Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

RGB-'D' Saliency Detection With Pseudo Depth.

Xiaolin Xiao, Yicong Zhou, Yue-Jiao Gong

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 20, 2018
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    PM<sub>2.5</sub> exposure exacerbates cerebral infarction via HPG axis downregulation and pituitary lipid metabolism dysregulation in mice.

    Neurotoxicology·2026
    Same author

    Rapid Monitoring of Storage Deterioration in Processed Coix Seeds Using Near-Infrared Spectroscopy Guided by GC-IMS.

    Foods (Basel, Switzerland)·2026
    Same author

    Regional Differences in Sensitization Patterns Among Children with Allergic Asthma in China: A Latent Class Analysis and Age-Related Characteristics.

    Respiratory medicine·2026
    Same author

    EEG Emotion Recognition With Uncertainty-Aware Contrastive Learning and Frequency-Aware Self-Attention.

    IEEE transactions on cybernetics·2026
    Same author

    A deprotection-oxidation cascade-regulated dual-responsive near-infrared fluorescent probe for individual and sequential detection of H<sub>2</sub>S/HClO with applications in food safety monitoring.

    Analytica chimica acta·2026
    Same author

    Polycationic silk fibroin chelating nano-hydroxyapatite promotes angiogenesis for burn wound healing.

    Journal of materials chemistry. B·2026
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    GoP-based Quality Enhancement on Video Compression.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces RGB-D saliency detection, using pseudo-depth from RGB images for enhanced 3D object detection. This approach boosts performance by integrating depth cues into traditional models.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Salient object detection typically uses RGB images, lacking depth information.
    • Human perception effectively uses RGB data for 3D scene understanding.
    • Existing methods struggle to leverage geometric scene properties from RGB images alone.

    Purpose of the Study:

    • To propose a novel RGB-D saliency detection framework by generating pseudo-depth from RGB images.
    • To enhance salient object detection by incorporating derived depth information.
    • To demonstrate the effectiveness and generalizability of the RGB-D saliency approach.

    Main Methods:

    • Deriving pseudo-depth from RGB images to create an RGB-D representation.
    • Utilizing pseudo-depth as image features, prior knowledge, or an additional channel.

    Related Experiment Videos

  • Developing a new salient object detection algorithm incorporating depth-driven background priors and depth contrast features.
  • Adapting existing RGB saliency models to the RGB-D framework.

    • Main Results:

    • The proposed RGB-D saliency algorithm shows promising performance on standard datasets.
    • Integrating pseudo-depth significantly enhances salient object detection accuracy.
    • The RGB-D saliency framework demonstrates strong generalization capabilities when applied to existing models.

    Conclusions:

    • RGB-D saliency detection, leveraging pseudo-depth, offers a powerful method for improving salient object detection.
    • The proposed framework effectively integrates geometric information from RGB images, mimicking human 3D perception.
    • This approach provides a versatile and effective strategy for enhancing various saliency detection models.