Year-end Sale % OFF 
Abstract
Tracking extended objects based on measurements provided by light detection and ranging (LIDAR) and millimeter wave radio detection and ranging (RADAR) sensors is a key task to obtain situational awareness in important applications including autonomous driving and indoor robotics. In this paper, we propose probabilistic data association methods for localizing and tracking of extended objects that originate an unknown number of measurements. Our approach is based on factor graphs and the sum-product algorithm (SPA). In particular, we reduce computational complexity in a principled manner by means of “stretching” factors in the graph. After stretching, new variable and factor nodes have lower dimensions than the original nodes. This leads to a reduced computational complexity of the resulting SPA. One of the introduced methods is based on an overcomplete description of data association uncertainty and has a computational complexity that only scales quadratically in the number of objects and linearly in the number of measurements. Without relying on suboptimal preprocessing steps such as a clustering of measurements, it can localize and track multiple objects that potentially generate a large number of measurements. Simulation results confirm that despite their lower computational complexity, the proposed methods can outperform reference methods based on clustering.
Highlights
L OCALIZATION [1]–[7] and multiobject tracking (MOT) [8]–[18] are key tasks to enable machine perception in fields such as autonomous driving, indoor localization, and robotic networks
Prominent methods for classical MOT include probabilistic data association (PDA) [8], multi-hypothesis tracking (MHT) [9]–[11], and methods based on random finite sets (RFS) [12]–[16]
We present simulation results demonstrating the performance of our methods and compare it with that of reference methods
Summary
L OCALIZATION [1]–[7] and multiobject tracking (MOT) [8]–[18] are key tasks to enable machine perception in fields such as autonomous driving, indoor localization, and robotic networks. In [27] a multisensor JPDA filter is combined with a random matrix model for the joint estimation of object extents All these methods suffer form computational complexity that is combinatorial in both the number of measurements and the number of objects. The methods discussed in this paragraph are feasible only if objects produce a small number of measurements, and no more than four objects are in close proximity at any given time Another well-established strategy for data association with extended objects is to perform a suboptimal preprocessing step that provides clusters of measurements. The second method is derived based on a more detailed factorization of the joint posterior PDF This detailed factorization results in factor graphs with a large number of loops, but the computation complexity of the resulting message passing algorithm only scales quadratically in the number of objects and linearly in the number of measurements.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Signal and Information Processing over Networks
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
