• Korean Journal of Remote Sensing
• /
• v.28 no.4
• /
• pp.369-392
• /
• 2012

Recently, many target detection algorithms were developed for hyperspectral image. However, almost of these studies focused only accuracy from 1 or 2 data sets to validate and compare the algorithms although they give limited information to users. This study aimed to compare usability of target detection algorithms with various parameters. Five parameters were proposed to compare sensitivity in aspect of detection accuracy which are related with radiometric and spectral characteristics of target, background and image. Six target detection algorithms were compared in aspect of accuracy and efficiency (processing time) by variation of the parameters and image size, respectively. The results shown different usability of each algorithm by each parameter in aspect of accuracy. Second order statistics based algorithms needed relatively long processing time. Integrated usabilities of accuracy and efficiency were various by characteristics of target, background and image. Consequently, users would consider appropriate target detection algorithms by characteristics of data and purpose of detection.

• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.527-535
• /
• 2013

Extraction of correct endmembers is prerequisite to successful spectral unmixing analysis. Various endmember extraction algorithms have been proposed and most experiments based on endmember extraction have used synthetic image and AVIRIS image data. However, these data can present different characteristics comparing with hyperspectral images acquired from real domestic environment. For this study, a test-bed was constructed for analysing the difference on diverse substances and sizes in domestic areas, and AISA hyperspectral imagery acquired from the test-bed was tested with two well-known endmember extraction algorithms: IEA, and N-FINDR. The results indicated that two different algorithms depended on the number of endmembers and material types in the test-bed. Therefore, optimized number of endmembers and characteristics of materials in test-bed site should be considered for the effective application of endmember extraction algorithms.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.4 s.310
• /
• pp.11-20
• /
• 2006

This paper presents a method for detecting tumors on chicken carcasses by fusion of hyperspectral fluorescence and reflectance images. Classification of normal skin and tumor is performed by the image obtain 어 from optimal band ratio which minimizes the overlapping area of PDFs for normal skin and tumor. This method yields four feature images, each of them represents the ratio of two intensity values from a pixel. Classification is achieved by applying ISODATA to each pixel from the feature images. For the analysis of reflectance image, band selection method is proposed based on the information quantity, many effective features are acquired for the classification by defining the linear transformation selecting the projection axis, accordingly, accurate interpretation of images is possible in the reflectance image and automatic feature selection method is realized. Feature images from reflectance images are also classified by ISODATA and combined with the result from fluorescence images. Experimental result indicates that improved performance in term of reducing false detection rate is observed.

• Journal of Biosystems Engineering
• /
• v.40 no.2
• /
• pp.145-152
• /
• 2015

Purpose: The inability to adequately judge the efficacy of cleaning and sanitation procedures in deli departments is a recognized food safety concern. In a prior study, our research group demonstrated that visual inspection of cleaned produce processing surfaces could be enhanced through the use of a portable fluorescence imaging device that detected residual produce residues. Methods: To explore the feasibility of using fluorescence imaging to similarly detect residual deli residues, spectra of American, Cheddar, Provolone, and Swiss cheeses and of processed chicken, ham, roast beef, and turkey were acquired using a laboratory hyperspectral imaging system. Circular punches of these commodities were placed onto stainless steel and high density polyethylene coupons for imaging. The coupon materials were selected to represent common surfaces found in deli departments. Results: Analysis of hyperspectral fluorescence images showed that cheeses exhibited peaks in the blue-green region and at around 675 nm. Meats exhibited peaks in the blue-green region with one of four ham and one of four chicken brands exhibiting peaks at around 675 nm, presumably due to use of plant-derived additives. When commodities were intermittently imaged over two weeks, locations of spectral peaks were preserved while intensity of peaks at shorter wavelengths increased with time. Conclusion: These results demonstrate that fluorescence imaging techniques have the potential to enhance surface hygiene inspection in deli departments and, given the immediate availability of imaging results, to help optimize routine cleaning procedures.

• Journal of Biosystems Engineering
• /
• v.40 no.2
• /
• pp.124-136
• /
• 2015

Purpose: Grain quality is a general concept that covers many characteristics, ranging from physical to biochemical and physiochemical properties. Rice aging during storage is currently a challenge in the rice industry, and is a complicated process involving changes in all of the above properties. Spectroscopic techniques can be used to obtain information on the quality of rice samples in a non-destructive manner. Methods: The objective of this review was to highlight the factors that contribute to rice quality and aging, and to describe various spectroscopic modalities, particularly vibrational and hyperspectral imaging, for the assessment of rice quality. Results: Starch and protein are the main components of the rice endosperm, and are therefore key factors contributing to eating and cooking quality. While the overall starch, protein, and lipid content in the rice grain remains essentially unchanged during storage, structural changes do occur. These changes affect pasting and gel properties, and ultimately the flavor of cooked rice. In addition, grain quality is significantly affected by growing and environmental conditions, such as water availability, temperature, fertilizer application, and salinity stress. These properties can be evaluated using spectroscopic techniques, and rice samples can be discriminated by using multivariate statistical analysis methods. Conclusion: Hyperspectral imaging and vibrational spectroscopy techniques have good potential for determining rice quality properties in a non-invasive manner, i.e., not requiring the introduction of instruments into the rice grain.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.4
• /
• pp.205-211
• /
• 2018

