Conference PaperPDF Available

SPUSPO: Spatially Partitioned Unsupervised Segmentation Parameter Optimization for Efficiently Segmenting Large Heterogeneous Areas

Authors:

Abstract and Figures

Very-High-Resolution (VHR) Remote Sensing (RS) data are crucial for deriving essential geospatial information on cities, e.g. for urban planning, population estimation and socioeconomic assessments with particular merit in sub-Saharan Africa (SSA) due to the scarcity or absence of reference data. One of the cornerstones of information that can be produced from RS is classified Land Use and Land Cover (LULC) maps. For VHR imagery, Object Based Image Analysis (OBIA) is the most efficient methodology to produce such outputs. A crucial intermediate step in OBIA is the selection of a suitable segmentation scale. However, for large, heterogeneous areas (e.g., at city level), little effort has been made to optimize OBIA algorithms. Supervised methods to optimize segmentation parameters are subjective and time consuming while Unsupervised Segmentation Parameter Optimization (USPO) techniques, assume spatial stationarity for the whole image. This is problematic for geographically large heterogenous areas and does not capture intra-urban variations due to building size, materials and fractions of LULC intrinsically varying in space. In this study, we employ a novel framework named Spatially Partitioned Unsupervised Segmentation Parameter Optimization (SPUSPO) that optimizes segmentation parameters locally for two SSA cities, Dakar and Ouagadougou. The framework employs the open access GRASS GIS software that is suitable for large scale computing. Our results suggest that SPUSPO is an efficient way to optimize segmentation parameters for large and heterogeneous urban areas.
Content may be subject to copyright.
SPUSPO: SPATIALLY PARTITIONED UNSUPERVISED SEGMENTATION PARAMETER
OPTIMIZATION FOR EFFICIENTLY SEGMENTING LARGE HETEROGENEOUS AREAS
S. Georganos1, T. Grippa1, M. Lennert1, S. Vanhuysse1, E. Wolff1
1 Université libre de Bruxelles (ULB), Department of Geosciences, Environment and Society (DGES-IGEAT)
ABSTRACT
Very-High-Resolution (VHR) Remote Sensing (RS) data are
crucial for deriving essential geospatial information on
cities, e.g. for urban planning, population estimation and
socioeconomic assessments with particular merit in sub-
Saharan Africa (SSA) due to the scarcity or absence of
reference data. One of the cornerstones of information that
can be produced from RS is classified Land Use and Land
Cover (LULC) maps. For VHR imagery, Object Based
Image Analysis (OBIA) is the most efficient methodology to
produce such outputs. A crucial intermediate step in OBIA
is the selection of a suitable segmentation scale. However,
for large, heterogeneous areas (e.g., at city level), little effort
has been made to optimize OBIA algorithms. Supervised
methods to optimize segmentation parameters are subjective
and time consuming while Unsupervised Segmentation
Parameter Optimization (USPO) techniques, assume spatial
stationarity for the whole image. This is problematic for
geographically large heterogenous areas and does not
capture intra-urban variations due to building size, materials
and fractions of LULC intrinsically varying in space. In this
study, we employ a novel framework named Spatially
Partitioned Unsupervised Segmentation Parameter
Optimization (SPUSPO) that optimizes segmentation
parameters locally for two SSA cities, Dakar and
Ouagadougou. The framework employs the open access
GRASS GIS software that is suitable for large scale
computing. Our results suggest that SPUSPO is an efficient
way to optimize segmentation parameters for large and
heterogeneous urban areas.
Index Terms unsupervised segmentation parameter
optimization, GRASS GIS, VHR imagery, land cover
1. INTRODUCTION
In sub-Saharan African cities, in the absence of adequate
data for urban planning, one of the most important pieces of
information we can derive through Very-High-Resolution
(VHR) Remote Sensing (RS), is detailed and accurate Land
Use and Land Cover (LULC) maps. These products are
often used as input for epidemiological, population and
socio-economic models, among others. Nonetheless, to
achieve adequate classification results in these challenging
landscapes, Object Based Image Analysis (OBIA) [1] is
frequently employed over pixel-based approaches due to
superior performance [2]. Nonetheless, OBIA can be a very
tedious and computationally demanding technique,
particularly for large-scale applications (e.g., at city level).
Moreover, the classification of relevant images requires
several preparatory tasks, ranging from the selection of an
appropriate segmentation (object-creating) algorithm, to the
effective calibration of the parameters of the algorithm itself
[3]. Such parameters control the shape and size of the
created segments. Since the segmentation quality is crucial
to the results of the classification itself, the optimization of
these parameters is a critical methodological facet.
Region-growing segmentation algorithms are very
frequent in the OBIA literature, mainly due to their
effectiveness and ease of implementation. The selection of
the parameters of the segmentation algorithm is most
commonly achieved through a time-consuming, user
dependent, trial and error process in which the quality of the
segmentations is assessed visually or through alternative
methodologies which rank different segmentations based on
reference data. However, supervised calibration approaches
are untenable for large heterogeneous regions if maximizing
classification accuracy and segmentation quality in an
automated approach is one of the aims. Consequently,
research efforts have been directed towards the development
of objectively defined Unsupervised Segmentation
Parameter Optimization (USPO) techniques, that evaluate
individual segmentations based on geostatistical metrics,
and do not require reference data and user interference, thus
allowing for automated processes [4]. The optimization of
USPO metrics has been attempted mainly by the use of
global methods, either at single or at multiple scales. This
means that the segmentation over the whole region of
interest is optimized by using one set of parameters. This
global approach has recently been shown to be inferior to
local approaches in urban and agricultural environments
either through evaluation metrics such as classification
accuracy and detailed visual examination [5],[6]. Thus, in
order to treat the growing amount of VHR remote sensing
data available in a way that is both time-efficient and
accurate, an approach based on the hypothesis that the
segmentation optimal parameters would intrinsically and
significantly vary across heterogeneous regions due to local
variations in data structure, is more appropriate. However,
there is no established automated framework for applying
local USPO for very large VHR urban datasets. In general,
little effort has been made to identify and quantify the
degree of spatial non-stationarity between the algorithm
parameters, especially for large heterogeneous areas such as
cities, where neighborhood structure and consequently,
optimal segmentation parameters might vary due to different
building materials, size, fractions and types of vegetation
and road network. As such, our aim is to present a
methodological framework to optimize segmentation results
for large heterogenous areas based on the following
premises: i) allowing segmentation parameters to vary,
which can provide significant increases in classification
quality and ii) implement the methods through an open
source semi-automated processing chain, suitable for large-
scale computing utilizing mainly GRASS GIS, in order to
make the previous task manageable.
2. DATA AND STUDY AREA
The classification scheme is implemented for Dakar and
Ouagadougou, the capitals of Senegal and Burkina Faso,
respectively (Figure 1). They are both major Sahelian cities,
which have been facing an extensive urban growth since the
last decades. Pansharpened tristereo Pleiades imagery
(VNIR, 0.5m, 400 km2) acquired in 2015 was used for
Dakar while Worldview-3 stereo imagery acquired in the
same year was used for Ouagadougou (VNIR, 0.5m, 630
km2). Normalized Digital Surface Models (nDSM) were
produced by photogrammetry from both datasets to aid in
built-up fabric identification.
Figure 1. True color composites of Ouagadougou (top) and
Dakar (bottom).
3. METHODS
In this paper, we present a methodological framework
named Spatially Partitioned Unsupervised Segmentation
Parameter Optimization (SPUSPO) in which
optimization of segmentation parameters is performed
locally. We followed a different approach for the spatial
partitioning of each city, a fully unsupervised process for
Dakar and a supervised one for Ouagadougou (Figure 2).
For Dakar, we split the image into 1700 500m by 500m grid
cells. For Ouagadougou, an expert-based visual delineation
of local morphological zones (LMZ) was performed by
applying the following ruleset:
LMZs should be homogeneous, both in terms of
building size and density, and should be visibly
different from their neighboring LMZs.
LMZs boundaries should follow, as far as possible,
man-made or natural linear elements, e. g., roads, paths,
rivers, streams, railways.
Built-up LMZs should be larger than 1.5 hectares (ha).
Both of these spatially partitioning methods were compared
to a global approach in which segmentation parameters were
optimized in a small subset of the study areas and the
suggested value was applied to the whole study area.
Figure 2. Different methods of spatial partitioning a)
automatic delineation of grid cells in Dakar and b) manual,
expert delineation of LMZ in Ouagadougou.
Afterwards, we made extensive use of the semi-
automated processing chain developed by Grippa et al. [7],
that combines GRASS GIS [8], Python and R programming
languages along with PostGIS support in a Jupyter
Notebook implementation. The chain allows for a complete
analysis, from input of the initial image datasets to the
production of final LC maps. An excerpt example of the
Jupyter chain is given in Figure 3, while the general
workflow is described in Figure 4. In detail, the
segmentation was optimized in each of the spatial subsets
(grid cells for Dakar and LMZs for Ouagadougou) using the
i.segment.uspo module of GRASS [9] with a region growing
algorithm. The module uses geospatial metrics to perform
the optimization, such as Moran’s I and the variance to find
the best compromise between intra- and inter-segment
heterogeneity. Moreover, it allows for parallelization and is
thus computationally efficient. Once layers of features
calculated on the segmentation layers coming from different
techniques were produced, a random forest classifier was
implemented to evaluate their efficacy [10]. To train and
evaluate the models we visually identified roughly 3000
objects for both cities. As shown in Table 1, we used a
detailed classification scheme to draw more robust
conclusions about the merits of using local optimization on
large regions.
Figure 3. Excerpt of the Jupyter notebook consisting of a
sequence of code and a descriptive text that documents the
different processing steps that can be executed directly from
the notebook.
Figure 4. General workflow of the processing chain.
Table 1. Classification scheme for Ouagadougou and Dakar
Ouagadougou
Dakar
Buildings
Building type 1
Swimming Pools
Building type 2
Asphalt
Asphalt
Brown/Red Bare Soil
Bare soil, dusty
concrete
White/Grey Bare Soil
Trees
Trees
Mixed Bare
Soil/Vegetation
Low vegetation
(e.g. grass)
Dry Vegetation
Bushes
Other Vegetation
Inland Waters
Inland waters
Shadow
Shadow
4. RESULTS
The results indicated that a local approach can be of merit.
Figure 5 demonstrates the variability of optimized threshold
parameter for each grid cell across Dakar (Figure 5). It is
evident that the local method suggests spatial non-
stationarity of the USPO parameter values. The patterns of
the deviation from the single parameter of the global
approach follow variations in the landscape such as the
types of vegetation and built-up fabric. Supporting our
hypothesis, the results from evaluating the classification
against a reference set implied that undertaking a local
optimization path constructs segments of a higher quality.
The overall accuracy (OA) for Dakar reached 88.20% and
89.50% for the global and local approaches, respectively. In
Ouagadougou, similar results were observed with an OA of
84.77% and 85.45%. Being an urban application, it is also
relevant to examine how well the built-up classes are
predicted. By using the F-score as an indicator to evaluate
per class performance, the results indicate an increase of 2%
and 1% for Dakar and Ouagadougou, respectively. Although
the improvements are not very strong, a detailed visual
examination implied that the local approaches predict built-
up and asphalt classes, in a more consistent fashion. This
can be important given that these products are frequently
used for population and epidemiological applications where
built-up information is the most important feature.
Figure 5. Deviation of the local threshold parameter from
the global one for each grid cell in Dakar. The threshold
parameter controls the shape and size of the segments and
thus, the quality of the segmentation.
There are several reasons that could explain these
improvements. A single segmentation parameter can over-
segment and under-segment objects of the same class in
different regions (Figure 6). For example, industrial areas
consist of large buildings while unplanned areas contain
very small housing units. By allowing the threshold
parameter to vary, SPUSPO can fit these changes in the data
allowing for better classification results.
5. CONCLUSIONS
In this paper, we assessed a new method for optimizing
segmentation parameters in large and highly heterogeneous
Figure 6. Segmentation and classification results for Dakar.
Top left: Classified segments resulting from the global
approach. Top right: Classified segments resulting from the
local approach. Bottom left: True color composite. Bottom
right: segments boundaries coming from the global (red) and
local (green) approaches.
Table 2. Classification accuracy for Ouagadougou and
Dakar with a global approach and SPUSPO, respectively.
Local
Global
Dakar
Ouagadougou
Dakar
OA%
85.45
89.50
84.77
88.20
Kappa%
0.840
0.878
0.833
0.863
Built-up%
0.930
0.960
0.920
0.940
urban areas with the prospect of deriving high quality
LU/LC maps. We call this method Spatially Partitioned
Unsupervised Segmentation Parameter Optimization
(SPUSPO). We employed two different ways to partition the
images i.e., automatic partition by grid cells and expert
based delineation using morphological criteria. The
methodological framework was realized through an open
source processing chain that mainly exploited the artillery of
GRASS GIS for large scale computing. Our results
suggested that spatial partition methods have merit as
increased classification accuracies were observed in
comparison to a global approach, along with better
prediction of artificial surfaces. Future work includes more
testing of the method in different imageries and refining
techniques of automatic delineating useful spatial subsets to
optimize the data. Finally, a comparison between the two
approaches demonstrated in this study automated vs expert
based, will be attempted to assess if a completely automated
approach can be as efficient with a focus in built-up areas
identification as they are the most challenging elements to
classify in SSA cities.
AKNOWLEDGEMENTS
The research presented in this paper is funded by BELSPO
(Belgian Science Policy Office) in the frame of the
STEREO III program project REACT (SR/00/337).
6. REFERENCES
[1] T. Blaschke, Object based image analysis for remote sensing,
ISPRS J. Photogramm. Remote Sens., vol. 65, no. 1, pp. 216,
2010.
[2] T. Blaschke et al., Geographic Object-Based Image Analysis -
Towards a new paradigm, ISPRS J. Photogramm. Remote Sens.,
vol. 87, pp. 180191, 2014.
[3] A. Rasanen, A. Rusanen, M. Kuitunen, and A. Lensu, What
makes segmentation good? A case study in boreal forest habitat
mapping, Int. J. Remote Sens., vol. 34, no. 23, pp. 86038627,
2013.
[4] B. Johnson, M. Bragais, I. Endo, D. Magcale-Macandog, and P.
Macandog, Image Segmentation Parameter Optimization
Considering Within- and Between-Segment Heterogeneity at
Multiple Scale Levels: Test Case for Mapping Residential Areas
Using Landsat Imagery, ISPRS Int. J. Geo-Information, vol. 4, no.
4, pp. 22922305, 2015.
[5] T. Grippa, S. Georganos, M. Lennert, S. Vanhuysse, and E.
Wolff, A local segmentation parameter optimization approach for
mapping heterogeneous urban environments using VHR imagery,
in Remote Sensing Technologies and Applications in Urban
Environments II, 2017, vol. 10431, p. 104310G.
[6] F. Cánovas-García and F. Alonso-Sarría, A local approach to
optimize the scale parameter in multiresolution segmentation for
multispectral imagery, Geocarto Int., vol. 30, no. 8, pp. 937961,
2015.
[7] T. Grippa, M. Lennert, B. Beaumont, S. Vanhuysse, N.
Stephenne, and E. Wolff, An Open-Source Semi-Automated
Processing Chain for Urban Object-Based Classification, Remote
Sens., vol. 9, no. 4, p. 358, 2017.
[8] M. Neteler, M. H. Bowman, M. Landa, and M. Metz, GRASS
GIS: A multi-purpose open source GIS, Environ. Model. Softw.,
vol. 31, pp. 124130, 2012.
[9] M. . Lennert and G. D. Team, Addon i.segment.uspo, Geogr.
Resour. Anal. Support Syst. SoftwareVersion 7.3, 2016.
[10] S. Georganos, T. Grippa, S. G. Vanhuysse, M. Lennert, and E.
Wolff, Optimizing classification performance in an object-based
very-high-resolution land use-land cover urban application, in
Remote Sensing Technologies and Applications in Urban
Environments II, vol. 10431.
... As Böck et al. [52] pointed out, the USPO metrics are sensitive to the range of candidate segmentations used as input, so we empirically found a range that corresponded to cases of evident over-and under-segmentations to be used as minimum and maximum possible values, as commonly done in similar studies [18,53]. Thus, we evaluated 27 different segmentations starting with a TP of 4 and finishing at a TP of 31, guided by an incrementing step value of 1, as in previous studies, [54]. For reader convenience, all TP values were multiplied by 1000 in the illustrative and text materials. ...
... This supports the hypothesis that in large and heterogeneous areas, a single TP may be inadequate, as it is simply an average expression of several non-stationary processes. The results confirm prior analysis in another Sub-Saharan city of Dakar, where a semi-automated local approach outperformed classical optimization methods [54]. Moreover, several other studies have described how regionalized approaches can be of merit for urban, semi-rural, and agricultural environments [35,43,44]. ...
Article
Full-text available
To classify Very-High-Resolution (VHR) imagery, Geographic Object Based Image Analysis (GEOBIA) is the most popular method used to produce high quality Land-Use/Land-Cover maps. A crucial step in GEOBIA is the appropriate parametrization of the segmentation algorithm prior to the classification. However, little effort has been made to automatically optimize GEOBIA algorithms in an unsupervised and spatially meaningful manner. So far, most Unsupervised Segmentation Parameter Optimization (USPO) techniques, assume spatial stationarity for the whole study area extent. This can be questionable, particularly for applications in geographically large and heterogeneous urban areas. In this study, we employed a novel framework named Spatially Partitioned Unsupervised Segmentation Parameter Optimization (SPUSPO), which optimizes segmentation parameters locally rather than globally, for the Sub-Saharan African city of Ouagadougou, Burkina Faso, using WorldView-3 imagery (607 km 2). The results showed that there exists significant spatial variation in the optimal segmentation parameters suggested by USPO across the whole scene, which follows landscape patterns-mainly of the various built-up and vegetation types. The most appropriate automatic spatial partitioning method from the investigated techniques, was an edge-detection cutline algorithm, which achieved higher classification accuracy than a global optimization, better predicted built-up regions, and did not suffer from edge effects. The overall classification accuracy using SPUSPO was 90.5%, whilst the accuracy from undertaking a traditional USPO approach was 89.5%. The differences between them were statistically significant (p < 0.05) based on a McNemar's test of similarity. Our methods were validated further by employing a segmentation goodness metric, Area Fit Index (AFI)on building objects across Ouagadougou, which suggested that a global USPO was more over-segmented than our local approach. The mean AFI values for SPUSPO and USPO were 0.28 and 0.36, respectively. Finally, the processing was carried out using the open-source software GRASS GIS, due to its efficiency in raster-based applications.
... However, even in state-of-the-art methods, the segmentation parameters are generally optimized for whole scenes, which is not effective for citywide mapping that involves large images with a high degree of heterogeneity. Therefore, a local segmentation optimization was developed (spatially partitioned unsupervised segmentation parameter optimization [101]) that outperforms global approaches, both in terms of thematic and geometric accuracy [102]. ...
Article
Urbanization in the global South has been accompanied by the proliferation of vast informal and marginalized urban areas that lack access to essential services and infrastructure. UN-Habitat estimates that close to a billion people currently live in these deprived and informal urban settlements, generally grouped under the term of urban slums. Two major knowledge gaps undermine the efforts to monitor progress towards the corresponding sustainable development goal (i.e., SDG 11-Sustainable Cities and Communities). First, the data available for cities worldwide is patchy and insufficient to differentiate between the diversity of urban areas with respect to their access to essential services and their specific infrastructure needs. Second, existing approaches used to map deprived areas (i.e., aggregated household data, Earth observation (EO), and community-driven data collection) are mostly siloed, and, individually, they often lack transferability and scalability and fail to include the opinions of different interest groups. In particular, EO-based-deprived area mapping approaches are mostly top-down, with very little attention given to ground information and interaction with urban communities and stakeholders. Existing top-down methods should be complemented with bottom-up approaches to produce routinely updated, accurate, and timely deprived area maps. In this review, we first assess the strengths and limitations of existing deprived area mapping methods. We then propose an Integrated Deprived Area Mapping System (IDeAMapS) framework that leverages the strengths of EO-and community-based approaches. The proposed framework offers a way forward to map deprived areas globally, routinely, and with maximum accuracy to support SDG 11 monitoring and the needs of different interest groups.
... The second data set consists of a very-high resolution land-cover map, derived from the Pleiades pan-sharpened tri-stereo images of 2015, with a spatial resolution of 0.5 m (see Figure 3). This map was previously produced thanks to a semi-automated open-source framework for object-based image analysis and supervised classification [21][22][23]. The overall accuracy (OA) of this product achieved 89.5%, and the building class reached 94% and 97% for user and producer accuracy, respectively (more details about the validation of this product are provided in [24]). ...
Article
Full-text available
Built-up layers derived from medium resolution (MR) satellite information have proven their contribution to dasymetric mapping, but suffer from important limitations when working at the intra-urban level, mainly due to their difficulty in capturing the whole range of variation in terms of built-up densities. In this regard, very-high resolution (VHR) remote sensing is known for its ability to better capture small variations in built-up densities and to derive detailed urban land use, which plead in favor of its use when mapping urban populations. In this paper, we compare the added value of various combinations of VHR data sets, compared to a MR one. A top-down dasymetric mapping strategy is applied to reallocate population counts from administrative units into a regular 100 × 100 m grid, according to different weighting layers. These weighting layers are created from MR and/or VHR input data, using simple built-up proportion or reallocation "weights", obtained from a set of multiple ancillary data used to train a Random Forest regression model. The results reveal that (1) a built-up mask derived from VHR can improve the accuracy of the reallocation by roughly 13%, compared to MR; (2) using VHR land-use information alone results in lower accuracy than using a MR built-up mask; and (3) there is a clear complementarity between VHR land cover and land use.
... Aiming at regional division, researches have presented different methods in recent years. Georganos et al. [27,28] used the cutline creating algorithm and two other regular grid creating methods to divide the image into local regions. Zhang et al. [29] used blocks data to divide images for functional zones classification, which is similar to other research (e.g., Heiden et al. and Hu et al. [30,31]); however, these methods include hard division of the whole image and they do not consider the aggregation effect and geo-object's self-hood scale. ...
Article
Full-text available
Extracting farmland from high spatial resolution remote sensing images is a basic task for agricultural information management. According to Tobler’s first law of geography, closer objects have a stronger relation. Meanwhile, due to the scale effect, there are differences on both spatial and attribute scales among different kinds of objects. Thus, it is not appropriate to segment images with unique or fixed parameters for different kinds of objects. In view of this, this paper presents a stratified object-based farmland extraction method, which includes two key processes: one is image region division on a rough scale and the other is scale parameter pre-estimation within local regions. Firstly, the image in RGB color space is converted into HSV color space, and then the texture features of the hue layer are calculated using the grey level co-occurrence matrix method. Thus, the whole image can be divided into different regions based on the texture features, such as the mean and homogeneity. Secondly, within local regions, the optimal spatial scale segmentation parameter was pre-estimated by average local variance and its first-order and second-order rate of change. The optimal attribute scale segmentation parameter can be estimated based on the histogram of local variance. Through stratified regionalization and local segmentation parameters estimation, fine farmland segmentation can be achieved. GF-2 and Quickbird images were used in this paper, and mean-shift and multi-resolution segmentation algorithms were applied as examples to verify the validity of the proposed method. The experimental results have shown that the stratified processing method can release under-segmentation and over-segmentation phenomena to a certain extent, which ultimately benefits the accurate farmland information extraction.
... The chain utilizes the open software GRASS GIS, along with Python and R programming languages in a Jupyter notebook format. The Pleiades spectral bands were used as input to a region-growing segmentation algorithm as implemented in the "i.segment" module of GRASS (Momsen et al., 2015;Neteler et al., 2008) whose parameters were optimized in a state of the art unsupervised approach (Georganos et al., , 2017bGrippa et al., 2017aGrippa et al., , 2017bLennert, 2016). ...
Article
In order to reduce climate-related health issues in Sub-Saharan cities, a better understanding of the spatial and temporal processes affecting urban climates is required. In this context, this paper mobilizes the potential of urban climate modelling and remote sensing to improve the understanding of urban health risk variations in Sub-Saharan Africa. The combination of Stewart and Oke's (2012) universal classification of Local Climate Zones with very high resolution satellite imagery is explored for the parameterization of a simple urban canopy model (TERRA_URB) over two cities: Kampala (Uganda) and Dakar (Senegal). Key challenges, such as data scarcity and performing analyses on multi spatio-temporal scales are emphasized. Applications for a better understanding of links between urban climates and intra-urban health issues in highly dynamic urban environments are illustrated and discussed taking intra-urban malaria risk as an example.
... The primary input data consisted of land-cover (LC) maps (Figures 1 and 2) derived from very-high resolution (VHR) satellite imagery, i.e., WorldView-3 and Pléiades for Ouagadougou and Dakar, respectively, with a spatial resolution of 0.5 m. These were produced using a semiautomated object-based image analysis (OBIA) [33] framework based on open-source solutions [34][35][36][37]. The overall accuracy (OA) of the LC products was 93.4% and 89.5% for Ouagadougou and Dakar, respectively. ...
Article
Full-text available
Up-to-date and reliable land-use information is essential for a variety of applications such as planning or monitoring of the urban environment. This research presents a workflow for mapping urban land use at the street block level, with a focus on residential use, using very-high resolution satellite imagery and derived land-cover maps as input. We develop a processing chain for the automated creation of street block polygons from OpenStreetMap and ancillary data. Spatial metrics and other street block features are computed, followed by feature selection that reduces the initial datasets by more than 80%, providing a parsimonious, discriminative, and redundancy-free set of features. A random forest (RF) classifier is used for the classification of street blocks, which results in accuracies of 84% and 79% for five and six land-use classes, respectively. We exploit the probabilistic output of RF to identify and relabel blocks that have a high degree of uncertainty. Finally, the thematic precision of the residential blocks is refined according to the proportion of the built-up area. The output data and processing chains are made freely available. The proposed framework is able to process large datasets, given that the cities in the case studies, Dakar and Ouagadougou, cover more than 1000 km2 in total, with a spatial resolution of 0.5 m.
... An important advantage of the proposed method is its potential for automation with particular merit for large, heterogeneous areas. As Grippa et al. [47] and Georganos et al. [48] pointed out, in heterogeneous urban scenes a single set of segmentation parameters is inadequate and less efficient than spatially partitioning the study area into several subsets and optimizing each separately. Similar studies for semi-rural and agricultural environments have demonstrated the efficacy of local optimization through the use of F-measure and ESP methods [25,27]. ...
Article
Full-text available
In object-based image analysis (OBIA), the appropriate parametrization of segmentation algorithms is crucial for obtaining satisfactory image classification results. One of the ways this can be done is by unsupervised segmentation parameter optimization (USPO). A popular USPO method does this through the optimization of a "global score" (GS), which minimizes intrasegment heterogeneity and maximizes intersegment heterogeneity. However, the calculated GS values are sensitive to the minimum and maximum ranges of the candidate segmentations. Previous research proposed the use of fixed minimum/maximum threshold values for the intrasegment/intersegment heterogeneity measures to deal with the sensitivity of user-defined ranges, but the performance of this approach has not been investigated in detail. In the context of a remote sensing very-high-resolution urban application, we show the limitations of the fixed threshold approach, both in a theoretical and applied manner, and instead propose a novel solution to identify the range of candidate segmentations using local regression trend analysis. We found that the proposed approach showed significant improvements over the use of fixed minimum/maximum values, is less subjective than user-defined threshold values and, thus, can be of merit for a fully automated procedure and big data applications.
Conference Paper
Full-text available
In this paper we investigate a local implementation of Random Forest (RF), named Geographical Random Forest (GRF) to predict population density with Very-High-Resolution Remote Sensing (VHHRS) data. As an independent variable we use population density at the neighborhood level from the 2013 census of Dakar, while as explanatory features, the proportions of three different built-up types in each neighborhood derived from a VHHRS land cover classification. The results demonstrated, that by using an appropriate geographic scale to calibrate GRF, we can maximize prediction accuracy due to the incorporation of spatial heterogeneity in the estimates. Additionally, since GRF is an ensemble of local sub-models, the results can be mapped, highlighting local model performance and other interesting spatial variations. Consequently, GRF is suggested as an interesting exploratory and explanatory technique to model remotely-sensed spatially heterogeneous relationships.
Thesis
Full-text available
Nowadays, in sub-Saharan Africa (SSA), about 40% of the population is urban and this region is expected to face the highest growth rates during the next decades. By 2100, the three most populated cities in the world will be located in SSA. As a consequence of the extremely fast transformations experienced during the last decades, SSA cities are facing social and environmental issues combined with a lack of financial means and capacity in urban planning and management. The poorest often constitute a large part of the urban population that is extremely vulnerable to health and disaster risks. In SSA cities, up-to-date and spatially detailed geographic information is often missing. This lack of information is an important issue for many scientific studies focusing on different urban issues and there is a real need to improve the availability of geoinformation for these cities in order to support urban planning, urban management, environment monitoring, epidemiology or risk assessment, etc. . . The work presented in this thesis aims to develop different frameworks for the production of geoinformation. For this purpose, advantage is taken of Very-High Resolution Remote Sensing imagery (0.5 meters) and open-source software. These frameworks implement cutting-edge methods and can handle a large amount of data in a semi-automated fashion to produce maps covering very large areas of interest. In the spirit of open science, the processing chains are entirely based on open-source software and are released publicly in open-access for any interested researchers, in order to make the methods developed completely transparent and in order to contribute to the creation of a pool of common tools and scientific knowledge. These frameworks are used to produce very detailed land-cover and land-use maps that provide essential information such as the built-up density, or the fact that a neighborhood is residential or not. This detailed geoinformation is then used as indicators of presence of populated places to improve existing population models at the intra-urban level.
Conference Paper
Full-text available
Mapping large heterogeneous urban areas using object-based image analysis (OBIA) remains challenging, especially with respect to the segmentation process. This could be explained both by the complex arrangement of heterogeneous land-cover classes and by the high diversity of urban patterns which can be encountered throughout the scene. In this context, using a single segmentation parameter to obtain satisfying segmentation results for the whole scene can be impossible. Nonetheless, it is possible to subdivide the whole city into smaller local zones, rather homogeneous according to their urban pattern. These zones can then be used to optimize the segmentation parameter locally, instead of using the whole image or a single representative spatial subset. This paper assesses the contribution of a local approach for the optimization of segmentation parameter compared to a global approach. Ouagadougou, located in sub-Saharan Africa, is used as case studies. First, the whole scene is segmented using a single globally optimized segmentation parameter. Second, the city is subdivided into 283 local zones, homogeneous in terms of building size and building density. Each local zone is then segmented using a locally optimized segmentation parameter. Unsupervised segmentation parameter optimization (USPO), relying on an optimization function which tends to maximize both intra-object homogeneity and inter-object heterogeneity, is used to select the segmentation parameter automatically for both approaches. Finally, a land-use/land-cover classification is performed using the Random Forest (RF) classifier. The results reveal that the local approach outperforms the global one, especially by limiting confusions between buildings and their bare-soil neighbors.
Conference Paper
Full-text available
This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although an increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.
Article
Full-text available
This study presents the development of a semi-automated processing chain for urban object-based land-cover and land-use classification. The processing chain is implemented in Python and relies on existing open-source software GRASS GIS and R. The complete tool chain is available in open access and is adaptable to specific user needs. For automation purposes, we developed two GRASS GIS add-ons enabling users (1) to optimize segmentation parameters in an unsupervised manner and (2) to classify remote sensing data using several individual machine learning classifiers or their prediction combinations through voting-schemes. We tested the performance of the processing chain using sub-metric multispectral and height data on two very different urban environments: Ouagadougou, Burkina Faso in sub-Saharan Africa and Liège, Belgium in Western Europe. Using a hierarchical classification scheme, the overall accuracy reached 93% at the first level (5 classes) and about 80% at the second level (11 and 9 classes, respectively).
Article
Full-text available
a b s t r a c t The amount of scientific literature on (Geographic) Object-based Image Analysis – GEOBIA has been and still is sharply increasing. These approaches to analysing imagery have antecedents in earlier research on image segmentation and use GIS-like spatial analysis within classification and feature extraction approaches. This article investigates these development and its implications and asks whether or not this is a new paradigm in remote sensing and Geographic Information Science (GIScience). We first discuss several limitations of prevailing per-pixel methods when applied to high resolution images. Then we explore the paradigm concept developed by Kuhn (1962) and discuss whether GEOBIA can be regarded as a paradigm according to this definition. We crystallize core concepts of GEOBIA, including the role of objects, of ontologies and the multiplicity of scales and we discuss how these conceptual developments support important methods in remote sensing such as change detection and accuracy assessment. The ramifications of the different theoretical foundations between the 'per-pixel paradigm' and GEOBIA are analysed, as are some of the challenges along this path from pixels, to objects, to geo-intelligence. Based on several paradigm indications as defined by Kuhn and based on an analysis of peer-reviewed scientific literature we conclude that GEOBIA is a new and evolving paradigm. Ó 2013 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) Published by Elsevier B.V. All rights reserved.
Article
Full-text available
Remote sensing imagery needs to be converted into tangible information which can be utilised in conjunction with other data sets, often within widely used Geographic Information Systems (GIS). As long as pixel sizes remained typically coarser than, or at the best, similar in size to the objects of interest, emphasis was placed on per-pixel analysis, or even sub-pixel analysis for this conversion, but with increasing spatial resolutions alternative paths have been followed, aimed at deriving objects that are made up of several pixels. This paper gives an overview of the development of object based methods, which aim to delineate readily usable objects from imagery while at the same time combining image processing and GIS functionalities in order to utilize spectral and contextual information in an integrative way. The most common approach used for building objects is image segmentation, which dates back to the 1970s. Around the year 2000 GIS and image processing started to grow together rapidly through object based image analysis (OBIA - or GEOBIA for geospatial object based image analysis). In contrast to typical Landsat resolutions, high resolution images support several scales within their images. Through a comprehensive literature review several thousand abstracts have been screened, and more than 820 OBIA-related articles comprising 145 journal papers, 84 book chapters and nearly 600 conference papers, are analysed in detail. It becomes evident that the first years of the OBIA/GEOBIA developments were characterised by the dominance of 'grey' literature, but that the number of peer-reviewed journal articles has increased sharply over the last four to five years. The pixel paradigm is beginning to show cracks and the OBIA methods are making considerable progress towards a spatially explicit information extraction workflow, such as is required for spatial planning as well as for many monitoring programmes.
Article
Multi-scale/multi-level geographic object-based image analysis (MS-GEOBIA) methods are becoming widely-used in remote sensing because single-scale/single-level (SS-GEOBIA) methods are often unable to obtain an accurate segmentation and classification of all land use/land cover (LULC) types in an image. However, there have been few comparisons between SS-GEOBIA and MS-GEOBIA approaches for the purpose of mapping a specific LULC type, so it is not well understood which is more appropriate for this task. In addition, there are few methods for automating the selection of segmentation parameters for MS-GEOBIA, while manual selection (i.e., trial-and-error approach) of parameters can be quite challenging and time-consuming. In this study, we examined SS-GEOBIA and MS-GEOBIA approaches for extracting residential areas in Landsat 8 imagery, and compared naïve and parameter-optimized segmentation approaches to assess whether unsupervised segmentation parameter optimization (USPO) could improve the extraction of residential areas. Our main findings were: (i) the MS-GEOBIA approaches achieved higher classification accuracies than the SS-GEOBIA approach, and (ii) USPO resulted in more accurate MS-GEOBIA classification results while reducing the number of segmentation levels and classification variables considerably.
Article
The results obtained using the object-based image analysis approach for remote sensing image analysis depend strongly on the quality of the segmentation step. In this paper, to optimize the scale parameter in a multiresolution segmentation, we analyse a high-resolution image of a large and heterogeneous agricultural area. This approach is based on using a set of agricultural plots extracted from official maps as uniform spatial units. The scale parameter is then optimized in each uniform spatial unit. Intra-object and inter-object heterogeneity measurements are used to evaluate each segmentation. To avoid subsegmentation, some oversegmentation is allowed, but is attenuated in a second step using the spectral difference segmentation algorithm. The statistical distribution of the scale parameter is not equal in all land uses, indicating the soundness of this local approach. A quantitative assessment of the results was also conducted for the different land covers. The results indicate that the spectral contrast between objects is larger with the local approach than with the global approach. These differences were statistically significant in all land uses except irrigated fruit trees and greenhouses. In the absence of subsegmentation, this suggests that the objects will be placed far apart in the space of variables, even if they are very close in the physical space. This is an obvious advantage in a subsequent classification of the objects. Link (only 50 first downloads): http://www.tandfonline.com/eprint/GY49xSXbphisVegWxjFB/full
Article
Segmentation goodness evaluation is a set of approaches meant for deciding which segmentation is good. In this study, we tested different supervised segmentation evaluation measures and visual interpretation in the case of boreal forest habitat mapping in Southern Finland. The data used were WorldView-2 satellite imagery, a lidar digital elevation model DEM, and a canopy height model CHM in 2 m resolution. The segmentation methods tested were the fractal net evolution approach FNEA and IDRISI watershed segmentation. Overall, 252 different segmentation methods, layers, and parameter combinations were tested. We also used eight different habitat delineations as reference polygons against which 252 different segmentations were tested. The ranking order of segmentations depended on the chosen supervised evaluation measure; hence, no single segmentation could be ranked as the best. In visual interpretation among the several different segmentations that we found rather good, we selected only one as the best. In the literature, it has been noted that better segmentation leads to higher classification accuracy. We tested this argument by classifying 12 of our segmentations with the random forest classifier. It was found out that there is no straightforward answer to the argument, since the definition of good segmentation is inconsistent. The highest classification accuracy 0.72 was obtained with segmentation that was regarded as one of the best in visual interpretation. However, almost similarly high classification accuracies were obtained with other segmentations. We conclude that one has to decide what one wants from segmentation and use segmentation evaluation measures with care.
Article
The GIS software sector has developed rapidly over the last ten years. Open Source GIS applications are gaining relevant market shares in academia, business, and public administration. In this paper, we illustrate the history and features of a key Open Source GIS, the Geographical Resources Analysis Support System (GRASS). GRASS has been under development for more than 28 years, has strong ties into academia, and its review mechanisms led to the integration of well tested and documented algorithms into a joint GIS suite which has been used regularly for environmental modelling. The development is community-based with developers distributed globally. Through the use of an online source code repository, mailing lists and a Wiki, users and developers communicate in order to review existing code and develop new methods. In this paper, we provide a functionality overview of the more than 400 modules available in the latest stable GRASS software release. This new release runs natively on common operating systems (MS-Windows, GNU/Linux, Mac OSX), giving basic and advanced functionality to casual and expert users. In the second part, we review selected publications with a focus on environmental modelling to illustrate the wealth of use cases for this open and free GIS.
Addon i.segment.uspo
  • M Lennert
  • G D Team
M.. Lennert and G. D. Team, "Addon i.segment.uspo," Geogr. Resour. Anal. Support Syst. SoftwareVersion 7.3, 2016.