Improving change vector analysis by cross-correlogram spectral matching for accurate detection of land-cover conversion

Time series of vegetation index (VI) information derived from remote sensing is important for land-cover change detection. Although traditional change vector analysis (TCVA) is an effective method for extracting land-cover change information from a time series of VI data, it has the disadvantage of being too sensitive to temporal fluctuations in VI values. The method tends to overestimate the changes and confuse the actual land-cover conversion with the land covers that have not been converted but experience significant VI changes. Cross-correlogram spectral matching (CCSM) can tell the degree of shape similarity between VI profiles and be used to detect land-cover conversion. However, this method may omit some land conversion in which the before and after land-cover types are rather similar in VI profile shape but differ significantly in absolute VI values. This article proposes a new approach that improves TCVA with an adapted use of CCSM. First, TCVA is employed for preliminary detection of land-cover changes. Second, the changes caused by temporal fluctuations of VI values are identified through the CCSM analysis and excluded to only keep the most likely land-cover conversions. Finally, classification is performed to map the different types of land-cover conversions. The improved change vector analysis (ICVA) was applied to detect land-cover conversions from 2000 to 2008, using a time series of Moderate Resolution Imaging Spectroradiometer (MODIS) enhanced VI images for the Beijing–Tianjin–Tangshan urban agglomeration district, China. The results show that ICVA is able to detect land-cover conversion with a significantly higher accuracy (78.00%, κ?=?0.56) than TCVA (64.00%, κ?=?0.35) or CCSM (66.60%, κ?=?0.27). The proposed approach is of particular value in distinguishing actual land-cover conversion from land-cover modifications resulting from phenological changes.     

Detecting dwelling destruction in Darfur through object-based change analysis of very high-resolution imagery

Timely and detailed information on the situation in conflict areas is essential to monitor the impact of conflicts on civilians and to document human rights issues, such as large scale displacement. Remote sensing provides valuable means for conflict monitoring, especially in areas where the ground-based documentation of violence is hampered, e.g. by the limited access to or persistent insecurity of conflict zones. The manual analysis of remote-sensing data is time consuming and labour intensive, but automatic methods can increase the efficiency of corresponding workflows, if the required user interference is minimized. In this study, the use of object-based change analysis for the automatic and selective detection of destructed dwellings in bi-temporal images is explored in test areas in Darfur. The presented approach automatically determines areas of interest (settlements), and detects changes in those areas by analysis of two change features (change of edge intensity and spectral change). It applies automatically defined local reference values and thresholds of these change features to reduce the required user interference. In addition, the extended feature space in the object-based approach (including, e.g. shape, size, and relational features in addition to spectral properties) is used to distinguish destructed dwellings from other, similarly changed objects. The developed method was applied to two study areas using images from three different sensors (GeoEye-1, WorldView-2, and QuickBird) without adaptation of the thresholds or rule sets. This resulted in a producer’s accuracy of 75.4% in the first and 81.2% in the second study area. The achieved user’s accuracy was 73.3% in study area 1 and 77.2% in study area 2. The evaluation of the results shows that the automatic calculation of local reference values and thresholds for the change detection can increase robustness when the proposed method is applied on study areas with different image properties. It also demonstrates the advantages as well as the specific constraints of using object- and context-specific features in this use case for the extraction of a certain structure type on a high level of detail.     

