Object-based Support Vector Machine Research Articles

Rockfall mapping and susceptibility evaluation based on UAV high-resolution imagery and support vector machine method

Abstract This study aims to develop a comprehensive method for automated rockfall mapping and susceptibility assessment using unmanned aerial vehicle (UAV) tilt photography and the support vector machine (SVM) algorithm. By employing Jinzhong Town in the mountainous forest landscapes of Southwest China as a case study, we leverage photogrammetry principles and computer vision algorithms to generate high-precision, high-resolution digital surface models (DSMs), and digital orthophoto maps through a UAV remote sensing system. The rockfall inventory is accurately and automatically mapped using the object-based classification method and SVM algorithm. The automated rockfall identification method achieves a 93% accuracy with a Kappa coefficient of 0.7967. Statistical analyses of spatial distribution characteristics reveal a significant correlation between rockfall volume and area with a correlation coefficient (R²) of 0.92316 under logarithmic coordinates. In addition, a power function relationship describes the link between rockfall volume and slope height (R² = 0.87), while the relationship with sliding distance is characterized by a weaker linear correlation (R² = 0.65). Rockfall runout distance also shows a significant linear correlation with slope height (R² = 0.79) but exhibits a less-pronounced association with rockfall volume (R² = 0.58). The SVM model employed to assess rockfall susceptibility indicates high accuracy (area under the curve = 0.896), affirming its efficacy in rockfall susceptibility assessment. Our findings underscore the utility of UAV remote sensing for rockfall information extraction and susceptibility evaluation, particularly in challenging mountainous forest environments characterized by intricate topography and geological complexities.

Identification of Pasture Degradation Using Remote Sensing Data and Machine Learning: A Case Study of Obichnik

The degradation of pastures and meadows is a global problem with a wide range of impacts. It affects farmers in different ways, such as decreases in cattle production, milk yield, and forage quality. Still, it also has other side effects, such as loss of biodiversity, loss of resources, etc. In this study, the degradation of a semi-natural pasture near the village of Obichnik, Bulgaria, was evaluated using machine learning algorithms, and an unmanned aerial vehicle (UAV) obtained visual spectrum images. A high-quality (HQ) orthomosaic of the area was created and numerous regions of interest were manually marked for training and validation purposes. Three machine learning algorithms were used—Maximum likelihood, Random trees (RT), and Support Vector Machine (SVM). Furthermore, object-based and pixel-based approaches were utilized. The obtained results indicate that the object-based RT and SVM models provide significantly better accuracy, with their Cohen’s Kappa reaching 0.86 and 0.82, respectively. The performed classification showed that approximately 61% of the investigated pasture area is covered with grass, which indicates light-to-medium degradation.

Towards reliable monitoring of grass species in nature conservation: Evaluation of the potential of UAV and PlanetScope multi-temporal data in the Central European tundra

The reliability of remote sensing technology is essential for its efficient operational applications in nature conservation practices. In our study, multi-temporal, multispectral, and hyperspectral data from an Unoccupied Aerial Vehicle (UAV) with a ground sampling distance (GSD) of 3 cm were applied to a permanent research plot (1 ha), while spaceborne PlanetScope multi-temporal data with GSD of 3 m were used for a wider area of 250 ha. The main aim of the study was to evaluate the potential of these data for monitoring vegetation at the species level in the Central European relict arcto-alpine tundra (in the Krkonoše Mountains, Czech Republic). We evaluated both types of data and their performance for various classifiers, and the benefits of adding multi-temporal aspects to the classification and robustness of remote sensing for monitoring grass species. This study addresses the requirements of nature conservation practices in the Krkonoše Mts. National Park to find a suitable method for monitoring changes in dominant and expanding grass species in response to global warming. The object-based Support Vector Machine, pixel-based Random Forest and Maximum Likelihood classifiers were evaluated. We confirmed that the UAV multispectral and hyperspectral data with GSD of 3 cm can monitor dominant grass species (Nardus stricta, Calamagrostis villosa, Molinia caerulea, Deschampsia cespitosa) in tundra with excellent accuracy (95.9% and 94.0% overall accuracy for multi-temporal and mono-temporal composites, respectively). The best F1-scores for these species ranged from 94.7 to 99.4%. However, the accuracies were substantially lower for small and sparse growing species (Avenella flexuosa and Carex bigelowii). Unexpectedly, the UAV multispectral and hyperspectral data yielded comparable results. The multi-temporal approach improved the accuracy of all types of data. Overall, we confirmed the robustness of the remote sensing approach for grass monitoring at the species level given the high spatial match between various classification outputs. Our study established a workflow for reliable monitoring of tundra grass vegetation according to the requirements of nature conservation and proposed innovative measures for the spatial accuracy assessment of classification outputs.

