WorldView-2 Satellite Imagery and Airborne LiDAR Data for Object-Based Forest Species Classification in a Cool Temperate Rainforest Environment (original) (raw)
Related papers
Cool temperate rainforest and adjacent forestsclassification using airborne LiDAR data
Area, 2011
The traditional methods of forest classification, based on the interpretation of aerial photographs and processing of multi-spectral and/or hyper-spectral remote sensing data are limited in their ability to capture the structural complexity of the forests compared with analysis of airborne LiDAR (light detection and ranging) data. This is because of LiDAR's penetration of forest canopies such that detailed and three-dimensional forest structure descriptions can be derived. This study applied airborne LiDAR data for the classification of cool temperate rainforest and adjacent forests in the Strzelecki Ranges, Victoria, Australia. Using normalised LiDAR point data, the forest vertical structure was stratified into three layers. Variables characterising the height distribution and density of forest components were derived from LiDAR data within each of these layers. The statistical analyses, which included one-way analysis of variance with post hoc tests, identified effective variables for forest-type classifications. The results showed that using linear discriminant analysis, an overall classification accuracy of 91.4% (as verified by the cross-validation) was achieved in the study area.
2011
Although remotely sensed data have been widely explored for forest applications, passive remote sensing techniques are limited in their ability to capture forest structural complexity, particularly in uneven-aged, mixed species forests with multiple canopy layers. Generally, these techniques are only able to provide information on horizontal (two-dimensional) forest extent. The vertical forest structure (or the interior of the canopy and understorey vegetation) cannot be mapped using these passive remote sensing techniques. Fortunately, it has been shown that active remote sensing techniques via airborne LiDAR (light detection and ranging) with capability of canopy penetration yields such high density sampling that detailed description of the forest structure in three-dimensions can be obtained. Accordingly, much interest is attached to exploring the application of this approach for identifying the distribution of designated vegetation communities. However, the suitability of LiDAR ...
International Journal of Remote Sensing, 2018
Land-cover mapping (LCM) at a fine scale would be useful for forest management across heterogeneous natural landscapes. However, the heterogeneity of land covers at such scales results in complex spectral and textural properties that hinder the applicability of LCM. Besides, the method suffers from, e.g. inconsistent representation of different land-cover types, lack of sufficient and balanced training samples, and instability of classifiers trained by a high number of predictor variables. Even well-known object-based classification approaches are challenged with an objective evaluation of segmentation outputs. Here we classified partially ambiguous land-cover types across heterogeneous forest landscapes in the Bavarian Forest National Park (Germany) by combining metrics from airborne light detection and ranging (LiDAR) and colour infrared (CIR) imagery data and a random forest classifier implemented in an object-based paradigm. We evaluated the segmentation results by creating a global quality score based on interand intra-measurements of variance and the number of segments. Selected segmentation outputs were combined with balanced training samples to run the classification algorithm based on representative blocks within the national park. The entire processing chain was implemented in an open-source domain. The final segmentation consisted of LiDAR-based height, image-based Normalized Difference Vegetation Index (NDVI) and red band, with 20 cluster seeds and a minimum segment size of 40 pixels. In the classification, the most important variables included the height of the top layer, NDVI, Enhanced Vegetation Index (EVI) and Green-Red Vegetation Index (GRVI). The average values of 500 random forest runs indicated an overall accuracy of 86.6% and an estimated Cohen's kappa coefficient of 85.2%, with different probabilities of correct classification for land-cover classes. Mature deciduous, standing deadwood, fallen deadwood, meadow, and bare soil classes were classified most accurately, whereas classification of young coniferous, intermediate-age coniferous, mature coniferous, young deciduous, and intermediate-age deciduous ARTICLE HISTORY
Landscape and Ecological Engineering, 2011
We evaluated the effectiveness of integrating discrete return light detection and ranging (LiDAR) data with high spatial resolution near-infrared digital imagery for object-based classification of land cover types and dominant tree species. In particular we adopted LiDAR ratio features based on pulse attributes that have not been used in past studies. Object-based classifications were performed first on land cover types, and subsequently on dominant tree species within the area classified as trees. In each classification stage, two different data combinations were examined: LiDAR data integrated with digital imagery or digital imagery only. We created basic image objects and calculated a number of spectral, textural, and LiDAR-based features for each image object. Decision tree analysis was performed and important features were investigated in each classification. In the land cover classification, the overall accuracy was improved to 0.975 when using the object-based method and integrating LiDAR data. The mean height value derived from the LiDAR data was effective in separating ''trees'' and ''lawn'' objects having different height. As for the tree species classification, the overall accuracy was also improved by object-based classification with LiDAR data although it remained up to 0.484 because spectral and textural signatures were similar among tree species. We revealed that the LiDAR ratio features associated with laser penetration proportion were important in the object-based classification as they can distinguish tree species having different canopy density. We concluded that integrating LiDAR data was effective in the object-based classifications of land cover and dominant tree species.
A detailed tree species inventory is needed to sustainably manage a natural, mixed, heterogeneous urban forest. An object-based image analysis of a combination of high-resolution WorldView-2 multi-spectral satellite imagery and airborne laser scanning (LiDAR) data was tested for classification of individual tree crowns of five different tree species. The model training data were obtained from a systematic grid of plots in the forest. In total, 304 coniferous (Norway spruce and Scots pine) and 270 deciduous (European beech, Sessile and Pedunculate oak (combined), and Sweet chestnut) trees were identified in the field. The classification was performed by applying the support vector machine model. An accuracy assessment was performed by calculating a confusion matrix to evaluate the accuracy of the classification output by comparing the classification result to the independent test data. The overall accuracy of the classification was 58 %.
