Traditional Pixel-based Methods Research Articles

High-resolution feature pyramid attention network for high spatial resolution images land-cover classification in arid oasis zones

ABSTRACT Land-cover classification based on remote sensing technology has been adopted for decision-making concerning agricultural development, urban planning, and ecosystem protection in arid oasis zones. The semantic segmentation method based on deep learning, as a new paradigm, can effectively overcome the limitations of traditional pixel-based and object-based methods and obtain good classification results from high spatial resolution (HSR) remote sensing images. However, how to extract the exact category boundary and realize the high precision mapping is still a problem. This paper proposes a novel high-resolution feature pyramid attention network (HRFPANet) for land-cover classification. It effectively integrates the advantages of multi-scale feature extraction, attention mechanism, and feature fusion and alleviates boundary inconsistency, roughness, and category fragmentation associated with previous semantic segmentation models. The experimental results show that the mIoU score of HRFPANet is 79.5%, which is 11.5% and 2.6% higher than that of PSPNet and UPerNet, respectively. It proves the proposed model can be used for qualified land-cover mapping in arid oasis zones. Our source code is available at https://github.com/HPU-CPD/HRFPANet.git.

Multi-Scale Fusion Siamese Network Based on Three-Branch Attention Mechanism for High-Resolution Remote Sensing Image Change Detection

Remote sensing image change detection (CD) is an important means in remote sensing data analysis tasks, which can help us understand the surface changes in high-resolution (HR) remote sensing images. Traditional pixel-based and object-based methods are only suitable for low- and medium-resolution images, and are still challenging for complex texture features and detailed image detail processing in HR images. At present, the method based on deep learning has problems such as inconsistent fusion and difficult model training in the combination of the difference feature information of the deep and shallow layers and the attention mechanism, which leads to errors in the distinction between the changing region and the invariant region, edge detection and small target detection. In order to solve the above problems of inconsistent fusions of feature information aggregation and attention mechanisms, and indistinguishable change areas, we propose a multi-scale feature fusion Siamese network based on attention mechanism (ABMFNet). To tackle the issues of inconsistent fusion and alignment difficulties when integrating multi-scale fusion and attention mechanisms, we introduce the attention-based multi-scale feature fusion module (AMFFM). This module not only addresses insufficient feature fusion and connection between different-scale feature layers, but also enables the model to automatically learn and prioritize important features or regions in the image. Additionally, we design the cross-scale fusion module (CFM) and the difference feature enhancement pyramid structure (DEFPN) to assist the AMFFM module in integrating differential information effectively. These modules bridge the spatial disparity between low-level and high-level features, ensuring efficient connection and fusion of spatial difference information. Furthermore, we enhance the representation and inference speed of the feature pyramid by incorporating a feature enhancement module (FEM) into DEFPN. Finally, the BICD dataset proposed by the laboratory and public datasets LEVIR-CD and BCDD are compared and tested. We use F1 score and MIoU values as evaluation metrics. For AMBMFNet, the F1 scores on the three datasets are 77.69%, 81.57%, and 77.91%, respectively, while the MIoU values are 84.65%, 85.84%, and 84.54%, respectively. The experimental results show that ABMFNet has better effectiveness and robustness.

Face De-Identification Using Convolutional Neural Network (CNN) Models for Visual-Copy Detection

The proliferation of media-sharing platforms has led to issues with illegally edited content and the distribution of pornography. To protect personal information, de-identification technologies are being developed to prevent facial identification. Existing de-identification methods directly alter the pixel values in the face region, leading to reduced feature representation and identification accuracy. This study aims to develop a method that minimizes the possibility of personal identification while effectively preserving important features for image- and video-copy-detection tasks, proposing a new deep-learning-based de-identification approach that surpasses traditional pixel-based alteration methods. We introduce two de-identification models using different approaches: one emphasizing the contours of the original face through feature inversion and the other generating a blurred version of the face using D2GAN (Dual Discriminator Generative Adversarial Network). Both models were evaluated on their performance in image- and video-copy-detection tasks before and after de-identification, demonstrating effective feature preservation. This research presents new possibilities for personal-information protection and digital-content security, contributing to digital-rights management and law enforcement.

