Lindi J. Quackenbush

A Review of Techniques for Extracting Linear Features from Imagery

The automated extraction of linear features from remotely sensed imagery has been the subject of extensive research over several decades. Recent studies show promise for extraction of feature information for applications such as updating geographic information systems (GIS). Research has been stimulated by the increase in available imagery in recent years following the launch of several airborne and satellite sensors. However, while the expansion in the range and availability of image data provides new possibilities for deriving image related products, it also places new demands on image processing. Efficiently dealing with the vast amount of available data necessitates an increase in automation, while still taking advantage of the skills of a human operator. This paper provides an overview of the types of imagery being used for linear feature extraction. The paper also describes methods used for feature extraction and considers quantitative and qualitative accuracy assessment of these procedures.

Spatial wildlife-vehicle collision models: a review of current work and its application to transportation mitigation projects.

In addition to posing a serious risk to motorist safety, vehicle collisions with wildlife are a significant threat for many species. Previous spatial modeling has concluded that wildlife-vehicle collisions (WVCs) exhibit clustering on roads, which is attributed to specific landscape and road-related factors. We reviewed twenty-four published manuscripts that used generalized linear models to statistically determine the influence that numerous explanatory predictors have on the location of WVCs. Our motivation was to summarize empirical WVC findings to facilitate application of this knowledge to planning, and design of mitigation strategies on roads. In addition, commonalities between studies were discussed and recommendations for future model design were made. We summarized the type and measurement of each significant predictor and whether they potentially increased or decreased the occurrence of collisions with ungulates, carnivores, small-medium vertebrates, birds, and amphibians and reptiles. WVCs commonly occurred when roads bisect favorable cover, foraging, or breeding habitat for specific species or groups of species. WVCs were generally highest on road sections with high traffic volumes, or low motorist visibility, and when roads cut through drainage movement corridors, or level terrain. Ungulates, birds, small-medium vertebrates, and carnivore collision locations were associated with road-side vegetation and other features such as salt pools. In several cases, results were spurious due to confounding and interacting predictors within the same model. For example, WVCs were less likely to occur when a road bisected steep slopes; however, steep slopes may be located along specific road-types and habitat that also influence the occurrence of WVCs. In conclusion, this review showed that much of the current literature has gleaned the obvious, broad-scale relationships between WVCs and predictors from available data sets, and localized studies can provide unique and novel results. Future research requires specific modeling for each target species on a road-by-road basis, and measuring the predictive power of model results within similar landscapes. In addition, research that builds on the current literature by investigating rare anomalies and interacting variables will assist in providing sound comprehensive guidelines for wildlife mitigation planning on roads.

A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing

Efficient forest management demands detailed, timely information. As high spatial resolution remotely sensed imagery becomes more available, there is a great potential for conducting high accuracy forest inventory and analysis automatically and cost-efficiently. Recent research aimed at providing tree-based forest inventory measurements has generated numerous algorithms for automatic individual tree-crown detection and delineation. This article reviews this research with a focus on algorithms applied to passive remote-sensing imagery. The article categorizes and evaluates methods for automatic tree-crown detection and delineation. It considers the types of imagery and the characteristics of the study areas these algorithms are applied to and evaluates the influence of these factors on the methods. The article also reviews and evaluates quantitative accuracy assessment methods for tree-crown delineation and detection. Finally, the article summarizes the commonalities of current algorithms, and the new development that can be expected in the future.

Population estimation based on multi-sensor data fusion

This research examines the utility of QuickBird imagery and Light Detection and Ranging (LiDAR) data for estimating population at the census-block level using two approaches: area-based and volume-based. Residential-building footprints are first delineated from the remote-sensing data using image segmentation and machine-learning decision-tree classification. Regression analysis is used to model the relationship between population and the area or volume of the delineated residential buildings. Both approaches result in successful performance for estimating population with high accuracy (coefficient of determination = 0.8–0.95; root-mean-square error = 10–30 people; relative root-mean-square error = 0.1–0.3). The area-based approach is slightly better than the volume-based approach because the residential areas of the study sites are generally homogeneous (i.e. single houses), and the volume-based approach is more sensitive to classification errors. The LiDAR-derived shape information such as height greatly improves population estimation compared to population estimation using only spectral data.

