Object-based land cover classification using airborne LiDAR

Antonarakis, Alexander S.; Richards, Keith; Brasington, James

doi:10.1016/j.rse.2008.02.004

Cited by 306 publications

(191 citation statements)

References 16 publications

Supporting

Mentioning

184

Contrasting

Unclassified

Order By: Relevance

“…For the "Evergreen coniferous stand" class, the producer and user's accuracy levels were respectively 94 and 77%. The accuracy levels of these classifications are within the same range as those found by Antonarakis et al (2008), who compared five riparian forest stand types in Southern France.…”

Section: Validation Resultssupporting

confidence: 79%

LiDAR derived ecological integrity indicators for riparian zones: Application to the Houille river in Southern Belgium/Northern France

Michez¹,

Piégay²,

Toromanoff³

et al. 2013

Ecological Indicators

View full text Add to dashboard Cite

a b s t r a c tRiparian zones are central landscape features providing several ecosystem services and are exceptionally rich in biodiversity. Despite their relatively low area coverage, riparian zones consequently represent a major concern for land and water resource managers confirmed within several European directives. These directives involve effective multi-scale monitoring to assess their conditions and their ability to carry out their functions. The objective of this research was to develop automated tools to provide from a single aerial LiDAR dataset new mapping tools and keystone riparian zone attributes assessing the ecological integrity of the riparian zone at a network scale (24 km).Different metrics were extracted from the original LiDAR point cloud, notably the Digital Terrain Model and Canopy Height Model rasters, allowing the extraction of riparian zones attributes such as the wetted channel (0.89 m; mean residual) and floodplain extents (6.02 m; mean residual). Different riparian forest characteristics were directly extracted from these layers (patch extent, overhanging character, longitudinal continuity, relative water level, mean and relative standard deviation of tree height). Within the riparian forest, the coniferous stands were distinguished from deciduous and isolated trees, with high accuracy (87.3%, Kappa index).Going further the mapping of the indicators, our study proposed an original approach to study the riparian zone attributes within different buffer width, from local scale (50 m long channel axis reach) to a network scale (ca. 2 km long reaches), using a disaggregation/re-agraggation process. This novel approach, combined to graphical presentations of the results allow natural resource managers to visualise the variation of upstream-downstream attributes and to identify priority action areas.In the case study, results showed a general decrease of the riparian forests when the river crosses built-up areas. They also highlighted the lower flooding frequency of riparian forest patches in habitats areas.Those results showed that LiDAR data can be used to extract indicators of ecological integrity of riparian zones in temperate climate zone. They will enable the assessment of the ecological integrity of riparian zones to be undertaken at the regional scale (13,000 km, completely covered by an aerial LIDAR survey in 2014).

show abstract

Section: Validation Resultssupporting

confidence: 79%

LiDAR derived ecological integrity indicators for riparian zones: Application to the Houille river in Southern Belgium/Northern France

Michez¹,

Piégay²,

Toromanoff³

et al. 2013

Ecological Indicators

View full text Add to dashboard Cite

show abstract

“…We used an object-based approach to classify land cover using the LiDAR point cloud, the Digital Elevation Models (DSM and DTM) and the 2D-model of buildings [13]. Using the height (DSM minus DTM) and LiDAR intensity (the ratio of the strength of the light reflected from an object related to the light emitted [6]), five classes were obtained using the following criteria: i) Water (water) with height = 0 and intensity = 0; ii) Permeable soil (soil per) with height < 1.5m and intensity > 30; iii) Forest (forest) with height > 1m , not matching the 2D built zone; iv) Impermeable soil (soil imp) with height < 1.5m and intensity < 30; v) Buildings (building) with height > 1m matching the 2D built zone.…”

Section: B Classification Based On Lidar and Demmentioning

confidence: 99%

Relationship between land cover type and Body Mass Index in Geneva

Rochat

Duruz

Widmer

et al. 2015

2015 Joint Urban Remote Sensing Event (JURSE)

View full text Add to dashboard Cite

Abstract-Past studies conducted in urban areas analyzed the impact of the presence of green spaces on public health, and highlighted in particular the psychological benefits of interacting with nature. To investigate a supposed relationship between overweight and dense built environment, we focused on the State of Geneva, Switzerland, and calculated the correlation between Body Mass Index (BMI) in a representative sample of 6663 adults and the percentage of natural areas at the locations where these individuals were living. To this end, we used populationbased health data from the "Bus Santé" study (Geneva University Hospitals) and multi-scale land cover maps obtained by means of satellite images and LiDAR data classification. We found little correlation between BMI (as a proxy for health) and land cover data and were not able to verify the working hypothesis at local and regional scales. However, an important phenomenon highlighted here is the difference in the results obtained between the city center and the whole State.

show abstract

“…One of the main advantages of OBIA over per-pixel approaches is that using objects negates the impact of intra-class heterogeneity observed at the pixel-level, therefore eliminating the "salt-and-pepper" artefact [27]. Consequently, OBIA has been used extensively for a variety of applications, including forestry [28], habitat mapping [29], land use/land cover mapping [30], landform mapping [31,32] and change detection [33], with numerous studies reporting that higher classification accuracies can be achieved through the OBIA approach in comparison to pixel-based approaches [34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Evaluating the Use of an Object-Based Approach to Lithological Mapping in Vegetated Terrain

2016

View full text Add to dashboard Cite

Abstract:Remote sensing-based approaches to lithological mapping are traditionally pixel-oriented, with classification performed on either a per-pixel or sub-pixel basis with complete disregard for contextual information about neighbouring pixels. However, intra-class variability due to heterogeneous surface cover (i.e., vegetation and soil) or regional variations in mineralogy and chemical composition can result in the generation of unrealistic, generalised lithological maps that exhibit the "salt-and-pepper" artefact of spurious pixel classifications, as well as poorly defined contacts. In this study, an object-based image analysis (OBIA) approach to lithological mapping is evaluated with respect to its ability to overcome these issues by instead classifying groups of contiguous pixels (i.e., objects). Due to significant vegetation cover in the study area, the OBIA approach incorporates airborne multispectral and LiDAR data to indirectly map lithologies by exploiting associations with both topography and vegetation type. The resulting lithological maps were assessed both in terms of their thematic accuracy and ability to accurately delineate lithological contacts. The OBIA approach is found to be capable of generating maps with an overall accuracy of 73.5% through integrating spectral and topographic input variables. When compared to equivalent per-pixel classifications, the OBIA approach achieved thematic accuracy increases of up to 13.1%, whilst also reducing the "salt-and-pepper" artefact to produce more realistic maps. Furthermore, the OBIA approach was also generally capable of mapping lithological contacts more accurately. The importance of optimising the segmentation stage of the OBIA approach is also highlighted. Overall, this study clearly demonstrates the potential of OBIA for lithological mapping applications, particularly in significantly vegetated and heterogeneous terrain.

show abstract

Object-based land cover classification using airborne LiDAR

Cited by 306 publications

References 16 publications

LiDAR derived ecological integrity indicators for riparian zones: Application to the Houille river in Southern Belgium/Northern France

LiDAR derived ecological integrity indicators for riparian zones: Application to the Houille river in Southern Belgium/Northern France

Relationship between land cover type and Body Mass Index in Geneva

Evaluating the Use of an Object-Based Approach to Lithological Mapping in Vegetated Terrain

Contact Info

Product

Resources

About