Luis A. Ruiz

Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification

In this paper, a comprehensive set of texture features extracted from the experimental semivariogram of specific image objects is proposed and described, and their usefulness for land use classification of high resolution images is evaluated. Fourteen features are defined and categorized into three different groups, according to the location of their respective parameters in the semivariogram curve: (i) features that use parameters close to the origin of the semivariogram, (ii) the parameters employed extend to the first maximum, and (iii) the parameters employed are extracted from the first to the second maximum. A selection of the most relevant features has been performed, combining the analysis and interpretation of redundancies, and using statistical discriminant analysis methods. The suitability of the proposed features for object-based image classification has been evaluated using digital aerial images from an agricultural area on the Mediterranean coast of Spain. The performance of the selected semivariogram features has been compared with two different sets of texture features: those derived from the grey level co-occurrence matrix, and the values of raw semivariance directly extracted from the semivariogram at different positions. As a result of the tests, the classification accuracies obtained using the proposed semivariogram features are, in general, higher and more balanced than those obtained using the other two sets of standard texture features.

Evaluation of Automatic Building Detection Approaches Combining High Resolution Images and LiDAR Data

In this paper, two main approaches for automatic building detection and localization using high spatial resolution imagery and LiDAR data are compared and evaluated: thresholding-based and object-based classification. The thresholding-based approach is founded on the establishment of two threshold values: one refers to the minimum height to be considered as building, defined using the LiDAR data, and the other refers to the presence of vegetation, which is defined according to the spectral response. The other approach follows the standard scheme of object-based image classification: segmentation, feature extraction and selection, and classification, here performed using decision trees. In addition, the effect of the inclusion in the building detection process of contextual relations with the shadows is evaluated. Quality assessment is performed at two different levels: area and object. Area-level evaluates the building delineation performance, whereas object-level assesses the accuracy in the spatial location of individual buildings. The results obtained show a high efficiency of the evaluated methods for building detection techniques, in particular the thresholding-based approach, when the parameters are properly adjusted and adapted to the type of urban landscape considered.

Non-linear fourth-order image interpolation for subpixel edge detection and localization

A fourth-order non-linear interpolation procedure based on the ENO (Essentially Non-Oscillatory) methodology is presented and evaluated, with the purpose of increasing the geometric accuracy of edge detection in digital images. Two possible cases are considered one that considers that each pixel of the image represents a point value, the other that the pixel is an average value of a function. After image interpolation to obtain a finer grid of pixels, the Canny edge detection algorithm is applied, with the objective of improving the localization and geometry of the edges at a subpixel level. The results are compared with other schemes based on fourth order two-dimensional interpolation methods, such as a centered scheme based on a cubic convolution, a fourth order non-centered lineal scheme and a centered cubic convolution based on local gradient features. The evaluation is performed using visual and analytical techniques applied over aerial and satellite images, analyzing the positional errors of the detected edges, as well as the errors due to changes in scale and orientation. In addition to the subpixel edge detection, the quality of the interpolated images is tested. We conclude that the proposed methodology based on ENO interpolation improves the detection of edges in images as compared to other fourth-order methods.

Analysis of the factors affecting LiDAR DTM accuracy in a steep shrub area

The creation of a quality Digital Terrain Model (DTM) is essential for representing and analyzing the Earth in a digital form. The continuous improvements in the acquisition and the potential of airborne Light Detection and Ranging (LiDAR) data are increasing the range of applications of this technique to the study of the Earth surface. The aim of this study was to determine the optimal parameters for calculating a DTM by using an iterative algorithm to select minimum elevations from LiDAR data in a steep mountain area with shrub vegetation. The parameters were: input data type, analysis window size, and height thresholds. The effects of slope, point density, and vegetation on DTM accuracy were also analyzed. The results showed that the lowest root mean square error (RMSE) was obtained with an analysis window size of 10 m, 5 m, and 2.5 m, rasterized data as input data, and height thresholds equal to or greater than 1.5 m. These parameters showed a RMSE of 0.19 m. When terrain slope varied from 0–10% to 50–60%, the RMSE increased by 0.11 m. The RMSE decreased by 0.06 m when point density was increased from 4 to 8 points/m2, and increased by 0.05 m in dense vegetation areas.

Estimation of forest structure and canopy fuel parameters from small-footprint full-waveform LiDAR data

Precise knowledge of fuel conditions is important for predicting fire hazards and simulating fire growth and intensity across the landscape. We present a methodology to retrieve and map forest canopy fuel and other forest structural parameters using small-footprint full-waveform airborne light detection and ranging (LiDAR) data. Full-waveform LiDAR sensors register the complete returned backscattered signal through time and can describe physical properties of the intercepted objects. This study was undertaken in a mixed forest dominated by Douglas-fir, occasionally mixed with other conifers, in north-west Oregon (United States). We extracted two sets of LiDAR metrics using pulse detection and waveform modelling and then constructed several predictive models using forward stepwise multiple linear regression. The resulting models explained ~80% of the variability for many of the canopy fuel and forest structure parameters: aboveground biomass (R2=0.84), quadratic mean diameter (R2=0.82), canopy height (R2=0.79), canopy base height (R2=0.78) and canopy fuel load (R2=0.79). The lowest performing models included basal area (R2=0.76), stand volume (R2=0.73), canopy bulk density (R2=0.67) and stand density index (R2=0.66). Our results indicate that full-waveform LiDAR systems show promise in systematically characterising the structure and canopy fuel loads of forests, which may enable accurate fire behaviour forecasting that in turn supports the development of prevention and planning policies.

