Object-based Method Research Articles

Object-Based Classification of Urban Distinct Sub-Elements Using High Spatial Resolution Orthoimages and DSM Layers

This paper aims to assess the ways in which multi-resolution object-based classification methods can be used to group urban environments made up of a mixture of buildings, sub-elements such as car parks, roads, shades and pavements and foliage such as grass and trees. This involves using both unmanned aerial vehicles (UAVs) which provide high-resolution mosaic Orthoimages and generate a Digital Surface Model (DSM). For the study area chosen for this paper, 400 Orthoimages with a spatial resolution of 7 cm each were used to build the Orthoimages and DSM, which were georeferenced using well distributed network of ground control points (GCPs) of 12 reference points (RMSE = 8 cm). As these were combined with onboard RTK-GNSS-enabled 2-frequency receivers, they were able to provide absolute block orientation which had a similar accuracy range if the data had been collected by traditional indirect sensor orientation. Traditional indirect sensor orientation involves the GNSS receiver in the UAV receiving a differential signal from the base station through a communication link. This allows for the precise position of the UAV to be established, as the RTK uses correction, allowing position, velocity, altitude and heading to tracked, as well as the measurement of raw sensor data. By assessing the results of the confusion matrices, it can be seen that the overall accuracy of the object-oriented classification was 84.37%. This has an overall Kappa of 0.74 and the data that had poor classification accuracy included shade, parking lots and concrete pavements. These had a producer accuracy (precision) of 81%, 74% and 74% respectively, while lakes and solar panels each scored 100% in comparison, meaning that they had good classification accuracy.

An Integrated Framework for Road Detection in Dense Urban Area from High-Resolution Satellite Imagery and Lidar Data

Automatic road detection, in dense urban areas, is a challenging application in the remote sensing community. This is mainly because of physical and geometrical variations of road pixels, their spectral similarity to other features such as buildings, parking lots and sidewalks, and the obstruction by vehicles and trees. These problems are real obstacles in precise detection and identification of urban roads from high-resolution satellite imagery. One of the promising strategies to deal with this problem is using multi-sensors data to reduce the uncertainties of detection. In this paper, an integrated object-based analysis framework was developed for detecting and extracting various types of urban roads from high-resolution optical images and Lidar data. The proposed method is designed and implemented using a rule-oriented approach based on a masking strategy. The overall accuracy (OA) of the final road map was 89.2%, and the kappa coefficient of agreement was 0.83, which show the efficiency and performance of the method in different conditions and interclass noises. The results also demonstrate the high capability of this object-based method in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite images and Lidar data.

An Object-Based Method for Sharing Secret High-Dynamic-Range Images

With the popularity of the Internet, how to securely transmit and store multimedia data, and effectively access them has become an issue of great concern. High-dynamic-range (HDR) images are predicted to be a future trend and have already received considerable attention. In this study, an object-based method for sharing secret HDR images is proposed. This method comprised three steps. First, HDR images were divided into several objects and the coordinates of the objects and related information were recorded. Second, a method for sharing secret images was used to share the produced objects and recorded information, which were ranked according to importance. Third, a Lagrange interpolation method was used to reconstruct the various objects. The method can be used to maintain high information security and provide a convenient and effective image-restoration method to users. Experimental results confirmed the effectiveness of the method proposed in this study.

Mapping urban impervious surface using object-based image analysis with WorldView-3 satellite imagery

Land use and land cover (LULC) data are important to monitor and assess environmental change. LULC classification using satellite images is a method widely used on a global and local scale. Especially, urban areas that have various LULC types are important components of the urban landscape and ecosystem. This study aims to classify urban LULC using WorldView-3 (WV-3) very high-spatial resolution satellite imagery and the object-based image analysis method. A decision rules set was applied to classify the WV-3 images in Kathu subdistrict, Phuket province, Thailand. The main steps were as follows: (1) the image was ortho-rectified with ground control points and using the digital elevation model, (2) multiscale image segmentation was applied to divide the image pixel level into image object level, (3) development of the decision ruleset for LULC classification using spectral bands, spectral indices, spatial and contextual information, and (4) accuracy assessment was computed using testing data, which sampled by statistical random sampling. The results show that seven LULC classes (water, vegetation, open space, road, residential, building, and bare soil) were successfully classified with overall classification accuracy of 94.14% and a kappa coefficient of 92.91%.

