• Korean Journal of Remote Sensing
• /
• v.18 no.6
• /
• pp.369-376
• /
• 2002

This paper presents a method to enhance the performance of supervised classification by separating the spectral signature of the training data sets for each class. Using clustering technique, a training data set is divided into several subsets which show a pattern of the normal distribution with small value of spectral variances. Then a supervised classification is applied with the divided training data set as training data for the temporary subclasses of the original class. The proposed method is applied to a Landsat TM image of Busan area for the applicability test. The result shows that the proposed method produces better classified results than the conventional statistical classification methods. It is expected that the proposed method will reduce the effort and expense for selecting the training data set for each class in an area which has spectrally homogeneous signature.

• Korean Journal of Remote Sensing
• /
• v.28 no.5
• /
• pp.531-548
• /
• 2012

To identify Cochlodinium polykrikoides red tide from non-red tide water (satellite high chlorophyll waters) in the South Sea of Korea (SSK), we improved a spectral classification method proposed by Son et al.(2011) for the world first Geostationary Ocean Color Imager (GOCI). C. polykrikoides blooms and non-red tide waters were classified based on four different criteria. The first step revealed that the radiance peaks of potential red tide water occurred at 555 and 680 nm (fluorescence peak). The second step separated optically different waters that were influenced by relatively low and high contributions of colored dissolved organic matter (CDOM) (including detritus) to chlorophyll. The third and fourth steps discriminated red tide water from non-red tide water based on the blue-to-green ratio, respectively. After applying the red tide classification, the spectral response of C. polykrikoides red tide water, which is influenced by pigment concentration as well as CDOM (detritus), showed different slopes for the blue and green bands (lower slope at blue bands and higher slope at green bands). The opposite result was found for non-red tide water. This modified spectral classification method for GOCI led to increase user accuracy for C. polykrikoides and non-red tide blooms and provided a more reliable and robust identification of red tides over a wide range of oceanic environments than was possible using chlorophyll a concentration, or proposed red tide detection algorithms. Maps of C. polykrikoides red tide in SSK outlined patches of red tide covering the area near Naro-do and Tongyeong during the end of July and early of August, 2012 and extending into from Wan-do and Geoje-do during the middle of August, 2012.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.493-503
• /
• 2014

A hierarchical classification scheme, which can reduce the spectral ambiguity and also reflect crop cultivation patterns from past land-cover maps, is presented for the purpose of the early production of crop classification maps in large-scale crop areas. Specifically, the effects of mixed pixels are minimized not only by applying a hierarchical classification approach based on different spectral characteristics from crop growth cycles, but also by considering temporal contextual information derived from past crop cultivation patterns. The applicability of the presented classification scheme was evaluated by a case study of Iowa State in USA with time-series MODIS 250 m Normalized Difference Vegetation Index(NDVI) data sets and past Cropland Data Layers(CDLs). Corn and soybean, which are major crop types in the study area and also display spectral similarity, could be properly classified by applying different classification stages and accounting for past crop cultivation patterns. The classification result by the presented scheme showed increases of minimum 7.68%p and maximum 20.96%p in overall accuracy, compared with one based on purely spectral information. In addition, the combination of temporal contextual information during classification was less affected by the number of NDVI data sets and the best overall accuracy of 86.63% was achieved. Thus, it is expected that this classification scheme can be effectively used for the early production of large-area crop classification maps in major feed-grain importing countries.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.647-650
• /
• 2006

Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery was acquired over the Little Miami River Watershed (1756 square miles) in Ohio, U.S.A., which is one of the largest hyperspectral image acquisition. For the development of a 4m-resolution land cover dataset, a hierarchical approach was employed using two different classification algorithms: 'Image Object Segmentation' for level-1 and 'Spectral Angle Mapper' for level-2. This classification scheme was developed to overcome the spectral inseparability of urban and rural features and to deal with radiometric distortions due to cross-track illumination. The land cover class members were lentic, lotic, forest, corn, soybean, wheat, dry herbaceous, grass, urban barren, rural barren, urban/built, and unclassified. The final phase of processing was completed after an extensive Quality Assurance and Quality Control (QA/QC) phase. With respect to the eleven land cover class members, the overall accuracy with a total of 902 reference points was 83.9% at 4m resolution. The dataset is available for public research, and applications of this product will represent an improvement over more commonly utilized data of coarser spatial resolution such as National Land Cover Data (NLCD).

• Korean Journal of Remote Sensing
• /
• v.20 no.3
• /
• pp.197-205
• /
• 2004

Wetlands are lands with a mixture of water, herbaceous or woody vegetation and wet soil. And linear spectral mixture analysis (LSMA) is one of the most often used methods in handling the spectral mixture problem. This study aims to test LSMA is an enhanced routine for classification of wetland land-covers in Paldang reservoir and vicinity (paldang Reservoir) using Landsat TM and ETM+ imagery. In the LSMA process, reference endmembers were driven from scatter-plots of Landsat bands 3, 4 and 5, and a series of endmember models were developed based on green vegetation (GV), soil and water endmembers which are the main indicators of wetlands. To consider phenological characteristics of Paldang Reservoir, a soil endmember was subdivided into bright and dark soil endmembers in spring and a green vegetation (GV) endmember was subdivided into GV tree and GV herbaceous endmembers in fall. We found that LSMA fractions improved the classification accuracy of the wetland land-cover. Four endmember models provided better GV and soil discrimination and the root mean squared (RMS) errors were 0.011 and 0.0039, in spring and fall respectively. Phenologically, a fall image is more appropriate to classify wetland land-cover than spring's. The classification result using 4 endmember fractions of a fall image reached 85.2 and 74.2 percent of the producer's and user's accuracy respectively. This study shows that this routine will be an useful tool for identifying and monitoring the status of wetlands in Paldang Reservoir.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.613-619
• /
• 2006

