Multiple Pedestrian Tracking Using LiDAR Network in Complex Indoor Scenarios

Authors:

Abstract
A LiDAR network is exploited for multiple human targets tracking in a complex indoor scenario. LiDAR are scattered across the surveillance area, which includes several regions.The human targets maneuver rapidly and may come close to each other. Meanwhile, lots of static objects in the scenario generate a mass of static clutter measurements. In this work, a track-before-detect (TBD) processing framework is developed for human trajectories. Initially, individual and overall clutter maps are constructed to eliminate static clutter. And then, three-dimensional (3D) region growth, 3D projection and tracklet association are applied for addressing the problem of multiple maneuvering targets and extended target. In the actual experiment, five pedestrians maneuver through an area comprising two corridors and a lobby. All human trajectories can be well detected by a network containing three LiDARs without false track or missed detection even though the scenario includes closely parallel tracks and crossed tracks. The average position error of human tracks could be as low as 24cm.
Funding Information
  • China Postdoctoral Science Foundation (2019M663633)
  • Science and Technology on Near-Surface Detection Laboratory (6142414211202)
  • National Natural Science Foundation of China (61771371, 52362050)
  • Civil Aerospace Technology Advanced Research Project (D020403)
  • Fundamental Research Funds for the Central Universities (300102343102)
  • Shaanxi Province Postdoctoral Funding (2023BSHEDZZ216)
  • Qin Chuang Yuan Cites High-Level Innovation or Entrepreneurship Talent (QCYRCXM-2023-110)