Operational land cover change detection using change vector analysis

This research study introduces the use of a change detection and classification algorithm that relies on the change vector analysis (CVA) method. Its implementation aims to ensure adequate response to operational production needs and allow optimized data processing over extended and environmentally complex areas. Automatic change class labelling relies on the use of a (3n+2)‐dimensional feature space, where n denotes the number of sensor bands. Such enhanced feature space allows for a finer and more accurate definition of change classes of the ‘from‐to’ type. Moreover, and to efficiently address the problem of change area overestimation, the proposed method takes into account specific evidence derived from the pixel's geographic neighbourhood, the latter defined as a 3×3 pixel kernel. The performance of this integrated algorithmic approach has been tested and validated in the framework of the CORINE Land Cover‐Greece 2000 and the ESA/GSE Forest Monitoring projects in three test sites located in the outskirts of the city of Ptolemais, Thasos island and the suburbs of Athens in Greece. Its implementation in such highly fragmented and dynamically changing landscape environments has resulted in qualified and accurate land cover change maps, achieving an overall level of classification accuracy of 88–96%. Compared to visual image interpretation, the method requires half the effort. In conclusion, the proposed method has proved effective and can be recommended for use in the framework of operational projects.     

Integrating conceptual and logical couplings for change impact analysis in software

The paper presents an approach that combines conceptual and evolutionary techniques to support change impact analysis in source code. Conceptual couplings capture the extent to which domain concepts and software artifacts are related to each other. This information is derived using Information Retrieval based analysis of textual software artifacts that are found in a single version of software (e.g., comments and identifiers in a single snapshot of source code). Evolutionary couplings capture the extent to which software artifacts were co-changed. This information is derived from analyzing patterns, relationships, and relevant information of source code changes mined from multiple versions in software repositories. The premise is that such combined methods provide improvements to the accuracy of impact sets compared to the two individual approaches. A rigorous empirical assessment on the changes of the open source systems Apache httpd, ArgoUML, iBatis, KOffice, and jEdit is also reported. The impact sets are evaluated at the file and method levels of granularity for all the software systems considered in the empirical evaluation. The results show that a combination of conceptual and evolutionary techniques, across several cut-off points and periods of history, provides statistically significant improvements in accuracy over either of the two techniques used independently. Improvements in F-measure values of up to 14% (from 3% to 17%) over the conceptual technique in ArgoUML at the method granularity, and up to 21% over the evolutionary technique in iBatis (from 9% to 30%) at the file granularity were reported.     

Comparison of pixel- and object-based classification in land cover change mapping

Land use/land cover (LULC) change occurs when humans alter the landscape, and this leads to increasing loss, fragmentation and spatial simplification of habitat. Many fields of study require monitoring of LULC change at a variety of scales. LULC change assessment is dependent upon high-quality input data, most often from remote sensing-derived products such as thematic maps. This research compares pixel- and object-based classifications of Landsat Thematic Mapper (TM) data for mapping and analysis of LULC change in the mixed land use region of eastern Ontario for the period 1995–2005. For single date thematic maps of 10 LULC classes, quantitative and visual analyses showed no significant accuracy difference between the two methods. The object-based method produced thematic maps with more uniform and meaningful LULC objects, but it suffered from absorption of small rare classes into larger objects and the incapability of spatial parameters (e.g. object shape) to contribute to class discrimination. Despite the similar map accuracies produced by the two methods, temporal change maps produced using post-classification comparison (PCC) and analysed using intensive visual analysis of errors of omission and commission revealed that the object-based maps depicted change more accurately than maximum likelihood classification (MLC)-derived change maps.     

Integrating independent component analysis and support vector machine for multivariate process monitoring

This study aims to develop an intelligent algorithm by integrating the independent component analysis (ICA) and support vector machine (SVM) for monitoring multivariate processes. For developing a successful SVM-based fault detector, the first step is feature extraction. In real industrial processes, process variables are rarely Gaussian distributed. Thus, this study proposes the application of ICA to extract the hidden information of a non-Gaussian process before conducting SVM. The proposed fault detector will be implemented via two simulated processes and a case study of the Tennessee Eastman process. Results demonstrate that the proposed method possesses superior fault detection when compared to conventional monitoring methods, including PCA, ICA, modified ICA, ICA–PCA and PCA–SVM.     

