Manifold Transfer Subspace Learning (MTSL) for Applications in Aided Target Recognition

Manifold Transfer Subspace Learning (MTSL) for Applications in Aided Target Recognition

Olga Mendoza-Schrock (Air Force Research Laboratory, Wright-Patterson Air Force Base, USA), Mateen M. Rizki (Wright State University, Dayton, USA) and Vincent J. Velten (Air Force Research Laboratory, Wright-Patterson Air Force Base, USA)
DOI: 10.4018/IJMSTR.2017070102

Abstract

This article describes how transfer subspace learning has recently gained popularity for its ability to perform cross-dataset and cross-domain object recognition. The ability to leverage existing data without the need for additional data collections is attractive for monitoring and surveillance technology, specifically for aided target recognition applications. Transfer subspace learning enables the incorporation of sparse and dynamically collected data into existing systems that utilize large databases. Manifold learning has also gained popularity for its success at dimensionality reduction. In this contribution, Manifold learning and transfer subspace learning are combined to create a new system capable of achieving high target recognition rates. The manifold learning technique used in this contribution is diffusion maps, a nonlinear dimensionality reduction technique based on a heat diffusion analogy. The transfer subspace learning technique used is Transfer Fisher's Linear Discriminative Analysis. The new system, manifold transfer subspace learning, sequentially integrates manifold learning and transfer subspace learning. In this article, the ability of the new techniques to achieve high target recognition rates for cross-dataset and cross-domain applications is illustrated using a variety of diverse datasets.
Article Preview

Manifold Transfer Subspace Learning (Mtsl)

The Manifold Transfer Subspace Learning (MTSL) technique combines Manifold Learning and Transfer Subspace Learning in a sequential process. Diffusion Maps (DM) is utilized as the Manifold Learning technique and the TrFLDA enhanced technique as the Transfer Subspace Learning technique. The basic framework for Manifold Transfer Subspace Learning can be described as a sequential process. In step one the original source and target data are transformed using Diffusion Maps. In step two the TrFLDA enhanced technique is used with the transformed data.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 7: 2 Issues (2019): Forthcoming, Available for Pre-Order
Volume 6: 2 Issues (2018): Forthcoming, Available for Pre-Order
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing