Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification

This study evaluated the synergistic use of high spatial resolution multispectral imagery (i.e., QuickBird, 2.4 m) and low-posting-density LIDAR data (3 m) for forest species classification using an object-based approach. The integration of QuickBird multispectral imagery and LIDAR data was considered during image segmentation and the subsequent object-based classification. Three segmentation schemes were examined: (1) segmentation based solely on the spectral image layers; (2) segmentation based solely on LIDAR-derived layers; and (3) segmentation based on both the spectral and LIDAR-derived layers. For each segmentation scheme, objects were generated at twelve different scales in order to determine optimal scale parameters. Six categories of classification metrics were generated for each object based on spectral data alone, LIDAR data alone and the combination of both data sources. Machine learning decision trees were used to build classification rule sets. Quantitative segmentation quality assessment and classification accuracy results showed the integration of spectral and LIDAR data, in both image segmentation and object-based classification, improved the forest classification compared to using either data source independently. Better segmentation quality led to higher classification accuracy. The highest classification accuracy (Kappa = 91.6%) was acquired when using both spectral- and LIDAR-derived metrics based on objects segmented from both spectral and LIDAR layers at scale parameter 250, where best segmentation quality was achieved. Optimal scales were analyzed for each segmentation-classification scheme. Statistical analysis of classification accuracies at different scales revealed that there was a range of optimal scales that provided statistically similar accuracy.     

Integrating airborne multispectral imagery and airborne LiDAR data for enhanced lithological mapping in vegetated terrain

Practical and financial constraints associated with traditional field-based lithological mapping are often responsible for the generation of maps with insufficient detail and inaccurately located contacts. In arid areas with well exposed rocks and soils, high-resolution multi- and hyperspectral imagery is a valuable mapping aid as lithological units can be readily discriminated and mapped by automatically matching image pixel spectra to a set of reference spectra. However, the use of spectral imagery in all but the most barren terrain is problematic because just small amounts of vegetation cover can obscure or mask the spectra of underlying geological substrates. The use of ancillary information may help to improve lithological discrimination, especially where geobotanical relationships are absent or where distinct lithologies exhibit inherent spectral similarity. This study assesses the efficacy of airborne multispectral imagery for detailed lithological mapping in a vegetated section of the Troodos ophiolite (Cyprus), and investigates whether the mapping performance can be enhanced through the integration of LiDAR-derived topographic data. In each case, a number of algorithms involving different combinations of input variables and classification routine were employed to maximise the mapping performance. Despite the potential problems posed by vegetation cover, geobotanical associations aided the generation of a lithological map - with a satisfactory overall accuracy of 65.5% and Kappa of 0.54 - using only spectral information. Moreover, owing to the correlation between topography and lithology in the study area, the integration of LiDAR-derived topographic variables led to significant improvements of up to 22.5% in the overall mapping accuracy compared to spectral-only approaches. The improvements were found to be considerably greater for algorithms involving classification with an artificial neural network (the Kohonen Self-Organizing Map) than the parametric Maximum Likelihood Classifier. The results of this study demonstrate the enhanced capability of data integration for detailed lithological mapping in areas where spectral discrimination is complicated by the presence of vegetation or inherent spectral similarities.     

Combining satellite multispectral image data and a digital elevation model for mapping debris-covered glaciers

Automated glacier mapping from satellite multispectral image data is hampered by debris cover on glacier surfaces. Supraglacial debris exhibits the same spectral properties as lateral and terminal moraines, fluvioglacial deposits, and bedrock outside the glacier margin, and is thus not detectable by means of multispectral classification alone. Based on the observation of low slope angles for debris-covered glacier tongues, we developed a multisource method for mapping supraglacial debris. The method combines the advantages of automated multispectral classification for clean glacier ice and vegetation with slope information derived from a digital elevation model (DEM). Neighbourhood analysis and change detection is applied for further improvement of the resulting glacier/debris map. A significant percentage of the processing can be done automatically. In order to test the sensitivity of our method against different DEM qualities, it was also applied to a DEM obtained from ASTER stereo data. Additionally, we compared our multisource approach to an artificial neural network (ANN) classification of debris, using only multispectral data. While the combination with an ASTER-derived DEM revealed promising results, the ANN classification without DEM data does not.     

Contextual classification of multispectral image data

Compound decision theory is invoked to develop a method for classifying image data using spatial context. Methods for characterizing contextual information in an image are proposed and tested. Experimental results based on both simulated and real multispectral remote sensing data demonstrate the effectiveness of the contextual classifier. A number of practical problems associated with this approach are discussed and possible solutions are explored.     

