• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.322-324
• /
• 2003

Leaf C:N ratio is a new factor in the field of biochemical inversion with hyperspectral data. Effects of common-used spectral transformations including log(R), log(1/R), 1/R, etc. from 400nm to 2490nm on its inversion are compared. Results show that their effects on statistical modeling are not apparent. Continuum removal is used on original reflectance in the range of 2030nm to 2220nm, in which exists an apparent absorption peak due to cellulose, lignin, protein, etc. The effect is distinctive and tends to improve the precision of C:N ratio inversion. Further, it is a robust and physically based transformation.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.397-400
• /
• 2007

For mapping the distribution of heavy metals in the mining area, field spectroscopy and hyperspectral remote sensing were used in this study. Although heavy metals are spectrally featureless from the visible to the short wave infrared range, possible variations in spectral signal due to heavy metals bound onto minerals can be explained with the metal binding reaction onto the mineral surface. Variations in the spectral absorption shapes of lattice OH and oxygen on the mineral surface due to the combination of heavy metals were surveyed over the range from 420 to 2400 nm. Spectral parameters such as peak ratio and peak area were derived and statistically linked to metal concentration levels in the streambed samples collected from the dry stream channels. The spatial relationships between spectral parameters and concentrations of heavy metals were yielded as well. Based on the observation at a ground level for the relationship between spectral signal and metal concentration levels, the spectral parameters were classified in a hyperspectral image and the spatial distribution patterns of classified pixels were compared with the product of analysis at the ground level. The degree of similarity between ground dataset and image dataset was statistically validated. These techniques are expected to support assessment of dispersion of heavy metal contamination and decision on optimal sampling point.

• Korean Journal of Remote Sensing
• /
• v.22 no.4
• /
• pp.295-304
• /
• 2006

Image fusion is defined as making new image by merging two or more images using special algorithms. In case of remote sensing, it means fusing multispectral low-resolution remotely sensed image with panchromatic high-resolution image. Generally, hyperspectral image fusion is accomplished by utilizing fusion technique of multispectral imagery or spectral unmixing model. But, the former may distort spectral information and the latter needs endmember data or additional data, and has a problem with not preserving spatial information well. This study proposes a new algorithm based on two stage spectral unmixing model for preserving hyperspectral image's spectral information. The proposed fusion technique is implemented and tested using Hyperion and ALI images. it is shown to work well on maintaining more spatial/spectral information than the PCA/GS fusion algorithms.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.209-212
• /
• 2005

Hyperspectral data consists of more than 200 spectral bands that are highly correlated. In order to utilize hyperspectral data for classification, dimensional reduction or feature extraction is desired. By applying feature extraction, computational complexity of classification can be reduced and classification accuracy may be improved. In this paper, a genetic algorithm based feature extraction technique is proposed. Measure from discriminant analysis is utilized as optimization criterion. A subset of spectral bands is selected by genetic algorithm. Dimension of feature space is further reduced by linear transformation. Feasibility of the proposed technique is evaluated with AVIRIS data.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.570-573
• /
• 2004

We proposed a new system to collect hyperspectral data using a general cargo crane. The system has advantageous characteristics for precise data collection and analysis. In order to evaluate the validity, we performed the system on actual rice paddy field and analyzed the observed data. On the process, we could successfully extract the pure vegetation spectrum with high stability. The data taken by the system are useful for detail analysis among fields. In future development, it can be used for obtaining the grand truth for calibrating satellite or aerial hyperspectral images.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.10-13
• /
• 2004

Hyperspectral data has a great advantage to classify various surface materials that are spectrally similar. In this study, we attempted to classify man-made materials in urban area using Hyperion data. Hyperion imagery of Seoul was initially processed to minimize radiometric distortions caused by sensor and atmosphere. Using color aerial photographs. we defined seven man-made surfaces (concrete, asphalt road. railroad, buildings, roof, soil, shadow) for the classification in Seoul. The hyperspectral data showed the potential to identify those manmade materials that were difficult to be classified by multispectral data. However. the classification of road and buildings was not quite satisfactory due to the relatively low spatial resolution of Hyperion image. Further, the low radiometric quality of Hyperion sensor was another limitation for the application in urban area.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.619-622
• /
• 2006

