Analysis Of Multispectral Imagery Research Articles

CerealNet: A Hybrid Deep Learning Architecture for Cereal Crop Mapping Using Sentinel-2 Time-Series

Remote sensing-based crop mapping has continued to grow in economic importance over the last two decades. Given the ever-increasing rate of population growth and the implications of multiplying global food production, the necessity for timely, accurate, and reliable agricultural data is of the utmost importance. When it comes to ensuring high accuracy in crop maps, spectral similarities between crops represent serious limiting factors. Crops that display similar spectral responses are notorious for being nearly impossible to discriminate using classical multi-spectral imagery analysis. Chief among these crops are soft wheat, durum wheat, oats, and barley. In this paper, we propose a unique multi-input deep learning approach for cereal crop mapping, called “CerealNet”. Two time-series used as input, from the Sentinel-2 bands and NDVI (Normalized Difference Vegetation Index), were fed into separate branches of the LSTM-Conv1D (Long Short-Term Memory Convolutional Neural Networks) model to extract the temporal and spectral features necessary for the pixel-based crop mapping. The approach was evaluated using ground-truth data collected in the Gharb region (northwest of Morocco). We noted a categorical accuracy and an F1-score of 95% and 94%, respectively, with minimal confusion between the four cereal classes. CerealNet proved insensitive to sample size, as the least-represented crop, oats, had the highest F1-score. This model was compared with several state-of-the-art crop mapping classifiers and was found to outperform them. The modularity of CerealNet could possibly allow for injecting additional data such as Synthetic Aperture Radar (SAR) bands, especially when optical imagery is not available.

Monitoring trophic status using in situ data and Sentinel-2 MSI algorithm: lesson from Lake Malombe, Malawi.

With excessive nutrient enrichment exacerbated by anthropogenic drivers, many standing water bodies are changing from oligotrophic to mesotrophic, eutrophic, and finally hypertrophic-negatively affecting ecosystem functioning, biodiversity, and human populations. Efforts have been devoted to developing novel algorithms for estimating chlorophyll-a (chl-a), cyno-blooms, and floating vegetation. However, to this date, little research has focused on freshwater lakes in the data-scarce Sub-Saharan African countries such as Malawi. We, therefore, estimated the trophic status of Lake Malombe in Malawi-a lake likely to be affected by eutrophication and algal bloom-emerging threats to freshwater ecosystem functioning globally-especially with the onset of climatic and anthropogenic drivers. We integrated in situ data with high-resolution Sentinel-2 Multispectral Imagery Analysis (MSI). We independently assessed the remote sensing technique using in situ data and tested the model at multiple stages. The scatter plot showed that most points were in the 95% confidence interval. The validation results between the measured in situ chl-a concentrations and the Sentinel-2 MSI-based chl-a retrieval had a root mean square error (RMSE) of 2.88µg/L. The chl-a concentrations retrieved from MSI images were consistent with in situ data, indicating that the normalized difference chlorophyll index (NDCI) algorithm estimated chl-a concentrations in Lake Malombe with acceptable accuracy. Dissolved oxygen (DO), sulfate (SO42-), nitrite [Formula: see text], soluble reactive phosphorous [Formula: see text]), total dissolved solids (TDS), and chl-a, except for temperatures from the hot-dry-season, cold-dry-windy-season, and rainy-season, were significantly different (P < 0.05). The Sentinel-2 MSI imagery analysis also depicted similar results, with high chl-a concentration reported in March (rainy season) and October (hot-dry season) and the lowest from May to August (cold-dry-windy season). On the contrary, the ANOVA results for water quality parameters from all five points had P > 0.05. The correlation matrix showed coefficients of (0.798 < r < 0.930, n = 30, P < 0.005), suggesting that Lake Malombe is homogenous. Our results demonstrate that integrating remote sensing based on MSI imagery and in situ data to estimate chl-a can provide an effective tool for monitoring eutrophication in small, medium, and large standing waterbodies-crucial information required to respond to global ecological and climaticdynamics.

UAV-Based Remote Sensing for Managing Alaskan Native Heritage Landscapes in the Yukon-Kuskokwim Delta

The Yukon-Kuskokwim (Y-K) Delta is home to the Alaskan Native Yup’ik people who have inhabited this remote, subarctic tundra for over 1500 years. Today, their ancestral lifeways and cultural landscapes are at risk from severe climate change-related threats. In turn, we propose that remote sensing technologies, particularly with sensors mounted on Unmanned Aerial Vehicle (UAV) platforms, are uniquely suited for protecting Yup’ik landscape heritage. Based on collaborative, community-based fieldwork in Quinhagak, AK, we present evidence that cultural sites—ranging from historic fishing camps to pre-contact winter villages—exhibit predictably atypical vegetation patterns based on the local ecological biome. Furthermore, these vegetation patterns can be recorded and statistically quantified through the analysis of multispectral imagery obtained from UAV-mounted sensors with three different false color composite rasters and vegetation indices depending on biome type. Finally, we suggest how the Yupiit can combine these methodologies/workflows with local knowledge to monitor the broader heritage landscape in the face of climate change.

Nuna Nalluyuituq (The Land Remembers): Remembering landscapes and refining methodologies through community‐based remote sensing in the Yukon‐Kuskokwim Delta, Southwest Alaska

AbstractThe following article outlines a collaborative, multidisciplinary approach to remote sensing in Southwest Alaska's Yukon‐Kuskokwim (Y‐K) Delta that combines ethnographic inquiry and remote sensing to monitor, detect and preserve cultural resources for Alaskan Native communities. Because distinctive vegetation differences are readily visible on cultural sites during the summer months, the analysis of multispectral imagery obtained from remote sensing is particularly useful. In turn, we demonstrate the efficacy of this protocol on pre‐contact settlement sites along the Ayakulik River system on Kodiak Island using a normalized difference vegetation index (NDVI) raster of the study area. Here, support vector machine (SVM) supervised classification was highly effective at identifying spectral patterns associated with anthropogenic activity while ethnographic data helped rule out false‐positive cases. In addition, we provide the results of a 2019 archaeological prospection survey carried out in conjunction with the ongoing Nunalleq Project in Quinhagak, Alaska, to further highlight the value of ethnographic data collection, ethnobotanical surveys and unmanned aerial vehicle (UAV)‐based spectroscopy alongside SVM supervised classification. Finally, we propose three suggestions for future research on Yup'ik landscapes in the Y‐K Delta regarding citizen science, language preservation and the use of collaborative online maps for community‐based decision making.

Enhanced Convolutional-Neural-Network Architecture for Crop Classification

Automatic crop identification and monitoring is a key element in enhancing food production processes as well as diminishing the related environmental impact. Although several efficient deep learning techniques have emerged in the field of multispectral imagery analysis, the crop classification problem still needs more accurate solutions. This work introduces a competitive methodology for crop classification from multispectral satellite imagery mainly using an enhanced 2D convolutional neural network (2D-CNN) designed at a smaller-scale architecture, as well as a novel post-processing step. The proposed methodology contains four steps: image stacking, patch extraction, classification model design (based on a 2D-CNN architecture), and post-processing. First, the images are stacked to increase the number of features. Second, the input images are split into patches and fed into the 2D-CNN model. Then, the 2D-CNN model is constructed within a small-scale framework, and properly trained to recognize 10 different types of crops. Finally, a post-processing step is performed in order to reduce the classification error caused by lower-spatial-resolution images. Experiments were carried over the so-named Campo Verde database, which consists of a set of satellite images captured by Landsat and Sentinel satellites from the municipality of Campo Verde, Brazil. In contrast to the maximum accuracy values reached by remarkable works reported in the literature (amounting to an overall accuracy of about 81%, a f1 score of 75.89%, and average accuracy of 73.35%), the proposed methodology achieves a competitive overall accuracy of 81.20%, a f1 score of 75.89%, and an average accuracy of 88.72% when classifying 10 different crops, while ensuring an adequate trade-off between the number of multiply-accumulate operations (MACs) and accuracy. Furthermore, given its ability to effectively classify patches from two image sequences, this methodology may result appealing for other real-world applications, such as the classification of urban materials.

