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

Kernel matched subspace detectors for hyperspectral target detection.

Heesung Kwon1, Nasser M Nasrabadi

  • 1Army Research Laboratory, AMSRDARL-SE-SE, 2800 Powder Mill Rd., Adelphi, MD 20783, USA. hkwon@arl.army.mil

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 14, 2006
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

Long-Range Thermal Target Detection in Data-Limited Settings Using Restricted Receptive Fields.

Sensors (Basel, Switzerland)·2023
Same author

A Multi-Purpose Realistic Haze Benchmark With Quantifiable Haze Levels and Ground Truth.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

MultiSDGAN: Translation of OCT Images to Superresolved Segmentation Labels Using Multi-Discriminators in Multi-Stages.

IEEE journal of biomedical and health informatics·2021
Same author

DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors.

IEEE transactions on pattern analysis and machine intelligence·2019
Same author

ME R-CNN: Multi-Expert R-CNN for Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Supervised Deep Sparse Coding Networks for Image Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

A new kernel-based nonlinear detector, the kernel matched subspace detector (KMSD), enhances target detection in hyperspectral images. KMSD outperforms conventional matched subspace detectors (MSD) by leveraging kernel methods for improved performance.

Area of Science:

  • Signal Processing
  • Remote Sensing
  • Machine Learning

Background:

  • Matched subspace detection (MSD) is a common technique for target detection.
  • Linear models in high-dimensional spaces can be computationally intractable.
  • Kernel methods offer a way to implicitly map data to higher dimensions.

Purpose of the Study:

  • To develop a kernel-based nonlinear detector for improved target detection in hyperspectral imagery.
  • To reformulate the generalized likelihood ratio test (GLRT) in a high-dimensional feature space.
  • To address the computational challenges of GLRT in feature space using kernelization.

Main Methods:

  • Reformulation of the linear subspace mixture model in a high-dimensional feature space.
  • Derivation of the generalized likelihood ratio test (GLRT) for the subspace mixture model.

Related Experiment Videos

  • Kernelization of the GLRT expression using kernel eigenvector representations and the kernel trick.
  • Application of the kernel matched subspace detector (KMSD) to hyperspectral image data.

    • Main Results:

    • The kernel-based nonlinear detector (KMSD) was successfully developed.
    • KMSD demonstrated superior detection performance compared to the conventional MSD.
    • Improved detection capabilities were observed on both synthetic and real hyperspectral imagery.

    Conclusions:

    • Kernelization provides an effective approach to nonlinear target detection in hyperspectral imaging.
    • KMSD offers a promising alternative to traditional MSD for enhanced target identification.
    • The proposed method shows significant potential for practical applications in remote sensing.