Research on Moving Object Segmentation Based on Optical Flow and FastSAM
Electronics · 26.10.2026 · 15 (21) · 4959
DOI: 10.3390/electronics15214959 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 26.10.2026. Verfasst von Boning Zhang und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
FastSAM is a lightweight general-purpose segmentation model built upon YOLOv8-seg as its backbone network, which demonstrates several advantages including fast inference speed, low deployment cost, and high training efficiency. However, it suffers from notable limitations in that object segmentation relies on manually defined prompts, and the model lacks the capability of moving object discovery. To achieve moving object segmentation in a fixed field of view, vector operators are employed to jointly measure the optical flow perturbation features induced by object motion. Based on this, a threshold-adaptive optical flow perturbation region extraction algorithm is designed. The bounding box of the perturbation region is subsequently computed and fed into FastSAM as a box prompt, thereby realizing moving object segmentation in a fixed field of view. The proposed approach achieves satisfactory performance in both single-object and multi-object segmentation scenarios.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, B., Wang, R., Ye, C., & Zhang, W. (2026). Research on Moving Object Segmentation Based on Optical Flow and FastSAM. Electronics, 15(21), 4959. https://doi.org/10.3390/electronics15214959
Vancouver
Zhang B, Wang R, Ye C, Zhang W. Research on Moving Object Segmentation Based on Optical Flow and FastSAM. Electronics. 2026;15(21):4959. doi:10.3390/electronics15214959
BibTeX
@article{Zhang2026,
author = {Zhang, Boning and Wang, Ruohan and Ye, Conghui and Zhang, Wei},
title = {Research on Moving Object Segmentation Based on Optical Flow and FastSAM},
journal = {Electronics},
year = {2026},
volume = {15},
number = {21},
pages = {4959},
doi = {10.3390/electronics15214959}
}
EUVIMED