Mapping vegetation community types in a highly disturbed landscape: integrating hierarchical object-based image analysis with lidar-derived canopy height data

Focusing on the semi-arid and highly disturbed landscape of San Clemente Island (SCI), California, we test the effectiveness of incorporating a hierarchical object-based image analysis (OBIA) approach with high-spatial resolution imagery and canopy height surfaces derived from light detection and ranging (lidar) data for mapping vegetation communities. The hierarchical approach entailed segmentation and classification of fine-scale patches of vegetation growth forms and bare ground, with shrub species identified, and a coarser-scale segmentation and classification to generate vegetation community maps. Such maps were generated for two areas of interest on SCI, with and without vegetation canopy height data as input, primarily to determine the effectiveness of such structural data on mapping accuracy. Overall accuracy is highest for the vegetation community map derived by integrating airborne visible and near-infrared imagery having very high spatial resolution with the lidar-derived canopy height data. The results demonstrate the utility of the hierarchical OBIA approach for mapping vegetation with very high spatial resolution imagery, and emphasizes the advantage of both multi-scale analysis and digital surface data for accurately mapping vegetation communities within highly disturbed landscapes.     

Assessment of forest cover in Russia by combining a wall-to-wall coarse-resolution land-cover map with a sample of 30 m resolution forest maps

The process of gathering land-cover information has evolved significantly over the last decade (2000–2010). In addition to this, current technical infrastructure allows for more rapid and efficient processing of large multi-temporal image databases at continental scale. But whereas the data availability and processing capabilities have increased, the production of dedicated land-cover products with adequate accuracy is still a prerequisite for most users. Indeed, spatially explicit land-cover information is important and does not exist for many regions. Our study focuses on the boreal Eurasia region for which limited land-cover information is available at regional level.

The main aim of this paper is to demonstrate that a coarse-resolution land-cover map of the Russian Federation, the ‘TerraNorte’ map at 230 m × 230 m resolution for the year 2010, can be used in combination with a sample of reference forest maps at 30 m resolution to correctly assess forest cover in the Russian federation.

First, an accuracy assessment of the TerraNorte map is carried out through the use of reference forest maps derived from finer-resolution satellite imagery (Landsat Thematic Mapper (TM) sensor). A sample of 32 sites was selected for the detailed identification of forest cover from Landsat TM imagery. A methodological approach is developed to process and analyse the Landsat imagery based on unsupervised classification and cluster-based visual labelling. The resulting forest maps over the 32 sites are then used to evaluate the accuracy of the forest classes of the TerraNorte land-cover map. A regression analysis shows that the TerraNorte map produces satisfactory results for areas south of 65° N, whereas several forest classes in more northern areas have lower accuracy. This might be explained by the strong reflectance of background (i.e. non-tree) cover.

A forest area estimate is then derived by calibration of the TerraNorte Russian map using a sample of Landsat-derived reference maps (using a regression estimator approach). This estimate compares very well with the FAO FRA exercise for 2010 (1% difference for total forested area). We conclude that the TerraNorte map combined with finer-resolution reference maps can be used as a reliable spatial information layer for forest resources assessment over the Russian Federation at national scale.     

Super‐resolution mapping of the waterline from remotely sensed data

Methods for mapping the waterline at a subpixel scale from a soft image classification of remotely sensed data are evaluated. Unlike approaches based on hard classification, these methods allow the waterline to run through rather than between image pixels and so have the potential to derive accurate and realistic representations of the waterline from imagery with relatively large pixels. The most accurate predictions of waterline location were made from a geostatistical approach applied to the output of a soft classification (RMSE = 2.25 m) which satisfied the standards for mapping at 1 : 5000 scale from imagery with a 20 m spatial resolution.     