Deep Learning for Concrete Crack Detection and Measurement

Concrete structures inevitably experience cracking, which is a common form of damage. If cracks are left undetected and allowed to worsen, catastrophic failures, with costly implications for human life and the economy, can occur. Traditional image processing techniques for crack detection and measurement have several limitations, which include complex parameter selection and restriction to measuring cracks in pixels, rather than more practical units of millimetres. This paper presents a three-stage approach that utilises deep learning and image processing for crack classification, segmentation and measurement. In the first two stages, custom CNN and U-Net models were employed for crack classification and segmentation. The final stage involved measuring crack width in millimetres by using a novel laser calibration method. The classification and segmentation models achieved 99.22% and 96.54% accuracy, respectively, while the mean absolute error observed for crack width measurement was 0.16 mm. The results demonstrate the adequacy of the developed crack detection and measurement method, and shows the developed deep learning and laser calibration method promotes safer, quicker inspections that are less prone to human error. The method’s ability to measure cracks in millimetres provides a more insightful assessment of structural damage, which is, in comparison to traditional pixel-based measurement methods, a significant improvement for practical field applications.

Object-based characterization of vegetation heterogeneity with sentinel images proves efficient in a highly human-influenced National Park of Côte d’Ivoire

Forest monitoring requires more automated systems to analyze high ecosystem heterogeneity. The traditional pixel-based detection method has proven to be less and less effective. A novel change detection method is therefore proposed to detect changes in forest cover using satellite images at very high spatial resolution. This is object-oriented classification, which groups pixels into interpreted objects, based on their spectral values, spatial, and textural properties. Using sentinel and Lansat images, we tested for the first time in the West African rainforest zone the effectiveness of this method for better detection, delineation, and analysis of land use and occupation types. The mean shift algorithm was used in both the segmentation and classification processes. Next, we compared the proposed object-oriented method with a pixel-based image classification detection method by implementing both methods under the same conditions. High detection accuracy (> 90%) and an overall Kappa greater than 0.90 were obtained by the object-oriented method, which is about 20% higher than the pixel-based method. The object-based method was free of salt and pepper effects and was less prone to image misregistration in terms of change detection accuracy and mapping results. This study demonstrates that the object-based classifier is a much better approach than the classical pixel-based classifier. In addition, it shows the problems of detecting heterogeneous landscapes and explains the observed confusions between the types of vegetation formations specific to tropical wetlands. The results obtained are encouraging and the contribution of high-resolution images and the object-based method to better discrimination of tropical wetland vegetation is discussed.

Large-scale deep learning based binary and semantic change detection in ultra high resolution remote sensing imagery: From benchmark datasets to urban application

With the acceleration of urban expansion, urban change detection (UCD), as a significant and effective approach, can provide the change information with respect to geospatial objects for dynamic urban analysis. In recent years, through the use of machine learning and artificial intelligence, change detection methods have gradually developed from the traditional pixel-based comparison methods in the 1980s to data-driven deep learning methods. Deep learning methods have huge advantages in the application of remote sensing big data, by virtue of their huge feature extraction and expression capabilities. Many change detection datasets have been released to meet the requirements of deep learning. However, the existing datasets suffer from three bottlenecks: (1) the volume of the datasets is small, which can easily cause overfitting; (2) most datasets have a spatial resolution of meters, making it difficult to detect changes in small objects because there are multi-scale objects in urban areas; and (3) most of the datasets have been designed for binary change detection (BCD), and lack semantic annotation, so that they cannot be used to obtain the direction of the change or to analyze the type of change, for further application in urban areas. Therefore, it is difficult to apply these datasets to detect large-scale urban semantic changes in complex environments. To address these issues, a large-scale ultra high resolution (0.1m) UCD dataset for deep learning based BCD and semantic change detection (SCD) is introduced in this article, which is named the Hi-UCD dataset. We selected an area of 102m2 in Tallinn, the capital of Estonia, as the study area. There are a total of 40800 pairs of 512 × 512 patches, nine types of land cover and 48 types of semantic change in the Hi-UCD dataset. We developed three metrics–binary consistency, change area consistency and no-change area consistency–to evaluate the semantic consistency of the SCD methods from different aspects. A comprehensive analysis and investigation is provided in this article after we benchmarked this dataset using deep learning methods for BCD and SCD. We also found that the unchanged samples can help distinguish the changed area, and HRNet used as the backbone to construct a multi-task model can perform well in the Hi-UCD dataset. Meanwhile, the visualization results obtained with the Hi-UCD test set, which is a large geographic area covering 54km2, are shown to reflect the real-world urban application scenarios. The experimental results show that the Hi-UCD dataset is a challenging yet useful benchmark dataset, which can be used for analyzing large-scale refined urban changes.