Comparing Machine Learning Algorithms for Pixel/Object-Based Classifications of Semi-Arid Grassland in Northern China Using Multisource Medium Resolution Imageries

Knowledge of grassland classification in a timely and accurate manner is essential for grassland resource management and utilization. Although remote sensing imagery analysis technology is widely applied for land cover classification, few studies have systematically compared the performance of commonly used methods on semi-arid native grasslands in northern China. This renders the grassland classification work in this region devoid of applicable technical references. In this study, the central Xilingol (China) was selected as the study area, and the performances of four widely used machine learning algorithms for mapping semi-arid grassland under pixel-based and object-based classification methods were compared: random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and naive Bayes (NB). The features were composed of the Landsat OLI multispectral data, spectral indices, Sentinel SAR C bands, topographic, position (coordinates), geometric, and grey-level co-occurrence matrix (GLCM) texture variables. The findings demonstrated that (1) the object-based methods depicted a more realistic land cover distribution and had greater accuracy than the pixel-based methods; (2) in the pixel-based classification, RF performed the best, with OA and Kappa values of 96.32% and 0.95, respectively. In object-based classification, RF and SVM presented no statistically different predictions, with OA and Kappa exceeding 97.5% and 0.97, respectively, and both performed significantly better than other algorithms. (3) In pixel-based classification, multispectral bands, spectral indices, and geographic features significantly distinguished grassland, whereas, in object-based classification, multispectral bands, spectral indices, elevation, and position features were more prominent. Despite the fact that Sentinel 1 SAR variables were chosen as an effective variable in object-based classification, they made no significant contribution to the grassland distinction.

Landscape Analysis of Cobalt Mining Activities from 2009 to 2021 Using Very High Resolution Satellite Data (Democratic Republic of the Congo)

The cobalt mining sector is well positioned to be a key contributor in determining the success of the Democratic Republic of the Congo (DRC) in meeting the Sustainable Development Goals (SDGs) by 2030. Despite the important contribution to the DRC’s economy, the rapid expansion of mining operations has resulted in major social, health, and environmental impacts. The objective of this study was to quantitatively assess the cumulative impact of mining activities on the landscape of a prominent cobalt mining area in the DRC. To achieve this, an object-based method, employing a support vector machine (SVM) classifier, was used to map land cover across the city of Kolwezi and the surrounding mining areas, where long-term mining activity has dramatically altered the landscape. The research used very high resolution (VHR) satellite imagery (2009, 2014, 2019, 2021) to map the spatial distribution of land cover and land cover change, as well as analyse the spatial relationship between land cover classes and visually identified mine features, from 2009 to 2021. Results from the object-based SVM land cover classification produced an overall accuracy of 85.2–90.4% across the time series. Between 2009 and 2021, land cover change accounted to: rooftops increasing by 147.2% (+7.7 km2); impervious surface increasing by 104.7% (+3.35 km2); bare land increasing by 85.4% (+33.81 km2); exposed rock increasing by 56.2% (+27.46 km2); trees decreasing by 4.5% (−0.34 km2); shrub decreasing by 38.4% (−26.04 km2); grass and cultivated land decreasing by 27.1% (−45.65 km2); and water decreasing by 34.6% (−3.28 km2). The co-location of key land cover classes and visually identified mine features exposed areas of potential environmental pollution, with 91.6% of identified water situated within a 1 km radius of a mine feature, and vulnerable populations, with 71.6% of built-up areas (rooftop and impervious surface class combined) situated within a 1 km radius of a mine feature. Assessing land cover patterns over time and the interplay between mine features and the landscape structure allowed the study to amplify the findings of localised on-the-ground research, presenting an alternative viewpoint to quantify the true scale and impact of cobalt mining in the DRC. Filling geospatial data gaps and examining the present and past trends in cobalt mining is critical for informing and managing the sustainable growth and development of the DRC’s mining sector.