Estimating area errors for fine‐scale feature‐based ecological mapping

High spatial resolution feature‐based approaches are especially useful for ecological mapping in densely populated landscapes. This paper evaluates errors in estimating ecological map class areas from fine‐scale current (～2002) and historical (～1945) feature‐based ecological mapping by a set of trained interpreters across densely populated rural sites in China based on field‐validated interpretation of high spatial resolution (1 m) imagery. Median overall map accuracy, corrected for chance, was greater than 85% for mapping by trained interpreters, with greater accuracy for current versus historical mapping. An error model based on feature perimeter proved as reliable in predicting 90% confidence intervals for map class areas as did models derived from the conventional error matrix. A conservative error model combining these approaches was developed and tested for statistical reliability in predicting confidence intervals for ecological map class areas from fine‐scale feature‐based mapping by a set of trained interpreters across rural China, providing a practical basis for statistically reliable ecological change detection in densely populated landscapes.     

Super-resolution land-cover mapping using multiple sub-pixel shifted remotely sensed images

Super-resolution land-cover mapping is a promising technology for prediction of the spatial distribution of each land-cover class at the sub-pixel scale. This distribution is often determined based on the principle of spatial dependence and from land-cover fraction images derived with soft classification technology. However, the resulting super-resolution land-cover maps often have uncertainty as no information about sub-pixel land-cover patterns within the low-resolution pixels is used in the model. Accuracy can be improved by incorporating supplemental datasets to provide more land-cover information at the sub-pixel scale; but the effectiveness of this is limited by the availability and quality of these additional datasets. In this paper, a novel super-resolution land-cover mapping technology is proposed, which uses multiple sub-pixel shifted remotely sensed images taken by observation satellites. These satellites take images over the same area once every several days, but the images are not identical because of slight orbit translations. Low-resolution pixels in these remotely sensed images therefore contain different land-cover fractions that can provide useful information for super-resolution land-cover mapping. We have constructed a Hopfield Neural Network (HNN) model to solve it. Maximum spatial dependence is the goal of the proposed model, and the fraction maps of all images are constraints added to the energy function of HNN. The model was applied to synthetic artificial images as well as to a real degraded QuickBird image. The output maps derived from different numbers of images at different zoom factors were compared visually and quantitatively to the super-resolution map generated from a single image. The resulting land-cover maps with multiple remotely sensed images were more accurate than was the single image map. The use of multiple remotely sensed images is therefore a promising method for decreasing the uncertainty of super-resolution land-cover mapping. Moreover, remotely sensed images with similar spatial resolution from different satellite platforms can be used together, allowing a fusion of information obtained from remotely sensed imagery.     

Combining per-pixel and object-based classifications for mapping land cover over large areas

A plethora of national and regional applications need land-cover information covering large areas. Manual classification based on visual interpretation and digital per-pixel classification are the two most commonly applied methods for land-cover mapping over large areas using remote-sensing images, but both present several drawbacks. This paper tests a method with moderate spatial resolution images for deriving a product with a predefined minimum mapping unit (MMU) unconstrained by spatial resolution. The approach consists of a traditional supervised per-pixel classification followed by a post-classification processing that includes image segmentation and semantic map generalization. The approach was tested with AWiFS data collected over a region in Portugal to map 15 land-cover classes with 10 ha MMU. The map presents a thematic accuracy of 72.6 ± 3.7% at the 95% confidence level, which is approximately 10% higher than the per-pixel classification accuracy. The results show that segmentation of moderate-spatial resolution images and semantic map generalization can be used in an operational context to automatically produce land-cover maps with a predefined MMU over large areas.     

Super-resolution mapping using Hopfield Neural Network with panchromatic imagery

Land-cover proportions of mixed pixels can be predicted using soft classification. From the land-cover proportions, a hard land-cover map can be predicted at sub-pixel spatial resolution using super-resolution mapping techniques. It has been demonstrated that the Hopfield Neural Network (HNN) provides a suitable method for super-resolution mapping. To increase the detail and accuracy of the sub-pixel land-cover map, supplementary information at an intermediate spatial resolution can be used. In this research, panchromatic (PAN) imagery was used as an additional source of information for super-resolution mapping. Information from the PAN image was captured by a new PAN reflectance constraint in the energy function of the HNN. The value of the new PAN reflectance constraint was defined based on forward and inverse models with local end-member spectra and local convolution weighting factors. Two sets of simulated and degraded data were used to test the new technique. The results indicate that PAN imagery can be used as a source of supplementary information to increase the detail and accuracy of sub-pixel land-cover maps produced by super-resolution mapping from land-cover proportion images.     

