• 대한원격탐사학회지
• /
• 제34권1호
• /
• pp.141-150
• /
• 2018

Crop type classification is essential for supporting agricultural decisions and resource monitoring. Remote sensing techniques, especially using hyperspectral imagery, have been effective in agricultural applications. Hyperspectral imagery acquires contiguous and narrow spectral bands in a wide range. However, large dimensionality results in unreliable estimates of classifiers and high computational burdens. Therefore, reducing the dimensionality of hyperspectral imagery is necessary. In this study, the Random Forest (RF) classifier was utilized for dimensionality reduction as well as classification purpose. RF is an ensemble-learning algorithm created based on the Classification and Regression Tree (CART), which has gained attention due to its high classification accuracy and fast processing speed. The RF performance for crop classification with airborne hyperspectral imagery was assessed. The study area was the cultivated area in Chogye-myeon, Habcheon-gun, Gyeongsangnam-do, South Korea, where the main crops are garlic, onion, and wheat. Parameter optimization was conducted to maximize the classification accuracy. Then, the dimensionality reduction was conducted based on RF variable importance. The result shows that using the selected bands presents an excellent classification accuracy without using whole datasets. Moreover, a majority of selected bands are concentrated on visible (VIS) region, especially region related to chlorophyll content. Therefore, it can be inferred that the phenological status after the mature stage influences red-edge spectral reflectance.

• 대한공간정보학회지
• /
• 제25권1호
• /
• pp.9-17
• /
• 2017

초분광 영상(hyperspectral imagery)은 주성분분석이나 최소잡음비율 등을 이용하여 자료의 차원과 잡음을 감소시켜 토지피복분류에 사용되는 것이 일반적이다. 최근에는 분광정보와 공간적 특성을 가진 다양한 입력 자료를 이용한 감독분류에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 초분광 영상을 이용한 토지피복분류를 위해 principle component(PC) 밴드와 normalized difference vegetation index(NDVI) 자료를 감독분류의 입력자료로 활용하였다. NDVI 자료는 초분광 영상에서 추출된 PC 밴드가 포함하고 있지 않는 추가적인 정보를 활용하여 식생지역에 대한 토지피복분류 정확도를 높이고자 사용하였으며, morphological filter를 통해 각 밴드의 extended attribute profiles(EAP)를 제작하여 분류를 위한 입력 자료로 사용하였다. 감독분류기법은 random forest 알고리즘을 이용하였으며, EAP를 기반으로 다양한 입력 자료의 적용에 따른 분류정확도를 비교하고자 하였다. 연구지역으로는 두 대상지를 선정하였으며, 영상 내에서 취득한 참조자료를 이용하여 정량적인 평가를 수행하였다. 본 연구에서 제안한 기법의 분류정확도는 85.72%와 91.14%로 다른 입력 자료들을 이용한 경우와 비교하여 가장 높은 분류정확도를 나타냈다. 향후, 초분광 영상을 이용한 토지피복분류의 정확도를 높이기 위한 분류 알고리즘 개발과 대상지역 특성에 맞는 추가 입력자료 개발에 관한 연구가 필요할 것으로 사료된다.

• 지적과 국토정보
• /
• 제44권2호
• /
• pp.103-112
• /
• 2014

본 연구의 목적은 토지와 물이 포함된 지역에서 초분광 영상을 이용한 토지피복 분류 가능성을 제시하는데 있다. CASI-1500 항공 초분광 영상을 통해 취득한 초분광 영상에 대해 전처리 작업으로서 대기보정을 수행한 후, 대기보정 전 후에서 몇 개의 토지피복 클래스에 대해 대기보정 효과가 비교 분석되었다. 항공사진과 수치지형도와 같은 참조자료로 활용하여 초분광 영상에 의한 토지피복 분류결과를 분석한 결과, 최대우도법에서는 약 67.0%의 전체정확도를 나타내었으며, 최소거리법은 52.4%의 전체정확도를 보였다. 또한 도로, 밭, 비닐하우스에서는 토지피복 분류의 생산자 정확도가 높게 나타났으나, 하천, 산지, 초지지역에서는 매우 복잡한 객체로 구성되어 있기 때문에 토지피복 분류의 생산자 정확도가 낮게 나타났다. 따라서 향후에는 특정객체 분류를 위한 최적의 밴드선별과 객체 고유의 분광특성을 고려한 분광 라이브러리를 구축하는 연구가 필요하다.

• 한국콘텐츠학회논문지
• /
• 제16권7호
• /
• pp.31-41
• /
• 2016

하이퍼스펙트럴 영상을 이용하여 토지피복 분류를 정확히 수행하기 위해서는 전처리 작업으로서 대기보정을 거쳐야 한다. 항공 하이퍼스펙트럴 영상에 대하여 대기보정을 실시하고 대기보정 유 무에 따른 해수, 갯벌, 식생, 아스팔트, 콘크리트 등의 토지피복 항목별 분광반사율 특성을 비교하여 대기보정의 뚜렷한 효과를 확인할 수 있었다. 대기보정 후의 영상에 대하여 최대우도법, 분광각맵퍼법 등의 화소기반 감독분류기법으로 각각 토지피복 분류를 행하고 그 결과를 비교하였다. 분광각맵퍼법의 경우 임계각 $0.4^{\circ}$에서 노이즈를 최소화하면서 해수영역을 가장 양호하게 분류해 낼 수 있었다. 같은 개체라도 다양한 분광특성을 나타내는 하이퍼스펙트럴 영상의 경우 연안지역에서는 종래의 화소기반 분류기법보다는 축척, 분광 정보, 형태, 결 등을 종합적으로 고려하는 객체기반 분류기법이 더 우월할 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.388-393
• /
• 2002

Remote sensing data is collected and analyzed to enhance understanding of the terrestrial surface. Since Landsat satellite was launched in 1972, many researches using multispectral data has been achieved. Recently, with the availability of airborne and satellite hyperspectral data, the study on hyperspectral data are being increased. It is known that as the number of spectral bands of high-spectral resolution data increases, the ability to detect more detailed cases should also increase, and the classification accuracy should increase as well. In this paper, we classified the hyperspectral and multispectral data and tested the classification accuracy. The MASTER(MODIS/ASTER Airborne Simulator, 50channels, 0.4~13$\mu$m) and Landsat TM(7channels) imagery including Yeong-Gwang area were used and we adjusted the classification items in several cases and tested their classification accuracy through statistical comparison. As a result of this study, it is shown that hyperspectral data offer more information than multispectral data.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• 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.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• 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).