Feature analysis for indoor radar target classification

Travis Dale Bufler, Ram Mohan Narayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper analyzes the spectral features from human beings and indoor clutter for building and tuning Support Vector Machines (SVMs) classifiers for the purpose of classifying stationary human targets. The spectral characteristics were obtained through simulations using Finite Difference Time Domain (FDTD) techniques where the radar cross section (RCS) of humans and indoor clutter objects were captured over a wide range of frequencies, polarizations, aspect angles, and materials. Additionally, experimental data was obtained using a vector network analyzer. Two different feature sets for class discrimination are used from the acquired target and clutter RCS spectral data sets. The first feature vectors consist of the raw spectral characteristics, while the second set of feature vectors are statistical features extracted over a set frequency interval. Utilizing variables of frequency and polarization, a SVM classifier can be trained to classify unknown targets as a human or clutter. Classification accuracy over 80% can be effectively achieved given appropriate features.

Original languageEnglish (US)
Title of host publicationRadar Sensor Technology XX
EditorsArmin Doerry, Kenneth I. Ranney
ISBN (Electronic)9781510600706
StatePublished - 2016
EventRadar Sensor Technology XX - Baltimore, United States
Duration: Apr 18 2016Apr 21 2016

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


OtherRadar Sensor Technology XX
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Feature analysis for indoor radar target classification'. Together they form a unique fingerprint.

Cite this