EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation

Jun Yin, Fei Wu, Hao Su iD, Peng Huang, Yuetong Qixuan

Sensors · 05.07.2025 · 25 (13) · 4199

DOI: 10.3390/s25134199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.07.2025. Verfasst von Jun Yin und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Segment Anything Model 2 (SAM2) has achieved state-of-the-art performance in pixel-level object segmentation for both static and dynamic visual content. Its streaming memory architecture maintains spatial context across video sequences, yet struggles with long-term tracking due to its static inference framework. SAM 2’s fixed temporal window approach indiscriminately retains historical frames, failing to account for frame quality or dynamic motion patterns. This leads to error propagation and tracking instability in challenging scenarios involving fast-moving objects, partial occlusions, or crowded environments. To overcome these limitations, this paper proposes SAM2Plus, a zero-shot enhancement framework that integrates Kalman filter prediction, dynamic quality thresholds, and adaptive memory management. The Kalman filter models object motion using physical constraints to predict trajectories and dynamically refine segmentation states, mitigating positional drift during occlusions or velocity changes. Dynamic thresholds, combined with multi-criteria evaluation metrics (e.g., motion coherence, appearance consistency), prioritize high-quality frames while adaptively balancing confidence scores and temporal smoothness. This reduces ambiguities among similar objects in complex scenes. SAM2Plus further employs an optimized memory system that prunes outdated or low-confidence entries and retains temporally coherent context, ensuring constant computational resources even for infinitely long videos. Extensive experiments on two video object segmentation (VOS) benchmarks demonstrate SAM2Plus’s superiority over SAM 2. It achieves an average improvement of 1.0 in J&F metrics across all 24 direct comparisons, with gains exceeding 2.3 points on SA-V and LVOS datasets for long-term tracking. The method delivers real-time performance and strong generalization without fine-tuning or additional parameters, effectively addressing occlusion recovery and viewpoint changes. By unifying motion-aware physics-based prediction with spatial segmentation, SAM2Plus bridges the gap between static and dynamic reasoning, offering a scalable solution for real-world applications such as autonomous driving and surveillance systems.

Schlagwörter

Stichwörter der Autor:innen

Kalman filterLVOSSA-VSAM 2long-term video

Autor:innen und Institutionen

  • School of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China.
  • Zhejiang Dahua Technology Co., Ltd., Hangzhou 310053, China.

ORCID-Profile: Hao Su

Zitieren

APA

Yin, J., Wu, F., Su, H., Huang, P., & Qixuan, Y. (2025). Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation. Sensors, 25(13), 4199. https://doi.org/10.3390/s25134199

Vancouver

Yin J, Wu F, Su H, Huang P, Qixuan Y. Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation. Sensors. 2025;25(13):4199. doi:10.3390/s25134199

BibTeX
@article{Yin2025,
  author = {Yin, Jun and Wu, Fei and Su, Hao and Huang, Peng and Qixuan, Yuetong},
  title = {Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4199},
  doi = {10.3390/s25134199}
}
Kostenlos starten →