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 Video

Updated: Jan 1, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

968

RGB-T Salient Object Detection via Fusing Multi-level CNN Features.

Qiang Zhang, Nianchang Huang, Lin Yao

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |December 24, 2019
    PubMed
    Summary

    This study introduces a new RGB-T salient object detection method using complementary RGB and thermal images. The approach effectively fuses features for improved performance in challenging visual conditions.

    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

    Probabilistic-Based Learning for Joint Light Field Image Compression and Enhancement Under Low-Light Conditions.

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

    Joint color-spatial iterative interaction and metric-based motion filtering for unsupervised polyp segmentation in endoscopic videos.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    Non-contact Heart Sound Measurement by Defocused Speckle Imaging.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

    Nonlinear hydrothermal associations between coupled landscape ecological risk and resilience in a major grain-producing region of China.

    Journal of environmental management·2026
    Same author

    LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding.

    IEEE transactions on pattern analysis and machine intelligence·2026

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Deep Convolutional Neural Networks (CNNs) have advanced RGB-based salient object detection.
    • Existing methods struggle with cluttered backgrounds, low light, and illumination variations.

    Purpose of the Study:

    • To propose a novel end-to-end network for multi-modal salient object detection using RGB and thermal infrared (RGB-T) images.
    • To address the limitations of RGB-only methods by leveraging complementary sensor data.

    Main Methods:

    • Utilizing a backbone network (e.g., VGG-16) for initial feature extraction from individual RGB and thermal images.
    • Employing Adjacent-Depth Feature Combination (ADFC) modules to refine single-modal features at multiple levels.
    • Implementing a Multi-Branch Group Fusion (MGF) module for cross-modal feature fusion at each level.

    Related Experiment Videos

    Last Updated: Jan 1, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    968
  • Integrating fused features using a Joint Attention guided Bi-directional Message Passing (JABMP) module for final saliency prediction.

    • Main Results:

    • The proposed RGB-T salient object detection algorithm demonstrates superior performance over state-of-the-art methods.
    • Significant improvements are observed particularly in challenging scenarios like poor illumination, complex backgrounds, and low contrast.
    • Experimental validation conducted on multiple public RGB-T salient object detection datasets.

    Conclusions:

    • The proposed multi-modal approach effectively overcomes the limitations of single-modality salient object detection.
    • Feature fusion techniques, specifically the ADFC, MGF, and JABMP modules, are crucial for robust performance.
    • The method offers a promising solution for salient object detection in adverse environmental conditions.