Learning-based tracking of fast moving objects

Tracking fast moving objects, which appear as blurred streaks in video sequences, is a difficult task for standard trackers as the object position does not overlap in consecutive video frames and texture information of the objects is blurred. Up-to-date approaches tuned for this task are based on background subtraction with static background and slow deblurring algorithms. In this paper, we present a tracking-bysegmentation approach implemented using state-of-the-art deep learning methods that performs near-realtime tracking on realworld video sequences. We implemented a physically plausible FMO sequence generator to be a robust foundation for our training pipeline and demonstrate the ease of fast generator and network adaptation for different FMO scenarios in terms of foreground variations
© Copyright 2020 arXiv e-print repository. All rights reserved.

Subjects: video mathematic-logical model real-time processing software table tennis tennis badminton volleyball beach-volley baseball
Notations: technical and natural sciences sport games
Tagging: deep learning k√ľnstliche Intelligenz motion tracking
Published in: arXiv e-print repository
Published: 2020
Issue: 4.5.2020
Pages: 1-7
Document types: article
Language: English
Level: advanced