Coastal wetland classification with multiseasonal high-spatial resolution satellite imagery

ABSTRACT

Accurate mapping of wetland distribution is required for wetland conservation, management, and restoration, but remains a challenge due to the complexity of wetland landscapes. This research employed four seasons of multispectral images from Gaofen-1 satellite to map wetland land-cover distribution in Hangzhou bay coastal wetland (245 km²) in China. Maximum likelihood classifier (MLC), random forest (RF), and the expert-based approach were examined based on spectral, spatial, and phenological features. The results showed that land-cover classification accuracies of 83.9% using RF and 90.3% using the expert-based approach were obtained, and they had higher accuracy than MLC, which had an overall accuracy of only 63.3%. The high classification accuracy for nine land-cover classes using the expert-based approach indicated the important role of expert knowledge from the phenological features in improving wetland classification accuracy. As high spatial resolution satellite images become more easily obtainable, effective use of temporal information of different sensor data will be valuable for detailed land-cover classification with higher accuracy. The approach to establish expert rules from multitemporal images provides a new way to improve land-cover classification in different terrestrial ecosystems.     

Comparison of multi-temporal NOAA-AVHRR and SPOT-XS satellite data for mapping land-cover dynamics in the west African Sahel

Abstract

Multi-resolution and multi-temporal remote sensing data (SPOT-XS and AVHRR) were evaluated for mapping local land cover dynamics in the Sahel of West Africa. The aim of this research was to evaluate the agricultural information that could be derived from both high and low spatial resolution data in areas where there is very often limited ground information. A combination of raster-based image processing and vector-based geographical information system mapping was found to be effective for understanding both spatial and spectral land-cover dynamics. The SPOT data proved useful for mapping local land-cover classes in a dominantly recessive agricultural region. The AVHRR-LAC data could be used to map the dynamics of riparian vegetation, but not the changes associated with recession agriculture. In areas where there was a complex mixture of recession and irrigated agriculture, as well as riparian vegetation, the AVHRR data did not provide an accurate temporal assessment of vegetation dynamics.     

Spectral–spatial based sub-pixel mapping of remotely sensed imagery with multi-scale spatial dependence

Sub-pixel mapping (SPM) is a technique used to obtain a land-cover map with a finer spatial resolution than input remotely sensed imagery. Spectral–spatial based SPM can directly apply original remote-sensing images as input to produce fine-resolution land-cover maps. However, the existing spectral–spatial based SPM algorithms only use the maximal spatial dependence principle (calculated at the sub-pixel scale) as the spatial term to describe the local spatial distribution of different land-cover features, which always results in an over-smoothed and discontinuous land-cover map. The spatial dependence can also be calculated at the coarse-pixel scale to maintain the holistic land-cover pattern information of the resultant fine-resolution land-cover map. In this article, a novel spectral–spatial based SPM algorithm with multi-scale spatial dependence is proposed to overcome the limitation in the existing spectral–spatial based SPM algorithms. The objective function of the proposed SPM algorithm is composed of three parts, namely spectral term, sub-pixel scale based spatial term, and coarse-pixel scale based spatial term. Synthetic multi-spectral, degraded Landsat multi-spectral and real IKONOS multi-spectral images are employed in the experiments to validate the performance of the proposed SPM algorithm. The proposed algorithm is evaluated visually and quantitatively by comparing with the hard-classification method and two traditional SRM algorithms including pixel-swapping (PS) and Markov-random-field (MRF) based SPM. The results indicate that the proposed algorithm can generate fine-resolution land-cover maps with higher accuracies and more detailed spatial information than other algorithms.     

