31 March 2010 Object identification by multispectral fusion and Haar classification
Author Affiliations +
Abstract
An approach to identify and classify objects in real time by multispectral imaging, wavelets based fusion, and Haar classification is presented. The specific object of interest is a cardboard box placed on the roadside. The proposed approach involves capturing a scene in the visible and infra red spectrum. Fusing the spectra is performed by using the wavelet transform. Further, Haar training is performed using sample positives and negatives prior to classification. The presented approach is tested to work in real time with very good accuracy. If successful, the method will be applied to the detection of a variety of anomalous objects placed at the roadside.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Arun Manohar, Arun Manohar, Francesco Lanza di Scalea, Francesco Lanza di Scalea, } "Object identification by multispectral fusion and Haar classification", Proc. SPIE 7647, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2010, 76471Q (31 March 2010); doi: 10.1117/12.847357; https://doi.org/10.1117/12.847357
PROCEEDINGS
7 PAGES


SHARE
Back to Top