Multiresolution Segmentation Method Research Articles

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Accurate mapping of mangrove forests is crucial for understanding their ecosystem function and developing effective management policies. However, the absence of an operational multi-feature fusion approach and an ensemble classification system restricts the achievement of this goal. This study aims to develop an object-oriented multi-feature ensemble classification scheme (OMEC). First, an enhanced mangrove spectral index (EMSI) is established by analyzing the spectral reflectance differences between mangrove forests and other land cover types. Sentinel-2 images are segmented into objects using the multi-resolution segmentation method. Then, spectral, textural, and geometric features are extracted, and these features (including EMSI) are inputted into the nearest neighbor classifier to implement mangrove classification. The experiment was conducted in three typical mangrove areas in China using Sentinle-2 images. The results demonstrate that EMSI exhibits good spectral separability for mangroves and performs well in the ensemble classification scheme. The overall accuracy of mangrove classification exceeds 90%, with a Kappa coefficient greater than 0.88. The object-oriented multi-feature ensemble classification scheme significantly improves accuracy and exhibits excellent performance. The method enhances the accuracy of mangrove classification, enriches the approach to mangrove remote sensing interpretation, and offers data support and scientific references for the restoration, management, and protection of coastal wetlands.

Semiautomatic Mapping of Center Pivot Irrigated Areas Using Sentinel-2 Images and GEOBIA Approach

Image analysis and feature extraction of remoted sensing data are significant for mapping irrigated agriculture areas as a source of information to improve water management and agricultural planning. This paper presents an image segmented base approach GEOBIA (Geographic Object-Based Image Analysis) to extract irrigated areas by Center Pivot Irrigation System (CPIS). This study suggests a semi-automated recognition of circular patterns for the mapping of irrigated regions by center pivots, using Sentinel -2 MSI images, 10 meters spatial resolution. A set of images from different seasons, humid and dry are used to maximize de CPIS’s occurrence. A multiresolution segmentation method was applied, and a large number of segment-based shape features was extracted and used as input to a feature selection procedure (shape descriptors: Area; Compactness; Circularity Factor; Length/Width; Radius of smallest enclosing ellipse; and Roundness). In addition, another shape descriptor “Circularity Factor” was developed in this research and played an important role during preliminaries classification processes. The accuracy assessment of preliminaries classifications has validated used the Circularity Factor together with the other chosen shape descriptors to reach better results to CPIS’s detection. Furthermore, 86.23% of the CPIS mapped in the classification process is in accordance with the ground truth map. This methodology can be used to map large areas in a relatively short time and provides a tool for monitoring irrigated areas.

Mapping abandoned cropland using Within-Year Sentinel-2 time series

Against the background of the COVID-19 pandemic and various armed conflicts, the world is experiencing an unprecedented food crisis. The reclamation of abandoned cropland with food production potential may increase the global food supply in a short period of time, ensuring food security. At present, the extraction of abandoned cropland is mainly based on low- and medium-resolution remote sensing image data, making it difficult to extract fragmented areas in mountainous regions and to distinguish between abandoned cropland and transitional classes (such as fallow cropland). We developed a change-detection method based on within-year Sentinel-2 time series to extract cropland abandoned from 2018 to 2021 and defined four types of croplands, namely spontaneously abandoned, induced abandoned, fallow, and lost cropland, using Linxia County in mountainous China as the study region. First, cropland objects were generated from multi-temporal Sentinel-2 images using the multi-resolution segmentation method, and the land use map of Linxia County from 2017 to 2021 was drawn using random forest classifier. Second, through defining and identifying different cropland types, the interannual dynamic changes in cropland from 2018 to 2021 were extracted by analyzing the annual land use change trajectory. Third, by analyzing the normalized difference vegetation index (NDVI) time series of cropland within-year, the active and cultivated cropland sites within-year were extracted by threshold segmentation. Finally, the changes in the four cropland types were extracted by intersecting the two result types. Our method captured the object level changes well (overall mapping accuracy = 93 ± 5 %), and the extraction accuracy of abandoned cropland reached 81 ± 2 %. Abandoned cropland was mostly located in areas of medium quality and with a moderate distance from rural settlements. Reclamation can potentially increase the grain production in Linxia County by at least 3.6 % and needs to be combined with the local natural geography and human activities. Our method is a robust method for extracting abandoned cropland and may be applied to other research related to land use change.

