OS22-3 Multi-Frame Track-Before-Detect with Adaptive Number of Frame as Noise Level

Title:	OS22-3 Multi-Frame Track-Before-Detect with Adaptive Number of Frame as Noise Level
Publication:	ICAROB2025
Volume:	30
Pages:	605-608
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2025.OS22-3
Author(s):	Je Hwa Lee, Jae Hong Lee, Chan Gook Park
Publication Date:	February 13, 2025
Keywords:	multi-frame track-before-detect, target tracking, adaptive number of frame, maneuvering target
Abstract:	Multi-frame Track-Before-Detect (MF-TBD) is a batch processing method used to enhance detection and tracking performance in low SNR environments. Unlike traditional filtering techniques, MF-TBD does not apply thresholding and instead uses all observed data to reduce the risk of target loss. By integrating observations across multiple frames, it leverages space-time correlations to improve detection robustness. However, as the number of frames increases, the computational cost grows exponentially due to the need to correlate data over a larger dataset, leading to inefficiencies. Especially in high SNR conditions, where fewer frames are sufficient for accurate detection. To address this, we propose an Adaptive MF-TBD framework that dynamically adjusts the number of frames based on SNR levels.
PDF File:	https://alife-robotics.co.jp/members2025/icarob/data/html/data/OS/OS22/OS22-3.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

HOME