Spatial assessment of intertidal seagrass meadows using optical imaging systems and a lightweight drone

Seagrass ecosystems are highly sensitive to environmental change. They are also in global decline and under threat from a variety of anthropogenic factors. There is now an urgency to establish robust monitoring methodologies so that changes in seagrass abundance and distribution in these sensitive coastal environments can be understood. Typical monitoring approaches have included remote sensing from satellites and airborne platforms, ground based ecological surveys and snorkel/scuba surveys. These techniques can suffer from temporal and spatial inconsistency, or are very localised making it hard to assess seagrass meadows in a structured manner. Here we present a novel technique using a lightweight (sub 7 kg) drone and consumer grade cameras to produce very high spatial resolution (∼4 mm pixel−1) mosaics of two intertidal sites in Wales, UK. We present a full data collection methodology followed by a selection of classification techniques to produce coverage estimates at each site. We trialled three classification approaches of varying complexity to investigate and illustrate the differing performance and capabilities of each. Our results show that unsupervised classifications perform better than object-based methods in classifying seagrass cover. We also found that the more sparsely vegetated of the two meadows studied was more accurately classified - it had lower root mean squared deviation (RMSD) between observed and classified coverage (9–9.5%) compared to a more densely vegetated meadow (RMSD 16–22%). Furthermore, we examine the potential to detect other biotic features, finding that lugworm mounds can be detected visually at coarser resolutions such as 43 mm pixel−1, whereas smaller features such as cockle shells within seagrass require finer grained data (<17 mm pixel−1).

Large scale mapping: an empirical comparison of pixel-based and object-based classifications of remotely sensed data

In the past, large scale mapping was carried using precise ground survey methods. Later, paradigm shift in data collection using medium to low resolution and, recently, high resolution images brought to bear the problem of accurate data analysis and fitness-for-purpose challenges. Using high resolution satellite images such as QuickBird and IKONOS are now preferred alternatives. This paper is aimed at comparing pixel-based (PIXBIA) and Geo-object-based (GEOBIA) classification methods using ENVI 4.8 and eCongnition software respectively, and ArcGIS 10.1 for map layout creation. It uses Aba main city in south-eastern Nigeria as a case study. The paper further evaluates the classification accuracies obtained using error matrix and then test the classifications’ agreement to geographic reality using Kappa Coefficient statistical analysis. Analyzing 2012 QuickBird image as a proof of concept, the study shows that the object-based approach had a higher overall accuracy (OA= 98.75%) than the pixel-based approach (OA=79.44%). With a Kappa Coefficient of K=0.97 (very good) for object-based approach and K=0.62 (good) for pixel-based, the object-based method showed a higher class separability between and among examined geographic objects such as water, bare-land and tree canopy as evidenced in the Golf Course under re-construction in Aba city. In addition, the object-based results also show a higher overall producer accuracy (PA=98.42% &gt; PA=85.37) and user accuracy (UA=96.70 &gt; UA=81.04%) respectively. The paper, therefore, recommends that object-based classification method be applied in analyzing high resolution satellite image. The approach is also recommended for mapping urban areas in developing countries such as Nigeria where the paucity of fund required in flying airplane for the production of orthophotos is a major challenge in large scale mapping.Keywords: Image Classification, Object-based Classification, Pixel-based Classification, Remote Sensing, Urban Planning and Mapping.

