Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 13, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Asymmetric Feature Consistency Reinforcement Network for Visual-Depth-Thermal Salient Object Detection and a New

Chang Xu, Qingwu Li, Shukai Zhao

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|May 11, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

You might also read

Related Articles

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

Sort by

Same author

Inhalation airflow and ventilation efficiency in subject-specific human upper airways.

Respiratory physiology & neurobiology·2020

Same author

Adverse Effects of Low-Dose Methotrexate in a Randomized Double-Blind Placebo-Controlled Trial: Adjudicated Hematologic and Skin Cancer Outcomes in the Cardiovascular Inflammation Reduction Trial.

ACR open rheumatology·2020

Same author

Preparation and <i>in Vitro</i> Antitumor Study of Two-Dimensional Muscovite Nanosheets.

Langmuir : the ACS journal of surfaces and colloids·2020

Same author

Identification and Bioinformatic Assessment of circRNA Expression After <i>RMI1</i> Knockdown and Ionizing Radiation Exposure.

DNA and cell biology·2020

Same author

Pollution haven or halo? The role of the energy transition in the impact of FDI on SO2 emissions.

The Science of the total environment·2020

Same author

Efficacy and Safety of Bevacizumab Plus Oxaliplatin- or Irinotecan-Based Doublet Backbone Chemotherapy as the First-Line Treatment of Metastatic Colorectal Cancer: A Systematic Review and Meta-analysis.

Drug safety·2020

Researchers developed a new method for Salient Object Detection (SOD) using Visual-Depth-Thermal (VDT) data. Their approach introduces a novel dataset and an Asymmetric Feature Consistency Reinforcement Network (AFCRNet) for improved accuracy in complex scenes.

Area of Science:

Computer Vision
Machine Learning
Data Fusion

Background:

Current Salient Object Detection (SOD) methods struggle with complex environments due to limited datasets and symmetric fusion strategies.
Visual-Depth-Thermal (VDT) data fusion shows promise for robust SOD but lacks comprehensive benchmarks and advanced fusion techniques.

Purpose of the Study:

To address dataset scarcity and fusion limitations in VDT-based SOD.
To propose a novel benchmark dataset (LiTR-2654) and an effective fusion network (AFCRNet) for enhanced SOD performance.

Main Methods:

Constructed the LiTR-2654 dataset with 2,654 spatially aligned VDT image triplets.
Developed the Asymmetric Feature Consistency Reinforcement Network (AFCRNet) with an "Unify-then-Integrate" fusion strategy.

Related Experiment Videos

Last Updated: May 13, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Incorporated a context-guided decoder, cross-level feature interaction, attention mechanisms, and edge supervision for improved segmentation.

Main Results:

AFCRNet effectively utilizes triple-modality cues for accurate SOD.
The proposed method significantly suppresses background interference and highlights salient objects.
Demonstrated superior performance compared to existing methods on multiple datasets.

Conclusions:

The novel LiTR-2654 dataset and AFCRNet advance the field of VDT-based SOD.
The asymmetric fusion strategy and context-guided decoder are key to achieving high accuracy in complex scenarios.
The developed benchmark and method offer practical solutions for real-world SOD applications.