Comprehensive Track Unswappinng for Improved Tracker Performance

In practical surveillance systems, multiple-target tracking can suffer from undesirable effects such as track breakages and track swaps. Track stitching or track segment association (TSA) algorithms have been proposed in the literature to stitch broken tracks deemed to have originated from the same target across time and to improve track continuity. Measurements from multiple neighboring targets may fall within the validation gates of one another, causing association errors that may eventually lead to not just track breaks but also track swaps. Therefore, TSA alone is insufficient to improve the overall tracker performance, as it considers only the broken tracks but not the continuous ones that might have swaps among themselves or with other broken tracks. To mitigate the effects of track swaps, this article proposes an algorithm that detects and resolves possible track swaps using kinematic and nonkinematic—classification and amplitude—information. Track swap detection involves identifying the most likely instant of track swap occurrence. Further, the proposed algorithm is extended to stitch broken track segments (as in the standard TSA) and those tracks that are algorithmically broken due to the detection of possible swaps. Simulation results demonstrate the effectiveness of the proposed algorithm in resolving track swaps and thereby improving track purity and the overall tracker performance.

• Publication year

  2025

• Venue

  IEEE Transactions on Aerospace and Electronic Systems

• Publication date

  2025-10-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/TAES.2025.3556810
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Track Segment Association With Dual Contrast Neural Network

  2021cited by this paper
• Comprehensive Track Segment Association for Improved Track Continuity

  2018cited by this paper
• Track Segment Association Based on Expectation-Maximization Algorithm for Joint Estimate and Identification

  2015influential reference
• Tracking through Occlusions and Track Segmentation Reduction

  2013cited by this paper
• Performance analysis of graph-based track stitching

  2013cited by this paper
• Track segment association with classification information

  2012cited by this paper
• Dynamic UAV path planning for multitarget tracking

  2012cited by this paper
• A multiple hypothesis tracker with interacting feature extraction

  2012cited by this paper
• Track Quality Based Multitarget Tracking Approach for Global Nearest-Neighbor Association

  2012cited by this paper
• Track Segment Association for GMTI Tracks of Evasive Move-Stop-Move Maneuvering Targets

  2011cited by this paper
• Decomposed particle filtering and track swap estimation in tracking two closely spaced targets

  2011cited by this paper
• Multi-target tracklet stitching through network flows

  2011cited by this paper
• An algorithm for reducing the swap of targets during the marine radar tracking

  2010influential reference
• New developments in flexible ID association-based tracking algorithm

  2010influential reference
• Multihypothesis Viterbi Data Association: Algorithm Development and Assessment

  2010influential reference
• Simultaneous tracking and classification: a modularized scheme

  2007cited by this paper
• Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information

  2006cited by this paper
• Adaptive multiaspect target classification and detection with hidden Markov models

  2005cited by this paper
• On target classification using kinematic data

  2004cited by this paper
• Multisensor track-to-track association for tracks with dependent errors

  2004cited by this paper
• Tracking with classification-aided multiframe data association

  2003cited by this paper
• An Automated Approach to Passive Sonar Track Segment Association

  2002cited by this paper
• Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software

  2001influential reference
• Multiaspect classification of airborne targets via physics-based HMMs and matching pursuits

  2001cited by this paper
• m-best S-D assignment algorithm with application to multitarget tracking

  2001cited by this paper
• A generalized S-D assignment algorithm for multisensor-multitarget state estimation

  1997influential reference
• India

  1995cited by this paper
• Low observable target motion analysis using amplitude information

  1995cited by this paper
• Interacting multiple model tracking with target amplitude feature

  1993cited by this paper
• Track Segment Association with a Distributed Field of Sensors

  1984cited by this paper
• Sliding Window Detection Probabilities

  1976cited by this paper

• No citing papers are available for this paper.