Remote estimation of water quality via radiometric instruments provides a convenient means for monitoring environmental changes in water bodies in wide areas. Combined with platforms such as satellite, manned/unmanned vehicles, it reduces the measurement cost and time for acquiring water quality information on the interested target areas. To develop accurate retrieval algorithms, however, acquisition of in-situ measurements from various optical environment is critical. In this study, hyperspectral radiometric measurements, the coincident water quality variables, and its optical properties were obtained to analyze the optical environment of the study area. Field data collected around the Tongyeong area showed that the area has optically complex environment, with occasional outbreak of red tide in summer seasons. Effect of water constituents on the optical variables (remote sensing reflectance and absorption coefficients) were qualitatively analyzed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.565-574
• /
• 2006

Satellite images have been used to obtain land cover information that is one of important factors for hydrological analysis over a large area. In urban area, more detailed land cover data are often required for hydrological analysis because of the relatively complex land cover types. The number of land cover classes that can be classified with traditional multispectral data is usually less than the ones required by most hydrological uses. In this study, we present the capabilities of hyperspectral data (Hyperion) for the classification of hydrological land cover types in urban area. To obtain 17 classes of urban land cover defined by the USDA SCS, spectral mixture analysis was applied using eight endmembers representing both impervious and pervious surfaces. Fractional values from the spectral mixture analysis were then reclassified into 17 cover types according to the ratio of impervious and pervious materials. The classification accuracy was then assessed by aerial photo interpretation over 10 sample plots.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.385-394
• /
• 2015

Pine wilt disease has greatly damaged pine forests not only in East Asia including South Korea and China, but also in European region. The damage caused by pine wood nematode (Bursaphelenchus xylophilus) is expressed in bundles within stands and rapidly spreading, however, present field survey methods have limitations to detecting damaged trees at regional level. This study extracted the damaged trees by pine wilt disease using time series hyperspectral aerial photographs, and analyzed their distribution characteristics. Hyperspectral aerial photographs of 1 meter spatial resolution were obtained in June, September, and October. Damaged trees by pine wilt disease were extracted using Normalized Difference Vegetation Index (NDVI) and Vegetation Index green (VIgreen) of the September photograph. Among extracted damaged trees, dead trees with leaves and without leaves were classified, and the spectral reflectance values from the photographs obtained in June, September, and October were compared to extract new outbreaks in September and October. Based on the time series dispersion of extracted damaged trees, nearest neighbor analysis was conducted to analyze distribution characteristics of the damaged trees within the region where hyperspectral aerial photographs were acquired. As a result, 2,262 damaged trees were extracted in the study area, and 604 dead trees (dead trees in last year) with leaves in relation to the damaged time and 300 and 101 newly damaged trees in September and October were classified. The result of nearest neighbor analysis using the data shows that aggregated distribution was the dominant pattern both previous and current year in the study area. Also, 80% of the damaged trees in current year were found within 60 m of dead trees in previous year.

• Journal of Conservation Science
• /
• v.36 no.2
• /
• pp.73-81
• /
• 2020

Considering the difficulties associated with the creation of deterioration maps for stone cultural heritages, quantitative determination of chemical and biological contaminants in them is still challenging. Hyperspectral image analysis has been proposed to overcome this drawback. In this study, hyperspectral imaging was performed on Stone Buddhas Temple in Four Directions at Gulbulsa Temple Site(Treasure 121), and several surface contaminants were observed. Based on the color and shape, these chemical and biological contaminants were classified into ten categories. Additionally, a method for establishing each class as a reference image was suggested. Simultaneously, with the help of Spectral Angle Mapper algorithm, two classification methods were used to classify the surface contaminants. Method A focused on the region of interest, while method B involved the application of the spectral library prepared from the image. Comparison of the classified images with the reference image revealed that the accuracies and kappa coefficients of methods A and B were 52.07% and 63.61%, and 0.43 and 0.55, respectively. Additionally, misclassified pixels were distributed in the same contamination series.