Marguerite Madden

HYPERSPECTRAL IMAGE DATA FOR MAPPING WETLAND VEGETATION

Data acquired by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) with 224 bands, each with 0.01-μm spectral resolution and 20-meter spatial resolution, were used to produce a vegetation map for a portion of Everglades National Park, Florida, USA. The vegetation map was tested for classification accuracy with a pre-existing detailed GIS wetland vegetation database compiled by manual interpretation of 1∶40,000-scale color infrared (CIR) aerial photographs. Although the accuracy varied greatly for different classes, ranging from 40 percent for scrub red mangroves (Rhizophora mangle) to 100 percent for spike rush (Eleocharis cellulosa) prairies, the Everglades communities generally were successfully identified, averaging 66 percent correct for all classes. In addition, the hyperspectral image data proved suitable for detecting the invasive exotic species lather leaf (Colubrina asiatica) that is sometimes difficult to differentiate on aerial photographs. The findings from this study have implications for operational uses of spaceborne hyperspectral image data that are now becoming available. Practical limitations of using such image data for wetland vegetation mapping include inadequate spatial resolution, complexity of image processing procedures, and lack of stereo viewing.

Forest type mapping using object-specific texture measures from multispectral Ikonos imagery: segmentation quality and image classification issues.

This study investigated the use of a geographic object-based image analysis (GEOBIA) approach with the incorporation of object-specific grey-level co-occurrence matrix (GLCM) texture measures from a multispectral Ikonos image for delineation of deciduous, evergreen, and mixed forest types in Guilford Courthouse National Military Park, North Carolina. A series of automated segmentations was produced at a range of scales, each resulting in an associated range of number and size of objects (or segments). Prior to classification, the spatial autocorrelation of each segmentation was evaluated by calculating Moran’s I using the average image digital numbers (DNs) per segment. An initial assumption was made that the optimal segmentation scales would have the lowest spatial autocorrelation, and conversely, that over- and under-segmentation would result in higher autocorrelation between segments. At these optimal segmentation scales, the automated segmentation was found to yield information comparable to manually interpreted stand-level forest maps in terms of the size and number of segments. A series of object-based classifications was carried out on the image at the entire range of segmentation scales. The results demonstrated that the scale of segmentation directly influenced the object-based forest type classification results. The accuracies were higher for classification of images identified from a spatial autocorrelation analysis to have an optimal segmentation, compared to those determined to have over- and under-segmentation. An overall accuracy of 79 percent with a Kappa of 0.65 was obtained at the optimal segmentation scale of 19. The addition of object-specific GLCM multiple texture analysis improved classification accuracies up to a value of 83 percent overall accuracy and a Kappa of 0.71 by reducing the confusion between evergreen and mixed forest types. Although some misclassification still remained because of local segmentation quality, a visual assessment of the texture-enhanced GEOBIA classification generally agreeable with manually interpreted forest types.

Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale, texture and image objects

This study used geographic object-based image analysis (GEOBIA) with very high spatial resolution (VHR) aerial imagery (0.3 m spatial resolution) to classify vegetation, channel and bare mud classes in a salt marsh. Three classification issues were investigated in the context of segmentation scale: (1) a comparison of single- and multi-scale GEOBIA using spectral bands, (2) the relative benefit of incorporating texture derived from the grey-level co-occurrence matrix (GLCM) in classifying the salt marsh features in single- and multi-scale GEOBIA and (3) the effect of quantization level of GLCM texture in the context of multi-scale GEOBIA. The single-scale GEOBIA experiments indicated that the optimal segmentation was both class and scale dependent. Therefore, the single-scale approach produced an only moderately accurate classification for all marsh classes. A multi-scale approach, however, facilitated the use of multiple scales that allowed the delineation of individual classes with increased between-class and reduced within-class spectral variation. With only spectral bands used, the multi-scale approach outperformed the single-scale GEOBIA with an overall accuracy of 82% vs. 76% (Kappa of 0.71 vs. 0.62). The study demonstrates the potential importance of ancillary data, GLCM texture, to compensate for limited between-class spectral discrimination. For example, gains in classification accuracies ranged from 3% to 12% when the GLCM mean texture was included in the multi-scale GEOBIA. The multi-scale classification overall accuracy varied with quantization level of the GLCM texture matrix. A quantization level of 2 reduced misclassifications of channel and bare mud and generated a statistically higher classification than higher quantization levels. Overall, the multi-scale GEOBIA produced the highest classification accuracy. The multi-scale GEOBIA is expected to be a useful methodology for creating a seamless spatial database of marsh landscape features to be used for further geographic information system (GIS) analyses.

Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery

The determination of segments that represents an optimal image object size is very challenging in object-based image analysis (OBIA). This research employs local variance and spatial autocorrelation to estimate the optimal size of image objects for segmenting forest stands. Segmented images are visually compared to a manually interpreted forest stand database to examine the quality of forest stand segmentation in terms of the average size and number of image objects. Average local variances are then graphed against segmentation scale in an attempt to determine the appropriate scale for optimally derived segments. In addition, an analysis of spatial autocorrelation is performed to investigate how between-object correlation changes with segmentation scale in terms of over-, optimal, and under-segmentation.

