Occlusion-aware multi-object tracking via Seq2Seq LSTM-based trajectory prediction in manufacturing environments

Yumin Kim

doi:10.1007/s10845-026-02940-1

Occlusion-aware multi-object tracking via Seq2Seq LSTM-based trajectory prediction in manufacturing environments

2026-08-07

0

PRE

AI

Y

Yumin Kim

Y

Yunho Seo

H

Haejoong Kim *

DOI：10.1007/s10845-026-02940-1

Original

Original request for help

Save

Abstract

En 中文

Vision-based real-time locating system (RTLS) approaches are promising for material tracking in smart manufacturing, in which multi-object tracking (MOT) plays a key role in autonomous logistics and process automation. However, conventional tracking algorithms often suffer from identity switches and trajectory fragmentation due to frequent occlusions, multiple visually indistinguishable objects, and nonlinear motion patterns in manufacturing environments. To overcome these limitations, this study develops a controlled, scaled-down, manufacturing-like conveyor testbed and proposes a prediction-assisted BoT-SORT framework integrated with a Seq2Seq LSTM module. Unlike conventional Kalman filter-based methods that rely on a constant-velocity assumption, the proposed Seq2Seq LSTM learns complex kinematic patterns from historical displacement sequences to predict object positions during occlusion. Experimental results show that the proposed method consistently improves tracking robustness in the controlled testbed. In the short-term occlusion scenario, the proposed framework reduced the mean number of identity switches (IDSWs) from 4.75 to 0.75 compared with the baseline BoT-SORT, corresponding to a reduction of approximately 84.2%. It also maintained object identity under extended occlusion and complex motion conditions in which existing appearance- and linear motion-based trackers showed severe performance degradation. Furthermore, despite the integration of the deep learning module, the additional computational overhead remained minimal, supporting the feasibility of real-time operation in high-speed production environments. This study provides a practical and robust approach to maintaining identity consistency in manufacturing environments where visual homogeneity and kinematic complexity coexist.

Keywords:

Real-time locating system (RTLS)

Multi-object tracking (MOT)

Occlusion

Identity switch (IDSW)

Seq2Seq LSTM

Trajectory prediction

Occlusion-aware multi-object tracking via Seq2Seq LSTM-based trajectory prediction in manufacturing environments

Abstract

Journal

Organization

Cited Papers

Citing Papers