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: Jun 27, 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

EDM-Net: A Multi-Scale Network for Object Detection in Remote Sensing Images.

Shuai Liang^1,2, Xiao Wang^1,2, Jialong Sun^1,2

¹School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222000, China.

Sensors (Basel, Switzerland)

|June 26, 2026

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

Efficient one-pot lactic acid production from cellulose via a Trichoderma reesei and Bacillus coagulans cooperation leveraging substrate-induced secretomes.

Bioresource technology·2026

Same author

TkNACs Heterodimerization and Methyl Jasmonate Signaling Synergistically Mediate Root Development in <i>Taraxacum kok-saghyz</i>.

Plants (Basel, Switzerland)·2026

Same author

The temporal dynamics of public attention to aviation safety events.

Journal of safety research·2026

Same author

Downregulation of Nrf2 and upregulation of TXNIP/NLRP3 signaling Induce postoperative cognitive dysfunction via oxidative stress and pyroptosis in the hippocampus.

Neuroscience·2026

Same author

Probiotic Effects of Marichromatium gracile DH-1 on Growth, Stress Resistance, and Water Quality in Juvenile Seahorses: A Potential Strategy for Sustainable Aquaculture.

Probiotics and antimicrobial proteins·2026

Same author

Hydrogen Sulfide Protects Against Cerebral Ischemia-Reperfusion Injury in Rats via S-Sulfhydrating NAMPT to Enhance Mitochondrial Function and Autophagy in Cerebrovascular Endothelial Cells.

Pharmaceuticals (Basel, Switzerland)·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

EDM-Net enhances remote sensing object detection by adaptively extracting, interacting, and fusing multi-scale features. This novel approach improves accuracy for objects with varying scales and dense layouts in complex backgrounds.

Area of Science:

Computer Vision
Remote Sensing
Artificial Intelligence

Background:

Remote sensing object detection faces challenges due to scale variation, dense layouts, and complex backgrounds.
Existing methods struggle to effectively handle these coupled difficulties.

Purpose of the Study:

To propose EDM-Net, an end-to-end multi-scale detector for improved remote sensing object detection.
To address scale variation, dense spatial layouts, and background interference.

Main Methods:

EDM-Net employs three coordinated stages: adaptive extraction, intra-scale interaction, and cross-scale fusion.
Key modules include efficient sparse mixture-of-experts (ES-MoE), dynamic mixing intra-scale feature interaction (DMIFI), and multi-scale synergistic attention fusion (MSAF).

Keywords:

cross-scale feature fusion intra-scale feature interaction multi-scale object detection remote sensing object detection transformer

Related Experiment Videos

Last Updated: Jun 27, 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

Main Results:

EDM-Net achieved superior performance on DIOR, NWPU VHR-10, and RSOD datasets, outperforming the RT-DETR-R18 baseline.
Attained mAP50 scores of 83.7%, 95.6%, and 95.8% respectively.
Demonstrated significant gains, particularly for small and densely distributed objects.

Conclusions:

Coordinated feature extraction, interaction, and fusion are effective for remote sensing object detection.
EDM-Net offers a robust solution for complex remote sensing scenarios.