In this chapter, we address the problem of data representation and its impact on human motion classification using radar. In examining the motion classifier performance, it has become apparent that some human motion articulations are more distinguish-able in some data domain representations than others. The potential effect of data representation on motion classification performance calls for devising proper strategies and new approaches of how to best manipulate or preprocess the data for the sake of achieving most desirable results. We discuss domain integration and suit-ability using a single range-Doppler radar sensor. No assumptions are made regarding the received radar backscattering data adhering to any specific models or signal structure.

Chapter Contents:

• 4.1 Introduction
• 4.2 Radar signal model and domain suitability
• 4.3 Multilinear subspace learning
• 4.3.1 Multilinear algebra basics and notations
• 4.3.2 Multilinear principal component analysis (MPCA)
• 4.3.3 Multilinear discriminant analysis
• 4.4 Optimization considerations for multidimensional methods
• 4.4.1 Iterative projections
• 4.4.2 Initialization
• 4.4.3 Termination criteria and convergence
• 4.4.4 Number of projections
• 4.5 Boosting the MPCA
• 4.6 Experimental results
• 4.7 Conclusion
• References

Inspec keywords: radar imaging; image classification; image representation; image motion analysis; data structures

Other keywords: daily living; human motion classification; received radar backscattering data; single range-Doppler radar sensor; signal structure; motion classifier performance; human motion articulations; radar data representation; activity classification

Subjects: Image recognition; General and management topics; Radar equipment, systems and applications; General electrical engineering topics; File organisation; Computer vision and image processing techniques