Using semivariogram indices to analyse heterogeneity in spatial patterns in remotely sensed images

The benchmark problem proposed in this paper is to identify regions in aerial or satellite images with geometric patterns and describe the geometric properties of the constituent elements of the pattern and their spatial distribution. This is a relevant topic in image analysis processes where spatial regular patterns are studied. This paper first presents two approaches based on multi-directional semivariograms for reducing the processing time required to compute omnidirectional semivariograms. A set of parameters for describing the structure of a semivariogram, introduced by Balaguer et al. (2010), is extracted from an experimental semivariogram and analysed to quantify the heterogeneity of the distribution of elements (trees) with periodic patterns in images of orchards. An assessment is made using four image datasets. The first dataset is composed of synthetic images that simulate regularly spaced tree crops and real images, and is used to evaluate the influence that the orientation of elements (regularly spaced trees) in the objects (crop plots) has in the descriptive parameter values. This dataset is also used to compare different semivariogram computational approaches. The other three are also composed of synthetic images and are used to evaluate the semivariogram parameters under different spatial heterogeneity conditions, and are generated by varying patterns and tree characteristics, i.e., existence or absence of faults, regular/irregular distributions, and size of the elements. Finally, the proposed methodology is applied to real aerial orthoimages of orchard plots.

Deriving pseudo-vertical waveforms from small-footprint full-waveform LiDAR data

When processing scanning LiDAR data, it is commonly assumed that the extracted full-waveform LiDAR pulse registers truly vertical information of forest canopies. This assumption may lead to uncertain results for the spatiotemporal analysis of the waveforms due to off-nadir scanning angles and varying trajectories travelled by the pulses in overlapping strips. In this letter, we investigate these assumptions and undertake some preliminary analysis to overcome their impacts on forest-based LiDAR analyses. Our results demonstrate that for a standard LiDAR forest acquisition programme in Oregon, USA, most of the hits (83%) are acquired off-nadir, which leads to positional displacements on the ground of the full-waveforms of about 0.20 m for each 1-m height increment. We propose an approach to synthetize multiple waveform data into composite waveforms containing the vertical profile of vegetation for a given location. This approach is based on partitioning the aboveground vertical space into voxels and using the maximum full-waveform intensity value to construct new full-waveforms comprising the vertical information of the various waveforms crossing over a location. Our initial results indicate that deriving spatiotemporal metrics from the composite pseudo-vertical full-waveforms produces a more consistent response across adjacent height levels, which in turn enables a more complete characterization and more vegetation structure to be retrieved. We conclude that this type of pseudo-vertical full-waveform analysis is necessary to more fully understand the impact of the return signals from tree crowns.

Using street based metrics to characterize urban typologies

Abstract Urban spatial structures reflect local particularities produced during the development of a city. High spatial resolution imagery and LiDAR data are currently used to derive numerical attributes to describe in detail intra-urban structures and morphologies. Urban block boundaries have been frequently used to define the units for extracting metrics from remotely sensed data. In this paper, we propose to complement these metrics with a set of novel descriptors of the streets surrounding the urban blocks under consideration. These metrics numerically describe geometrical properties in addition to other distinctive aspects, such as presence and properties of vegetation and the relationship between the streets and buildings. For this purpose, we also introduce a methodology for partitioning the street area related to an urban block into polygons from which the street urban metrics are derived. We achieve the assessment of these metrics through application of a one-way ANOVA procedure, the winnowing technique, and a decision tree classifier. Our results suggest that street metrics, and particularly those describing the street geometry, are suitable for enhancing the discrimination of complex urban typologies and help to reduce the confusion between certain typologies. The overall classification accuracy increased from 72.7% to 81.1% after the addition street of descriptors. The results of this study demonstrate the usefulness of these metrics for describing street properties and complementing information derived from urban blocks to improve the description of urban areas. Street metrics are of particular use for the characterization of urban typologies and to study the dynamics of cities.

Assessment of factors affecting shrub volume estimations using airborne discrete-return LiDAR data in Mediterranean areas

Shrub vegetation is a key element of Mediterranean forest areas and it is necessary to develop tools that allow a precise knowledge of this vegetation. This study aims to predict shrub volume and analyze the factors affecting the accuracy of these estimations in small stands using airborne discrete-return LiDAR data. The study was performed over 83 circular stands with 0.5 m radius located in Chiva (Spain) mainly occupied by Quercus coccifera. The vegetation inside each area was clear cut, and the height and the diameter of each plant was measured to compute the volume of shrub vegetation per stand. Volume values were related with maximum height values derived from LiDAR data reaching a coefficient of determination value R 2 = 0.26 . Afterwards, factors affecting the quality of volume estimations were analyzed, i.e., vegetation type, LiDAR density, and accuracy of the digital terrain model (DTM). Significant accuracy improvements ( R 2 = 0.71 ) were detected for stands with 0.5 m, LiDAR data density greater than 8     points / m 2 , vegetation Q. coccifera, and error associated to the DTM less than 0.20 m. These results show the feasibility of using LiDAR data to predict shrub volume under certain conditions, which can contribute to improved forest management and characterization.

Historical Land Use as a Feature for Image Classification

This paper analyzes the effect of the addition of historical land-use as a descriptive feature in plot-based image classification when updating land-use/land-cover geospatial databases. Several historical databases have been simulated to assess the influence and significance of this feature in the classification. The causes, nature, and evolution of classification errors as the database currency varies are analyzed; and the impact of these errors on change detection during the updating process is evaluated. The results show that the addition of historical land-use information increases the overall accuracy of image classifications. During a database updating process, changes are detected by comparing the historical land-use with the classification results. The main drawback of employing historical land-use as a descriptive feature in image classification for change detection is that the percentage of undetectable errors significantly increases as more accurate is the database information.