Atmospheric correction is one of critical procedures to extract quantitative information related to biophysical variables from hyperspectral data. In this study, we attempted to generate the water vapor contents image from hyperspectral data itself and developed the atmospheric correction algorithm for EO-1 Hyperion data using pre-calculated atmospheric look-up-table (LUT) for fast processing. To apply the new atmospheric correction algorithm, Hyperion data acquired June 3, 2001 over Seoul area is used. Reflectance spectrums of various targets on atmospheric corrected Hyperion reflectance images showed the general spectral pattern although there must be further development to reduce the spectral noise.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.334-336
• /
• 2003

Satellite and airborne hyperspectral sensor images are suitable for investigating the vegetation state in agricultural land. However, image data obtained by an optical sensor inevitably includes mixels caused by high altitude observation. Therefore, mixel analysis method, which estimates both the pure spectra and the coverage of endmembers simultaneously, is required in order to distinguish the qualitative spectral changes due to the chlorophyll quantity or crop variety, from the quantitative coverage change. In this paper, we apply our agricultural independent component analysis (ICA) model to an airborne hyperspectral sensor image, which includes noise and fluctuation of coverage, and estimate pure spectra and the mixture ratio of crop and soil in agricultural land simultaneously.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.25-36
• /
• 2014

Multispectral image classification of individual tree species is often difficult because of the spectral similarity among species. In this study, we attempted to analyze the suitability of hyperspectral image to classify coniferous tree species. Several image sets and classification methods were applied and the classification results were compared with the ones from multispectral image. Two airborne hyperspectral images (AISA, CASI) were obtained over the study area in the Gwangneung National Forest. For the comparison, ETM+ multispectral image was simulated using hyperspectral images as to have lower spectral resolution. We also used the transformed hyperspectral data to reduce the data volume for the classification. Three supervised classification schemes (SAM, SVM, MLC) were applied to thirteen image sets. In overall, hyperspectral image provides higher accuracies than multispectral image to discriminate coniferous species. AISA-dual image, which include additional SWIR spectral bands, shows the best result as compared with other hyperspectral images that include only visible and NIR bands. Furthermore, MNF transformed hyperspectral image provided higher classification accuracies than the full-band and other band reduced data. Among three classifiers, MLC showed higher classification accuracy than SAM and SVM classifiers.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.959-971
• /
• 2019

CNN (Convolutional Neural Network) is one representative deep learning algorithm, which can extract high-level spatial and spectral features, and has been applied for hyperspectral image classification. However, one significant drawback behind the application of CNNs in hyperspectral images is the high dimensionality of the data, which increases the training time and processing complexity. To address this problem, several CNN based hyperspectral image classification studies have exploited PCA (Principal Component Analysis) for dimensionality reduction. One limitation to this is that the spectral information of the original image can be lost through PCA. Although it is clear that the use of PCA affects the accuracy and the CNN training time, the impact of PCA for CNN based hyperspectral image classification has been understudied. The purpose of this study is to analyze the quantitative effect of PCA in CNN for hyperspectral image classification. The hyperspectral images were first transformed through PCA and applied into the CNN model by varying the size of the reduced dimensionality. In addition, 2D-CNN and 3D-CNN frameworks were applied to analyze the sensitivity of the PCA with respect to the convolution kernel in the model. Experimental results were evaluated based on classification accuracy, learning time, variance ratio, and training process. The size of the reduced dimensionality was the most efficient when the explained variance ratio recorded 99.7%~99.8%. Since the 3D kernel had higher classification accuracy in the original-CNN than the PCA-CNN in comparison to the 2D-CNN, the results revealed that the dimensionality reduction was relatively less effective in 3D kernel.