Trends in Automatic Individual Tree Crown Detection and Delineation—Evolution of LiDAR Data

Automated individual tree crown detection and delineation (ITCD) using remotely sensed data plays an increasingly significant role in efficiently, accurately, and completely monitoring forests. This paper reviews trends in ITCD research from 1990–2015 from several perspectives—data/forest type, method applied, accuracy assessment and research objective—with a focus on studies using LiDAR data. This review shows that active sources are becoming more prominent in ITCD studies. Studies using active data—LiDAR in particular—accounted for 80% of the total increase over the entire time period, those using passive data or fusion of passive and active data comprised relatively small proportions of the total increase (8% and 12%, respectively). Additionally, ITCD research has moved from incremental adaptations of algorithms developed for passive data sources to innovative approaches that take advantage of the novel characteristics of active datasets like LiDAR. These improvements make it possible to explore more complex forest conditions (e.g., closed hardwood forests, suburban/urban forests) rather than a single forest type although most published ITCD studies still focused on closed softwood (41%) or mixed forest (22%). Approximately one-third of studies applied individual tree level (30%) assessment, with only a quarter reporting more comprehensive multi-level assessment (23%). Almost one-third of studies (32%) that concentrated on forest parameter estimation based on ITCD results had no ITCD-specific evaluation. Comparison of methods continues to be complicated by both choice of reference data and assessment metric; it is imperative to establish a standardized two-level assessment framework to evaluate and compare ITCD algorithms in order to provide specific recommendations about suitable applications of particular algorithms. However, the evolution of active remotely sensed data and novel platforms implies that automated ITCD will continue to be a promising technology and an attractive research topic for both the forestry and remote sensing communities.

A comparison of three methods for automatic tree crown detection and delineation from high spatial resolution imagery

This article compares the performance of three algorithms representative of published methods for tree crown detection and delineation from high spatial resolution imagery, and demonstrates a standardized accuracy assessment framework. The algorithms – watershed segmentation, region growing and valley-following – were tested on softwood and hardwood sites using Emerge natural colour vertical aerial imagery with 60 cm ground sampled distance and QuickBird panchromatic imagery with an 11˚ look angle. The evaluation considered both plot-level and individual tree crown detection and delineation results. The study shows that while all three methods reasonably delineate crowns in the softwood stand on the Emerge image, region growing provided the highest accuracies, with producers and users accuracy for tree detection reaching 70% and root mean square error for crown diameter estimation of 15%. Crown detection accuracies were lower on the QuickBird image. No algorithm proved accurate for the hardwood stand on either image set (both producers and users accuracies < 30%).

Forest Biomass and Carbon Stock Quantification Using Airborne LiDAR Data: A Case Study Over Huntington Wildlife Forest in the Adirondack Park

In response to the need for a better understanding of biosphere-atmosphere interactions as well as carbon cycles, there is a high demand for monitoring key forest parameters such as biomass and carbon stock. These monitoring tasks provide insight into relevant biogeochemical processes as well as anthropogenic impacts on the environment. Recent advances in remote sensing techniques such as Light Detection and Ranging (LiDAR) enable scientists to nondestructively identify structural and biophysical characteristics of forests. This study quantified forest biomass and carbon stock at the plot level from small-footprint full-waveform LiDAR data collected over a montane mixed forest in September 2011, using seven modeling methods: ordinary least squares, generalized additive model, Cubist, bagging, random forest, boosted regression trees, and support vector regression (SVR). Results showed that higher percentiles of canopy height and intensity made significant contributions to the predictions, while other explanatory variables related to canopy geometric volume, structure, and canopy coverage were generally not as important. Boosted regression trees provided the highest accuracy for model calibration, whereas SVR and ordinary least squares performed slightly better than the other models in model validation. In this study, the simple ordinary least squares approach performed just as well as any advanced machine learning method.

