Overcomplete Dictionary Design for Building Feature Extraction
bookPart
There are several scenarios for which it is desirable to obtain the layout of a building interior using outside radar sensing and surveillance. These situations may arise after an earthquake, when a building might become unstable or when the building entrance is blocked in hostage taking or criminal acts by outlaws. In this chapter, several approaches will be introduced for obtaining building features. Two approaches, point target matched filtering and smashed filtering, are classical Nyquist based. The third approach, overcomplete dictionary (OCD), which uses sparse reconstruction, is the main focus of this chapter. The authors would like to stress that although the sparse reconstruction results shown at the end of the chapter are based on data obtained through noncompressive sensing, the approach can easily be extended to include compressed measurements, as indicated in the theoretical discourse. Also, some concepts will be introduced for completeness but will not be used in obtaining the results shown
Topics
TNO Identifier
511245
ISBN
978-1-4665-9784-6
Publisher
CRC Press
Source title
Compressive Sensing for Urban Radar
Editor(s)
Amin, M.G.
Place of publication
Boca Raton
Pages
49-86
Files
To receive the publication files, please send an e-mail request to TNO Repository.