Comparison of Spectral Reflectance-Based Smart Farming Tools and a Conventional Approach to Determine Herbage Mass and Grass Quality on Farm

The analysis of multispectral imagery (MSI) acquired by unmanned aerial vehicles (UAVs) and mobile near-infrared reflectance spectroscopy (NIRS) used on-site has become increasingly promising for timely assessments of grassland to support farm management. However, a major challenge of these methods is their calibration, given the large spatiotemporal variability of grassland. This study evaluated the performance of two smart farming tools in determining fresh herbage mass and grass quality (dry matter, crude protein, and structural carbohydrates): an analysis model for MSI (GrassQ) and a portable on-site NIRS (HarvestLabTM 3000). We compared them to conventional look-up tables used by farmers. Surveys were undertaken on 18 multi-species grasslands located on six farms in Switzerland throughout the vegetation period in 2018. The sampled plots represented two phenological growth stages, corresponding to an age of two weeks and four to six weeks, respectively. We found that neither the performance of the smart farming tools nor the performance of the conventional approach were satisfactory for use on multi-species grasslands. The MSI-model performed poorly, with relative errors of 99.7% and 33.2% of the laboratory analyses for herbage mass and crude protein, respectively. The errors of the MSI-model were indicated to be mainly caused by grassland and environmental characteristics that differ from the relatively narrow Irish calibration dataset. The On-site NIRS showed comparable performance to the conventional Look-up Tables in determining crude protein and structural carbohydrates (error ≤ 22.2%). However, we identified that the On-site NIRS determined undried herbage quality with a systematic and correctable error. After corrections, its performance was better than the conventional approach, indicating a great potential of the On-site NIRS for decision support on grazing and harvest scheduling.

Combining Satellite Multispectral Imagery and Topographic Data for the Detection and Mapping of Fluvial Avulsion Processes in Lowland Areas

Fluvial avulsion is an important process in the dynamics of the riverscapes and plays a key role in the drainage network evolution in lowland areas, also influencing past and present social processes and economic activities. Crevasse splays represent significant geomorphological features for understanding the fluvial morphodynamics in lowland areas dominated by avulsion processes. Within wide floodplains characterized by very low elevation ranges, the detection and accurate mapping of crevasse splay morphology and features, such as crevasse channels, levees, and deposit, can be very challenging considering floodplain extension, anthropic impact on the natural channels network, logistic difficulties, and in some cases, climate conditions that prevent field work. This research aims at improving the detection and mapping of crevasse splays in lowland areas through the combination of different remote sensing techniques based on optical multispectral imagery and topographic data derived from satellite earth observation missions. The Lower Mesopotamia Plain (LMP) offers a unique opportunity to study the avulsion processes because it presents numerous examples of crevasse splays, characterized by different sizes and states of activity. Furthermore, in this area, a strong correlation exists between the formation and development of crevasse splays and the expansion of agriculture and early societies since the Early Holocene. Different supervised classification (SC) methods of Landsat 8 satellite images have been tested together with topographic analysis of the microrelief, carried out based on two different 1-arcsec DEMs (AW3D30 and GDEM2). The results of this study demonstrate that the combination of multispectral imagery analysis and topographic analysis of the microrelief is useful for discerning different crevasse elements, distinguishing between active and relict landforms. The methodological approach proved helpful for improving the mapping of erosional and depositional landforms generated by the avulsion process and, in the study area, provided the best results for the active landforms.