Impact of training and validation sample selection on classification accuracy and accuracy assessment when using reference polygons in object-based classification

Reference polygons are homogenous areas that aim to provide the best available assessment of ground condition that the user can identify. Delineation of such polygons provides a convenient and efficient approach for researchers to identify training and validation data for supervised classification. However, the spatial dependence of training and validation data should be taken into account when the two data sets are obtained from a common set of reference polygons. We investigate the effect on classification accuracy and the accuracy estimates derived from the validation data when training and validation data are obtained from four selection schemes. The four schemes are composed of two sampling designs (simple random and systematic) and two methods for splitting sample points between training and validation (validation points in separate polygons from training points and validation points and training points split within the same polygons). A supervised object-based classification of the study region was repeated 30 times for each selection scheme. The selection scheme did not impact classification accuracy, but estimates of overall (OA), users (UA), and producers (PA) accuracies produced from the validation data overestimated accuracy for the study region by about 10%. The degree of overestimation was slightly greater when the validation sample points were allowed to be in the same polygons as the training data points. These results suggest that accuracy estimates derived from splitting training and validation within a limited set of reference polygons should be regarded with suspicion. To be fully confident in the validity of the accuracy estimates, additional validation sample points selected from the region outside the reference polygons may be needed to augment the validation sample selected from the reference polygons.

A Volumetric Approach to Population Estimation Using Lidar Remote Sensing

This research investigated the applicability of lidar data for estimating population at the census block level using a volumetric approach. The study area, near the urban downtown area of Denver, Colorado, was selected since it includes dense distribution of different types of residential buildings. A modified morphological building detection algorithm was proposed to extract buildings from the lidar-derived surfaces. The extraction results showed that the modified morphological building detection algorithm can effectively recover building pixels occluded by nearby trees. The extracted buildings were further refined to residential buildings using parcel data. Two approaches (i.e., area- and volume-based) to population estimation were investigated at the census block level. Four regression models (i.e., simple linear regression, multiple linear regression, regression tree using one variable, and regression tree using multiple variables) were used to identify the relationship between census population and the area or volume information of the residential buildings. The volume-based models overwhelmingly outperformed the area-based models in the study area, and the models using multiple variables yielded more accurate estimation than the single variable models. The volume-based regression tree model using multiple variables yielded the most accurate estimations: R 2 = 0.89, RMSE = 21 people, and RRMSE = 26.8 percent in the calibration site; and R 2 = 0.80, RMSE = 27 people, and RRMS E = 30.1 percent in the validation site. As the results show, the volumetric approach using lidar remote sensing is effective for population estimation in regions with heterogeneous housing characteristics.

A simple Landsat–MODIS fusion approach for monitoring seasonal evapotranspiration at 30 m spatial resolution

Persistent cloud-cover in the humid southeastern USA and the low temporal resolution of Landsat sensors limit the derivation of seasonal evapotranspiration (ET) maps at moderate spatial resolution. This article introduces a Landsat Moderate Resolution Imaging Spectroradiometer (Landsat–MODIS) ET fusion model that uses simple linear regression to integrate Landsat-derived reference ET fraction (ETrF) from mapping ET at high resolution with internalized calibration (METRIC) model and the vegetation temperature condition index (VTCI) derived from MODIS images. For a study site in Florida, model-estimated ET and ET estimated using energy budget eddy covariance at a US Geological Survey (USGS) station in Ferris Farm, Florida, were found to be in a good agreement with a root mean squared error of 0.44 mm day–1, coefficient of determination (R2) of 0.80, Nash–Sutcliffe efficiency of 0.79 for daily ET (ETd), and 2% relative error for cumulative seasonal ET during the growing season of 2001. At another study site in Alabama, the model underestimated 2008 annual water balance ET for the Fish River Watershed by 39 mm or 4%. Comparisons of model-estimated ET with that obtained using a non-fusion Landsat-only approach at both sites indicated that the fusion of Landsat and MODIS ET values reduces potential errors in ET estimation that would otherwise arise due to insufficient availability of cloud-free Landsat images for METRIC processing. Validation results and application of the model in deriving seasonal/annual ET for different land-cover classes in the Fish River Watershed suggested that the fusion model has the potential to be used in continuously monitoring ET for field- to watershed-level agricultural and hydrological applications in the southeastern USA.