A PROCEDURE FOR IDENTIFYING INVASIVE WILD PARSNIP PLANTS BASED ON VISIBLE BANDS FROM UAV IMAGES

Abstract. Wild parsnip is an invasive plant that has serious health risks to humans due to the toxin in its sap. Monitoring its presence has been a challenging task for conservation authorities due to its small size and irregular shape. Unmanned Aerial Vehicles (UAV) can obtain ultra-high resolution (UHR) imagery and have been used for vegetation monitoring in recent years. In this study, UAV images captured at Lemoine Point Conservation Area in Kingston, Ontario, are used to test a methodology for distinguishing wild parsnip. The objective of this study is to develop an efficient invasive wild parsnip classification workflow based on UHR digital UAV imagery. Image pre-processing flow includes image orientation, digital elevation model (DEM) and digital surface model (DSM) extractions, and orthomosaicking using Simactive’s software. Three vegetation indices and three texture features are calculated and added to the mosaicked images as additional bands. Image analysis frameworks namely pixel- and object-based method and three classifiers are tested and the object-based Support Vector Machine (SVM) is selected to distinguish wild parsnip from other vegetation types. The optimal image resolutions are undertaken by comparing accuracy assessments. The results provide an executable workflow to distinguish wild parsnip and show that UAV images, with a simple digital camera, are an appropriate and economic resource for small and irregular vegetation detection. This method yields reliable and valid outcomes in detecting wild parsnip plants and demonstrates excellent performance in mapping small vegetation.

Correction of training process in object-based image interpretation via knowledge based system capabilities

For accurate interpretation of high-resolution images, correct training-samples are required to model the decision-making process for data classification. The automatic production of that is an important step; however, the control and correction, whether at the level of pruning the wrong data or resolving their defects, should be considered. Accordingly, in this research, a hybrid (combined deductive and inductive) interpretation system by modeling and improving the training processing was proposed for very high-resolution images. In other words, an automatic knowledge-based method is performed to apply the modeling of the ontological relationships in order to train and control the object-based support vector machine classification. In the correction process, sequence stages including automatic separation and expanding the training data and the ontology properties of the target classes for improving the defect of training data were used. Finally, high-resolution test images are used to validate the results and evaluate the method. In this respect, the proposed method is tested in different implementation cases and compared with other algorithms in each step. The experimental results indicate the reliability and efficiency of the proposed method.

Comparison of pixel- and object-based image analysis for tea plantation mapping using hyperspectral Gaofen-5 and synthetic aperture radar data

Accurately mapping tea plantation distribution is crucial to environmental protection and sustainable development. Hyperspectral and synthetic aperture radar (SAR) data have recently been widely used in land cover classification, but their ability to extract tea plantation regions still needs to be confirmed. Compared with traditional pixel-based image analysis (PBIA), object-based image analysis (OBIA) for tea plantation mapping is more worthy of implementation. This study explored the performance of Gaofen-5 (GF-5) and copolarized SAR data for tea plantation mapping using pixel- and object-based support vector machine algorithms in Wuyishan, China. Comparison of PBIA and OBIA demonstrated the significant differences in visual effect and classification accuracy. The object-based classifications especially offered a more contiguous depiction with fewer speckles of tea plantations than pixel-based classifications did. Moreover, object-based classifications improved overall accuracy (OA) between 1.7% and 7.9% in all scenarios when compared to pixel-based classifications. As for datasets, classifications using only GF-5 data obtained an OA of over 85%, while fusing images decreased classification accuracy due to the lower separability between tea and forest, showcasing that the fusion of hyperspectral and SAR data does not guarantee the improvement of classification accuracy. The integration of GF-5, horizontal transmit and horizontal receive (HH), and vertical transmit and vertical receive (VV) polarized data outperformed other data combinations in both pixel- and object-based classifications and achieved the highest OA (95.58%) in OBIA, with a 98.13% producer accuracy and 93.34% user accuracy of tea plantations. The results indicated OBIA could overcome the shortcomings of the PBIA and effectively improve the mapping accuracy of tea plantation, and OBIA integrating GF-5, HH, and VV polarized data could play a distinguished role in tea plantation mapping. This work provides a promising approach for mapping tea plantations and demonstrates that the integration of GF-5 and copolarized data can improve spectral separability of vegetation, which is also significant for general forest mappings.