Complete classification of raw LIDAR data and 3D reconstruction of buildings

LIDAR (LIght Detection And Ranging) data are a primary data source for digital terrain model (DTM) generation and 3D city models. This paper presents a three-stage framework for a robust automatic classification of raw LIDAR data as buildings, ground and vegetation, followed by a reconstruction of 3D models of the buildings. In the first stage the raw data are filtered and interpolated over a grid. In the second stage, first a double raw data segmentation is performed and then geometric and topological relationships among regions resulting from segmentation are computed and stored in a knowledge base. In the third stage, a rule-based scheme is applied for the classification of the regions. Finally, polyhedral building models are reconstructed by analysing the topology of building outlines, building roof slopes and eaves lines. Results obtained on data sets with different ground point density, gathered over the town of Pavia (Italy) with Toposys and Optech airborne laser scanning systems, are shown to illustrate the effectiveness of the proposed approach.     

A feature reduction and unsupervised classification algorithm for multispectral data

A new scheme, incorporating dimensionality reduction and clustering, suitable for classification of a large volume of remotely sensed data using a small amount of memory is proposed. The scheme involves transforming the data from multidimensional n-space to a 3-dimensional primary color space of blue, green and red coordinates. The dimensionality reduction is followed by data reduction, which involves assigning 3-dimensional samples to a 2-dimensional array. Finally, a multi-stage ISODATA technique incorporating a novel seedpoint picking method is used to obtain the desired number of clusters.

The storage requirements are reduced to a low value by making five passes through the data and storing necessary information during each pass. The first three passes are used to find the minimum and maximum values of some of the variables. The data reduction is done and a classification table is formed during the fourth pass. The classification map is obtained during the fifth pass. The computer memory required is about 2K machine words.

The efficacy of the algorithm is justified by simulation studies using multispectral LANDSAT data.     

Mapping vegetation in a heterogeneous mountain rangeland using landsat data: an alternative method to define and classify land-cover units

Three major problems are faced when mapping natural vegetation with mid-resolution satellite images using conventional supervised classification techniques: defining the adequate hierarchical level for mapping; defining discrete land cover units discernible by the satellite; and selecting representative training sites. In order to solve these problems, we developed an approach based on the: (1) definition of ecologically meaningful units as mosaics or repetitive combinations of structural types, (2) utilization of spectral information (indirectly) to define the units, (3) exploration of two alternative methods to classify the units once they are defined: the traditional, Maximum Likelihood method, which was enhanced by analyzing objective ways of selecting the best training sites, and an alternative method using Discriminant Functions directly obtained from the statistical analysis of signatures. The study was carried out in a heterogeneous mountain rangeland in central Argentina using Landsat data and 251 field sampling sites. On the basis of our analysis combining terrain information (a matrix of 251 stands×14 land cover attributes) and satellite data (a matrix of 251 stands×8 bands), we defined 8 land cover units (mosaics of structural types) for mapping, emphasizing the structural types which had stronger effects on reflectance. The comparison through field validation of both methods for mapping units showed that classification based on Discriminant Functions produced better results than the traditional Maximum Likelihood method (accuracy of 86% vs. 78%).     

PoNet: A universal physical optimization-based spectral super-resolution network for arbitrary multispectral images

Spectral super-resolution is a very important technique to obtain hyperspectral images from only multispectral images, which can effectively solve the high acquisition cost and low spatial resolution of hyperspectral images. However, in practice, multispectral channels or images captured by the same sensor are often with different spatial resolutions, which brings a severe challenge to spectral super-resolution. This paper proposed a universal spectral super-resolution network based on physical optimization unfolding for arbitrary multispectral images, including single-resolution and cross-scale multispectral images. Furthermore, two new strategies are proposed to make full use of the spectral information, namely, cross-dimensional channel attention and cross-depth feature fusion. Experimental results on five data sets show superiority and stability of PoNet addressing any spectral super-resolution situations.     

A supervoxel-based vegetation classification via decomposition and modelling of full-waveform airborne laser scanning data

Vegetation classification is a fundamental task in several applications such as forest management, remote sensing-based crop monitoring, and mitigation of plant diseases, digital prototyping of plants, and plant phenotyping, among others. We propose a novel supervoxel-based methodology to accurately detect vegetation from small-footprint full-waveform airborne laser scanning data in urban and mountainous scenes. Mathematically, the full-waveform decomposition and fitting model based on multiple kernels is presented to generate high-density 3D point clouds and their relevant attributes. The homogeneous supervoxels are then generated by using an enhanced probability density clustering (PDC) algorithm. For each supervoxel, we employ latent Dirichlet allocation to obtain supervoxels features through generalisation of geometric and full-waveform features of point clouds. The Support Vector Machine (SVM) and ensemble classifier random forest (RF) are used to classify these supervoxels into vegetation and non-vegetation. Our experiments on urban and mountainous scenes demonstrate that our approach achieves an overall accuracy of 98.27% and 96.47% respectively by RF classifier and achieves an overall accuracy of 98.16% and 97.67% on the same data sets by SVM classifier. By integrating full-waveform information and more meaningful generalised features, our method outperforms state-of-the-art methods at preserving a trade-off between missing alarm rate and false alarm rate.     