Land Use and Land Cover Mapping Using RapidEye Imagery Based on a Novel Band Attention Deep Learning Method in the Three Gorges Reservoir Area

Land use/land cover (LULC) change has been recognized as one of the most important indicators to study ecological and environmental changes. Remote sensing provides an effective way to map and monitor LULC change in real time and for large areas. However, with the increasing spatial resolution of remote sensing imagery, traditional classification approaches cannot fully represent the spectral and spatial information from objects and thus have limitations in classification results, such as the “salt and pepper” effect. Nowadays, the deep semantic segmentation methods have shown great potential to solve this challenge. In this study, we developed an adaptive band attention (BA) deep learning model based on U-Net to classify the LULC in the Three Gorges Reservoir Area (TGRA) combining RapidEye imagery and topographic information. The BA module adaptively weighted input bands in convolution layers to address the different importance of the bands. By comparing the performance of our model with two typical traditional pixel-based methods including classification and regression tree (CART) and random forest (RF), we found a higher overall accuracy (OA) and a higher Intersection over Union (IoU) for all classification categories using our model. The OA and mean IoU of our model were 0.77 and 0.60, respectively, with the BA module and were 0.75 and 0.58, respectively, without the BA module. The OA and mean IoU of CART and RF were both below 0.51 and 0.30, respectively, although RF slightly outperformed CART. Our model also showed a reasonable classification accuracy in independent areas well outside the training area, which indicates the strong model generalizability in the spatial domain. This study demonstrates the novelty of our proposed model for large-scale LULC mapping using high-resolution remote sensing data, which well overcomes the limitations of traditional classification approaches and suggests the consideration of band weighting in convolution layers.

How Well Do Deep Learning-Based Methods for Land Cover Classification and Object Detection Perform on High Resolution Remote Sensing Imagery?

Land cover information plays an important role in mapping ecological and environmental changes in Earth’s diverse landscapes for ecosystem monitoring. Remote sensing data have been widely used for the study of land cover, enabling efficient mapping of changes of the Earth surface from Space. Although the availability of high-resolution remote sensing imagery increases significantly every year, traditional land cover analysis approaches based on pixel and object levels are not optimal. Recent advancement in deep learning has achieved remarkable success on image recognition field and has shown potential in high spatial resolution remote sensing applications, including classification and object detection. In this paper, a comprehensive review on land cover classification and object detection approaches using high resolution imagery is provided. Through two case studies, we demonstrated the applications of the state-of-the-art deep learning models to high spatial resolution remote sensing data for land cover classification and object detection and evaluated their performances against traditional approaches. For a land cover classification task, the deep-learning-based methods provide an end-to-end solution by using both spatial and spectral information. They have shown better performance than the traditional pixel-based method, especially for the categories of different vegetation. For an objective detection task, the deep-learning-based object detection method achieved more than 98% accuracy in a large area; its high accuracy and efficiency could relieve the burden of the traditional, labour-intensive method. However, considering the diversity of remote sensing data, more training datasets are required in order to improve the generalisation and the robustness of deep learning-based models.

Water Requirement for Irrigation of Complicated Agricultural Land by Using Classified Airborne Digital Sensor Images

Land use of irrigated areas nearby the metropolitan is complex. On fields, crop growth may differ with variations in the water demand. Among the image classification methods, combined object-oriented classification is currently preferred over conventional pixel-based classification. Compared with the traditional pixel-based method, which generally exhibits a spot-like salt-and-pepper effect, object-based classification can significantly reduce the salt-and-pepper effect and amount of data required for analysis. To obtain improved spectral recognition, maximum image information is described using color, texture, and shape to enhance image recognition. In this study, image information extraction and crop interpretation were performed using the airborne digital sensor ADS40 to obtain experimental data, and the traditional supervised image and image object classification methods were compared. The results indicate that both the image classification methods could yield an overall accuracy of more than 80%, and the accuracy of object-based classification (88.68%) was higher than that of the other classification. The daily water requirement of crops in the study area, calculated using a high-precision image object classification method, was approximately 2585 m3. The current results may aid in the effective estimation of agricultural irrigation water consumption.