Unsupervised change detection using spectral features and a texture difference measure for VHR remote-sensing images

This article proposes an unsupervised change-detection method using spectral and texture information for very-high-resolution (VHR) remote-sensing images. First, a new local-similarity-based texture difference measure (LSTDM) is defined using a grey-level co-occurrence matrix. A mathematical analysis shows that LSTDM is robust with respect to noise and spectral similarity. Second, the difference image is generated by integrating the spectral and texture features. Then, the unsupervised change-detection problem in VHR remote-sensing images is formulated as minimizing an energy function related with changed and unchanged classes in the difference image. A modified expectation-maximization-based active contour model (EMCVM) is applied to the difference image to separate the changed and unchanged regions. Finally, two different experiments are performed with SPOT-5 images and compared with state-of-the-art unsupervised change-detection methods to evaluate the effectiveness of the proposed method. The results indicate that the proposed method can sufficiently increase the robustness with respect to noise and spectral similarity and obtain the highest accuracy among the methods addressed in this article.     

Integrating remotely sensed data,GIS and expert knowledge to update object-based land use/land cover information

Remote-sensing technology provides a powerful means for land use/land cover (LU/LC) monitoring at global and regional scales. However, it is more efficient and effective to combine remote-sensing measurements with a geographic information system (GIS) database and expert knowledge for change updating than to use remote-sensing technology alone. In this article, these different sources of information are integrated in the proposed framework, which is able to provide rapid updating of LU/LC information. An object-based data analysis is adopted for thematic mapping, taking both spectral and spatial properties into consideration. An expert knowledge coding is introduced and combined quantitatively with other evidence provided by remotely sensed data and the GIS database. A case study using Landsat Thematic Mapper (TM) datasets demonstrated an overall successful LU/LC map updating and a satisfactory change detection using the proposed change-updating framework.     

Performance of different spectral and textural aerial photograph features in multi-source forest inventory

Most multi-source forest inventory (MSFI) applications have thus far been based on the use of medium resolution satellite imagery, such as Landsat TM. The high plot and stand level estimation errors of these applications have, however, restricted their use in forest management planning. One reason suggested for the high estimation errors has been the coarse spatial resolution of the imagery employed. Therefore, very high spatial resolution (VHR) imagery sources provide interesting data for stand-level inventory applications. However, digital interpretation of VHR imagery, such as aerial photographs, is more complicated than the use of traditional satellite imagery. Pixel-by-pixel analysis is not applicable to VHR imagery because a single pixel is small in relation to the object of interest, i.e. a forest stand, and therefore it does not adequately represent the spectral properties of a stand. Additionally in aerial photographs, the spectral properties of the objects are dependent on their location in the image. Therefore, MSFI applications based on aerial imagery must employ features that are less sensitive to their location in the image and that have been derived using the spatial neighborhood of each pixel, e.g. a square-shaped window of pixels. In this experiment several spectral and textural features were extracted from color-infrared aerial photographs and employed in estimation of forest attributes. The features were extracted from original, normalized difference vegetation index and channel ratio images. The correlations between the extracted image features and forest attributes measured from sample plots were examined. Additionally, the spectral and textural features were used for estimating the forest attributes of sample plots, applying the k nearest neighbor estimation method. The results show that several spectral and textural image features that are moderately or well correlated with the forest attributes. Furthermore, the accuracy of forest attribute estimation can be significantly improved by a careful selection of image features.     

A new spectrogoniophotometer to measure leaf spectral and directional optical properties

In this paper we present a new spectrogoniophotometer (SGP) dedicated to the assessment of plant leaf bidirectional optical properties. It consists of a mechanical apparatus coupled with an imaging spectrometer using a bidimensional CCD photodetector. Unpolarized light fluxes are sampled at high spectral and directional resolution to provide biconical reflectance and transmittance factors, every nanometer from 500 nm to 880 nm and at 800 source-sensor configurations (four illumination directions by 200 viewing directions covering the whole sphere). From these calibrated measurements we derive the leaf Bidirectional Reflectance and Transmittance Distribution Functions (BRDF and BTDF). The angular-integrated quantities defined as the Directional Hemispherical Reflectance and Transmittance Function (DHRF and DHTF) are also calculated. The first three sections emphasize the instrumental and calibration issues, as well as the radiometric definitions. In the last section we present some experimental results acquired on various monocot and dicot leaves with special attention to surface reflection. The shape, position and magnitude of the specular lobe, which is a characteristic of many leaves in the forward direction, is investigated for beech (Fagus sylvatica L.) and laurel (Prunus laurocerasus L.) using a leaf BRDF model. The width of the specular peak is very variable according to the species and the illumination angle, as well as its contribution to the directional-hemispherical reflectance. Finally, implications in plant physiology or remote sensing are broached.     

