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 Videos

A MAP approach for joint motion estimation, segmentation, and super resolution.

Huanfeng Shen1, Liangpei Zhang, Bo Huang

  • 1State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, China.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 3, 2007
PubMed
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

Prevalence of crt and mdr-1 mutations in Plasmodium falciparum isolates from Grande Comore island after withdrawal of chloroquine.

Malaria journal·2016
Same author

Treatment of proximal and middle one-third humeral fractures with lateral distal tibial helical plate.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2016
Same author

MIF Plays a Key Role in Regulating Tissue-Specific Chondro-Osteogenic Differentiation Fate of Human Cartilage Endplate Stem Cells under Hypoxia.

Stem cell reports·2016
Same author

Tumor Exosomal RNAs Promote Lung Pre-metastatic Niche Formation by Activating Alveolar Epithelial TLR3 to Recruit Neutrophils.

Cancer cell·2016
Same author

Ultra-compact strain- and temperature-insensitive torsion sensor based on a line-by-line inscribed phase-shifted FBG.

Optics express·2016
Same author

The Safety and Immunological Effects of rAd5-EBV-LMP2 Vaccine in Nasopharyngeal Carcinoma Patients: A Phase I Clinical Trial and Two-Year Follow-Up.

Chemical & pharmaceutical bulletin·2016
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Multi-Branch Tree-based Fusion Neural Architecture Search with Zero-Cost Screen for Multi-Modal Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a new method for super-resolution image reconstruction, enhancing detail from low-resolution images with moving objects. The approach effectively combines motion estimation, segmentation, and reconstruction for clearer results.

Area of Science:

  • Computer Vision
  • Image Processing

Background:

  • Super-resolution image reconstruction aims to create high-resolution images from multiple low-resolution inputs.
  • Existing methods often struggle with complex scenes containing independently moving objects.

Purpose of the Study:

  • To develop a joint formulation for super-resolution in scenes with multiple independently moving objects.
  • To integrate motion estimation, segmentation, and super-resolution within a unified framework.

Main Methods:

  • A Maximum A Posteriori (MAP) framework was employed for joint formulation.
  • A cyclic coordinate descent optimization procedure was used, alternating between estimating motion fields, segmentation fields, and high-resolution images.
  • Gradient-based methods and iterated conditional mode optimization were utilized for specific component estimations.

Related Experiment Videos

Main Results:

  • The proposed algorithm demonstrated efficacy on synthetic and real-world image sequences, including 'Mobile and Calendar' and 'Motorcycle and Car'.
  • Error analyses confirmed the algorithm's performance in complex super-resolution scenarios.

Conclusions:

  • The joint MAP formulation effectively addresses super-resolution challenges in dynamic scenes.
  • The developed algorithm provides a robust solution for reconstructing high-resolution images from degraded inputs with multiple moving objects.