Joint view-identity manifold for infrared target tracking and recognition

•We propose a new joint view-identity manifold (JVIM) for multi-view shape modeling.•JVIM is well-suited for target tracking and recognition (ATR) in infrared (IR) imagery.•We propose a new GPLVM-based algorithm for JVIM learning and inference.•Experimental results on both the synthetic CAD data and...

Full description

Saved in:
Bibliographic Details
Published in:Computer vision and image understanding 2014-01, Vol.118, p.211-224
Main Authors: Gong, Jiulu, Fan, Guoliang, Yu, Liangjiang, Havlicek, Joseph P., Chen, Derong, Fan, Ningjun
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Automatic target tracking and recognition
Computer science
control theory
systems
Data processing. List processing. Character string processing
Exact sciences and technology
Generative models
GPLVM
Inference
Infrared
Infrared imagery
Learning
Learning and adaptive systems
Manifold learning for shape modeling
Manifolds
Memory organisation. Data processing
Recognition
Shape interpolation
Software
Target tracking
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We propose a new joint view-identity manifold (JVIM) for multi-view shape modeling.•JVIM is well-suited for target tracking and recognition (ATR) in infrared (IR) imagery.•We propose a new GPLVM-based algorithm for JVIM learning and inference.•Experimental results on both the synthetic CAD data and recent IR database demonstrate JVIM’s advantages over several recent shape models. We propose a new joint view-identity manifold (JVIM) for multi-view and multi-target shape modeling that is well-suited for automated target tracking and recognition (ATR) in infrared imagery. As a shape generative model, JVIM features a novel manifold structure that imposes a conditional dependency between the two shape-related factors, view and identity, in a unified latent space, which is embedded with one view-independent identity manifold and infinite identity-dependent view manifolds. A modified local linear Gaussian process latent variable model (LL-GPLVM) is proposed for JVIM learning where a stochastic gradient descent method is used to improve the learning efficiency. We also develop a local inference technique to speed up JVIM-based shape interpolation. Due to its probabilistic and continuous nature, JVIM provides effective shape synthesis and supports robust ATR inference for both known and unknown target types under arbitrary views. Experiments on both synthetic data and the SENSIAC infrared ATR database demonstrate the advantages of the proposed method over several existing techniques both qualitatively and quantitatively.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2013.10.002