Photogrammetric and GIS techniques for the development of vegetation databases of mountainous areas: Great Smoky Mountains National Park

Detailed vegetation databases and associated maps of the Great Smoky Mountains National Park, a rugged, forested area of more than 2000 km 2 , were constructed to support resource management activities of the U.S. National Park Service (NPS). These detailed vegetation databases and associated maps have a terrain relief exceeding 1700 m and a continuous forest cover over 95% of the Park. The requirement to use 1:12,000- and 1:40,000-scale color infrared aerial photographs as the primary data source for mapping overstory and understory vegetation, respectively, necessitated the integration of analog photointerpretation with both digital softcopy photogrammetry and geographic information system (GIS) procedures to overcome problems associated with excessive terrain relief and a lack of ground control. Applications of the vegetation database and associated large-scale maps include assessments of vegetation patterns related to management activities and quantification of forest fire fuels.

China's Wetlands: conservation plans and policy impacts.

Since the Ramsar Convention on Wetlands in 1971, wetland conservation (maintenance and sustainable use) and restoration (recovery of degraded natural wetlands) have been high priorities for many countries. China has the world’s fourth largest wetland area, which exceeds the whole territory of Great Britain. While the Chinese government has increasingly recognized the importance of wetland protection, particularly after joining the Ramsar Convention in 1992, natural wetlands in China have suffered great loss and degradation. To address this problem, China has implemented the National Wetland Conservation Program (NWCP)—one of the largest of its kind in the world—with ambitious goals, massive investments, and potentially enormous impacts. Furthermore, NWCP has global implications because it aims to rehabilitate habitats for water birds of international importance, enhance carbon sequestration, conserve soil and water, and protect important headwaters of international rivers and lakes.

Genocide and GIScience: Integrating Personal Narratives and Geographic Information Science to Study Human Rights

This project combines qualitative data of personal narratives with geographic information science (GIScience) technologies to explore the potential for critical cartography in the study of mass atrocity. The case study used is northern Uganda, where millions have been affected by physical violence and hardship, displacement, and fear. Web-based virtual globes as a ready source of imagery for remote areas and derived spatial data imported to geographic information systems (GIS) provide quantified data that complement testimonials and other qualitative data from the field. Cartographic functions, geovisualization, and spatial analyses available in GIS are used to extract information from high-resolution remote sensing images documenting internally displaced persons (IDP) camps and quantifying evidence of crimes against humanity. These techniques explore spatial relationships and communicate results on the extent and impact of the atrocities in northern Uganda.

K Nearest Neighbor Method for Forest Inventory Using Remote Sensing Data

The K nearest neighbor (KNN) method of image analysis is practical, relatively easy to implement, and is becoming one of the most popular methods for conducting forest inventory using remote sensing data. The KNN is often named K nearest neighbor classifier when it is used for classifying categorical variables, while KNN is called K nearest neighbor regression when it is applied for predicting noncategorical variables. As an instance-based estimation method, KNN has two problems: the selection of K values and computation cost. We address the problems of K selection by applying a new approach, which is the combination of the Kolmogorov-Smirnov (KS) test and cumulative distribution function (CDF) to determine the optimal K. Our research indicates that the KS tests and CDF are much more efficient for selecting K than cross-validation and bootstrapping, which are commonly used today. We use remote sensing data reduction techniques—such as principal components analysis, layer combination, and computation of a vegetation index—to save computation cost. We also consider the theoretical and practical implications of different K values in forest inventory.

Effects of spatial resolution ratio in image fusion

In image fusion, the spatial resolution ratio can be defined as the ratio between the spatial resolution of the high‐resolution panchromatic image and that of the low‐resolution multispectral image. This paper attempts to assess the effects of the spatial resolution ratio of the input images on the quality of the fused image. Experimental results indicate that a spatial resolution ratio of 1 : 10 or higher is desired for optimal multisensor image fusion provided the input panchromatic image is not downsampled to a coarser resolution. Due to the synthetic pixels generated from resampling, the quality of the fused image decreases as the spatial resolution ratio decreases (e.g. from 1 : 10 to 1 : 30). However, even with a spatial resolution ratio as small as 1 : 30, the quality of the fused image is still better than the original multispectral image alone for feature interpretation. In cases where the spatial resolution ratio is too small (e.g. 1 : 30), to obtain better spectral integrity of the fused image, one may downsample the input high‐resolution panchromatic image to a slightly lower resolution before fusing it with the multispectral image.

GEOBIA vegetation mapping in Great Smoky Mountains National Park with spectral and non-spectral ancillary information.

Vegetation mapping was performed using geographic object-based image analysis (GEOS1A) and very high spatial resolution (VHR) imagery for two study areas in Great Smoky Mountains National Park. This study investigated how accurately GEOB1A with ancillary data emulates manual interpretation in rugged mountain areas for multi-level vegetation classes of the National Vegetation Classification System (NVCS). It was discovered that the incorporation of texture and topographic variables with spectral data from scanned color infrared aerial photographs increased the overall accuracy of GEOBIA vegetation classification by 2.8 percent and 5.0 percent Kappa. In a separate study using multispectral Ikonos imagery, the use of elevation, aspect, slope and proximity to streams produced NVCS macro-group vegetation segmentations that resembled manual interpretation and significantly improved the overall accuracy to 76.6 percent, Kappa 0.57. Ancillary information may thus aid in GEOBIA vegetation mapping for updating vegetation inventories in rugged mountain areas.