Spatial verification approaches as a tool to evaluate the performance of high resolution precipitation forecasts

The spatial resolution of Numerical Weather Prediction (NWP) models has increased significantly in recent years. While high-resolution models are able to produce more detailed precipitation structures, their true benefit lies in more realistic statistics rather than the information provided for a specific grid point. Unfortunately, NWP model verification using traditional grid-point-by-grid-point methods has not managed to keep pace due to the limited amount of point observations available in comparable resolution. Spatial verification methods represent a possible solution since they reward closeness or resemblance by relaxing the requirement for exact matches between the forecast and observations.An intense convective event in the Mediterranean region is used as a test case to analyze the forecasting performance of the Consortium for Small-scale Modeling model (COSMO) at two different resolutions. Satellite estimates of precipitation are used as ground truth. The precipitation forecasts are assessed using various spatial methods and averaging techniques, each of which provides distinctly useful information on model performance.The results from this particular test case indicate that a neighbourhood verification framework as well as the use of the Structure, Amplitude and Location (SAL) index, which belongs to the object-based methods, can identify the scales and precipitation thresholds at which the fine resolution configuration (COSMO-GR3) provides more accurate forecasts than the coarser resolution configuration (COSMO-GR7) and is therefore worth the additional computational burden. Additional insight is gained by comparing the results of various spatial methods with traditional verification metrics based on point observations. Finally, it is demonstrated that the interpolation method used in the adaptation of data at various scales can, in some cases, influence verification results as much as model resolution.

Characterization of particulate matter deposited on urban tree foliage: A landscape analysis approach

Plants can mitigate ambient particulate matter by cleaning the air, which is crucial to urban environments. A novel approach was presented to quantitatively characterize particulate matter deposited on urban tree foliage. This approach could accurately quantify the number, size, shape, and spatial distribution of particles with different diameters on leaves. Spatial distribution is represented by proximity, which measures the closeness of particles. We sampled three common broadleaf species and obtained images through field emission scanning electron microscopy. We conducted the object-based method to extract particles from images. We then used Fragstats to analyze the landscape characteristics of these particles in term of selected metrics. Results reveal that Salix matsudana is more efficient than Ailanthus altissima and Fraxinus chinensis in terms of the number and area of particles per unit area and the proportion of fine particulate matter. The shape complexity of the particles increases with their size. Among the three species, S. matsudana and A. altissima particles respectively yield the highest and lowest proximity. PM1 in A. altissima and PM10 in F. chinensis and S. matsudana show the highest proximity, which may influence subsequent particle retention. S. matsudana should be generally considered to collect additional small particles. Different species and particle sizes exhibit various proximities, which should be further examined to elucidate the underlying mechanism.

A comparison of pixel-based decision tree and object-based Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data

ABSTRACTPrecisely monitoring land cover/use is crucial for urban environmental assessment and management. Various classification techniques such as pixel-based and object-based approaches have advantages and disadvantages. In this article, based on our experiment data from an unmanned platform carried lidar scanner system and camera, we explored and compared classification accuracies of pixel-based decision tree (DT) and object-based Support Vector Machine (SVM) approaches. Lidar height information can improve classification accuracy based on either object-based SVM or pixel-based DT. From total classification accuracy, object-based SVM was higher than that of pixel-based DT classification, and total accuracy and kappa coefficient of the former were 92.71% and 0.899, respectively. However, pixel-based DT outperformed object-based SVM when classifying small ‘scatter’ tree along roads. Additionally, in order to evaluate the accuracy of pixel-based DT and object-based SVM, we added benchmark data of ISPRS to compare the classification results of two methods. Object-based SVM classification methods by combining aerial imagery with lidar height information can achieve higher classification accuracy. And, accurately extracting tree class of different landscape pattern should select appropriate machine-learning algorithms. Comparison of the results on two methods will provide a reference for selecting a particular classification approaches according to local conditions.

Automatic Counting of Large Mammals from Very High Resolution Panchromatic Satellite Imagery

Estimating animal populations by direct counting is an essential component of wildlife conservation and management. However, conventional approaches (i.e., ground survey and aerial survey) have intrinsic constraints. Advances in image data capture and processing provide new opportunities for using applied remote sensing to count animals. Previous studies have demonstrated the feasibility of using very high resolution multispectral satellite images for animal detection, but to date, the practicality of detecting animals from space using panchromatic imagery has not been proven. This study demonstrates that it is possible to detect and count large mammals (e.g., wildebeests and zebras) from a single, very high resolution GeoEye-1 panchromatic image in open savanna. A novel semi-supervised object-based method that combines a wavelet algorithm and a fuzzy neural network was developed. To discern large mammals from their surroundings and discriminate between animals and non-targets, we used the wavelet technique to highlight potential objects. To make full use of geometric attributes, we carefully trained the classifier, using the adaptive-network-based fuzzy inference system. Our proposed method (with an accuracy index of 0.79) significantly outperformed the traditional threshold-based method (with an accuracy index of 0.58) detecting large mammals in open savanna.