Evaluation of Features Derived from High-Resolution Multispectral Imagery and LiDAR Data for Object-Based Support Vector Machine Classification of Tree Species

Remote sensing can play a key role in understanding the make-up of urban forests. This study analyzes how high-resolution Geoeye-1 multispectral imagery and LiDAR point clouds allow for improved classification of urban tree species using object-based and support vector machine classification (SVM). Five common urban trees are classified: Acer platanoides; Acer platanoides ‘Schwedleri’; Picea pungens; Gleditsia triacanthos; and Tilia cordata. Numerous features are used for classification: index derived from imagery reflectance; texture of imagery; LiDAR height and intensity; and a LiDAR-generated normalized digital surface model. Classification is performed to evaluate the contribution of individual features, groups of features, and the combination of features from both imagery and LiDAR data. Classification results in an overall accuracy of 85.08% when features from both data sources are combined, compared with 77.73% when using only LiDAR features, and 71.85% when using only imagery features.

Comparing Pixel-Based Random Forest and the Object-Based Support Vector Machine Approaches to Map the Quasi-Circular Vegetation Patches Using Individual Seasonal Fused GF-1 Imagery

The seasonal effect on land cover classification has been widely recognized. It is important to use the imagery acquired at key points of vegetation phenological development to obtain a higher classification accuracy for land cover. This study compared the effect of seasons on landscape classification and the quasi-circular vegetation patches (QVPs) detection from four fused Gaofen 1 images acquired in the different seasons by using the pixel-based random forest (RF) and object-based support vector machine (SVM) methods over the Yellow River Delta, China. The results from this study demonstrated that the seasonal effect on classifying landscapes and detecting the QVPs is significant, especially for the pixel-based RF method. The object-based SVM method was more appropriate for classifying landscape from the non-growing season images, while the pixel-based RF approach was more suitable for classifying the growing-season images. The spring data (April imagery; overall accuracy = 99.8%) and the winter data (February imagery; F measure = 65.9%) yielded the best results for landscape classification and QVP detection, respectively, by using the object-based SVM approach. Therefore, in practice, we recommend the use of February to April imagery with the object-based SVM approach to map the QVPs in the future.

A hybrid OSVM-OCNN Method for Crop Classification from Fine Spatial Resolution Remotely Sensed Imagery

Accurate information on crop distribution is of great importance for a range of applications including crop yield estimation, greenhouse gas emission measurement and management policy formulation. Fine spatial resolution (FSR) remotely sensed imagery provides new opportunities for crop mapping at a detailed level. However, crop classification from FSR imagery is known to be challenging due to the great intra-class variability and low inter-class disparity in the data. In this research, a novel hybrid method (OSVM-OCNN) was proposed for crop classification from FSR imagery, which combines a shallow-structured object-based support vector machine (OSVM) with a deep-structured object-based convolutional neural network (OCNN). Unlike pixel-wise classification methods, the OSVM-OCNN method operates on objects as the basic units of analysis and, thus, classifies remotely sensed images at the object level. The proposed OSVM-OCNN harvests the complementary characteristics of the two sub-models, the OSVM with effective extraction of low-level within-object features and the OCNN with capture and utilization of high-level between-object information. By using a rule-based fusion strategy based primarily on the OCNN’s prediction probability, the two sub-models were fused in a concise and effective manner. We investigated the effectiveness of the proposed method over two test sites (i.e., S1 and S2) that have distinctive and heterogeneous patterns of different crops in the Sacramento Valley, California, using FSR Synthetic Aperture Radar (SAR) and FSR multispectral data, respectively. Experimental results illustrated that the new proposed OSVM-OCNN approach increased markedly the classification accuracy for most of crop types in S1 and all crop types in S2, and it consistently achieved the most accurate accuracy in comparison with its two object-based sub-models (OSVM and OCNN) as well as the pixel-wise SVM (PSVM) and CNN (PCNN) methods. Our findings, thus, suggest that the proposed method is as an effective and efficient approach to solve the challenging problem of crop classification using FSR imagery (including from different remotely sensed platforms). More importantly, the OSVM-OCNN method is readily generalisable to other landscape classes and, thus, should provide a general solution to solve the complex FSR image classification problem.