Mapping salt marsh soil properties using imaging spectroscopy

Tidal salt marshes sequester and store blue carbon at both short and long time scales. Marsh soils shape and maintain the ecosystem by supporting complex biogeochemical reactions, deposition of sediment, and accumulation of organic matter. In this study, we examined the potential of imaging spectroscopy techniques to indirectly quantify and map tidal marsh soil properties at a National Estuarine Research Reserve in Georgia, USA. A framework was developed to combine modern digital image processing techniques for marsh soil mapping, including object-based image analysis (OBIA), machine learning modeling, and ensemble analysis. We also evaluated the efficacy of airborne hyperspectral sensors in estimating marsh soil properties compared to spaceborne multispectral sensors, WorldView-2 and QuickBird. The pros and cons of object-based modeling and mapping were assessed and compared with traditional pixel-based mapping methods. The results showed that the designed framework was effective in quantifying and mapping three marsh soil properties using the composite reflectance from salt marsh environment: soil salinity, soil water content, and soil organic matter content. Multispectral sensors were successful in quantifying soil salinity and soil water content but failed to model soil organic matter. The study also demonstrated the value of minimum noise fraction transformation and ensemble analysis techniques for marsh soil mapping. The results suggest that imaging spectroscopy based modeling is a promising tool to quantify and map marsh soil properties at a local scale, and is a potential alternative to traditional soil data acquisition to support carbon cycle research and the conservation and restoration of tidal marshes.

Deep Learning-Based Classification Methods for Remote Sensing Images in Urban Built-Up Areas

Urban areas have been focused recently on the remote sensing applications since their function closely relates to the distribution of built-up areas, where reflectivity or scattering characteristics are the same or similar. Traditional pixel-based methods cannot discriminate the types of urban built-up areas very well. This paper investigates a deep learning-based classification method for remote sensing images, particularly for high spatial resolution remote sensing (HSRRS) images with various changes and multi-scene classes. Specifically, to help develop the corresponding classification methods in urban built-up areas, we consider four deep neural networks (DNNs): 1) convolutional neural network (CNN); 2) capsule networks (CapsNet); 3) same model with a different training rounding based on CNN (SMDTR-CNN); and 4) same model with different training rounding based on CapsNet (SMDTR-CapsNet). The performances of the proposed methods are evaluated in terms of overall accuracy, kappa coefficient, precision, and confusion matrix. The results revealed that SMDTR-CNN obtained the best overall accuracy (95.0%) and kappa coefficient (0.944) while also improving the precision of parking lot and resident samples by 1% and 4%, respectively.

A Hierarchical Multiscale Super-Pixel-Based Classification Method for Extracting Urban Impervious Surface Using Deep Residual Network From WorldView-2 and LiDAR Data

High-resolution optical imagery can provide detailed information of urban land objects for impervious surface extraction, while airborne light detection and ranging (LiDAR) data can provide height features of land objects. Therefore, synergistic use of high-resolution imagery and LiDAR data is considered as an effective method to improve impervious surfaces extraction. In this paper, a novel hierarchical multiscale super-pixel-based classification method is proposed and applied to the urban impervious surfaces extraction from WorldView-2 and normalized digital surface model (nDSM) images derived from airborne LiDAR data. Three subsets in rural, rural–urban, and urban subsets are selected as the study areas. First, we split nonground and ground objects based on nDSM thresholds. Second, a hierarchical multiresolution segmentation method is used to generate nonground and ground super pixels. Then, we determine the multiscale input images based on the size of super pixels. Third, we construct optimal deep residual network (ResNet) and Spatial Pyramid Pooling (SPP-net) to train the model using multiscale input images. Finally, we use our deep models to predict hierarchically total super pixels in three subsets and generate the classification and impervious surfaces results. Our proposed method adopts hierarchical classification based on LiDAR nDSM height, which significantly improves the impervious surfaces extraction accuracies. Then, the deep residual network is applied further on multispectral and height fused data to extract urban impervious surfaces. Moreover, we propose an adaptive method to determine multiscale input images based on the segmentation of super pixels, which are inputs into the ResNet+SPP-net to train the deep model. Our proposed method reduces the uncertainty of multiscale input images and extracts better multiscale features. The results of the experiment show that our proposed method has a significant superiority to traditional pixel-based method and single scale method for urban impervious surfaces extraction.

