In this video we showcase the ability of the two presented approaches (the voxel grid based approach and the clustering based approach) to detect, classify and track moving humans and robot arms.
The voxel based approach is based on the work of Azim et al:
Asma Azim and Olivier Aycard, Detection, classification and tracking of moving
objects in a 3D environment. In 2012 IEEE Intelligent Vehicles Symposium.
The clustering based approach, as well as the classifier and tracker used in both approaches is based on the work of Yan et al. :
Zhi Yan, Tom Duckett, and Nicola Bellotto. Online learning for human Classification in 3D LiDAR-based tracking. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Zhi Yan, Tom Duckett, and Nicola Bellotto. Online learning for 3D LiDAR-based human detection: experimental analysis of point cloud clustering and classification methods. Autonomous Robots, 44(2):147–164, 2020.
