LIDAR, Dpeth-camera, Pedestrian Tracking, Kalman-filter

Robust Pedestrian Tracking Against Occlusions in Public Spaces Using 3D Point Clouds from Depth/LiDAR Sensors

We propose an approach to pedestrian tracking in a public passageway with pedestrians, such as those carrying luggage and baby strollers, and family groups close to each other, based on 3D point cloud data captured by a single 3D depth sensor. Since we assume a wall-attached sensor, which is easy to deploy in passageways, pedestrians walking nearby the sensor frequently occlude the others behind. This causes a severe error in pedestrian segmentation in the 3D point cloud and Kalman-filter-based tracking. We introduce a new technique to spatially complement the missing part of segments in Kalman-filter-based multi-object tracking to cope with this issue. We have evaluated our method using the 3D point cloud data capturing pedestrians at the entrance of an existing commercial facility (shopping small) and the one collected in our laboratory space. As a result, the tracking accuracy index (MOTA) for multiple objects is 0.914, with severe and frequent occlusions.


Published Paper:

  • Masakazu Ohno, Riki Ukyo, Tatsuya Amano, Hamada Rizk and Hirozumi Yamaguchi, "Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs", In proc. of 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom 2023) , pp.43--52
    • IEEE xplore:
    • Arxiv:
  • Riki Ukyo, Tatsuya Amano, Akihito Hiromori and Hirozumi Yamaguchi, "Pedestrian Tracking in Public Passageway by Single 3D Depth Sensor", Proceedings of the 2022 IEEE International Workshop on Pervasive Computing for Vehicular Systems Co-located with IEEE PerCom 2022, pp. 581-586
Back to Research Themes