Monitoring Land-Use/Land-Cover Changes at a Provincial Large Scale Using an Object-Oriented Technique and Medium-Resolution Remote-Sensing Images

An object-based image analysis (OBIA) technique is replacing traditional pixel-based methods and setting a new standard for monitoring land-use/land-cover changes (LUCC). To date, however, studies have focused mainly on small-scale exploratory experiments and high-resolution remote-sensing images. Therefore, this study used OBIA techniques and medium-resolution Chinese HJ-CCD images to monitor LUCC at the provincial scale. The results showed that while woodland was mainly distributed in the west, south, and east mountain areas of Hunan Province, the west had the largest area and most continuous distribution. Wetland was distributed mainly in the northern plain area, and cultivated land was distributed mainly in the central and northern plains and mountain valleys. The largest impervious surface was the Changzhutan urban agglomerate in the northeast plain area. The spatial distribution of land cover in Hunan Province was closely related to topography, government policy, and economic development. For the period 2000–2010, the areas of cultivated land transformed into woodland, grassland, and wetland were 183.87 km2, 5.57 km2, and 70.02 km2, respectively, indicating that the government-promoted ecologically engineered construction was yielding some results. The rapid economic growth and urbanization, high resource development intensity, and other natural factors offset the gains made in ecologically engineered construction and in increasing forest and wetland areas, respectively, by 229.82 km2 and 132.12 km2 from 2000 to 2010 in Hunan Province. The results also showed large spatial differences in change amplitude (LUCCA), change speed (LUCCS), and transformation processes in Hunan Province. The Changzhutan urban agglomerate and the surrounding prefectures had the largest LUCCA and LUCCS, where the dominant land cover accounted for the conversion of some 189.76 km2 of cultivated land, 129.30 km2 of woodland, and 6.12 km2 of wetland into impervious surfaces in 2000–2010. This conversion was attributed to accelerated urbanization and rapid economic growth in this region.

Tea Garden Detection from High-Resolution Imagery Using a Scene-Based Framework

Tea cultivation has a long history in China, and it is one of the pillar industries of the Chinese agricultural economy. It is therefore necessary to map tea gardens for their ongoing management. However, the previous studies have relied on fieldwork to achieve this task, which is time-consuming. In this paper, we propose a framework to map tea gardens using high-resolution remotely sensed imagery, including three scene-based methods: the bag-of-visual-words (BOVW) model, supervised latent Dirichlet allocation (sLDA), and the unsupervised convolutional neural network (UCNN). These methods can develop direct and holistic semantic representations for tea garden scenes composed of multiple sub-objects, thus they are more suitable than the traditional pixel-based or object-based methods, which focus on the local characteristics of pixels or objects. In the experiments undertaken in this study, the three different methods were tested on four datasets from Longyan (Oolong tea), Hangzhou (Longjing tea), and Puer (Puer tea). All the methods achieved a good performance, both quantitatively and visually, and the UCNN outperformed the other methods. Moreover, it was found that the addition of textural features improved the accuracy of the BOVW and sLDA models, but had no effect on the UCNN.

High-Resolution Remote Sensing Image Classification Method Based on Convolutional Neural Network and Restricted Conditional Random Field

Convolutional neural networks (CNNs) can adapt to more complex data, extract deeper characteristics from images, and achieve higher classification accuracy in remote sensing image scene classification and object detection compared to traditional shallow-model methods. However, directly applying common-structure CNNs to pixel-based remote sensing image classification will lead to boundary or outline distortions of the land cover and consumes enormous computation time in the image classification stage. To solve this problem, we propose a high-resolution remote sensing image classification method based on CNN and the restricted conditional random field algorithm (CNN-RCRF). CNN-RCRF adopts CNN superpixel classification instead of pixel-based classification and uses the restricted conditional random field algorithm (RCRF) to refine the superpixel result image into a pixel-based result. The proposed method not only takes advantage of the classification ability of CNNs but can also avoid boundary or outline distortions of the land cover and greatly reduce computation time in classifying images. The effectiveness of the proposed method is tested with two high-resolution remote sensing images, and the experimental results show that the CNN-RCRF outperforms the existing traditional methods in terms of overall accuracy, and CNN-RCRF’s computation time is much less than that of traditional pixel-based deep-model methods.

