12345qiupeng
/
multiple-object-tracking-lidar
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6 Commits
1 Branch
0 Tags
82 KiB
C++ 91.6%
CMake 8.4%
 
 
Go to file
Praveen Palanisamy 6fbb298128 Updated package info & version num 2019-04-13 12:05:25 -04:00
include/kf_tracker v1. Object ID/data association works. In this version PCL based unsupervised clustering is done separately. 2015-12-07 17:20:12 -05:00
src Working state of Multiple object stable tracking using Lidar scans with an extended Kalman Filter (rosrun kf_tracker tracker). A naive tracker is implemented in main_naive.cpp for comparison (rosrun kf_tracker naive_tracker). 2015-12-10 17:13:49 -05:00
.gitignore v1. Object ID/data association works. In this version PCL based unsupervised clustering is done separately. 2015-12-07 17:20:12 -05:00
CMakeLists.txt v1. Object ID/data association works. In this version PCL based unsupervised clustering is done separately. 2015-12-07 17:20:12 -05:00
README.md Updated with a short demo on sample AV LIDAR scans 2018-07-23 23:32:18 -04:00
package.xml Updated package info & version num 2019-04-13 12:05:25 -04:00

README.md

Multiple objects detection, tracking and classification from LIDAR scans/point-clouds

Sample demo of multiple object tracking using LIDAR scans

PCL based ROS package to Detect/Cluster --> Track --> Classify static and dynamic objects in real-time from LIDAR scans implemented in C++.

Features:

  • K-D tree based point cloud processing for object feature detection from point clouds
  • Unsupervised k-means clustering based on detected features and refinement using RANSAC
  • Stable tracking (object ID & data association) with an ensemble of Kalman Filters
  • Robust compared to k-means clustering with mean-flow tracking