Multiple kernel collaborative fuzzy clustering algorithm with weighted super-pixels for satellite image land-cover classification

Applications are dealing with processing the large data size, especially in satellite multi-spectral imagery analysis. In fact, many reasons related to security respect, big data or limited bandwidth, the datasets cann’t be centrally clustered by the FCM algorithm or its variants, so the collaborative clustering algorithms are efficiently used. The clustering algorithms have been applied to analyze the surface of the earth, specifically a variety of multispectral satellite image (MSI) classification. In this paper, a novel collaborative fuzzy clustering based framework is proposed, in particular, which is Multiple kernel Collaborative Fuzzy C-means Clustering with weighted super-pixel granulation technique (SMKCFCM algorithms) for satellite image classification. There are two phases consisting of (1) MSI are preprocessed by grouping of the similar pixels into super-pixels granules and then (2) the super-pixels granules are clustered using the collaborative fuzzy clustering with multiple kernels and the their weights. The granule’s weight is determined based on its size. It means that amount of the considered objects reduces from a large amount of pixels to only a few hundred super-pixels. In the final step, the performance is improved by the collaborative clustering algorithm on multiple sites of image data. This method is combined with multiple kernels that implicitly convert the original feature space into a higher dimensional space via a non-linear map. This transformation leads to greatly increases the linear separability of the non-spherical and complex input patterns. Experiments were performed on the multi-spectral satellite image datasets and the validity indices were summarized with comparison between the SMKCFCM algorithm and some algorithms in the family of collaborative fuzzy clustering.

Unsupervised Change Detection of Multispectral Imagery Using Multi Level Fuzzy Based Deep Representation

Change detection in remote sensing images provides useful information for various applications. This paper proposes a robust methodology for the analysis of multispectral imagery using Deep belief network (DBN) and Fuzzy interference system (FIS). Initially Euclidean distance and cosine angle distance features are extracted from the image. Deep learning is a robust machine learning method in which the extracted features are processed through set linear mapping and the changes are detected. However, the coarse spatial resolution indicating the intensity of modifications in class proportion instead of accounting for the change using discrete land covers classes is used in fuzzy image classification. Hence, the FIS is combined with DBN which allows defining our own rules to detect the changes accurately. It uses triangular membership function to plot the changes. The experimental results show that the proposed method enhanced the change detection by improving the performance parameters.

Image Processing for Art Investigation

Recent advances in digital image acquisition methods and the wide range of imaging modalities currently available have triggered museums to digitize their painting collections. Not only is this crucial for archival or dissemination purposes but it also enabled the digital analysis of the painting through its digital image counterpart. It also set in motion a cross-disciplinary collaboration between image analysis specialists, mathematicians, statisticians and art historians that have the common goal to develop algorithms and build a digital toolbox in support of art scholarship. Computer processing of digital images of paintings has become a fast growing and challenging field of research during the last few years. Our contribution to this research domain consists of a set of tools that are based on dimensionality reduction methods, sparse representations and dictionary learning techniques. These tools are used to assist in art related matters such as restoration, conservation, art history, material and structure characterization, authentication, dating and even style analysis. Since paintings are complex structures the analysis of all pictorial layers and the support requires a multimodal set of high-resolution image acquisitions. The presented research can broadly be subdivided into three main fields. The first one is the digital enhancement of painting acquisitions in order to assist the art specialist in his professional assessment of the painting. The second main field of research is the automated detection of cracks within the Ghent Altarpiece, which is meant to help in the delicate matter of the conservation of this exceptional masterpiece but also as guidance during its current campaign of restoration. The last field consists of a set of methods that can be deployed in art forensics. These methods consist of the characterization of canvas, the analysis of multispectral imagery of a painting and even the objective quantification of the style of a particular artist.

Texture analysis for colorectal tumour biopsies using multispectral imagery.