Integrating visible, near-infrared and short-wave infrared hyperspectral and multispectral thermal imagery for geological mapping at Cuprite, Nevada

This study investigated the potential value of integrating hyperspectral visible, near-infrared, and short-wave infrared imagery with multispectral thermal data for geological mapping. Two coregistered aerial data sets of Cuprite, Nevada were used: Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral data, and MODIS/ASTER Airborne Simulator (MASTER) multispectral thermal data. Four classification methods were each applied to AVIRIS, MASTER, and a combined set. Confusion matrices were used to assess the classification accuracy. The assessment showed, in terms of kappa coefficient, that most classification methods applied to the combined data achieved a marked improvement compared to the results using either AVIRIS or MASTER thermal infrared (TIR) data alone. Spectral angle mapper (SAM) showed the best overall classification performance. Minimum distance classification had the second best accuracy, followed by spectral feature fitting (SFF) and maximum likelihood classification. The results of the study showed that SFF applied to the combination of AVIRIS with MASTER TIR data are especially valuable for identification of silicified alteration and quartzite, both of which exhibit distinctive features in the TIR region. SAM showed some advantages over SFF in dealing with multispectral TIR data, obtaining higher accuracy in discriminating low albedo volcanic rocks and limestone which do not have unique, distinguishing features in the TIR region.     

Combining vegetation indices, constrained ordination and fuzzy classification for mapping semi-natural vegetation units from hyperspectral imagery

Vegetation mapping of plant communities at fine spatial scales is increasingly supported by remote sensing technology. However, combining ecological ground truth information and remote sensing datasets for mapping approaches is complicated by the complexity of ecological datasets. In this study, we present a new approach that uses high spatial resolution hyperspectral datasets to map vegetation units of a semiarid rangeland in Central Namibia. Field vegetation surveys provide the input to the workflow presented in this study. The collected data were classified by hierarchical cluster analysis into seven vegetation units that reflect different ecological states occurring in the study area. Spectral indices covering vegetation and soil characteristics were calculated from hyperspectral remote sensing imagery and used as environmental variables in a constrained ordination by applying redundancy analysis (RDA). The resulting statistical relationships between vegetation data and spectral indices were transferred into images of ordination axes, which were subsequently used in a supervised fuzzy c-means classification approach relying on a k-NN distance metric. Membership images for each vegetation unit as well as a confusion image of the classification result allowed a sound ecological interpretation of the resulting hard classification map. Classification results were validated with two independent reference datasets. For an internal and external validation dataset, overall accuracy reached 98% and 64% with kappa values of 0.98 and 0.53, respectively. Critical steps during the mapping workflow were highlighted and compared with similar mapping approaches.     

Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications

Urban vegetation cover is a critical component in urban systems modeling and recent advances in remote sensing technologies can provide detailed estimates of vegetation characteristics. In the present study we classify urban vegetation characteristics, including species and condition, using an approach based on spectral unmixing and statistically developed decision trees. This technique involves modeling the location and separability of vegetation characteristics within the spectral mixing space derived from high spatial resolution Quickbird imagery for the City of Vancouver, Canada. Abundance images, field based land cover observations and shadow estimates derived from a LiDAR (Light Detection and Ranging) surface model are applied to develop decision tree classifications to extract several urban vegetation characteristics. Our results indicate that along the vegetation-dark mixing line, tree and vegetated ground cover classes can be accurately separated (80% and 94% of variance explained respectively) and more detailed vegetation characteristics including manicured and mixed grasses and deciduous and evergreen trees can be extracted as second order hierarchical categories with variance explained ranging between 67% and 100%. Our results also suggest that the leaf-off condition of deciduous trees produce pixels with higher dark fractions resulting from branches and soils dominating the reflectance values. This research has important implications for understanding fine scale biophysical and social processes within urban environments.     