International Journal of Applied Earth Observation and Geoinformation, 2014
Knowledge of tree species distribution is important worldwide for sustainable forest management and resource evaluation. The accuracy and information content of species maps produced using remote sensing images vary with scale, sensor (optical, microwave, LiDAR), classification algorithm, verification design and natural conditions like tree age, forest structure and density. Imaging spectroscopy reduces the inaccuracies making use of the detailed spectral response. However, the scale effect still has a strong influence and cannot be neglected. This study aims to bridge the knowledge gap in understanding the scale effect in imaging spectroscopy when moving from 4 to 30 m pixel size for tree species mapping, keeping in mind that most current and future hyperspectral satellite based sensors work with spatial resolution around 30 m or more.
Isprs Journal of Photogrammetry and Remote Sensing, 2018
Light detection and ranging (lidar) data have been increasingly used for forest classification due to its ability to penetrate the forest canopy and provide detail about the structure of the lower strata. In this study we demonstrate forest classification approaches using airborne lidar data as inputs to random forest and linear unmixing classification algorithms. Our results demonstrated that both random forest and linear unmixing models identified a distribution of rainforest and eucalypt stands that was comparable to existing ecological vegetation class (EVC) maps based primarily on manual interpretation of high resolution aerial imagery. Rainforest stands were also identified in the region that have not previously been identified in the EVC maps. The transition between stand types was better characterised by the random forest modelling approach. In contrast, the linear unmixing model placed greater emphasis on field plots selected as endmembers which may not have captured the variability in stand structure within a single stand type. The random forest model had the highest overall accuracy (84%) and Cohen's kappa coefficient (0.62). However, the classification accuracy was only marginally better than linear unmixing. The random forest model was applied to a region in the Central Highlands of southeastern Australia to produce maps of stand type probability, including areas of transition (the 'ecotone') between rainforest and eucalypt forest. The resulting map provided a detailed delineation of forest classes, which specifically recognised the coalescing of stand types at the landscape scale. This represents a key step towards mapping the structural and spatial complexity of these ecosystems, which is important for both their management and conservation.
Central European Forestry Journal, 2017
Remote Sensing provides a variety of data and resources useful in mapping of forest. Currently, one of the common applications in forestry is the identification of individual trees and tree species composition, using the object-based image analysis, resulting from the classification of aerial or satellite imagery. In the paper, there is presented an approach to the identification of group of tree species (deciduous - coniferous trees) in diverse structures of close-to-nature mixed forests of beech, fir and spruce managed by selective cutting. There is applied the object-oriented classification based on multispectral images with and without the combination with airborne laser scanning data in the eCognition Developer 9 software. In accordance to the comparison of classification results, the using of the airborne laser scanning data allowed identifying ground of terrain and the overall accuracy of classification increased from 84.14% to 87.42%. Classification accuracy of class “conife...
Geocarto International, 2016
An object-based approach for mapping forest structural types based on low density LiDAR and multispectral imagery Mapping forest structure variables provides important information for estimation of forest biomass, carbon stocks, pasture suitability or for wildfire risk prevention and control. The optimization of the prediction models of these variables requires an adequate stratification of the forest landscape in order to create specific models for each structural type or strata. This paper aims to propose and validate the use of an object-oriented classification methodology based on low density LiDAR data (0.5 m-2) available at national level, WorldView-2 and Sentinel-2 multispectral imagery to categorize Mediterranean forests in generic structural types. After preprocessing the data sets, the area was segmented using a multiresolution algorithm, features describing 3D vertical structure were extracted from LiDAR data, and spectral and texture features from satellite images. Objects were classified after feature selection in the following structural classes: grasslands, shrubs, forest (without shrubs), mixed forest (trees and shrubs) and dense young forest. Four classification algorithms (C4.5 decision trees, random forest, k-nearest neighbor and support vector machine) were evaluated using cross-validation techniques. The results show that the integration of low density LiDAR and multispectral imagery provide a set of complementary features that improve the results (90.75% overall accuracy), and the objectoriented classification techniques are efficient for stratification of Mediterranean forest areas in structural and fuel related categories. Further work will be focused on the creation and validation of a different prediction model adapted to the various strata.
Object Based Technique for Delineating and Mapping 15 Tree Species using VHR WorldView-2 Imagery
Monitoring and analyzing forests and trees are required task to manage and establish a good plan for the forest sustainability. To achieve such a task, information and data collection of the trees are requested. The fastest way and relatively low cost technique is by using satellite remote sensing. In this study, we proposed an approach to identify and map 15 tree species in the Mangish sub-district, Kurdistan Region-Iraq. Image-objects (IOs) were used as the tree species mapping unit. This is achieved using the shadow index, normalized difference vegetation index and texture measurements. Four classification methods (Maximum Likelihood, Mahalanobis Distance, Neural Network, and Spectral Angel Mapper) were used to classify IOs using selected IO features derived from WorldView-2 imagery. Results showed that overall accuracy was increased 5-8% using the Neural Network method compared with other methods with a Kappa coefficient of 69%. This technique gives reasonable results of various tree species classifications by means of applying the Neural Network method with IOs techniques on WorldView-2 imagery.