Colorectal cancer is one of the most common cancers in the world. As part of its diagnosis, a histological analysis is often run on biopsy samples. Multispecral imagery taken from cancer tissues can be useful to capture more meaningful features. However, the resulting data is usually very large having a large number of varying feature types. This papers aims to investigate and compare the performances of multispectral imagery taken from colorectal biopsies using different techniques for texture feature extraction inclduing local binary patterns, Haraclick features and local intensity order patterns. Various classifiers such as Support Vector Machine and Random Forest are also investigated. The results show the superiority of multispectral imaging over the classical panchromatic approach. In the multispectral imagery's analysis, the local binary patterns combined with Support Vector Machine classifier gives very good results achieving an accuracy of 91.3%.

The impact of atmospheric conditions and instrument noise on atmospheric correction and spectral mixture analysis of multispectral imagery

The purpose of this study was to evaluate the effect of instrument noise, atmospheric conditions, and reflectance retrieval method on multispectral reflectance and fractional cover estimates derived from spectral mixture analysis. Top-of-atmosphere (TOA) radiance was simulated for pixels with various ground (fractional cover of green vegetation (GV), nonphotosynthetic vegetation (NPV), and soil) and atmospheric/geometric (solar zenith angle, visibility, and water vapor) conditions for four operational spaceborne multispectral images, Landsat 5 Thematic Mapper (TM), Landsat 7 Enhance Thematic Mapper Plus (ETM+), Landsat 8 Operational Land Imager (OLI), and the Moderate Resolution Imaging Spectroradiometer (MODIS). Instrument noise was added to the TOA radiance. Three reflectance retrieval methods were used to estimate surface reflectance, and fractional cover estimates of GV, NPV, and soil were made using spectral mixture analysis (SMA) and multiple endmember spectral mixture analysis (MESMA). Among atmospheric characteristics, we found that visibility and solar zenith angle made the greatest contributions to spectral and fractional cover error. In all cases, GV fraction was estimated with lower error than NPV or soil fraction. The reflectance retrieval method that provided the best reflectance estimates did not produce the fractional cover estimates with the lowest error due to variable bias across bands. Fractional cover estimates for all ground components were strongly impacted by instrument noise, but MESMA significantly improved fractional cover estimates for NPV and soil, regardless of noise level. This study suggests that there are practical constraints on the level of accuracy that can be attained in multispectral estimates of NPV and soil. A set of recommendations for the use of spectral unmixing of multispectral reflectance data is developed.

Wavelet packets for time-frequency analysis of multispectral imagery

Multispectral geospatial image sets retain the scene’s spatial and spectral information. To jointly use both of them for analysis purposes, we propose to extend the concept of wavelet packets, by introducing a new integrated multispectral entropy function. Each spectral band is individually decomposed by the wavelet packets transform, and then the entropy term is jointly guided by information from all bands, simultaneously. Finally, the wavelet packets coefficients undergo a dimension reduction process. We present examples of this theory applied to hyperspectral satellite imagery.

Digital image processing techniques demonstrating the anomalous nature of the radiocarbon dating sample area of the Shroud of Turin

This article reports on the use of digital image processing techniques to analyze an ultraviolet-fluorescence photograph of the area of the Shroud of Turin where the radiocarbon dating samples were taken. Results of this analysis demonstrate the anomalous nature of the radiocarbon data sample area. The techniques employed in this investigation are those used by the land remote sensing community for the analysis of multispectral imagery. The techniques included extraction of the RGB bands from a digital version of the ultraviolet-fluorescence photograph, use of principal components analysis for statistical compression of the RGB bands, calculation of z-score values using the first component of the principal components analysis, unsupervised classification of the RGB bands via K-MEANS clustering, and image segmentation. These techniques were also used to determine whether the area where the radiocarbon dating samples were taken exhibited any spectral anomalies. A one sample z-test demonstrated that there is a statistically significant difference between the mean z-scores for the four radiocarbon data samples and the mean z-score for a sample area of the Shroud with representative ultraviolet fluorescence. Results of the investigation suggest there is a new set of non-destructive techniques available to support further analysis of the Shroud. Recommendations are made regarding the need for high spatial resolution multispectral imagery and a Shroud coordinate system for mapping Shroud features. Key words: Brightness values, digital image processing, image segmentation, K-MEANS clustering, principal components analysis, radiocarbon dating sample area, Shroud of Turin, ultraviolet-fluorescence photograph.

