher_backend Size [#] 13 6.58287 {1.00000 +- 0.00000} [1,1]
mesher_frontend Size [#] 26 13.1329 {1.46154 +- 0.508391} [1,2]
visualizer_backend_queue Size [#] 13 6.58290 {1.00000 +- 0.00000} [1,1]
visualizer_frontend_queue Size [#] 26 13.1330 {1.46154 +- 0.508391} [1,2]
visualizer_mesher_queue Size [#] 13 6.56580 {1.00000 +- 0.00000} [1,1]
^C[velo_link_broadcaster-3] killing on exit
[kimera_vio_ros/posegraph_viewer-2] killing on exit
[kimera_vio_ros/kimera_vio_ros_node-1] killing on exit
W0908 15:19:40.892812 4024 StereoMatcher.cpp:130] sparseStereoMatching: StereoFrame is already rectified!
W0908 15:19:40.892828 4024 StereoCamera.cpp:263] Rectifying already rectified stereo frame ...
I0908 15:19:40.901916 4025 RegularVioBackend.cpp:212] Tracker has a LOW_DISPARITY status.
W0908 15:19:40.902426 4026 Mesher.cpp:1377] Missing landmark information to build 3D Mesh.
I0908 15:19:40.980886 3994 KimeraVioRos.cpp:144] Shutting down ROS and Kimera-VIO.
I0908 15:19:40.980904 3994 Pipeline.cpp:225] Shutting down VIO pipeline.
I0908 15:19:40.980907 3994 Pipeline.cpp:231] Calling registered shutdown callbacks...
I0908 15:19:40.980913 3994 DataProviderInterface.cpp:70] Shutting down DataProviderInterface.
I0908 15:19:40.980916 3994 RosDataProviderInterface.h:41] RosDataProviderInterface shutdown.
I0908 15:19:40.980937 3994 MesherModule.cpp:65] Shutting down queues for: Mesher
W0908 15:19:40.980938 4024 PipelineModule.h:397] Module: VioFrontend - Input queue: frontend_input_queue didn't return an output.
W0908 15:19:40.980988 4030 MonoDataProviderModule.cpp:74] Module: Stereo Data Provider - queue is down
I0908 15:19:40.980942 3994 Visualizer3DModule.cpp:122] Shutting down queues for: Visualizer
W0908 15:19:40.981029 4025 PipelineModule.h:397] Module: VioBackend - Input queue: backend_input_queue didn't return an output.
W0908 15:19:40.981047 4027 Visualizer3DModule.cpp:76] Module: Visualizer - visualizer_backend_queue queue is down
W0908 15:19:40.981050 4029 DisplayModule.cpp:54] Module: Display - Input queue: display_input_queue didn't return an output.
W0908 15:19:40.981110 4026 MesherModule.cpp:36] Module: Mesher - Backend queue is down
W0908 15:19:40.981206 3994 Pipeline.cpp:353] No lcd thread, not joining.
I0908 15:19:40.981221 3994 Pipeline.cpp:246] VIO Pipeline's threads shutdown successfully.
VIO Pipeline successful shutdown.
I0908 15:19:40.981225 3994 KimeraVioRos.cpp:152] Joining Kimera-VIO thread.
I0908 15:19:40.981240 3994 KimeraVioRos.cpp:154] Kimera-VIO thread joined successfully.
I0908 15:19:40.981241 3994 KimeraVioRos.cpp:155] Joining Ros Data Provider thread.
I0908 15:19:40.981248 3994 KimeraVioRos.cpp:157] Ros Data Provider thread joined successfully.
I0908 15:19:40.981251 3994 KimeraVioRos.cpp:158] Joining RosDisplay thread.
I0908 15:19:40.981272 3994 KimeraVioRos.cpp:160] RosDisplay thread joined successfully.
W0908 15:19:40.981276 3994 KimeraVioRos.cpp:181] Spin took: 2150 ms.
I0908 15:19:40.981303 3994 KimeraVioRos.cpp:182] Pipeline successful? Yes!
I0908 15:19:40.981369 3994 RosOnlineDataProvider.cpp:226] RosOnlineDataProvider successfully shutdown.
I0908 15:19:40.981462 3994 DataProviderInterface.cpp:29] Data provider destructor called.
Console output:
Checking log directory for disk usage. This may take a while.
Press Ctrl-C to interrupt
Done checking log file disk usage. Usage is <1GB.
started roslaunch server http://127.0.0.1:38463/
SUMMARY
========
CLEAR PARAMETERS
* /kimera_semantics_node/
PARAMETERS
* /cloudify/queue_size: 20
* /kimera_semantics_node/color_mode: lambert_color
* /kimera_semantics_node/dynamic_semantic_labels: [20]
* /kimera_semantics_node/enable_icp: False
* /kimera_semantics_node/icp_iterations: 10
* /kimera_semantics_node/max_ray_length_m: 2.5
* /kimera_semantics_node/mesh_filename: /home/shab/kimera...