THE EXTRACTION OF POST-EARTHQUAKE BUILDING DAMAGE INFORMATIOM BASED ON CONVOLUTIONAL NEURAL NETWORK

Abstract. The seismic damage information of buildings extracted from remote sensing (RS) imagery is meaningful for supporting relief and effective reduction of losses caused by earthquake. Both traditional pixel-based and object-oriented methods have some shortcoming in extracting information of object. Pixel-based method can’t make fully use of contextual information of objects. Object-oriented method faces problem that segmentation of image is not ideal, and the choice of feature space is difficult. In this paper, a new stratage is proposed which combines Convolution Neural Network (CNN) with imagery segmentation to extract building damage information from remote sensing imagery. the key idea of this method includes two steps. First to use CNN to predicate the probability of each pixel and then integrate the probability within each segmentation spot. The method is tested through extracting the collapsed building and uncollapsed building from the aerial image which is acquired in Longtoushan Town after Ms 6.5 Ludian County, Yunnan Province earthquake. The results show that the proposed method indicates its effectiveness in extracting damage information of buildings after earthquake.

Colorimetry-based edge preservation approach for color image enhancement

“Subpixel-based downsampling” is an approach that can implicitly enhance perceptible image resolution of a downsampled image by managing subpixel-level representation preferably with individual pixel. A subpixel-level representation for color image sample at edge region and color image representation is focused with the problem of directional filtration based on horizontal and vertical orientations using colorimetric color space with the help of saturation and desaturation pixels. A diagonal tracing algorithm and an edge preserving approach with colorimetric color space were used for color image enhancement. Since, there exist high variations at the edge regions, it could not be considered as constant or zero, and when these variations are random the need to compensate these to minimum value and then process for image representation. Finally, the results of the proposed method show much better image information as compared with traditional direct pixel-based methods with increased luminance and chrominance resolutions.

객체기반 분류기법을 이용한 토지피복 특성분석 - 강원도 인제군의 DMZ지역 일원을 대상으로 -

최근 픽셀기반분류보다 더 많은 정보를 이용할 수 있는 객체기반에 대한 연구가 활발히 진행 중이다. 따라서, 본 연구는 인제군 Demilitarized Zone(DMZ)지역 일원을 대상으로 객체기반 분류기법을 이용한 토지피복분류를 실시하였다. 분류항목은 환경부 기준의 대분류 항목 7개, 중분류 항목 13개로 선정하였고, 사용된 인자는 분광 값의 평균과 표준편차, Grey Level Co-occurrence Matrix(GLCM)의 Homogeneity를 사용하여 감독분류방법 중 최근린기법을 이용하여 계층적 토지피복도를 구축하였다. 구축된 토지피복도를 이용하여 남방한계선으로부터의 거리와 Digital elevation model(DEM)을 통해 지형특성에 따른 분류항목 별 분포 특성을 분석하였다. 객체기반 분류를 위한 최적 가중치는 Scale 72, Shape 0.2. Color 0.8, Compactness 0.5, Smoothness 0.5로 선정하였고, 가중치 선정과정에서 Scale, Shape, Color가 가장 많은 영향을 주었다. 대분류 토지피복분류는 산림, 초지, 시가지의 순으로 각각 약 92%, 약 5%, 약 2%였으며, 중분류 토지피복분류는 활엽수림, 혼효림, 침엽수림의 순으로 각각 약 44%, 약 42%, 약 6% 순으로 분포하였다. 토지피복형태에 따른 분포특성을 보면, 남방한계선으로부터 2km이내의 지역에서 공공시설 지역과 도로의 이용이 높았으며, 남방한계선 6km이상의 지역에서는 논과 밭, 나지의 형태가 많았다. 산림은 표고 600m, 경사 <TEX>$30^{\circ}$</TEX>이상의 지역에서는 면적분포가 높았고, 농업지역과 나지, 초지는 표고 600m, 경사 <TEX>$30^{\circ}$</TEX>이하의 지역에서 면적분포가 높았다. Object-based classification methods provide a valid alternative to traditional pixel-based methods. This study reports the results of an object-based classification to examine land cover in the demilitarized zones(DMZs) of Inje-gun. We used land cover classes(7 classes for main category and 13 classes for sub-category) selected from the criteria by Korea Ministry of Environment. The average and standard deviation of the spectrum values, and homogeneity of GLCM were chosen to map land cover types in an hierarchical approach using the nearest neighborhood method. We then identified the distributional characteristics of land cover by considering 3 topographic characteristics (altitude, slope gradient, distance from the Southern Limited Line(SLL)) within the DMZs. The results showed that scale 72, shape 0.2, color 0.8, compactness 0.5 and smoothness 0.5 were the optimum weight values while scale, shape and color were most influenced parameters in image segmentation. The forests (92%) were main land cover type in the DMZs; the grassland(5%), the urban area (2%) and the forests (broadleaf forest: 44%, mixed forest: 42%, coniferous forest: 6%) also occupied mostly in land cover classes for sub-category. The results also showed that facilities and roads had higher density within 2 km from the SLL, while paddy, field and bare land were distributed largely outside 6 km from the SLL. In addition, there was apparent distinction in land cover by topographic characteristics. The forest had higher density at above altitude 600m and above slope gradient <TEX>$30^{\circ}$</TEX> while agriculture, bare land and grass land were distributed mainly at below altitude 600m and below slope gradient <TEX>$30^{\circ}$</TEX>.

