Giters

praveen-palanisamy / multiple-object-tracking-lidar

C++ implementation to Detect, track and classify multiple objects using LIDAR scans or point cloud

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Moving platform

YangSiri opened this issue · comments

commented

Hi, i think you've done a great job with this simple lidar tracker. Here i'd like to raise a question about its adaptation on outdoor moving platform. Is it robust ?

commented

Hey @YangSiri : Thank you. The algorithms used are applicable to outdoor moving platform too. In fact, this was developed mainly for outdoor autonomous navigation application. Though, I haven't tested this extensively at very high speeds.

commented

That's great. Thanks for your reply. I'm gonna try it.

commented

So I installed this and ROS and everything and started ROS. Got to this point

Run the kf_tracker ROS node in this package: rosrun multi_object_tracking_lidar kf_tracker

works ok? So now what do I do?

Right now I have no real data but the two scenarios I am looking at are

  1. what do i do next when I do get a lidar?

  2. how do I continue to run it on test data and actually see the output?

Thanks in advance for your help!

commented

hey @wanfuse123 : Glad that you are able to run the ROS node.

  1. Run the node on your robot/platform on which you will be mounting the LIDAR to detect/cluster and track obstacles/objects.
  2. You can also just use logged LIDAR data (eg. Played from a rosbag file) to test. Once you have the kf_tracker node running, as long as you have the point clouds (from LIDAR or other pointcloud generator) published on to the filtered_cloud rostopic, you should see outputs published onto the obj_id, cluster_0, cluster_1, …, cluster_5 topics along with the markers on viz topic which you can visualize using RViz.
commented

Hi @YangSiri , @wanfuse123 : I'm closing this issue as the questions were answered. Feel free to follow-up if required.