EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3D CNN Architecture for Video Scene Interpretation to Assist People With Visual Impairments

Miguel Ruiz Adarmes, David Mauricio, Luis Rivera, Jimmy Aurelio Rosales Huamani

IEEE Access · 2026 · 14 · 86298-86312

DOI: 10.1109/access.2026.3699268 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Miguel Ruiz Adarmes und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video scene understanding in computer vision requires robust models capable of capturing both spatial and temporal information. Convolutional neural networks (CNNs) have traditionally excelled at extracting spatial features, while transformers have demonstrated superior performance in modeling sequential data and long-range dependencies. This paper proposes a 3D CNN architecture for video scene understanding in computer vision for the visually impaired, evaluating it based on performance metrics of accuracy and computational efficiency for action recognition in videos. The results reveal that the proposed model excels in modeling local spatial features and long-range dependencies, achieving an accuracy of 85.09% for validation. The article concludes with perspectives on future research directions, emphasizing the need for optimized architectures and improved datasets. Furthermore, experimental validation on an NVIDIA RTX A1000 GPU with 8 GB memory demonstrates that our model achieves a favorable accuracy-resource trade-off, requiring only 1240 MB of GPU memory and 92 ms inference time per video, outperforming Transformer-based methods in resource-constrained scenarios.

Zitieren

APA

Adarmes, M. R., Mauricio, D., Rivera, L., & Huamani, J. A. R. (2026). 3D CNN Architecture for Video Scene Interpretation to Assist People With Visual Impairments. IEEE Access, 14, 86298-86312. https://doi.org/10.1109/access.2026.3699268

Vancouver

Adarmes MR, Mauricio D, Rivera L, Huamani JAR. 3D CNN Architecture for Video Scene Interpretation to Assist People With Visual Impairments. IEEE Access. 2026;14:86298-86312. doi:10.1109/access.2026.3699268

BibTeX
@article{Adarmes2026,
  author = {Adarmes, Miguel Ruiz and Mauricio, David and Rivera, Luis and Huamani, Jimmy Aurelio Rosales},
  title = {3D CNN Architecture for Video Scene Interpretation to Assist People With Visual Impairments},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {86298--86312},
  doi = {10.1109/access.2026.3699268}
}
Kostenlos starten →