search

s-duuu / pred_fusion

Object Trajectory Prediction using ROS, YOLOv5, PointPillars, CRAT-Pred
14 stars 2 forks source link

rviz does not display or rarely displays 3D detection boxes #4

Open FYYLHH opened 1 year ago

FYYLHH commented 1 year ago

Hello, when I am applying my own radar data, rviz does not display or rarely displays 3D detection boxes. Is this related to my data? Where can I modify the code? (I am using Raytheon 16 line LiDAR), the 3D detection frame of the KITTI dataset can be displayed. Looking forward to your reply, thank you Best wishes

s-duuu commented 1 year ago

3D bounding boxes detected by PointPillars model are published as a ROS topic (type : jsk_recognition_msgs/BoundingBoxArray / topic name : pillars/detections). It is displayed by fusion_display.rviz file, and it is executed by integrated.launch file.

So, please check that if your PointPillars detection result is well being published as the topic I mentioned.

Thanks.