Using spectral and textural features from RapidEye images to estimate age and structural parameters of Cerrado vegetation

Cerrado is a savannah biome covering about 60% of the State of Minas Gerais, Brazil, but with a rate of conversion that surpasses that of all other biomes in Brazil. Remote sensing is the only practical means of monitoring the conversion and regeneration of this vegetation formation. The objective of this article is to model the process of regeneration of Cerrado vegetation and to estimate its age using a RapidEye image mosaic and textural features derived from the grey-level co-occurrence matrix. The study area is Parque Estadual Veredas do Peruaçu, a State Park in Minas Gerais, which was a plantation of eucalyptus until 1994 with a broad range of regeneration ages between 15 and 37 years. A total of 47 plots were surveyed for which the exact ages of regeneration are known and other structural variables were measured. Multiple regression and stepwise feature selection were used to create models that explain over 80% of the age, 58% of the crown closure, and 48% of the height of the vegetation. Texture proved essential for capturing the patterns of light and shadow generated by the trees of varying widths and heights.     

Integrating LiDAR and high-resolution imagery for object-based mapping of forest habitats in a heterogeneous temperate forest landscape

ABSTRACT

Land-cover mapping (LCM) at a fine scale would be useful for forest management across heterogeneous natural landscapes. However, the heterogeneity of land covers at such scales results in complex spectral and textural properties that hinder the applicability of LCM. Besides, the method suffers from, e.g. inconsistent representation of different land-cover types, lack of sufficient and balanced training samples, and instability of classifiers trained by a high number of predictor variables. Even well-known object-based classification approaches are challenged with an objective evaluation of segmentation outputs. Here we classified partially ambiguous land-cover types across heterogeneous forest landscapes in the Bavarian Forest National Park (Germany) by combining metrics from airborne light detection and ranging (LiDAR) and colour infrared (CIR) imagery data and a random forest classifier implemented in an object-based paradigm. We evaluated the segmentation results by creating a global quality score based on inter- and intra-measurements of variance and the number of segments. Selected segmentation outputs were combined with balanced training samples to run the classification algorithm based on representative blocks within the national park. The entire processing chain was implemented in an open-source domain. The final segmentation consisted of LiDAR-based height, image-based Normalized Difference Vegetation Index (NDVI) and red band, with 20 cluster seeds and a minimum segment size of 40 pixels. In the classification, the most important variables included the height of the top layer, NDVI, Enhanced Vegetation Index (EVI) and Green–Red Vegetation Index (GRVI). The average values of 500 random forest runs indicated an overall accuracy of 86.6% and an estimated Cohen’s kappa coefficient of 85.2%, with different probabilities of correct classification for land-cover classes. Mature deciduous, standing deadwood, fallen deadwood, meadow, and bare soil classes were classified most accurately, whereas classification of young coniferous, intermediate-age coniferous, mature coniferous, young deciduous, and intermediate-age deciduous were associated with the highest uncertainties. Our methodology is sufficiently robust to be applied to other similarly structured sites across temperate forested landscapes. The versatility of the method is partially guaranteed by the proposed segmentation quality score, which satisfactorily corrects under- and over-segmentation.     

