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: Jul 7, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

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

Published on: December 15, 2023

A neural network filter to detect small targets in high clutter backgrounds.

M V Shirvaikar1, M M Trivedi

  • 1Comput. Vision and Robotics Res. Lab., Tennessee Univ., Knoxville, TN.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary

This study introduces a neural network filter for detecting objects in cluttered thermal infrared aerial images. The filter, trained on raw image data or model-based data, significantly outperforms traditional methods, offering excellent detection and low false alarm rates.

Related Concept Videos

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

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...

You might also read

Related Articles

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

Sort by
Same author

Food environment index and preterm birth rate in the counties of the United States.

Journal of neonatal-perinatal medicine·2023
Same author

A neuro-fuzzy controller for mobile robot navigation and multirobot convoying.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Circular-Mellin features for texture segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·1995
Same author

Simulation and animation of sensor-driven robots.

IEEE transactions on robotics and automation : a publication of the IEEE Robotics and Automation Society·1994

Area of Science:

  • Computer Vision
  • Machine Learning
  • Remote Sensing

Background:

  • Object detection in high-resolution aerial imagery is challenging due to high image clutter.
  • Traditional methods relying on low-level image cues perform poorly in cluttered environments.

Purpose of the Study:

  • To design and train a neural network filter for detecting targets in thermal infrared images.
  • To evaluate the performance of the neural network filter against traditional methods in cluttered aerial imagery.

Main Methods:

  • A neural network filter was developed, utilizing raw gray levels as input and eliminating feature extraction.
  • Two training set approaches were employed: actual image data and a model-based approach.
  • The neuron transfer function was modified to enhance convergence and speed, using the backpropagation algorithm for training.

Related Experiment Videos

Last Updated: Jul 7, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

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

Published on: December 15, 2023

Main Results:

  • The neural network filter demonstrated excellent detection and low false alarm rates when tested on real image data.
  • Receiver operating characteristic (ROC) curves confirmed the filter's effectiveness.
  • Performance was significantly superior to the size-matched contrast-box filter, particularly in highly cluttered images.

Conclusions:

  • Neural network filters are highly effective for object detection in challenging thermal infrared aerial imagery.
  • The proposed method, using raw gray levels and tailored training sets, offers a robust solution for cluttered environments.
  • This approach provides a substantial improvement over conventional filtering techniques for aerial surveillance and object recognition.