EUVIMEDEUVIMED entdecken
Crossref

ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection

Junhao Lin, Lei Zhu, Jiaxing Shen, Huazhu Fu, Qing Zhang, Liansheng Wang

International Journal of Computer Vision · 2024-11 · 132 (11) · 5173-5191

DOI: 10.1007/s11263-024-02051-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 04.06.2024. Verfasst von Junhao Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 84 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of depth sensor, more and more RGB-D videos could be obtained. Identifying the foreground in RGB-D videos is a fundamental and important task. However, the existing salient object detection (SOD) works only focus on either static RGB-D images or RGB videos, ignoring the collaborating of RGB-D and video information. In this paper, we first collect a new annotated RGB-D video SOD (ViDSOD-100) dataset, which contains 100 videos within a total of 9362 frames, acquired from diverse natural scenes. All the frames in each video are manually annotated to a high-quality saliency annotation. Moreover, we propose a new baseline model, named attentive triple-fusion network (ATF-Net), for RGB-D video salient object detection. Our method aggregates the appearance information from an input RGB image, spatio-temporal information from an estimated motion map, and the geometry information from the depth map by devising three modality-specific branches and a multi-modality integration branch. The modality-specific branches extract the representation of different inputs, while the multi-modality integration branch combines the multi-level modality-specific features by introducing the encoder feature aggregation (MEA) modules and decoder feature aggregation (MDA) modules. The experimental findings conducted on both our newly introduced ViDSOD-100 dataset and the well-established DAVSOD dataset highlight the superior performance of the proposed ATF-Net.This performance enhancement is demonstrated both quantitatively and qualitatively, surpassing the capabilities of current state-of-the-art techniques across various domains, including RGB-D saliency detection, video saliency detection, and video object segmentation. We shall release our data, our results, and our code upon the publication of this work.

Zitieren

APA

Lin, J., Zhu, L., Shen, J., Fu, H., Zhang, Q., & Wang, L. (2024). ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection. International Journal of Computer Vision, 132(11), 5173-5191. https://doi.org/10.1007/s11263-024-02051-5

Vancouver

Lin J, Zhu L, Shen J, Fu H, Zhang Q, Wang L. ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection. International Journal of Computer Vision. 2024;132(11):5173-5191. doi:10.1007/s11263-024-02051-5

BibTeX
@article{Lin2024,
  author = {Lin, Junhao and Zhu, Lei and Shen, Jiaxing and Fu, Huazhu and Zhang, Qing and Wang, Liansheng},
  title = {ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection},
  journal = {International Journal of Computer Vision},
  year = {2024},
  volume = {132},
  number = {11},
  pages = {5173--5191},
  doi = {10.1007/s11263-024-02051-5}
}
Kostenlos starten →