Production of Landsat ETM+ reference imagery of burned areas within Southern African savannahs: comparison of methods and application to MODIS

Accurate production of regional burned area maps are necessary to reduce uncertainty in emission estimates from African savannah fires. Numerous methods have been developed that map burned and unburned surfaces. These methods are typically applied to coarse spatial resolution (1 km) data to produce regional estimates of the area burned, while higher spatial resolution (<30 m) data are used to assess their accuracy with little regard to the accuracy of the higher spatial resolution reference data. In this study we aimed to investigate whether Landsat Enhanced Thematic Mapper (ETM+)‐derived reference imagery can be more accurately produced using such spectrally informed methods. The efficacy of several spectral index methods to discriminate between burned and unburned surfaces over a series of spatial scales (ground, IKONOS, Landsat ETM+ and data from the MOderate Resolution Imaging Spectrometer, MODIS) were evaluated. The optimal Landsat ETM+ reference image of burned area was achieved using a charcoal fraction map derived by linear spectral unmixing (k = 1.00, a = 99.5%), where pixels were defined as burnt if the charcoal fraction per pixel exceeded 50%. Comparison of coincident Landsat ETM+ and IKONOS burned area maps of a neighbouring region in Mongu (Zambia) indicated that the charcoal fraction map method overestimated the area burned by 1.6%. This method was, however, unstable, with the optimal fixed threshold occurring at >65% at the MODIS scale, presumably because of the decrease in signal‐to‐noise ratio as compared to the Landsat scale. At the MODIS scale the Mid‐Infrared Bispectral Index (MIRBI) using a fixed threshold of >1.75 was determined to be the optimal regional burned area mapping index (slope = 0.99, r ² = 0.95, SE = 61.40, y = Landsat burned area, x = MODIS burned area). Application of MIRBI to the entire MODIS temporal series measured the burned area as 10 267 km² during the 2001 fire season. The char fraction map and the MIRBI methodologies, which both produced reasonable burned area maps within southern African savannah environments, should also be evaluated in woodland and forested environments.     

A technique for spatial sharpening of thermal imagery of coastal waters and of watercourses

Although satellite thermal infrared (TIR) remote sensing is a valuable tool for the thermal mapping of coastal waters and watercourses, it has many problematic issues, the most important of which are linked to spatial resolution. In the literature, several algorithms for sharpening thermal imagery can be found. Nevertheless, most of them are devoted to land temperature and are not applicable to water–land mixed pixels. In this article, a new algorithm for sharpening water thermal imagery (SWTI) at the water–land boundaries is presented. SWTI is based on the assumption that a relationship exists between the TIR radiance emitted by the pixels of the scene and the fractional water coverage, the fractional non-vegetated soil coverage and a variable describing the presence of vegetated soils. The algorithm works on a pixel by pixel basis and the results are accepted or refused using an analysis of variance (ANOVA) test. SWTI was applied to two Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) scenes acquired on areas where complex water surfaces are present: the delta of the Po river and the lagoon of Venice (Italy). The spatial resolution of ASTER TIR scenes was improved from 90 to 30 m. Different variables were tested to represent vegetated soils, and the SWTI sensitivity to them has been inspected. The performance of SWTI has been studied using visual inspection and statistical and simulation methods. Visual inspection indicated that the spatial enhancement was significant for most of the water surfaces and, in particular, for watercourses. Most of the details with dimension ≥60 m (i.e. 2 pixels at the final spatial resolution) were discernible. Quantitative analysis showed that the algorithm was successfully applicable for 94% and for 84% of the mixed pixels at the water–land boundary in the Po and in the Venice case studies, respectively. Expected and maximum errors were 1 and 1.4 K in the Po case, and 1 and 2.1 K in the Venice case. These values can be considered satisfactory when compared with the ASTER thermal accuracy (1 K). Further research is required to confirm the accuracy and performance analysis using methods based on accurate and higher resolution thermal imagery and on ground measurements.     