Toward an operational framework for fine-scale urban land-cover mapping in Wallonia using submeter remote sensing and ancillary vector data

Encouraged by the EU INSPIRE directive requirements and recommendations, the Walloon authorities, similar to other EU regional or national authorities, want to develop operational land-cover (LC) and land-use (LU) mapping methods using existing geodata. Urban planners and environmental monitoring stakeholders of Wallonia have to rely on outdated, mixed, and incomplete LC and LU information. The current reference map is 10-years old. The two object-based classification methods, i.e., a rule- and a classifier-based method, for detailed regional urban LC mapping are compared. The added value of using the different existing geospatial datasets in the process is assessed. This includes the comparison between satellite and aerial optical data in terms of mapping accuracies, visual quality of the map, costs, processing, data availability, and property rights. The combination of spectral, tridimensional, and vector data provides accuracy values close to 0.90 for mapping the LC into nine categories with a minimum mapping unit of 15 m2. Such a detailed LC map offers opportunities for fine-scale environmental and spatial planning activities. Still, the regional application poses challenges regarding automation, big data handling, and processing time, which are discussed.

Enhanced change detection index for disaster response, recovery assessment and monitoring of buildings and critical facilities—A case study for Muzzaffarabad, Pakistan

The availability of Very High Resolution (VHR) optical sensors and a growing image archive that is frequently updated, allows the use of change detection in post-disaster recovery and monitoring for robust and rapid results. The proposed semi-automated GIS object-based method uses readily available pre-disaster GIS data and adds existing knowledge into the processing to enhance change detection. It also allows targeting specific types of changes pertaining to similar man-made objects such as buildings and critical facilities. The change detection method is based on pre/post normalized index, gradient of intensity, texture and edge similarity filters within the object and a set of training data. More emphasis is put on the building edges to capture the structural damage in quantifying change after disaster. Once the change is quantified, based on training data, the method can be used automatically to detect change in order to observe recovery over time in potentially large areas. Analysis over time can also contribute to obtaining a full picture of the recovery and development after disaster, thereby giving managers a better understanding of productive management and recovery practices. The recovery and monitoring can be analyzed using the index in zones extending from to epicentre of disaster or administrative boundaries over time.

Classification of Soil Types Using Geographic Object-Based Image Analysis and Random Forests

There is increasing interest in developing automatic procedures to segment landscapes into soil spatial entities that replace conventional, expensive manual procedures for delineating and classifying soils. Geographic object-based image analysis (GEOBIA) partitions remote sensing imagery or digital elevation models into homogeneous image objects based on image segmentation. We used an object-based methodology for the detailed delineation and classification of soil types using digital maps of topography and vegetation as soil covariates, based on the Random Forests (RF) classifier. We compared the object-based method's results with those of a pixel-based classification using the same classifier. We used 18 digital elevation model derivatives and 5 remote sensing indices that were related to vegetation cover and soil. Using 171 soil profiles with their associated environmental variable values, the RF method was used to identify the most important soil type predictors for use in the segmentation process. A stack of raster-geodatasets corresponding to the selected predictors was segmented using a multi-resolution segmentation algorithm, which resulted in homogeneous objects related to soil types. These objects were further classified as soil types using the same method, RF. We also conducted a pixel-based classification using the same classifier and soil profiles, and the resulting maps were assessed in terms of their accuracy using 30% of the soil profiles for validation. We found that GEOBIA was an effective method for soil type mapping, and was superior to the pixel-based approach. The optimized object-based soil map had an overall accuracy of 58%, which was 10% higher than that of the optimized pixel-based map.