Use of a dark object concept and support vector machines to automate forest cover change analysis

An automated method was developed for mapping forest cover change using satellite remote sensing data sets. This multi-temporal classification method consists of a training data automation (TDA) procedure and uses the advanced support vector machines (SVM) algorithm. The TDA procedure automatically generates training data using input satellite images and existing land cover products. The derived high quality training data allow the SVM to produce reliable forest cover change products. This approach was tested in 19 study areas selected from major forest biomes across the globe. In each area a forest cover change map was produced using a pair of Landsat images acquired around 1990 and 2000. High resolution IKONOS images and independently developed reference data sets were available for evaluating the derived change products in 7 of those areas. The overall accuracy values were over 90% for 5 areas, and were 89.4% and 89.6% for the remaining two areas. The user's and producer's accuracies of the forest loss class were over 80% for all 7 study areas, demonstrating that this method is especially effective for mapping major disturbances with low commission errors. IKONOS images were also available in the remaining 12 study areas but they were either located in non-forest areas or in forest areas that did not experience forest cover change between 1990 and 2000. For those areas the IKONOS images were used to assist visual interpretation of the Landsat images in assessing the derived change products. This visual assessment revealed that for most of those areas the derived change products likely were as reliable as those in the 7 areas where accuracy assessment was conducted. The results also suggest that images acquired during leaf-off seasons should not be used in forest cover change analysis in areas where deciduous forests exist. Being highly automatic and with demonstrated capability to produce reliable change products, the TDA-SVM method should be especially useful for quantifying forest cover change over large areas.     

Multiscale spectral analysis for detecting short and long range change points in time series

Identifying short and long range change points in an observed time series that consists of stationary segments is a common problem. These change points mark the time boundaries of the segments where the time series leaves one stationary state and enters another. Due to certain technical advantages, analysis is carried out in the frequency domain to identify such change points in the time domain. What is considered as a change may depend on the time scale. The results of the analysis are displayed in the form of graphs that display change points on different time horizons (time scales), which are observed to be statistically significant. The methodology is illustrated using several simulated and real time series data. The method works well to detect change points and illustrates the importance of analysing the time series on different time horizons.     

Segmentation parameter selection for object-based land-cover mapping from ultra high resolution spectral and elevation data

Segmentation is the primary task for image analysis in many practical applications, such as object-based image analysis. Segmentation algorithms need to have properly estimated parameters to provide efficient performance and reliable results. Due to the fact that some features have different shapes and spectral characteristics, it is hard to find the proper parameters for the whole image. In this article, we propose a new method for resolving this issue through the building of a hierarchy of segmentations, based on the number of land-cover classes in the image, namely segmentation scale space (SSS). Both spectral and elevation data are employed in order to enhance the SSS and to obtain a single segmentation for the image. The performance of the proposed algorithm is evaluated using two data sets, which consist of ultra-high resolution aerial images and elevation data with ground sampling distance of 5 and 9 cm, respectively. The experiments demonstrate the efficiency of enhanced segmentation with respect to over and under segmentation cases. Finally, the comparative analysis shows that the accuracy of the proposed method is superior to the classical methods.     

Linguistic continuous ordered weighted distance measure and its application to multiple attributes group decision making

This paper develops a new method for group decision making and introduces a linguistic continuous ordered weighted distance (LCOWD) measure. It is a new distance measure that combines the linguistic continuous ordered weighted averaging (LCOWA) operator with the ordered weighted distance (OWD) measure considering the risk attitude of decision maker. Moreover, it also can relieve the influence of extremely large or extremely small deviations on the aggregation results by assigning them smaller weights. These advantages make it suitable to deal with the situations where the input arguments are represented with uncertain linguistic information. Some of the main properties of the LCOWD measure and different particular cases are studied. The applicability of the new approach is also analyzed focusing on a group decision making problem.     

