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 Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

8.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
8.0K
Detection of Black Holes01:10

Detection of Black Holes

2.5K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.5K

You might also read

Related Articles

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

Sort by
Same author

SMDNet: A Self-Training-Aware and Multi-Modal-Adaptive Deep Learning Network for Low-Data Aβ<sub>42</sub> Probe Design and Optimization.

Journal of medicinal chemistry·2026
Same author

A Contrastive-Learning-Based Pre-Training Framework for Optical Property Prediction of Low-Data Rhodamines with Interpretable Multitask Graph Neural Networks.

Molecules (Basel, Switzerland)·2026
Same author

Revealing GRK5 Activation Features by Interpretable Machine Learning and Molecular Dynamics Simulation.

International journal of molecular sciences·2026
Same author

Thermostability Prediction Powered by Synergistic Deep Learning at Experimental and Theoretical Levels for Nanobodies.

ACS applied materials & interfaces·2026
Same author

Machine Learning Navigated Allosteric Network to Unveil Biased Allosteric Modulation of GPCRs.

Journal of chemical theory and computation·2025
Same author

TRIM21-Driven Degradation of BRD4: Development of Heterobifunctional Degraders and Investigation of Recruitment and Selectivity Mechanisms.

Journal of chemical information and modeling·2025

Related Experiment Video

Updated: Dec 22, 2025

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

930

A Novel Detector Based on Convolution Neural Networks for Multiscale SAR Ship Detection in Complex Background.

Wenxin Dai1, Yuqing Mao2, Rongao Yuan1

  • 1College of Computer Science, Sichuan University, Chengdu 610065, China.

Sensors (Basel, Switzerland)
|May 6, 2020
PubMed
Summary

This study introduces a novel Convolutional Neural Network (CNN) detector for improved synthetic aperture radar (SAR) ship detection. The new method enhances detection of multiscale and small ships, even in complex backgrounds.

Keywords:
complex backgroundconvolutional neural network (CNN)multiscale and small ship detectionship detectionsynthetic aperture radar (SAR)

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

Related Experiment Videos

Last Updated: Dec 22, 2025

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

930
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Artificial Intelligence

Background:

  • Convolutional Neural Network (CNN) detectors show promise for Synthetic Aperture Radar (SAR) ship detection.
  • Existing models struggle with detecting multiscale and small ships against complex backgrounds.

Purpose of the Study:

  • To develop a novel CNN-based ship detector for enhanced SAR image analysis.
  • To improve the detection accuracy of multiscale and small ships in challenging SAR imagery.

Main Methods:

  • A novel CNN framework comprising a Fusion Feature Extractor Network (FFEN), Region Proposal Network (RPN), and Refine Detection Network (RDN).
  • Feature fusion using bottom-up and top-down approaches within FFEN and merging RoI features in RDN.
  • Integration of residual blocks to increase network depth for improved precision.

Main Results:

  • The proposed method significantly enhances location and semantic information for multiscale ships, especially small ones.
  • Validation on the SAR Ship Dataset (SSDD) and Gaofen-3 satellite data demonstrates superior performance compared to existing models.
  • The detector shows excellent performance in identifying multiscale and small ships.

Conclusions:

  • The novel CNN framework effectively addresses limitations in current SAR ship detection models.
  • The proposed feature representation strategy and network architecture enhance detection capabilities for challenging targets.
  • The method holds high potential for practical applications in SAR image analysis.