La Carència (Valencia, España) y su territorio Resultados de la aplicación de metodologías digitales

&lt;p&gt;'La Carència. Chronological and urban change. Evaluation in its territorial context' is an archaeological project whose application of digital methodologies to the study of la Carència Ibero-Roman oppidum and its territory has been prominent during the last ten years. This application has been twofold: archaeological research has employed GIS analyses, photogrammetrical modelling of past landscapes and multispectral imagery analysis. Scientific dissemination has been enhanced by the use of aerial photogrammetry but 3D virtual modelling was also employed to develop a hypothetical reconstruction of the city walled area. In general the application of digital methodologies benefited archaeological analysis and, at the same time, helped developing the heritage value of both site and territory.&lt;/p&gt;

Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007

Abstract. Remote sensing is increasingly being used as a cost-effective and practical solution for the rapid evaluation of impacts from wildland fires. The present study investigates the use of the support vector machine (SVM) classification method with multispectral data from the Advanced Spectral Emission and Reflection Radiometer (ASTER) for obtaining a rapid and cost effective post-fire assessment in a Mediterranean setting. A further objective is to perform a detailed intercomparison of available burnt area datasets for one of the most catastrophic forest fire events that occurred near the Greek capital during the summer of 2007. For this purpose, two ASTER scenes were acquired, one before and one closely after the fire episode. Cartography of the burnt area was obtained by classifying each multi-band ASTER image into a number of discrete classes using the SVM classifier supported by land use/cover information from the CORINE 2000 land nomenclature. Overall verification of the derived thematic maps based on the classification statistics yielded results with a mean overall accuracy of 94.6% and a mean Kappa coefficient of 0.93. In addition, the burnt area estimate derived from the post-fire ASTER image was found to have an average difference of 9.63% from those reported by other operationally-offered burnt area datasets available for the test region.

Using Multi-Spectral Imagery To Evaluate Corn Grown Under Nitrogen and Drought Stressed Conditions

The in-season estimation of crop stresses which have the potential of adversely affecting crop yield and/or quality could allow producers to make in-season management decisions to correct for the particular stress. A field study was conducted to evaluate the use of multi-spectral imagery for estimating corn (Zea mays L.) grain yield, in-season biomass and nitrogen (N) concentration under varying N and drought stresses. The experiment was a split-plot design with three replications using a factorial arrangement of treatments. Three irrigation (whole-plot) treatments included dry land, irrigation based on 0.5, and full evapotranspiration (ET). Sub-plot treatments included five N rates (0, 45, 90, 134, 269 kg N ha−1). Multi-spectral imagery consisted of four wavebands; blue (485 nm ± 35 nm), green (550 nm ± 35 nm), red (660 nm ± 30 nm), and near-infrared (NIR) (830 nm ± 70 nm). Imagery was collected on various dates throughout the growing season; biomass sampling was performed within two days of image collection. Grain yield, in-season biomass, and N concentration increased with increasing N rate regardless of sampling date or year. Yield was only affected by irrigation during 1997 due to a significant difference in rainfall between 1997 and 1998, 247 vs. 457 mm, respectively. Regression correlation coefficients for the 1998 values were generally higher compared to 1997 values across years for imagery collected at similar growth stages, possibly due to differences in sensor sensitivity or the increased plant response to applied N. Regression correlation coefficients increased as the growing season progressed. The green waveband and normalized difference greenness vegetation index (GNDVI) had the greatest ability to estimate grain yield in the presence of varying N and/or drought stresses. This study demonstrates the ability of multi-spectral imagery analysis to estimate grain production in the presence of N and/or drought stresses.

