Feature Selection for Classification of Human Micro-Doppler

Date

2013-01-01

Author

Gurbuz, Sevgi Zubeyde
Tekeli, Burkan
Karabacak, Cesur
Yüksel Turgut, Ayşe Melda

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

66
views

0
downloads

Dozens of features have been proposed for the use in a variety of human micro-Doppler classification problems, such as activity classification, target identification, and arm swing detection. However, the issues of how many features are truly required, which features should be selected, and whether or how this selection will vary depending upon human activity has not yet been rigorously addressed in the context of human micro-Doppler analysis. Moreover, most classification results are present for the case when the human directly walks towards or away from the radar. As the aspect angle between target and antenna increases, the observed micro-Doppler spread diminishes, leading to increasingly poor feature estimates. Thus, there is also a question of how features should be selected by taking into consideration estimate quality. This work examines the application of information theory to shed light on these questions. Mutual information is used to compute the contribution of features as a function of physical relevance and estimate quality. An importance ranking of features is derived, with results shown for arm swing detection and discrimination of walking from running.

Subject Keywords

human micro-Doppler, feature selection, classification, multistatic radar, radar network, RADAR

URI

https://hdl.handle.net/11511/96458

DOI

https://doi.org/10.1109/comcas.2013.6685318

Conference Name

IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems (COMCAS)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Information-Theoretic Feature Selection for Human Micro-Doppler Signature Classification Tekeli, Burkan; Gurbuz, Sevgi Zubeyde; Yüksel Turgut, Ayşe Melda (2016-05-01) Micro-Doppler signatures can be used not only to recognize different targets, such as vehicles, helicopters, animals, and people, but also to classify varying activities, e.g., walking, running, creeping, and crawling. For this purpose, a plethora of features have been proposed in the literature; however, dozens of features are not required to achieve high classification performance. The topic of feature selection has been under addressed in micro-Doppler studies. Moreover, the optimal feature set is not st...
Jammer cancelation by using space-time adaptive processing Uysal, Halil; Severcan, Mete; Department of Electrical and Electronics Engineering (2011) Space-Time Adaptive Processing (STAP) has been widely used in spaceborne and airborne radar platforms in order to track ground moving targets. Jammer is an hostile electronic countermeasure that is being used to degrade radar detection and tracking performance. STAP adapts radar’s antenna radiating pattern in order to reduce jamming effectiveness. Jamming power that enters the system is decreased with respect to the adapted radiation pattern. In this thesis, a generic STAP radar model is developed and imple...
Optimization of vibration characteristics of a radar antenna structure Baran, İsmet; Özgen, Gökhan Osman; Ciğeroğlu, Ender; Department of Mechanical Engineering (2011) Radar antenna structures especially array antennas which are integrated onto structures of aerial vehicles are subject to dynamic structural and aerodynamic loads. Due to occurrences of these dynamic loads there will be certain dynamic deformations which affect the antenna’s performance in an adverse manner. The influence of deformations and vibrations are important on array antenna structures, since they cause a change in orientation of elements of the phased array antenna which affects the gain of the ant...
Spectral and statistical analyses of experimental radar clutter data Kahyaoğlu, Nazlı Deniz; Yılmaz, Ali Özgür; Department of Electrical and Electronics Engineering (2010) The performance of radar detection and imaging systems strongly depends on the characteristics of radar clutter. In order to improve the radar signal processing algorithms, successful analysis and modeling of radar clutter are required. For a successful model of radar clutter, both the spectral and statistical characteristics of the clutter should be revealed. Within the scope of this study, an experimental radar data acquisition system is established to analyze radar clutter. The hardware and the data proc...
Algebraic spectral moments based moving clutter parameter estimation and clutter suppression Oktar, Onur; Tanık, Yalçın; Department of Electrical and Electronics Engineering (2014) In many modern radar systems, it is desired to detect the presence of targets in the interference which includes clutter and noise. Various signal processing techniques are proposed to effectively suppress the clutter and increase the signal to interference ratio. To achieve optimum suppression, radar system must know clutter characteristics and process the radar echoes based on these characteristics. For ground radars, the clutter environment characteristics are relatively stable and predictable. These cha...

Citation Formats

S. Z. Gurbuz, B. Tekeli, C. Karabacak, and A. M. Yüksel Turgut, “Feature Selection for Classification of Human Micro-Doppler,” presented at the IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems (COMCAS), Tel-Aviv-Yafo, İsrail, 2013, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/96458.