Obtaining crop-specific time profiles of NDVI: the use of unmixing approaches for serving the continuity between SPOT-VGT and PROBA-V time series

The study examined the potential of two unmixing approaches for deriving crop-specific normalized difference vegetation index (NDVI) profiles so that upon availability of Project for On-Board Autonomy – Vegetation (PROBA-V) imagery in winter 2013, this new data set can be combined with existing Satellite Pour l’Observation de la Terre – VEGETATION (SPOT-VGT) data despite the differences in spatial resolution (300 m of PROBA-V versus 1 km of SPOT-VGT). To study the problem, two data sets were analysed: (1) a set of 10 temporal NDVI images, with 300 and 1000 m spatial resolution, from the state of São Paulo (Brazil) synthesized from 30 m Landsat Thematic Mapper (TM) images, and (2) a corresponding set of 10 observed Moderate Resolution Imaging Spectroradiometer (MODIS) images (250 m spatial resolution). To mimic the influence of noise on the retrieval accuracy, different sensor/atmospheric noise levels were applied to the first data set. For the unmixing analysis, a high-resolution land-cover (LC) map was used. The LC map was derived beforehand using a different set of Landsat TM images. The map distinguishes nine classes, with four different sugarcane stages, two agricultural sub-classes, plus forest, pasture, and urban/water. Unmixing aiming at the retrieval of crop-specific NDVI profiles was done at administrative level. For the synthesized data set it was demonstrated that the ‘true’ NDVI temporal profiles of different land-cover classes (from 30 m TM data) can generally be retrieved with high accuracy. The two simulated sensors (PROBA-V and SPOT-VGT) and the two unmixing algorithms gave similar results. Analysing the MODIS data set, we also found a good correspondence between the modelled NDVI profiles (both approaches) and the (true) Landsat temporal endmembers.     

Assessing tropical cyclone impacts using object-based moderate spatial resolution image analysis: a case study in Bangladesh

The environmental and societal impacts of tropical cyclones could be reduced using a range of management initiatives. Remote sensing can be a cost effective, accurate, and potential tool for mapping the multiple impacts caused by tropical cyclones using high-to-moderate spatial resolution (5–30 m) satellite imagery to provide data on the following essential parameters – evacuation, relief, and management of natural resources. This study developed and evaluated an approach for assessing the impacts of tropical cyclones through object-based image analysis and moderate spatial resolution imagery. Pre- and post-cyclone maps of artificial and natural features are required for assessing the overall impacts in the landscape that could be acquired by mapping specific land cover types. We used the object-based approach to map land-cover types in pre- and post-cyclone Satellite Pour l’Observation de la Terre (SPOT) 5 image data and the post-classification comparison technique to identify changes in the particular features in the landscape. Cyclone Sidr (2007) was used to test the applicability of this approach in Sarankhola Upazila in Bangladesh. The object-based approach provided accurate results for classifying features from pre- and post-cyclone satellite images with an overall accuracy of 95.43% and 93.27%, respectively. Mapped changes identified the extent, type, and form of cyclone induced impacts. Our results indicate that 63.15% of the study area was significantly affected by cyclone Sidr. The majority of mapped damage was found in vegetation, cropped lands, settlements, and infrastructure. The damage results were verified through the high spatial resolution satellite imagery, reports and pictures that were taken after the cyclone. The methods developed may be used in future to assess the multiple impacts caused by tropical cyclones in Bangladesh and other similar environments for the purposes of tropical cyclone disaster management.     

