12 October 2010 Illumination independent object recognitions in hyperspectral imaging
Author Affiliations +
Hyperspectral imaging (HSI) systems have been used widely in many applications including the defence and military for target acquisitions. However, the effectiveness of HSI can be greatly hampered by illumination artifacts such as shadowing or bidirectional reflection differentials issues. This paper addresses how shadows in the HSI, particularly for the imageries that are taken in the indoor scenarios, can be partially mitigated through a diffused irradiance compensation (DIC) methodology. The effectiveness of the proposed work is then compared with the widely adopted pixel normalisation and band ratioing methods. The performances of all these processing methods have been assessed using Maximum Likelihood Classifier. The result has shown an almost 70% improvement in classification accuracy after the raw DN data is translated into 'apparent' reflectance using simple ELM based method, and the classification accuracy after spectral normalisation is ~26% worse than without normalization. When the proposed diffused irradiance compensation (DIC) is combined with other band ratioing techniques, the classification accuracy is found to be improved by ~7% over that processed by the ELM method for the entire scene. There are about 32% of shadowed pixels in this data set and hence 7% of improvement represents a significant improvement on the shadow mitigation.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Izzati Ibrahim, Peter Yuen, Aristeidis Tsitiridis, Kan Hong, Tong Chen, James Jackman, David James, Mark Richardson, "Illumination independent object recognitions in hyperspectral imaging", Proc. SPIE 7838, Optics and Photonics for Counterterrorism and Crime Fighting VI and Optical Materials in Defence Systems Technology VII, 78380O (12 October 2010); doi: 10.1117/12.864535; https://doi.org/10.1117/12.864535

Back to Top