* /kimera_semantics_node/method: fast
* /kimera_semantics_node/min_time_between_msgs_sec: 0.2
* /kimera_semantics_node/publish_pointclouds: False
* /kimera_semantics_node/semantic_color_mode: semantic
* /kimera_semantics_node/semantic_label_2_color_csv_filepath: /home/shab/kimera...
* /kimera_semantics_node/semantic_measurement_probability: 0.8
* /kimera_semantics_node/sensor_frame: depth_cam
* /kimera_semantics_node/slice_level: 1.0
* /kimera_semantics_node/tsdf_voxel_size: 0.05
* /kimera_semantics_node/tsdf_voxels_per_side: 32
* /kimera_semantics_node/update_mesh_every_n_sec: 1.0
* /kimera_semantics_node/use_const_weight: False
* /kimera_semantics_node/use_freespace_pointcloud: False
* /kimera_semantics_node/use_tf_transforms: True
* /kimera_semantics_node/verbose: True
* /kimera_semantics_node/voxel_carving_enabled: True
* /rosdistro: melodic
* /rosversion: 1.14.13
* /use_sim_time: False
NODES
/
cloudify (nodelet/nodelet)
imu_to_left_cam (tf/static_transform_publisher)
inter_cam_tf (tf/static_transform_publisher)
inter_cam_tf_2 (tf/static_transform_publisher)
kimera_semantics_node (voxblox_ros/tsdf_server)
nodelet_manager (nodelet/nodelet)
ROS_MASTER_URI=http://localhost:11311
process[imu_to_left_cam-1]: started with pid [5089]
process[inter_cam_tf-2]: started with pid [5090]
process[inter_cam_tf_2-3]: started with pid [5091]
process[nodelet_manager-4]: started with pid [5096]
process[cloudify-5]: started with pid [5103]
process[kimera_semantics_node-6]: started with pid [5108]
[ INFO] [1694179271.113295435]: Loading nodelet /cloudify of type depth_image_proc/point_cloud_xyzrgb to manager nodelet_manager with the following remappings:
[ INFO] [1694179271.113927450]: /depth_registered/image_rect -> /camera/aligned_depth_to_color/image_raw
[ INFO] [1694179271.113939218]: /depth_registered/points -> /semantic_pointcloud
[ INFO] [1694179271.113946053]: /rgb/camera_info -> /camera/aligned_depth_to_color/camera_info
[ INFO] [1694179271.113951927]: /rgb/image_rect_color -> /camera/color/image_raw
[ INFO] [1694179271.114726337]: waitForService: Service [/nodelet_manager/load_nodelet] has not been advertised, waiting...
[ INFO] [1694179271.117893427]: Initializing nodelet with 12 worker threads.
[ INFO] [1694179271.135317575]: waitForService: Service [/nodelet_manager/load_nodelet] is now available.
[ INFO] [1694179272.176908983]: Updating mesh.
[ INFO] [1694179273.176721496]: Updating mesh.
[ INFO] [1694179274.176763900]: Updating mesh.
[ INFO] [1694179275.176767221]: Updating mesh.
[ INFO] [1694179276.176760732]: Updating mesh.
[ INFO] [1694179277.176750728]: Updating mesh.
[ INFO] [1694179278.176769857]: Updating mesh.