Evaluating MODIS soil fractional cover for arid regions,using albedo from high-spatial resolution satellite imagery

Broad-scale high-temporal frequency satellite imagery is increasingly used for environmental monitoring. While the normalized difference vegetation index (NDVI) is the most commonly used index to track changes in vegetation cover, newer spectral mixture approaches aim to quantify sub-pixel fractions of photosynthesizing vegetation, non-photosynthesizing vegetation, and exposed soil. Validation of the unmixing products is essential to enable confident use of the products for management and decision-making. The most frequently used validation method is by field data collection, but this is very time consuming and costly, in particular in remote regions where access is difficult.

This study developed and demonstrates an alternative method for quantifying land-cover fractions using high-spatial resolution satellite imagery. The research aimed to evaluate the bare soil fraction in a sub-pixel product, MODIS Fract-G, for the natural arid landscapes of the far west of South Australia. Twenty-two sample regions, of 3400 sampling points each, were investigated across several arid land types in the study area. Albedo thresholds were carefully determined in Advanced Land Observing Satellite Panchromatic Remote-sensing Instrument Stereo Mapping (ALOS PRISM) images (2.5 m spatial resolution), which separated predominantly bare soil from predominantly vegetated or covered soil, and created classified images. Correlation analysis was carried out between MODIS Fract-G bare soil fractional cover and ALOS PRISM bare soil proportions for the same areas. Results showed much lower correlations than expected, though limited agreement was found in some specific areas. It is posited that the Moderate Resolution Imaging Spectroradiometer (MODIS) fractional cover product, which is based on unmixing using the NDVI and a cellulose absorption index (CAI) proxy, may be generally unable to separate soil from vegetation in situations where both indices are low. In addition, separation is hampered by the lack of ‘pure pixels’ in this heterogeneous landscape. This suggests that the MODIS fractional cover product, at least in its present form, is unsuited to monitor sparsely vegetated arid landscapes.     

Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery

Mapping the land-cover distribution in arid and semiarid urban landscapes using medium spatial resolution imagery is especially difficult due to the mixed-pixel problem in remotely sensed data and the confusion of spectral signatures among bare soils, sparse density shrub lands, and impervious surface areas (ISAs hereafter). This article explores a hybrid method consisting of linear spectral mixture analysis (LSMA), decision tree classifier, and cluster analysis for mapping land-cover distribution in two arid and semiarid urban landscapes: Urumqi, China, and Phoenix, USA. The Landsat Thematic Mapper (TM) imagery was unmixed into four endmember fraction images (i.e. high-albedo object, low-albedo object, green vegetation (GV), and soil) using the LSMA approach. New variables from these fraction images and TM spectral bands were used to map seven land-cover classes (i.e. forest, shrub, grass, crop, bare soil, ISA, and water) using the decision tree classifier. The cluster analysis was further used to modify the classification results. QuickBird imagery in Urumqi and aerial photographs in Phoenix were used to assess classification accuracy. Overall classification accuracies of 86.0% for Urumqi and 88.7% for Phoenix were obtained, much higher accuracies than those utilizing the traditional maximum likelihood classifier (MLC). This research demonstrates the necessity of using new variables from fraction images to distinguish between ISA and bare soils and between shrub and other vegetation types. It also indicates the different effects of spatial patterns of land-cover composition in arid and semiarid landscapes on urban land-cover classification.     

Efficiencies of remotely sensed data and sensitivity of grid spacing in sampling and mapping a soil erosion relevant cover factor by cokriging

This study investigates applications and efficiencies of remotely sensed data and the sensitivity of grid spacing for the sampling and mapping of a ground and vegetation cover factor in a monitoring system of soil erosion dynamics by cokriging with Landsat Thematic Mapper (TM) imagery based on regionalized variable theory. The results show that using image data can greatly reduce the number of ground sample plots and sampling cost required for collection of data. Under the same precision requirement, the efficiency gain is significant as the ratio of ground to image data used varies from 1: 1 to 1: 16. Moreover, we proposed and discussed several modifications to the cokriging procedure with image data for sampling and mapping. First, directly using neighbouring pixels for image data in sampling design and mapping is more efficient at increasing the accuracy of maps than using sampled pixels. Although information among neighbouring pixels might be considered redundant, spatial cross-correlation of spectral variables with the cover factor can provide the basis for an increase in accuracy. Secondly, this procedure can be applied to investigate the appropriate spatial resolution of imagery, which, for sampling and mapping the cover factor, should be 90 m?×?90 m – nearly consistent with the line transect size of 100 m used for the ground field survey. In addition, we recommend using the average of cokriging variance to determine the global grid spacing of samples, instead of the maximum cokriging variance.     