WorldView-2 Data for Hierarchical Object-Based Urban Land Cover Classification in Kigali: Integrating Rule-Based Approach with Urban Density and Greenness Indices

The emergence of high-resolution satellite data, such as WorldView-2, has opened the opportunity for urban land cover mapping at fine resolution. However, it is not straightforward to map detailed urban land cover and to detect urban deprived areas, such as informal settlements, in complex urban environments based merely on high-resolution spectral features. Thus, approaches integrating hierarchical segmentation and rule-based classification strategies can play a crucial role in producing high quality urban land cover maps. This study aims to evaluate the potential of WorldView-2 high-resolution multispectral and panchromatic imagery for detailed urban land cover classification in Kigali, Rwanda, a complex urban area characterized by a subtropical highland climate. A multi-stage object-based classification was performed using support vector machines (SVM) and a rule-based approach to derive 12 land cover classes with the input of WorldView-2 spectral bands, spectral indices, gray level co-occurrence matrix (GLCM) texture measures and a digital terrain model (DTM). In the initial classification, confusion existed among the informal settlements, the high- and low-density built-up areas, as well as between the upland and lowland agriculture. To improve the classification accuracy, a framework based on a geometric ruleset and two newly defined indices (urban density and greenness density indices) were developed. The novel framework resulted in an overall classification accuracy at 85.36% with a kappa coefficient at 0.82. The confusion between high- and low-density built-up areas significantly decreased, while informal settlements were successfully extracted with the producer and user’s accuracies at 77% and 90% respectively. It was revealed that the integration of an object-based SVM classification of WorldView-2 feature sets and DTM with the geometric ruleset and urban density and greenness indices resulted in better class separability, thus higher classification accuracies in complex urban environments.

Finer Resolution Mapping of Marine Aquaculture Areas Using WorldView-2 Imagery and a Hierarchical Cascade Convolutional Neural Network

Marine aquaculture plays an important role in seafood supplement, economic development, and coastal ecosystem service provision. The precise delineation of marine aquaculture areas from high spatial resolution (HSR) imagery is vital for the sustainable development and management of coastal marine resources. However, various sizes and detailed structures of marine objects make it difficult for accurate mapping from HSR images by using conventional methods. Therefore, this study attempts to extract marine aquaculture areas by using an automatic labeling method based on the convolutional neural network (CNN), i.e., an end-to-end hierarchical cascade network (HCNet). Specifically, for marine objects of various sizes, we propose to improve the classification performance by utilizing multi-scale contextual information. Technically, based on the output of a CNN encoder, we employ atrous convolutions to capture multi-scale contextual information and aggregate them in a hierarchical cascade way. Meanwhile, for marine objects with detailed structures, we propose to refine the detailed information gradually by using a series of long-span connections with fine resolution features from the shallow layers. In addition, to decrease the semantic gaps between features in different levels, we propose to refine the feature space (i.e., channel and spatial dimensions) using an attention-based module. Experimental results show that our proposed HCNet can effectively identify and distinguish different kinds of marine aquaculture, with 98% of overall accuracy. It also achieves better classification performance compared with object-based support vector machine and state-of-the-art CNN-based methods, such as FCN-32s, U-Net, and DeeplabV2. Our developed method lays a solid foundation for the intelligent monitoring and management of coastal marine resources.

Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data

We use freely available Sentinel-2 data and forest inventory data to evaluate the potential of different machine-learning approaches to classify tree species in two forest regions in Bavaria, Germany. Atmospheric correction was applied to the level 1C data, resulting in true surface reflectance or bottom of atmosphere (BOA) output. We developed a semiautomatic workflow for the classification of deciduous (mainly spruce trees), beech and oak trees by evaluating different classification algorithms (object- and pixel-based) in an architecture optimized for distributed processing. A hierarchical approach was used to evaluate different band combinations and algorithms (Support Vector Machines (SVM) and Random Forest (RF)) for the separation of broad-leaved vs. coniferous trees. The Ebersberger forest was the main project region and the Freisinger forest was used in a transferability study. Accuracy assessment and training of the algorithms was based on inventory data, validation was conducted using an independent dataset. A confusion matrix, with User´s and Producer´s Accuracies, as well as Overall Accuracies, was created for all analyses. In total, we tested 16 different classification setups for coniferous vs. broad-leaved trees, achieving the best performance of 97% for an object-based multitemporal SVM approach using only band 8 from three scenes (May, August and September). For the separation of beech and oak trees we evaluated 54 different setups, the best result achieved an accuracy of 91% for an object-based, SVM, multitemporal approach using bands 8, 2 and 3 of the May scene for segmentation and all principal components of the August scene for classification. The transferability of the model was tested for the Freisinger forest and showed similar results. This project points out that Sentinel-2 had only marginally worse results than comparable commercial high-resolution satellite sensors and is well-suited for forest analysis on a tree-stand level.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Mapping Mangrove Forests Based on Multi-Tidal High-Resolution Satellite Imagery

Mangrove forests, which are essential for stabilizing coastal ecosystems, have been suffering from a dramatic decline over the past several decades. Mapping mangrove forests using satellite imagery is an efficient way to provide key data for mangrove forest conservation. Since mangrove forests are periodically submerged by tides, current methods of mapping mangrove forests, which are normally based on single-date, remote-sensing imagery, often underestimate the spatial distribution of mangrove forests, especially when the images used were recorded during high-tide periods. In this paper, we propose a new method of mapping mangrove forests based on multi-tide, high-resolution satellite imagery. In the proposed method, a submerged mangrove recognition index (SMRI), which is based on the differential spectral signature of mangroves under high and low tides from multi-tide, high-resolution satellite imagery, is designed to identify submerged mangrove forests. The proposed method applies the SMRI values, together with textural features extracted from high-resolution imagery and geographical features of mangrove forests, to an object-based support vector machine (SVM) to map mangrove forests. The proposed method was evaluated via a case study with GF-1 images (high-resolution satellites launched by China) in Yulin City, Guangxi Zhuang Autonomous Region of China. The results show that our proposed method achieves satisfactory performance, with a kappa coefficient of 0.86 and an overall accuracy of 94%, which is better than results obtained from object-based SVMs that use only single-date, remote sensing imagery.

Exploring the Potential of Sentinels-1 & 2 of the Copernicus Mission in Support of Rapid and Cost-effective Wildfire Assessment

The present study explores the use of the recently launched Sentinel-1 and -2 data of the Copernicus mission in wildfire mapping with a particular focus on retrieving information on burnt area, burn severity as well as in quantifying soil erosion changes. As study area, the Sierra del Gata wildfire occurred in Spain during the summer of 2015 was selected. First, diverse image processing algorithms for burnt area extraction from Sentinel-2 data were evaluated. In the next step, burn severity maps were derived from Sentinel-2 data alone, and the synergy between Sentinel-2 & Sentinel-1 for this purpose was evaluated. Finally, the impact of the wildfire to soil erodibility estimates derived from the Revised Universal Soil Loss Equation (RUSLE) model implemented to the acquired Sentinel images was explored. In overall, the Support Vector Machines (SVMs) classifier obtained the most accurate burned area mapping, with a derived accuracy of 99.38%. An object-based SVMs classification using as input both optical and radar data was the most effective approach of delineating burn severity, achieving an overall accuracy of 92.97%. Soil erosion mapping predictions allowed quantifying the impact of wildfire to soil erosion at the studied site, suggesting the method could be potentially of a wider use. Our results contribute to the understanding of wildland fire dynamics in the context of the Mediterranean ecosystem, demonstrating the usefulness of Sentinels and of their derived products in wildfire mapping and assessment.