Combined high-density lidar and multispectral imagery for individual tree crown analysis

Lidar technology has reached a point where ground and forest canopy elevation models can be produced at high spatial resolution. Individual tree crown isolation and classification methods are developing rapidly for multispectral imagery. Analysis of multispectral imagery, however, does not readily provide tree height information and lidar data alone cannot provide species and health attributes. The combination of lidar and multispectral data at the individual tree level may provide a very useful forest inventory tool. A valley following approach to individual tree isolation was applied to both high resolution digital frame camera imagery and a canopy height model (CHM) created from high-density lidar data over a test site of even aged (55 years old) Douglas-fir plots of varying densities (300, 500, and 725 stems/ha) on the west coast of Canada. Tree height was determined from the laser data within the automated crown delineations. Automated tree isolations of the multispectral imagery achieved 80%‐90% good correspondence with the ground reference tree delineations based on ground data. However, for the more open plot there were serious commission errors (false trees isolated) mostly related to sunlit ground vegetation. These were successfully reduced by applying a height filter to the isolations based on the lidar data. Isolations from the lidar data produced good isolations with few commission errors but poorer crown outline delineations especially for the densest plot. There is a complimentarity in the two data sources that will help in tree isolation. Heights of the automated isolations were consistently underestimated versus ground reference trees with an average error of 1.3 m. Further work is needed to test and develop tools and capabilities, but there is an effective synergy of the two high resolution data sources for providing needed forest inventory information.

Early Detection of Douglas-Fir Beetle Infestation with Subcanopy Resolution Hyperspectral Imagery

Abstract Early detection of insect or pathogen infestations in forests would be useful to forest managers who want to make decisions that minimize timber losses. Typical methods of forest reconnaissance to detect infestations have included analysis of multispectral imagery. Multispectral imagery, however, often lacks the sensitivity to detect subtle changes in tree canopy reflectance because of physiologic stress from insects or pathogens. Most hyperspectral imaging has the sensitivity to detect subtle changes in canopy reflectance but lacks high spatial resolution to identify affected trees. Our study examined the use of subcanopy spatial resolution hyperspectral imagery for differentiating Douglas-fir trees attacked by the Douglas-fir beetle. Comparison of the accuracies of step-wise discriminant analysis and classification and regression tree analysis (CART) revealed that CART provided the best separability among tree health classes (93% overall) because of CART's ability to use different band combinations for each class. Predictive accuracy of the CART method was estimated through cross-validation of the dataset using a jackknife resampling technique. Overall classification accuracy was promising (69%), as was classification among healthy and attacked, but still living, trees (50–70%). The results of our study provide support that hyperspectral imagery might be used for detecting and mapping tree stress in Douglas-fir stands. Although the rapid progress of beetle infestation somewhat limited the ability to differentiate among tree stress classes, which might limit the utility of this approach for fast moving infestations, the results were well beyond what might be expected from alternative detection methods. Slower moving infestations would benefit from the use of hyperspectral imagery because a lower percentage of infested trees would be asymtomatic. West. J. Appl. For. 18(3):202–206.

Concepts in imaging and microscopy: color image processing for microscopy.

Digital image analysis has long been applied to monochrome images from the light microscope. Using these techniques one can locate, measure, identify, and count the objects of interest in a microscope field of view. Since microscope images often contain color information of interest, it is now becoming more common to analyze the spectral content of images as well. Although most of the digital imaging techniques developed for monochrome microscopy work well with color images, there are a few considerations specific to the analysis of multispectral imagery. These include obtaining a properly balanced multicolor digital image, specifying the color components of the image, and compensating for imperfect separation among the color channels.