Combining medium and coarse spatial resolution satellite data to improve the estimation of sub-pixel NDVI time series

The potential of multitemporal coarse spatial resolution remotely sensed images for vegetation monitoring is reduced in fragmented landscapes, where most of the pixels are composed of a mixture of different surfaces. Several approaches have been proposed for the estimation of reflectance or NDVI values of the different land-cover classes included in a low resolution mixed pixel. In this paper, we propose a novel approach for the estimation of sub-pixel NDVI values from multitemporal coarse resolution satellite data. Sub-pixel NDVIs for the different land-cover classes are calculated by solving a weighted linear system of equations for each pixel of a coarse resolution image, exploiting information about within-pixel fractional cover derived from a high resolution land-use map. The weights assigned to the different pixels of the image for the estimation of sub-pixel NDVIs of a target pixel i are calculated taking into account both the spatial distance between each pixel and the target and their spectral dissimilarity estimated on medium-resolution remote-sensing images acquired in different periods of the year. The algorithm was applied to daily and 16-day composite MODIS NDVI images, using Landsat-5 TM images for calculation of weights and accuracy evaluation.Results showed that application of the algorithm provided good estimates of sub-pixel NDVIs even for poorly represented land-cover classes (i.e., with a low total cover in the test area). No significant accuracy differences were found between results obtained on daily and composite MODIS images. The main advantage of the proposed technique with respect to others is that the inclusion of the spectral term in weight calculation allows an accurate estimate of sub-pixel NDVI time series even for land-cover classes characterized by large and rapid spatial variations in their spectral properties.     

Identifying potential areas of Cannabis sativa plantations using object-based image analysis of SPOT-5 satellite data

The rapid and efficient detection of illicit drug cultivation, such as that of Cannabis sativa, is important in reducing consumption. The objective of this study was to identify potential sites of illicit C. sativa plantations located in the semi-arid, southern part of Pernambuco State, Brazil. The study was conducted using an object-based image analysis (OBIA) of Système Pour l'Observation de la Terre high-resolution geometric (SPOT-5 HRG) images (overpass: 31 May, 2007). OBIA considers the target's contextual and geometrical attributes to overcome the difficulties inherent in detecting illicit crops associated with the grower's strategies to conceal their fields and optimizes the spectral information extracted to generate land-cover maps. The capabilities of the SPOT-5 near-infrared and shortwave infrared bands to discriminate herbaceous vegetation with high water content, and employment of the support vector machine classifier, contributed to accomplishing this task. Image classification included multiresolution segmentation with an algorithm available in the eCognition Developer software package. In addition to a SPOT-5 HRG multispectral image with 10 m spatial resolution and a panchromatic image with 2.5 m spatial resolution, first-order indices such as the normalized difference vegetation index and ancillary data including land-cover classes, anthropogenic areas, slope, and distance to water sources were also employed in the OBIA. The classification of segments (objects) related to illegal cultivation employed fuzzy logic and fixed-threshold membership functions to describe the following spectral, geometrical, and contextual properties of targets: vegetation density, topography, neighbourhood, and presence of water supplies for irrigation. The results of OBIA were verified from a weight of evidence analysis. Among 15 previously known C. sativa sites identified during police operations conducted on 5–17 June 2007, eight sites were classified as maximum-alert areas (total area of 22.54 km² within a total area of object-oriented image classification of ～1800 km²). The approach proposed in this study is feasible for reducing the area to be searched for illicit cannabis cultivation in semi-arid regions.