Improving Landslide Detection from Airborne Laser Scanning Data Using Optimized Dempster–Shafer

A detailed and state-of-the-art landslide inventory map including precise landslide location is greatly required for landslide susceptibility, hazard, and risk assessments. Traditional techniques employed for landslide detection in tropical regions include field surveys, synthetic aperture radar techniques, and optical remote sensing. However, these techniques are time consuming and costly. Furthermore, complications arise for the generation of accurate landslide location maps in these regions due to dense vegetation in tropical forests. Given its ability to penetrate vegetation cover, high-resolution airborne light detection and ranging (LiDAR) is typically employed to generate accurate landslide maps. The object-based technique generally consists of many homogeneous pixels grouped together in a meaningful way through image segmentation. In this paper, in order to address the limitations of this approach, the final decision is executed using Dempster–Shafer theory (DST) rule combination based on probabilistic output from object-based support vector machine (SVM), random forest (RF), and K-nearest neighbor (KNN) classifiers. Therefore, this research proposes an efficient framework by combining three object-based classifiers using the DST method. Consequently, an existing supervised approach (i.e., fuzzy-based segmentation parameter optimizer) was adopted to optimize multiresolution segmentation parameters such as scale, shape, and compactness. Subsequently, a correlation-based feature selection (CFS) algorithm was employed to select the relevant features. Two study sites were selected to implement the method of landslide detection and evaluation of the proposed method (subset “A” for implementation and subset “B” for the transferrable). The DST method performed well in detecting landslide locations in tropical regions such as Malaysia, with potential applications in other similarly vegetated regions.

OBJECT-ORIENTED CLASSIFICATION OF LIDAR DATA FOR POST-EARTHQUAKE DAMAGE DETECTION

Abstract. The collapse of buildings during the earthquake is a major cause of human casualties. Furthermore, the threat of earthquakes will increase with growing urbanization and millions of people will be vulnerable to earthquakes. Therefore, building damage detection has gained increasing attention from the scientific community. The advent of Light Detection And Ranging (LiDAR) technique makes it possible to detect and assess building damage in the aftermath of earthquake disasters using this data. The purpose of this paper is to propose and implement an object-based approach for mapping destructed buildings after an earthquake using LiDAR data. For this purpose, first, multi-resolution segmentation of post-event LiDAR data is done after building extraction from pre-event building vector map. Then obtained image objects from post-event LiDAR data is located on the pre-event satellite image. After that, appropriate features, which make a better difference between damage and undamaged buildings, are calculated for all the image objects on both data. Finally, appropriate training samples are selected and imported into the object-based support vector machine (SVM) classification technique for detecting the building damage areas. The proposed method was tested on the data set after the 2010 earthquake of Port-au-Prince, Haiti. Quantitative evaluation of results shows the overall accuracy of 92 % by this method.

Pixel-Wise vs. Object-Based Impervious Surface Analysis from Remote Sensing: Correlations with Land Surface Temperature and Population Density

Impervious surface areas (ISA) are heavily influenced by urban structure and related structural features. We examined the effects of object-based impervious surface spatial pattern analysis on land surface temperature and population density in Guangzhou, China, in comparison to classic per-pixel analyses. An object-based support vector machine (SVM) and a linear spectral mixture analysis (LSMA) were integrated to estimate ISA fraction using images from the Chinese HJ-1B satellite for 2009 to 2011. The results revealed that the integrated object-based SVM-LSMA algorithm outperformed the traditional pixel-wise LSMA algorithm in classifying ISA fraction. More specifically, the object-based ISA spatial patterns extracted were more suitable than pixel-wise patterns for urban heat island (UHI) studies, in which the UHI areas (landscape surface temperature >37 °C) generally feature high ISA fraction values (ISA fraction >50%). In addition, the object-based spatial patterns enable us to quantify the relationship of ISA with population density (correlation coefficient >0.2 in general), with global human settlement density (correlation coefficient >0.2), and with night-time light map (correlation coefficient >0.4), and, whereas pixel-wise ISA did not yield significant correlations. These results indicate that object-based spatial patterns have a high potential for UHI detection and urbanization monitoring. Planning measures that aim to reduce the urbanization impacts and UHI intensities can be better supported.