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

Deconvolution01:20

Deconvolution

664
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
664

You might also read

Related Articles

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

Sort by
Same author

Seasonal Contrast in Oceanic Regulation of Traditional and Emerging Per- and Polyfluoroalkyl Substances in the Coastal East China Sea.

Environmental science & technology·2025
Same author

Human activities regulate the sources and composition pattern of organic matter in the coastal bays of the East China Sea during spring.

Marine environmental research·2025
Same author

Divergent hemispheric trends in marine dust deposition over the past two decades.

Science bulletin·2025
Same author

Spatiotemporal patterns and driving factors of nitrogen concentrations in Daya bay via remote sensing.

Marine pollution bulletin·2025
Same author

Development of the operational atmospheric correction algorithm for the COCTS2 onboard the Chinese new-generation ocean color satellite.

Optics express·2025
Same author

Satellite estimation of the spectral power exponent of particulate backscattering coefficient in the global ocean.

Optics express·2025

Related Experiment Video

Updated: Mar 15, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

253

Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature.

Jianglei Zhou1, Zhaoyu Wei1, Yisen Zhong1

  • 1School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, China.

Sensors (Basel, Switzerland)
|March 14, 2026
PubMed
Summary

This study introduces an efficient unmanned aerial vehicle (UAV) image stitching method using dense kernelized features and geometric constraints. It significantly reduces stitching time while maintaining high visual quality for large-scale remote sensing images.

Keywords:
dense deep featureefficient stitchinghigh-resolution imagehomographyunmanned aerial vehicle (UAV)

More Related Videos

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.6K

Related Experiment Videos

Last Updated: Mar 15, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

253
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.6K

Area of Science:

  • Computer Vision
  • Remote Sensing
  • Photogrammetry

Background:

  • Unmanned aerial vehicle (UAV) image stitching is crucial for creating panoramic remote sensing images.
  • Traditional methods face challenges with computationally intensive feature extraction and alignment accuracy, especially in high-resolution, low-texture scenes.
  • Existing techniques are often slow and struggle with sparse matching and parallax issues.

Purpose of the Study:

  • To develop an efficient and accurate image stitching method for UAV-based remote sensing.
  • To overcome the limitations of traditional feature matching and alignment in challenging scenarios.
  • To enable rapid and precise generation of large-scale panoramic images.

Main Methods:

  • Proposed an efficient image stitching method incorporating dense depth kernelized feature extraction and geometric constraint optimization.
  • Utilized a learning-based kernelized feature matching framework for subpixel-level dense matching.
  • Implemented a two-layer geometrically constrained mismatching filtering strategy for improved alignment accuracy.
  • Employed a hybrid strategy with single-responsive transform and max-intensity pixel blending for final stitching.

Main Results:

  • Achieved subpixel-level dense matching, overcoming deficiencies of traditional methods like SIFT in high-resolution images.
  • Significantly improved alignment accuracy in low-texture and large-parallax scenarios through the filtering strategy.
  • Experimental results demonstrated comparable visual quality metrics (PSNR, SSIM, LPIPS) to baseline methods.
  • Reduced stitching time to 17.5% of the baseline method, indicating high efficiency.

Conclusions:

  • The proposed method offers a practical and efficient solution for stitching large UAV images.
  • It effectively addresses computational intensity and alignment accuracy challenges in remote sensing image stitching.
  • The technique enables faster and more accurate generation of panoramic remote sensing data.