Title :
A quantitative method to evaluate the performance of hyperspectral data fusion
Author :
Wang, Qiang ; Shen, Yi ; Ye Zhang
Author_Institution :
Dept. of Control Sci. & Eng., Harbin Inst. of Technol., China
fDate :
6/24/1905 12:00:00 AM
Abstract :
Hyperspectral data fusion technique is the focus of hyperspectral data processing in recent years. Many fusion methods have been proposed, but little research work has been done to evaluate the performances of different data fusion methods. In order to meet the urgent need, a new method called quantitative correlation analysis is proposed in this paper. With this method, the performances of different fusion methods can be compared and analyzed directly based on the data of before and after the data fusion take place. The experiment results show that the new method is effective and the comparative results conform to the application results.
Keywords :
correlation theory; eigenvalues and eigenfunctions; entropy; feature extraction; geophysical signal processing; infrared imaging; infrared spectroscopy; principal component analysis; remote sensing; sensor fusion; visible spectroscopy; wavelet transforms; AVIRIS data; Gauss pyramid; Laplace pyramid; correlation information entropy; correlation matrix; eigenvalues; feature extraction; hyperspectral data fusion; image fusion method; multisensor system; performance evaluation; pixel level; principal component analysis; pyramid-based fusion; quantitative correlation analysis; quantitative method; remote sensing; visible to infrared range; wavelet-based fusion; Communication system control; Data processing; Focusing; Hyperspectral imaging; Hyperspectral sensors; Image fusion; Performance analysis; Performance evaluation; Quantum cellular automata; Remote sensing;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2002. IMTC/2002. Proceedings of the 19th IEEE
Print_ISBN :
0-7803-7218-2
DOI :
10.1109/IMTC.2002.1007076