Multi-Object Tracking With Separation in Deep Space

doi:10.1109/TGRS.2024.3522290

Multi-Object Tracking With Separation in Deep Space

2025-01-01

0

PRE

AI

DOI：10.1109/TGRS.2024.3522290

Original

Original request for help

Save

Abstract

En 中文

In deep space environment, some objects may split into several small fragments during movement, and these deep space objects often appear as points in satellite images. In this article, we conduct research on multi-object tracking (MOT) for these objects. First, we propose a simulation dataset, ScatterDataset, which simulates the movement and separation of objects in deep space background. By assigning two IDs to a trajectory, we describe the trajectory's relationship before and after separation. Second, we present an end-to-end motion association model, ScatterNet, which encodes the position information of trajectories and detections into motion features. These features are processed through temporal aggregation by a Transformer encoder and spatial aggregation by a graph network; then, we get the association results by calculating the similarity between these features. Finally, we introduce a tracker, ScatterTracker, which is suitable for tracking in scenarios with object separation. Experiments with state-of-the-art tracking methods on ScatterDataset demonstrate that our approach has achieved significant performance improvements in deep space scenarios. The code is available at: https://github.com/wht-bupt/ScatterTrack.

Keywords:

Trajectory

Tracking

Deep-space communications

Videos

Transformers

Predictive models

Kalman filters

Feature extraction

Deep learning

Satellites

Deep space

graph network

multi-object tracking (MOT)

object separation

position encoding

transformer encoder

Multi-Object Tracking With Separation in Deep Space

Abstract

Journal

Organization