Analysis of the Efficiency of Hyperspectral Data Classification under Constraints on the Quantization Bit Depth, the Number of Spectral Channels, and Spatial Resolution.

Autor: Shipko, V. V., Borzov, S. M.
Zdroj: Optoelectronics Instrumentation & Data Processing; Jun2022, Vol. 58 Issue 3, p273-280, 8p
Abstrakt: The possibility of creating an operational frame hyperspectrometer functioning as a conventional camera is studied. It is considered how the classification efficiency will change with the implementation of the idea of creating a compact and easy-to-use hyperspectral camera with promptly tunable parameters. On a test hyperspectral image, experimental studies of the classification accuracy were performed depending on the number of spectral channels and the method of their selection, spatial resolution, and the bit depth of signal brightness quantization. It is shown that the resulting accuracy decreases but remains reasonable for a wide range of practical problems. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index
Externí odkaz: