Andrés García Lorca

Object-Based Greenhouse Horticultural Crop Identification from Multi-Temporal Satellite Imagery: A Case Study in Almeria, Spain

Greenhouse detection and mapping via remote sensing is a complex task, which has already been addressed in numerous studies. In this research, the innovative goal relies on the identification of greenhouse horticultural crops that were growing under plastic coverings on 30 September 2013. To this end, object-based image analysis (OBIA) and a decision tree classifier (DT) were applied to a set consisting of eight Landsat 8 OLI images collected from May to November 2013. Moreover, a single WorldView-2 satellite image acquired on 30 September 2013, was also used as a data source. In this approach, basic spectral information, textural features and several vegetation indices (VIs) derived from Landsat 8 and WorldView-2 multi-temporal satellite data were computed on previously segmented image objects in order to identify four of the most popular autumn crops cultivated under greenhouse in Almeria, Spain (i.e., tomato, pepper, cucumber and aubergine). The best classification accuracy (81.3% overall accuracy) was achieved by using the full set of Landsat 8 time series. These results were considered good in the case of tomato and pepper crops, being significantly worse for cucumber and aubergine. These results were hardly improved by adding the information of the WorldView-2 image. The most important information for correct classification of different crops under greenhouses was related to the greenhouse management practices and not the spectral properties of the crops themselves.

Classification of urban areas from GeoEye-1 imagery through texture features based on Histograms of Equivalent Patterns

Abstract A family of 26 non-parametric texture descriptors based on Histograms of Equivalent Patterns (HEP) has been tested, many of them for the first time in remote sensing applications, to improve urban classification through object-based image analysis of GeoEye-1 imagery. These HEP descriptors have been compared to the widely known texture measures derived from the gray-level co-occurrence matrix (GLCM). All the five finally selected HEP descriptors (Local Binary Patterns, Improved Local Binary Patterns, Binary Gradient Contours and two different combinations of Completed Local Binary Patterns) performed faster in terms of execution time and yielded significantly better accuracy figures than GLCM features. Moreover, the HEP texture descriptors provided additional information to the basic spectral features from the GeoEye-1s bands (R, G, B, NIR, PAN) significantly improving overall accuracy values by around 3%. Conversely, and in statistic terms, strategies involving GLCM texture derivatives did not improve the classification accuracy achieved from only the spectral information. Lastly, both approaches (HEP and GLCM) showed similar behavior with regard to the training set size applied.

Agriculture in Drylands: Experience in Almeria

The fundamental basis for security and peace in a territory is linked to the absence of internal and external conflicts. Situations of internal conflicts in modern societies normally have their immediate origin in social inequalities and are expressed in an unjust distribution of wealth. The causes that determine these inequalities may be derived from environmental situations, as is the case with the exhaustion of natural resources which assured the existence of a community; they may also be due to the abandonment or isolation of social groups who are then deprived of the possibility of developing their own capacities to access resources, as a result of administrative or political irredentism. They may even derive from the installation of external models of socio-economic exploitation, as is the case of 19th century colonialism, which drained the resources of territories without promoting the socio-economic development of their inhabitants.

Improving georeferencing accuracy of Very High Resolution satellite imagery using freely available ancillary data at global coverage

ABSTRACT While impressive direct geolocation accuracies better than 5.0 m CE90 (90% of circular error) can be achieved from the last DigitalGlobe’s Very High Resolution (VHR) satellites (i.e. GeoEye-1 and WorldView-1/2/3/4), it is insufficient for many precise geodetic applications. For these sensors, the best horizontal geopositioning accuracies (around 0.55 m CE90) can be attained by using third-order 3D rational functions with vendor’s rational polynomial coefficients data refined by a zero-order polynomial adjustment obtained from a small number of very accurate ground control points (GCPs). However, these high-quality GCPs are not always available. In this work, two different approaches for improving the initial direct geolocation accuracy of VHR satellite imagery are proposed. Both of them are based on the extraction of three-dimensional GCPs from freely available ancillary data at global coverage such as multi-temporal information of Google Earth and the Shuttle Radar Topography Mission 30 m digital elevation model. The application of these approaches on WorldView-2 and GeoEye-1 stereo pairs over two different study sites proved to improve the horizontal direct geolocation accuracy values around of 75%.

Optimizing multiresolution segmentation for extracting plastic greenhouses from worldview-3 imagery

Multiresolution segmentation (MRS) has been pointed out as one of the most successful image segmentation algorithms within the object-based image analysis (OBIA) framework. The performance of this algorithm depends on the selection of three tuning parameters (scale, shape and compactness) and the bands combination and weighting considered. In this work, we tested MRS on a WorldView-3 bundle imagery in order to extract plastic greenhouse polygons. A recently published command line tool created to assess the quality of segmented digital images (AssesSeg), which implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2), was used to select both the best aforementioned MRS parameters and the optimum image data source derived from WorldView-3 (i.e., panchromatic, multispectral and atmospherically corrected multispectral orthoimages). The best segmentation results were always attained from the atmospherically corrected multispectral WorldView-3 orthoimage.

Assessing Shoreline Change Rates in Mediterranean Beaches

Shoreline change rate constitutes an essential parameter for coastal areas management and monitoring in order to map erosion/accretion areas and to forecast the future shoreline position. Here, shoreline rates were assessed in a heavily human influenced coastal sector of the Mediterranean coast located at Almeria province, Spain. In order to evaluate shoreline rate change assessment in Mediterranean beaches, a comparison was carried out between three methods applied throughout 2009 to 2011 period. In this sense, two kinds of sources were used in order to derive shoreline positions: (i) digitizing the high water line (HWL) through orthoimage interpretation and (ii) automatically extracting a contour level from a LiDAR-derived coastal elevation model (CEM). Shoreline extraction quality was studied by comparing HWL and two datum-based contours, one extrapolated up to 0 m and the other interpolated at 0.75 m above mean sea level (Spanish altimetric datum). It was found a significant bias between HWL and datum-based shoreline positions which had been qualified as negligible in other previous studies carried out in microtidal areas. Since HWL and 0.75 m contour-based shorelines showed a similar distribution, although presenting an added offset, and the 0 m contour was too noisy because of extrapolation errors, it was concluded that the 0.75 m contour-based shoreline was the most stable and accurate proxy datum for multitemporal shorelines comparison. Finally, a high variability of shoreline position could be tested when HWL was used as a proxy for shoreline, being HWL less accurate than CEM-derived shorelines except for the case of using poorly accurate photogrammetrically derived CEMs (e.g. based on very old aerial flights).

The integration of multi-source remote sensing data for the modelling of shoreline change rates in a mediterranean coastal sector

ABSTRACT A novel methodological approach is presented to estimate the shoreline change rate in complex coastal settings by using multi-source/multi-temporal shoreline data extracted from both orthoimages and digital elevation models. Several stages are covered to integrate the information available for the coastal area under study by means of a well-balanced and robust data fusion approach: i) determining the most accurate approach for extracting each shoreline from the different available sources, also estimating their corresponding accuracy, ii) finding out the best set of multi-temporal shorelines, within the available ones, to help avoid temporal oversampling and remove local severe shoreline change rate oscillations and, finally, iii) testing linear regression methods to include shoreline accuracy and automatic outlier removal in order to model the underlying general trend of shoreline evolution. A reweighted-weighted linear regression together with an evenly distributed shorelines dataset were chosen as the best approach to robustly integrate all the multisource remote sensing data available and determine which shorelines did not follow the general linear trend.

Remote sensing as a complementary tool for monitoring the effects of agricultural policies: The case of the irrigated area of Tadla Azilal (Morocco)

Agricultural policies are human driving forces that can influence various processes within the landscape due to land-use assignation. Along this work, an innovative methodological framework based on remote sensing techniques is proposed for the analysis of the effects coming from the implementation of any change in agricultural production and for diagnosing the sustainability of irrigated agricultural systems located at arid regions in developing countries. In this sense, the main goal of this paper lies in proposing an efficient and reliable methodology for the multitemporal mapping of cultivated areas at a regional scale and the calculation of socio-economic performance. The undergoing hypothesis is that the emerging “object-based image analysis” techniques could be successfully applied on medium resolution satellite images such as Landsat series. This approach has been tested on a representative region of intensive cultivation in arid areas such as the irrigated area of Tadla Azilal (central Morocco). The application of the developed methodology has allowed helping, as a complementary tool, in strengthening the underlying hypothesis of a relative failure of the liberalization of agricultural production sector and the refunding of the code of agricultural investment after nearly thirty years of its application. In accordance with this hypothesis, yet to be contrasted through other field-based studies, a series of recommendations for improving socio-economic and environmental sustainability of the agricultural system are conducted to serve as guidance for other similar agricultural systems also located in arid areas.