An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution

Tracking land cover changes using remotely-sensed data contributes to evaluating to what extent human activities impact the environment. Recent studies have pointed out some limitations of single-date comparisons between years and have emphasized the usefulness of time series. However, less effort has hitherto been dedicated to properly account for the temporal dependences typifying the successive images of a time series. An automated change detection method based on a per-object approach and on a probabilistic procedure is proposed here to better cope with this issue. This innovative procedure is applied to a tropical forest environment using high temporal resolution SPOT-VEGETATION time series from 2001 and 2004 in the Brazilian state of Rondônia. The principle of the method is to identify the objects that most deviate from an unchanged reference defined by objective rules. A probabilistic changed-unchanged threshold provides a change map where each object is associated with a likelihood of having changed. This improvement on a binary diagnostic makes the method relevant to meet the requirements of different users, ranging from a comprehensive detection of changes to a detection of the most dramatic changes. According to the threshold value, overall accuracy indices of up to 91% were obtained, with errors involving change omissions for the most part. The isolation of changes within objects was made possible through a segmentation procedure implemented in a temporal context. In addition, the method was formulated so as to differentiate between inter- and intra-annual vegetation dynamics. These technical peculiarities will likely make this analytical framework suitable for detecting changes in environments subject to a strongly marked phenology.     

Segmentation optimization and stratified object-based analysis for semi-automated geomorphological mapping

Semi-automated geomorphological mapping techniques are gradually replacing classical techniques due to increasing availability of high-quality digital topographic data. In order to efficiently analyze such large amounts of data, there is a need for optimizing the processing of automated mapping techniques. In this context, we present a novel approach to semi-automatically map alpine geomorphology using stratified object-based image analysis. We used a 1 m Digital Terrain Model (DTM) derived from laser altimetry data from a mountainous catchment from which we calculated various Land-Surface Parameters (LSPs). The LSPs ‘slope angle’ and ‘topographic openness’ have been combined into a single composite layer for selecting reference material and delineating training samples. We developed a novel method to semi-automatically assess segmentation results by comparing 2D frequency distribution matrices of training samples and image objects. The segmentation accuracy assessment allowed us to automate optimization of the scale parameter and LSPs used for segmentation. We concluded that different geomorphological feature types have different sets of optimal segmentation parameters. The feature-dependent parameters were used in a new approach of stratified feature extraction for classifying karst, glacial, fluvial and denudational landforms. In this way, we have used stratified object-based image analysis to semi-automatically extract contrasting geomorphological features from high-resolution digital terrain data. A further step would be to also automate the optimization of classification rules. We would then be able to create a library of feature characteristics that could be transferred and applied to other mountain regions and further automate geomorphological mapping strategies.     

Integrating multi-temporal spectral and structural information to map wetland vegetation in a lower Connecticut River tidal marsh

This study examines the effectiveness of using multi-temporal satellite imagery, field spectral data, and LiDAR top of canopy data to classify and map the common plant communities of the Ragged Rock Creek marsh, located near the mouth of the Connecticut River. Visible to near-infrared (VNIR) reflectance spectra were measured in the field over the 2004–2006 growing seasons to assess the phenological variability of the dominant marsh plant species, Spartina patens, Phragmites australis and Typha spp. Phragmites was best distinguished from other species by its high NIR response late in the growing season. Typha spp. had a high red/green ratio and S. patens had a unique green/blue ratio relative to other species throughout the bulk of the growing season. The field spectra and single date (2004) LiDAR canopy height data were used to define an object-oriented classification methodology for the three plant communities in multi-temporal QuickBird multispectral imagery collected over the same time interval. The classification was validated using an extensive field inventory of marsh species. Overall maximum fuzzy accuracy for the classification was 97% for Phragmites, 63% for Typha spp. and 80% for S. patens meadows and improved to 97%, 76%, and 92%, respectively, using a fuzzy acceptable match measure. This study demonstrated the importance of the timing of image acquisition for the identification of targeted plant species in a heterogeneous marsh. These datasets and protocols may provide coastal resource managers, municipal officials and researchers a set of recommended guidelines for remote sensing data collection for marsh inventory and monitoring.