Sub-pixel vs. super-pixel-based greenspace mapping along the urban–rural gradient using high spatial resolution Gaofen-2 satellite imagery: a case study of Haidian District, Beijing, China

ABSTRACTGreenspace in urban areas is closely related to urban ecosystems, economy, culture, and society. Recently, rapid urban development and expansion are always dominated by a series of human–environment interactions, which can lead to various spatial patterns of urban greenspace especially along the urban–rural gradient. Urban–rural greenspace mapping is therefore of great importance to provide a comprehensive insight for urban planners and managers. In our study, we adopted both the sub-pixel and super-pixel strategies to map the greenspace in Haidian District, Beijing, China. Specifically, the fully constrained linear spectral unmixing and object-based classification methods were implemented as the representatives of sub-pixel and super-pixel strategies, respectively. The high spatial resolution Gaofen-2 multispectral imagery collected in September, 2015 was used in this study. The results showed that the overall accuracies of greenspace mapping by the super-pixel method were higher than those by the sub-pixel method in the selected dense urban, sub-urban, and rural subsets. Obviously, the super-pixel method was more advantageous for mapping greenspace from the high spatial resolution imagery, especially for patches of greenspace in rural and mountain areas. When further comparing these two methods using the medium spatial resolution Landsat-8 imagery, we concluded that the sub-pixel method failed to keep the same levels of greenspace mapping accuracies as those using the high spatial resolution Gaofen-2 imagery but outperformed the super-pixel method especially in the dense urban and sub-urban subsets due to their high degrees of greenspace fragmentation. Furthermore, the sub-pixel method also demonstrated its merits in terms of automation and operability compared to the super-pixel method.

Object-based cloud detection of multitemporal high-resolution stationary satellite images

Satellite remote sensing that utilizes highly accurate cloud detection is important for monitoring natural disasters. The GaoFen-4, China’s first high-resolution stationary satellite, was recently launched and acquires imagery at a spatial resolution of 50 m and a high temporal resolution (up to 10 min). An object-based cloud detection method was conducted for a time series of GaoFen-4 images. The cloudy objects were obtained from the individual images, and the outlier detection of multiple temporal objects was further processed for refinement. In the initial cloud detection, the objects were segmented by the mean-shift algorithm, and their morphological features were extracted by extended attribute profiles. The threshold-detected cloudy objects were trained according to spectral and morphological features, and the initial objects were classified as cloudy or clear by a regularized least-squares classifier. Furthermore, the medians and standard deviations of the classified cloudy and clear objects were calculated and subsequently refined by the outlier detection of multiple temporal images. The clear object features deviated more than a multiple of standard deviations from the medians of the clear objects that were classified as cloudy objects. Additionally, the refined clear objects were obtained by a similar outlier detection method. Flood event monitoring using GaoFen-4 images showed that the average overall accuracy of the initial cloud detection was 83.4% and increased to 93.3% after refinement. This object-based cloud detection method was insensitive to variations in land objects and can effectively improve cloud detection within small or thin areas, which can be helpful for the monitoring of natural disasters.

Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada

ABSTRACTNewfoundland and Labrador (NL) is the only province in Atlantic Canada that does not have a wetland inventory system. As a consequence, both classifying and monitoring wetland areas are necessary for wetland conservation and human services in the province. In this study, wetlands in 5 pilot sites, distributed across NL, were classified using multi-source and multi-temporal optical remote sensing images. The procedures involved the application of an object-based method to segment and classify the images. To classify the areas, 5 different machine learning algorithms were examined. The results showed that the Random Forest (RF) algorithm in combination with an object-based approach was the most accurate method to classify wetlands. The average producer and user accuracies of wetland classes considering all pilot sites were 68% and 73%, respectively. The overall classification accuracies, which considered the accuracy of all wetland and non-wetland classes varied from 86% to 96% across all pilot sites confirming the robustness of the methodology despite the biological, ecological, and geographical differences among the study areas. Additionally, we assessed the effects of the tuning parameters on the accuracy of results, as well as the difference between pixel-based and object-based methods for wetland classification in this study.