Additional files:
kimera_metric_realsense.launch
<?xml version="1.0" encoding="ISO-8859-15"?>
<launch>
<!-- If you aren't running a bag file, set to false-->
<arg name="should_use_sim_time" default="false"/>
<arg name="max_ray_length_m" default="2.5"/>
<!-- If you just want to run 3D reconstruction without semantics, set this flag to false-->
<arg name="metric_semantic_reconstruction" value="false"/>
<arg name="semantic_label_2_color_csv_filepath" default="$(find kimera_semantics_ros)/cfg/maskrcnn_mapping.csv"/>
<!-- Change sensor frame to:
- 1. VIO's estimated base_link: `left_cam_base_link`
- 2. Or, if you want to use simulator's ground-truth: `left_cam`
-->
<arg name="sensor_frame" value="depth_cam"/>
<!-- Input -->
<arg name="left_cam_info_topic" default="/camera/aligned_depth_to_color/camera_info"/>
<arg name="left_cam_topic" default="/camera/color/image_raw"/>
<arg name="left_cam_segmentation_topic" default="/camera/color/semantic_image"/>
<arg name="left_cam_depth_topic" default="/camera/aligned_depth_to_color/image_raw"/>
<!-- Tracking IMU to Tracking Camera tf -->
<node pkg="tf" type="static_transform_publisher" name="imu_to_left_cam"
args="-0.0107491 0.00339225 0.02843741 0.0052734748 0.0001508149 0.0022978430 0.9999834436 base_link_dvio left_cam 100"/>
<!-- Tracking to Mapping Camera tf -->
<node pkg="tf" type="static_transform_publisher" name="inter_cam_tf"
args="0.075 0 -0.065 0 0.7071 0 0.7071 left_cam depth_cam 100"/>
<node pkg="tf" type="static_transform_publisher" name="inter_cam_tf_2"
args="0.075 0 -0.065 0 0.7071 0 0.7071 left_cam depth_camera_color_optical_frame 100"/>
<!-- Launch actual pipeline -->
<include file="$(find kimera_semantics_ros)/launch/kimera_semantics.launch" pass_all_args="true"/>
</launch>
kimera_vio_ros_realsense_IR.launch
<launch>
<arg name="dataset_name" value="RealSenseIR"/>
<arg name="online" default="True" />
<arg name="log_output" default="false"/>
<arg name="log_output_path"
default="$(find kimera_vio_ros)/output_logs/"
if="$(arg log_output)"/>
<arg name="log_gt_data" default="false"/>
<arg name="gt_topic" default=""/>
<!-- Set use_sim_time to true if you use rosbag with clock argument -->
<arg name="should_use_sim_time" default="false"/>
<!-- Only used when parsing a rosbag -->
<arg name="rosbag_path" default="default.bag"
unless="$(arg online)"/>"/>
<!-- Frame IDs. These DO NOT match frame id's on the video streams, as the
RealSense and Kimera publish conflicting Tf's -->
<arg name="world_frame_id" value="world"/>
<arg name="base_link_frame_id" value="base_link"/>
<arg name="map_frame_id" value="map"/>
<arg name="left_cam_frame_id" value="left_cam"/>
<arg name="right_cam_frame_id" value="right_cam"/>
<!-- Subscribed Topics -->
<arg name="left_cam_topic" value="/camera/infra1/image_rect_raw"/>
<arg name="right_cam_topic" value="/camera/infra2/image_rect_raw"/>
<arg name="imu_topic" value="/camera/imu"/>
<!-- Launch actual pipeline -->
<include file="$(find kimera_vio_ros)/launch/kimera_vio_ros.launch"
pass_all_args="true"/>
<!-- Launch static TF node from base_link to velo_link -->
<node pkg="tf" type="static_transform_publisher" name="velo_link_broadcaster"
args="0 0 0 0 0 0 1 base_link velo_link 100"/>
</launch>
Please give also the following information:
- Kimera-Semantics branch, tag or commit used: commit 1ed69c6
- GTSAM version used:
- OpenCV version used: type
opencv_version - Operating system and version (e.g. Ubuntu 16.04 or Windows 10): Ubuntu 18.04
- ROS Distribution (kinetic, melodic, …): melodic
- Did you change the source code? (yes / no): no (only launch files)
shabpompeiano commented
The issue persists also with D435i
jolags313 commented
@shabpompeiano Have you solved this issue? I'm experiencing the same thing.
Also, for me, nothing is streaming on the /camera/aligned_depth_to_color/camera_info or /camera/aligned_depth_to_color/image_raw topics. Could you tell me how you got the depth image in the second screenshot you have?
shabpompeiano commented
If you set the argument align_depth:=true when initializing realsense ros, the aligned depth should be published under /camera/aligned_depth_to_color/image_raw.
To get the depth image in rviz, I am showing the topic /camera/depth/image_rect_raw
jolags313 commented
Sorry for the late response, but thank you for the advice- I also had to do a lot of troubleshooting with the camera and firmware to get it to work. I now see the same rviz output you do. However, I am still unable to generate any mesh. Have you figured this out?
shabpompeiano commented
I suspect based on the following issues, that the issue is related to the TF transformations.
I had to resolve all the issues related TF and it worked for me.
Originally posted by @madhu-korada in #75 (comment)
Hi @julienip,
The pose is inferred from the TF tree in ROS (it will look for the tfs you mentioned above, `left_cam` or `left_cam_base_link` depending on what you use).
Nevertheless, you can also subscribe to a pose topic `transform`, which will be used in case you set the parameter `use_tf_transforms` to false:
Note that these are parameters already available in voxblox, and therefore the documentation remains the same, note here https://voxblox.readthedocs.io/en/latest/pages/The-Voxblox-Node.html
use_tf_transforms
If true the ros tf tree will be used to get the pose of the sensor relative to the world (sensor_frame and world_frame will be used). If false the pose must be given via the transform topic.
Originally posted by @ToniRV in #26 (comment)
sguttikon commented
@shabpompeiano Where you able to solve the issue?