SU-D-217A-03: Nuclear Medicine Uniformity Assessment Using 2D Noise Power Spectrum.

Nuclear medicine quality control programs require daily evaluation for the presence of potential non-uniformities by commonly utilizing a traditional pixel value-based assessment (Integral CFOVUniformity). While this method effectively captures regional non- uniformities in the image, it does not adequately reflect subtle periodic structures that are visually apparent and clinically unacceptable, therefore requiring the need for additional visual inspection of the image. The goal of this project was to develop a new uniformity assessment metric by targetingstructural patterns and more closely correlating with visual inspection. The new quantitative uniformity assessment metric is based on the 2D Noise Power Spectrum (NPS). A full 2D NPS was performed on each image. The NPS was thresholded to remove quantum noise and further filtered by the visual response function. A score, the Structure Noise Index (SNI), was then applied to each based on the average magnitude of the structured noise in the processed image. To verify the validity of the new metric, 50 daily uniformity images with varying degrees of visual structured and non-structured non-uniformity were scored by 5 expert nuclear medicine physicists. The correlation between the visual score and SNI were assessed. The Integral CFOV was also compared against the visual score. Our new SNI assessment metric compared to the Integral CFOV showed in increase in sensitivity from 67% to 100% in correctly identifying structured non-uniformities. The overall positive predictive value also increased from 55% to 72%. Our new uniformity metric correlates much more closely with visual assessment of structured non- uniform NM images than the traditional pixel-based method. Using this new metric in conjunction with the traditional pixel value-based assessment will allow a more accurate quantitative assessment of nuclear medicineuniformity.

Facies Modeling Using a Markov Mesh Model Specification

The spatial continuity of facies is one of the key factors controlling flow in reservoir models. Traditional pixel-based methods such as truncated Gaussian random fields and indicator simulation are based on only two-point statistics, which is insufficient to capture complex facies structures. Current methods for multi-point statistics either lack a consistent statistical model specification or are too computer intensive to be applicable. We propose a Markov mesh model based on generalized linear models for geological facies modeling. The approach defines a consistent statistical model that is facilitated by efficient estimation of model parameters and generation of realizations. Our presentation includes a formulation of the general framework, model specifications in two and three dimensions, and details on how the parameters can be estimated from a training image. We illustrate the method using multiple training images, including binary and trinary images and simulations in two and three dimensions. We also do a thorough comparison to the snesim approach. We find that the current model formulation is applicable for multiple training images and compares favorably to the snesim approach in our test examples. The method is highly memory efficient.