EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SiamSMN: Siamese Cross-Modality Fusion Network for Object Tracking

Shuo Han, Lisha Gao, Yue Wu, Tian Wei, Manyu Wang, Xu Cheng

Information · 19.07.2024 · 15 (7) · 418

DOI: 10.3390/info15070418 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 19.07.2024. Verfasst von Shuo Han und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research on Cloud Edge Collaborative Intelligent Image Analysis Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The existing Siamese trackers have achieved increasingly successful results in visual object tracking. However, the interactive fusion among multi-layer similarity maps after cross-correlation has not been fully studied in previous Siamese network-based methods. To address this issue, we propose a novel Siamese network for visual object tracking, named SiamSMN, which consists of a feature extraction network, a multi-scale fusion module, and a prediction head. First, the feature extraction network is used to extract the features of the template image and the search image, which is calculated by a depth-wise cross-correlation operation to produce multiple similarity feature maps. Second, we propose an effective multi-scale fusion module that can extract global context information for object search and learn the interdependencies between multi-level similarity maps. In addition, to further improve tracking accuracy, we design a learnable prediction head module to generate a boundary point for each side based on the coarse bounding box, which can solve the problem of inconsistent classification and regression during the tracking. Extensive experiments on four public benchmarks demonstrate that the proposed tracker has a competitive performance among other state-of-the-art trackers.

Förderung

  • Research on Cloud Edge Collaborative Intelligent Image Analysis Technology

Zitieren

APA

Han, S., Gao, L., Wu, Y., Wei, T., Wang, M., & Cheng, X. (2024). SiamSMN: Siamese Cross-Modality Fusion Network for Object Tracking. Information, 15(7), 418. https://doi.org/10.3390/info15070418

Vancouver

Han S, Gao L, Wu Y, Wei T, Wang M, Cheng X. SiamSMN: Siamese Cross-Modality Fusion Network for Object Tracking. Information. 2024;15(7):418. doi:10.3390/info15070418

BibTeX
@article{Han2024,
  author = {Han, Shuo and Gao, Lisha and Wu, Yue and Wei, Tian and Wang, Manyu and Cheng, Xu},
  title = {SiamSMN: Siamese Cross-Modality Fusion Network for Object Tracking},
  journal = {Information},
  year = {2024},
  volume = {15},
  number = {7},
  pages = {418},
  doi = {10.3390/info15070418}
}
Kostenlos starten →