Integrating profiling LIDAR with Landsat data for regional boreal forest canopy attribute estimation and change characterization

Forest dynamics are characterized by both continuous (i.e., growth) and discontinuous (i.e., disturbance) changes. Change detection techniques that use optical remotely sensed data to capture disturbance related changes are established and commonly applied; however, approaches for the capture of continuous forest changes are less mature. Optical remotely sensed imagery is well suited for capturing horizontally distributed conditions, structures, and changes, while Light Detection And Ranging (LIDAR) data are more appropriate for capturing vertically distributed elements of forest structure and change. The integration of optical remotely sensed imagery and LIDAR data provides improved opportunities to fully characterize forest canopy attributes and dynamics.The study described in this paper captures forest conditions along a corridor approximately 600 km long through the boreal forest of Canada. Two coincident LIDAR transects, representing 1997 and 2002 forest conditions respectively, are compared using image segments generated from Landsat ETM+ imagery. The image segments are used to provide a spatial framework within which the attributes and temporal dynamics of the forest canopy are estimated and compared. Segmented and classified Landsat imagery provides a context for the comparison of sufficiently spatially related LIDAR profiles and for the provision of categories to aid in the application of empirical models requiring knowledge of land cover.Global and local approaches were employed for characterizing changes in forest attributes over time. The global approach, emphasized the overall trend in forest change along the length of the entire transect, and indicated that key canopy attributes were stable, and transect characteristics, including forest canopy height, did not change significantly over the five-year period of this study (two sample t-test, p = 0.08). The local approach analyzed segment-based changes in canopy attributes, providing spatially explicit indications of forest growth and depletion. The local approach identified that 84% of the Landsat segments intercepted by both LIDAR transects either have no change, or have a small average increase in canopy height (0.7 m), while the other 16% of segments have an average decrease in canopy height of 1.6 m. As expected, the difference in the magnitude of the changes was markedly greater for depletions than it was for growth, but was less spatially extensive. Growth tends to occur incrementally over broad areas; whereas, depletions are dramatic and spatially constrained. The approach presented holds potential for investigating the impacts of climate change across a latitudinal gradient of boreal forest.     

Integration of 3D and multispectral data for cultural heritage applications: Survey and perspectives

Cultural heritage is increasingly put through imaging systems such as multispectral cameras and 3D scanners. Though these acquisition systems are often used independently, they collect complementary information (spectral vs. spatial) used for the study, archiving and visualization of cultural heritage. Recording 3D and multispectral data in a single coordinate system enhances the potential insights in data analysis.     

Object-based image classification for burned area mapping of Creus Cape, Spain, using NOAA-AVHRR imagery

Due to the ability of the NOAA-AVHRR sensor to cover a wide area and its high temporal frequency, it is possible to quickly obtain a general overview of the prevailing situation over a large area of terrain and, more specifically, quickly assess the damage caused by a recent large forest fire by mapping the extent of the burned area. The aim of this work was to map a large forest fire that recently took place on the Spanish Mediterranean coast using innovative image classification techniques and low spatial resolution imagery. The methodology involved developing an object-based classification model using spectral as well as contextual object information. The burned area map resulting from the image classification was compared with the fire perimeter provided by the Catalan Environmental Department in terms of spatial overlap and size in order to determine to what extent they were compatible. Results of the comparison indicated a high degree (≈90%) of spatial agreement. The total burned area of the classified image was found to be 6900 ha, compared to a fire perimeter of 6000 ha produced by the Catalan Environmental Department. It was concluded that, although the object-oriented classification approach was capable of affording very promising results when mapping a recent burn on the Spanish Mediterranean coast, the method in question required further assessment to ascertain its ability to map other burned areas in the Mediterranean.     

Integrating ontological modelling and Bayesian inference for pattern classification in topographic vector data

This paper presents an ontology-driven approach for spatial database enrichment in support of map generalisation. Ontology-driven spatial database enrichment is a promising means to provide better transparency, flexibility and reusability in comparison to purely algorithmic approaches. Geographic concepts manifested in spatial patterns are formalised by means of ontologies that are used to trigger appropriate low level pattern recognition techniques. The paper focuses on inference in the presence of vagueness, which is common in definitions of spatial phenomena, and on the influence of the complexity of spatial measures on classification accuracy. The concept of the English terraced house serves as an example to demonstrate how geographic concepts can be modelled in an ontology for spatial database enrichment. Owing to their good integration into ontologies, and their ability to deal with vague definitions, supervised Bayesian inference is used for inferring complex concepts. The approach is validated in experiments using large vector datasets representing buildings of four different cities. We compare classification results obtained with the proposed approach to results produced by a more traditional ontology approach. The proposed approach performed considerably better in comparison to the traditional ontology approach. Besides clarifying the benefits of using ontologies in spatial database enrichment, our research demonstrates that Bayesian networks are a suitable method to integrate vague knowledge about conceptualisations in cartography and GIScience.     

