mikkelkh / fieldsafe Goto Github PK

Thanks for your great work in creating this dataset and for posting details on how you created it. I am looking to create a similar dataset for my own purposes. Which tool did you use to label your dataset? I have been looking at tools like semantiic segmentation editor and semantic-kitti which can load many point clouds at once but was unsure how to best handle dynamic obstacles.

Hi,

I would like to enlarge the dataset. Will this be possibile? Do you have any standardization in place for this procedure? Or at least a checklist on how to organize the data?

Thanks.

Best,
Matteo

Hi

I couldnt able to see and access the dataset,there is any otherway or resource to use the fieldsafe website and dataset?

Thanks for the dataset. I am looking at using it in my own research, however, I have a few questions regarding the demo.launch.

1. I noticed in the rtk_gps_node you subscribe to the topic /fmData/can_rx_rtk_gps but, this topic does not exist (in the list of provided topics or in the example bag). This means that /Trimble_rtk_gps/course_speed_can and /Trimble_rtk_gps/GNSS_position_data_can are not generated. Are these topics not required?
2. In the robot_localization.launch you use a navsat_transform_node to produce odometry from GPS. Why do you utilise the /Trimble_rtk_gps/imu topic, created by converting the GPS heading data into a sensor_msgs/Imu message, rather than utilising the /VectorNav_IMU/imu topic? Is it simply to increase the amount of information going into the EKF?

Thanks for the open-source.
I just found this from your paper-

remaining sensors were synchronized in software using a best effort approach in ROS

under the topic synchronization in section 2-sensor setup.
I wanted to know how exactly the usb webcam,lidar and imu can be synchronized using ROS.
Also,what was the synchronization error you obtained using ROS.
Any suggestion is greatly appreciated.
Thankyou

I'm getting these errors when running the pose_estimation launch file:

[ WARN] [1687370573.898947213]: Could not obtain transform from RTK_GPS_HEADING to base_link. Error was "RTK_GPS_HEADING" passed to lookupTransform argument source_frame does not exist. 

[ WARN] [1687370573.899616218]: Could not obtain transform from RTK_GPS to base_link. Error was "RTK_GPS" passed to lookupTransform argument source_frame does not exist. 

[ WARN] [1687370573.899663829]: Unable to obtain base_link->RTK_GPS transform. Will assume navsat device is mounted at robot's origin

And indeed I see no transform connecting these frames. Is this on purpose?

I see the following:

<!-- BASE LINK -->
	<!-- Child frame for robot_localization and robot_pose_ekf, should be actually the projection of base_link_mount to the ground.
		   It is calculated with respect of the height delivered by the velodyne: TODO: SHOULD BE A DYNAMIC TRANSFORM -->
	<node pkg="tf2_ros" type="static_transform_publisher" name="base_tf_broadcaster" args="0 0 .9097 0 0 0  base_link base_link_mount" />

which starts and ends there, there's no other transformations from or to base_link or base_link_mount.

The FieldSAFE Dataset website points to two calibration files, namely:

• https://vision.eng.au.dk/data/FieldSAFE/ParamsMultiSenseLeft.mat
• https://vision.eng.au.dk/data/FieldSAFE/ParamsFlirA65.mat
  which when read with a current version of MATLAB (ex 2023b) only seem to show parameters for one of the cameras (for example for the first, it shows as having a single cameraParameters and not a stereoParameters).

Could you provide some pointers on how to use this file? For example the version of MATLAB used to generate them?
Otherwise, could you provide a converter to a more recent version or to a more generally readable file (like a yaml or something that can be read by an open-source software like python + OpenCV?).

Thanks! I'm open to help on this because I would really like to use the dataset.

Thanks for your great work，I would like to know what the paper mentions about the moving obstacles were manually annotated in each frame of one of the videos using the vatic video annotation tool,Where is this labelled data？