szm88 / hdl_people_tracking

Real-time people tracking using a 3D LIDAR

hdl_people_tracking

hdl_people_tracking is a ROS package for real-time people tracking using a 3D LIDAR. It first performs Haselich's clustering technique to detect human candidate clusters, and then applies Kidono's person classifier to eliminate false detections. The detected clusters are tracked by using Kalman filter with a contant velocity model.

Video:

Requirements

hdl_people_tracking requires the following libraries:

• OpenMP
• PCL 1.7

The following ros packages are required:

• pcl_ros
• ndt_omp
• hdl_localization

Example

Bag file (recorded in an outdoor environment):

• hdl_400.bag.tar.gz (933MB)

rosparam set use_sim_time true
roslaunch hdl_people_tracking hdl_people_tracking.launch

roscd hdl_localizatrion/rviz
rviz -d hdl_localizatrion.rviz

rosbag play --clock hdl_400.bag

If it doesn't work well, change ndt_neighbor_search_method in hdl_localization.launch to "DIRECT1". It makes the scan matching significantly fast, but a little bit unstable.

Related packages

• hdl_graph_slam
• hdl_localization
• hdl_people_tracking

Papers

Kenji Koide, Jun Miura, and Emanuele Menegatti, A Portable 3D LIDAR-based System for Long-term and Wide-area People Behavior Measurement, IEEE Transactions on Human-Machine Systems (under review) [PDF].

Contact

Kenji Koide, Active Intelligent Systems Laboratory, Toyohashi University of Technology [URL]
[e-mail]