Multi-Frame Track-Before-Detect for Scalable Extended Target Tracking

EasyChair Preprint 8275

Abstract

This paper mainly addresses the scalable detection and tracking of the extended target in the low signal-to-noise(SNR) environment. As the appearance and shape of the extended target are constantly varied, it is challenging to achieve robust detection and tracking. For this, a novel adaptive scale (AS) kernelized correlation filter (KCF) based on multi-frame track-before-detect (MF-TBD) framework is proposed. By embedding scaling pools into the response map to handle the scale variation and accumulating target energy overall feasible trajectories, AS-MF-TBD estimates the kinematic state and geometric shapes simultaneously. Both simulation data and real radar data are used to demonstrate the superiority of the proposed method in terms of detection performance and estimation accuracy.

Keyphrases: Extended Target Tracking, Kernelized Correction Filter, Multi-frame Detect, adaptive scale, track-before-detect

@booklet{EasyChair:8275,
  author    = {Desheng Zhang and Wujun Li and Shixing Yang and Yingshun Wang and Chuan Zhu and Wei Yi},
  title     = {Multi-Frame Track-Before-Detect for Scalable Extended Target Tracking},
  howpublished = {EasyChair Preprint 8275},
  year      = {EasyChair, 2022}}