This study proposed an unsupervised image classification through the dendrogram of agglomerative clustering as a higher stage of image segmentation in image processing. The proposed algorithm is a hierarchical clustering which includes searching a set of MCSNP (Mutual Closest Spectral Neighbor Pairs) based on the data structures of RAG(Regional Adjacency Graph) defined on spectral space and Min-Heap. It also employes a multi-window system in spectral space to define the spectral adjacency. RAG is updated for the change due to merging using RNV (Regional Neighbor Vector). The proposed algorithm provides a dendrogram which is a graphical representation of data. The hierarchical relationship in clustering can be easily interpreted in the dendrogram. In this study, the proposed algorithm has been extensively evaluated using simulated images and applied to very large QuickBird imagery acquired over an area of Korean Peninsula. The results have shown it potentiality for the application of remotely-sensed imagery.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.939-944
• /
• 2002

In this paper, we propose and apply new classification method to the remotely sensed image acquired from airborne multi-spectral scanner. This is a neuro-fuzzy image classifier derived from the generic model of a 3-layer fuzzy perceptron. We implement a classification software system with the proposed method for land cover image classification. Comparisons with the proposed and maximum-likelihood classifiers are also presented. The results show that the neuro-fuzzy classification method classifies more accurately than the maximum likelihood method. In comparing the maximum-likelihood classification map with the neuro-fuzzy classification map, it is apparent that there is more different as amount as 7.96% in the overall accuracy. Most of the differences are in the "Building" and "Pine tree", for which the neuro-fuzzy classifier was considerably more accurate. However, the "Bare soil" is classified more correctly with the maximum-likelihood classifier rather than the neuro-fuzzy classifier.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1095-1106
• /
• 2019

Damage of forest fire should be investigated quickly and accurately for recovery, compensation and prevention of secondary disaster. Using remotely sensed data, burn severity is investigated based on the difference of reflectance or spectral indices before and after forest fire. Recently, the use of high resolution satellite and UAV imagery is increasing, but it is not easy to obtain an image before forest fire that cannot be predicted where and when. This study tried to analyze availability of high-resolution images and supervised classifiers on the burn severity classification. Two supervised classifiers were applied to the KOMPSAT-3A image and the UAV multispectral image acquired after the forest fire. The maximum likelihood (MLH) classifier use absolute value of spectral reflectance and the spectral angle mapper (SAM) classifier use pattern of spectra. As a result, in terms of spatial resolution, the classification accuracy of the UAV image was higher than that of the satellite image. However, both images shown very high classification accuracy, which means that they can be used for classification of burn severity. In terms of the classifier, the maximum likelihood method showed higher classification accuracy than the spectral angle mapper because some classes have similar spectral pattern although they have different absolute reflectance. Therefore, burn severity can be classified using the high resolution multispectral images after the fire, but an appropriate classifier should be selected to get high accuracy.

• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.445-455
• /
• 2011

A probabilistic classification framework is presented that can combine temporal contextual information derived from an existing land-cover map in order to improve the classification accuracy of land-cover classes that can not be discriminated well when using spectral information only. The transition probability is computed by using the existing land-cover map and training data, and considered as a priori probability. By combining the a priori probability with conditional probability computed from spectral information via a Bayesian combination rule, the a posteriori probability is finally computed and then the final land-cover types are determined. The method presented in this paper can be adopted to any probabilistic classification algorithms in a simple way, compared with conventional classification methods that require heavy computational loads to incorporate the temporal contextual information. A case study for crop classification using time-series MODIS data sets is carried out to illustrate the applicability of the presented method. The classification accuracies of the land-cover classes, which showed lower classification accuracies when using only spectral information due to the low resolution MODIS data, were much improved by combining the temporal contextual information. It is expected that the presented probabilistic method would be useful both for updating the existing past land-cover maps, and for improving the classification accuracy.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.1
• /
• pp.57-78
• /
• 2017

There are several statistical classification algorithms available for land use/land cover classification. However, each has a certain bias or compromise. Some methods like the parallel piped approach in supervised classification, cannot classify continuous regions within a feature. On the other hand, while unsupervised classification method takes maximum advantage of spectral variability in an image, the maximally separable clusters in spectral space may not do much for our perception of important classes in a given study area. In this research, the output of an ANN algorithm was compared with the Possibilistic c-Means an improvement of the fuzzy c-Means on both moderate resolutions Landsat8 and a high resolution Formosat 2 images. The Formosat 2 image comes with an 8m spectral resolution on the multispectral data. This multispectral image data was resampled to 10m in order to maintain a uniform ratio of 1:3 against Landsat 8 image. Six classes were chosen for analysis including: Dense forest, eucalyptus, water, grassland, wheat and riverine sand. Using a standard false color composite (FCC), the six features reflected differently in the infrared region with wheat producing the brightest pixel values. Signature collection per class was therefore easily obtained for all classifications. The output of both ANN and FCM, were analyzed separately for accuracy and an error matrix generated to assess the quality and accuracy of the classification algorithms. When you compare the results of the two methods on a per-class-basis, ANN had a crisper output compared to PCM which yielded clusters with pixels especially on the moderate resolution Landsat 8 imagery.