The application of discriminant analysis for mapping cereals and pasture using object-based features

ABSTRACTHigh mapping accuracies occur where crops differ spectrally (e.g.>90.0%; canola, corn, soybeans) and vice versa (e.g. <75.0%; cereals and pasture). Developing improved mapping methods has been an ongoing priority of Agriculture and Agri-Food Canada (AAFC) remote-sensing science. To this end, this study tests a data-driven object-based classification method using Discriminant Analysis (DA) method for mapping cereals and pasture from satellite data. In this approach, variables (number >400) derived from the image segmentation and object-based feature extraction of multi-date and multi-band optical (RapidEye) and microwave (RADARSAT-2) imagery were applied in a data-driven approach. We use in situ and satellite information collected over two study sites with different levels of heterogeneity (Winnipeg, Brandon) situated in the Canadian Prairies during the 2013 growing season to assess: (a) the type of DA model that most accurately classifies the cereals and pasture cover classes; and (b) how the classification accuracies obtained by the application of this DA model compare to those obtained from more traditional Maximum Likelihood (ML), Decision Tree (DT), and Random Forest (RF) classifications. We found that our DA-based approach was able to map cereals and pastures at our two study sites with the highest accuracies, but these accuracies did not improve significantly with the use of more complex DA model (including priori classification probabilities, more input principle components (PCs), the use of weights proportional to field area). Our results are encouraging for the wider application of the data-driven pre-processing of the inputs to the image classification by DA.

A shadow identification method using vegetation indices derived from hyperspectral data

ABSTRACTShadows in high-spatial-resolution remote-sensing images become more pronounced. The detection of shadows is an essential requirement for both detailed high-spatial land-cover classification and applications such as three-dimensional (3D) reconstruction of buildings as well as cloud removal. This article presents a method for integrating the photochemical reflectance index (PRI) and Red Edge normalized difference vegetation index (RENDVI) for shadow identification (IPRSI) using high-spatial-resolution airborne hyperspectral data. This method detects shadows by setting thresholds to the PRI and RENDVI to separate shadows from vegetated and non-vegetated areas. The proposed method outperformed the invariant colour spaces model and the object-based method in terms of shadow extraction accuracy. The overall shadow identification accuracy of the IPRSI was 88.97% with an F-score of 90.96 (81.32% with F-score 81.97 for the invariant colour spaces model and 78.02% with F-score 82.07 for the object-based method). The IPRSI is a potential method with the wide application of hyperspectral data in high spatial resolution that is increasingly easier to be obtained with the development of remote-sensing platforms (such as unmanned aerial vehicles (UAVs), small satellites, and airships).

Object- and pixel-based classifications of macroalgae farming area with high spatial resolution imagery

Macroalgae plays an important role in coastal ecosystems. The accurate delineation of macroalgae areas is important for environmental management. This study compared the pixel- and object-based methods using Gaofen satellite no. 2 image to explore an efficient classification approach. Expert system rules and nearest neighbour classifier were adopted for object-based classification, whereas maximum likelihood classifier was implemented in the pixel-based approach. Normalized difference vegetation index, normalized difference water index, mean value of the blue band and geometric characteristics were selected as features to distinguish macroalgae farms by considering the spectral and spatial characteristics. Results show that the object-based method achieved a higher overall accuracy and kappa coefficient than the pixel-based method. Moreover, the object-based approach displayed superiority in identifying Porphyra class. These findings suggest that the object-based method can delineate macroalgae farming areas efficiently and be applied in the future to monitor the macroalgae farms with high spatial resolution imagery.

An Improved Pigeon-Inspired Optimization for Clustering Analysis Problems

Clustering is an important technology in data mining, which attempts to partition a set of objects into clusters based on the values of their attributes. [Formula: see text]-means is a simple and efficient data clustering algorithm. However, it highly depends on the initial solution and is extremely easy to be trapped in local optima. In contrast, meta-heuristic algorithms show good performance to break through the local optima obstacle. In this paper, we propose an improved pigeon-inspired optimization (IPIO) algorithm towards resolving this problem. The algorithm uses an object-based initialization method to generate the initial population and introduces a parametric control strategy to navigate the flying direction. Meanwhile, the climb process of monkey algorithm (MA) with dimension by dimension improvement is adopted to strengthen the local search ability. In this paper, experiments over six real datasets are conducted to validate the effectiveness of IPIO. The experimental results show that IPIO is an efficient alternative in resolving the clustering analysis problem.