Land-cover classification of China: Integrated analysis of AVHRR imagery and geophysical data

Over last two decades, numerous studies have used remotely sensed data from the Advanced Very High Resolution Radiometer (AVHRR) sensors to map land use and land cover at large spatial scales, but achieved only limited success. In this paper, we employed an approach that combines both AVHRR images and geophysical datasets (e.g. climate, elevation). Three geophysical datasets are used in this study: annual mean temperature, annual precipitation, and elevation. We first divide China into nine bio-climatic regions, using the long-term mean climate data. For each of nine regions, the three geophysical data layers are stacked together with AVHRR data and AVHRR-derived vegetation index (Normalized Difference Vegetation Index) data, and the resultant multi-source datasets were then analysed to generate land-cover maps for individual regions, using supervised classification algorithms. The nine land-cover maps for individual regions were assembled together for China. The existing land-cover dataset derived from Landsat Thematic Mapper (TM) images was used to assess the accuracy of the classification that is based on AVHRR and geophysical data. Accuracy of individual regions varies from 73% to 89%, with an overall accuracy of 81% for China. The results showed that the methodology used in this study is, in general, feasible for large-scale land-cover mapping in China.     

Fusion of airborne LiDAR and satellite multispectral data for the estimation of timber volume in the Southern Alps

Remote sensing can be considered a key instrument for studies related to forests and their dynamics. At present, the increasing availability of multisensor acquisitions over the same areas, offers the possibility to combine data from different sensors (e.g., optical, RADAR, LiDAR). This paper presents an analysis on the fusion of airborne LiDAR and satellite multispectral data (IRS 1C LISS III), for the prediction of forest stem volume at plot level in a complex mountain area (Province of Trento, Southern Italian Alps), characterized by different tree species, complex morphology (i.e. altitude ranges from 65 m to 3700 m above sea level), and a range of different climates (from the sub-Mediterranean to Alpine type). 799 sample plots were randomly distributed over the 3000 km² of the forested areas of the Trento Province. From each plot, a set of variables were extracted from both LiDAR and multispectral data. A regression analysis was carried out considering two data sources (LiDAR and multispectral) and their combination, and dividing the plot areas into groups according to their species composition, altitude and slope. Experimental results show that the combination of LiDAR and IRS 1C LISS III data, for the estimation of stem volume, is effective in all the experiments considered. The best developed models comprise variables extracted from both of these data sources. The RMSE% on an independent validation set for the stem volume estimation models ranges between 17.2% and 26.5%, considering macro sets of tree species (deciduous, evergreen and mixed), between 17.5% and 29.0%, considering dominant species plots, and between 15.5% and 21.3% considering altitude and slope sets.     

Analysis of time-series MODIS 250 m vegetation index data for crop classification in the U.S. Central Great Plains

The global environmental change research community requires improved and up-to-date land use/land cover (LULC) datasets at regional to global scales to support a variety of science and policy applications. Considerable strides have been made to improve large-area LULC datasets, but little emphasis has been placed on thematically detailed crop mapping, despite the considerable influence of management activities in the cropland sector on various environmental processes and the economy. Time-series MODIS 250 m Vegetation Index (VI) datasets hold considerable promise for large-area crop mapping in an agriculturally intensive region such as the U.S. Central Great Plains, given their global coverage, intermediate spatial resolution, high temporal resolution (16-day composite period), and cost-free status. However, the specific spectral-temporal information contained in these data has yet to be thoroughly explored and their applicability for large-area crop-related LULC classification is relatively unknown. The objective of this research was to investigate the general applicability of the time-series MODIS 250 m Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) datasets for crop-related LULC classification in this region. A combination of graphical and statistical analyses were performed on a 12-month time-series of MODIS EVI and NDVI data from more than 2000 cropped field sites across the U.S. state of Kansas. Both MODIS VI datasets were found to have sufficient spatial, spectral, and temporal resolutions to detect unique multi-temporal signatures for each of the region's major crop types (alfalfa, corn, sorghum, soybeans, and winter wheat) and management practices (double crop, fallow, and irrigation). Each crop's multi-temporal VI signature was consistent with its general phenological characteristics and most crop classes were spectrally separable at some point during the growing season. Regional intra-class VI signature variations were found for some crops across Kansas that reflected the state's climate and planting time differences. The multi-temporal EVI and NDVI data tracked similar seasonal responses for all crops and were highly correlated across the growing season. However, differences between EVI and NDVI responses were most pronounced during the senescence phase of the growing season.