Mapping burned areas and land-uses in Kangaroo Island using an object-based image classification framework and Landsat 8 Imagery from Google Earth Engine

In Australia, fire has become part of the natural ecosystem. Severe fires have devastated Australia's unique forest ecosystems due to the global climate change. In this study, we integrated a multi-resolution segmentation method and a hierarchical classification framework based on expert-based knowledge to classify the burned areas and land-uses in Kangaroo Island, South Australia. Using an object-based image classification framework that combines colour and shape features from input layers, we demonstrated that the objects segmented from the multi-source data lead to a higher accuracy in classification with an overall accuracy of 90.2% and a kappa coefficient of 85.2%. On the other hand, the single source data from post-fire Landsat-8 imagery showed an overall accuracy of 87.4% which is also statistically acceptable. According to our experiment results, more than 30.44% of the study area was burned during the 2019–2020 ‘Black-Summer’ fire season in Australia. Among the burned areas, high severity accounted for 12.14%, moderate severity for 11.48%, while low severity was 6.82%. For unburned areas, farmland accounted for 45.52% of the study area, of which about one-third was affected by the disturbances other than fire. The remaining area consists of 19.42% unaffected forest, 3.48% building and bare land, and 1.14% water. The comparison analysis shows that our object-based image classification framework takes full advantage of the multi-source data and generates the edges of burned areas more clearly, which contributes to the improved fire management and control.

What Is the Effect of Quantitative Inversion of Photosynthetic Pigment Content in Populus euphratica Oliv. Individual Tree Canopy Based on Multispectral UAV Images?

It is highly necessary to apply unmanned aerial vehicle (UAV) remote sensing technology to forest health assessment. To prove the feasibility of quantitative inversion of photosynthetic pigment content (PPC) in Populus euphratica Oliv. individual tree canopy (PeITC) by using multispectral UAV images, in this study, Parrot Sequoia+ multispectral UAV system was manipulated to collect the images of Populus euphratica (Populus euphratica Oliv.) sample plots in Daliyabuyi Oasis from 2019 to 2020, and the canopy PPCs of five Populus euphratica sample trees per plot were determined in six plots. The Populus euphratica crown regions were extracted by grey wolf optimizer-OTSU (GWO-OTSU) multithreshold segmentation algorithm from the normalized difference vegetation index (NDVI) images of Populus euphratica sample plots obtained after preprocessing, and the PeITCs were segmented by multiresolution segmentation algorithm. The mean values of 27 spectral indices in the PeITCs were calculated in each plot, and the optimal model was constructed for quantitative estimation of the PPCs in the PeITCs, then the inversion results were compared and verified based on GF-6 and ZY1-02D satellite imageries respectively. The results were as follows. (1) The average value of canopy chlorophyll content (Chl) was 2.007 mg/g, the mean value of canopy carotenoid content (Car) was 0.703 mg/g. The coefficient of variation (C.V) of both were basically the same and they were both of strong variability. The measured PPCs of the PeITCs in Daliyabuyi Oasis was generally low. The average contents of chlorophyll and carotenoid in PeITC in June were more than twice those in August, while the mean ratio between them was significantly lower in June than in August. The measured PPCs had no obvious spatial distribution law. However, that could prove the rationality of sample selection in this study. (2) NDVI had the best effect of highlighting vegetation among all quadrats in the study area. Based on the GWO-OTSU multithreshold segmentation method, the canopy area of Populus euphratica could be quickly and effectively extracted from the quadrat NDVI map. The best segmentation effect of PeITCs was obtained based on a multiresolution segmentation method when the segmentation scale was 120, the shape index was 0.7, and the compactness index was 0.5. Compared with manual vectorization method of visual interpretation, the root mean square error (RMSE) and Pearson correlation coefficient (R) values of the mean NDVI values in PeITCs obtained by these two methods were 0.038 and 0.951. (3) Only 12 of the 27 spectral indices were significantly correlated with Chl and Car at the significance level of 0.02. Characteristics of the calibration set and validation set were basically consistent with those of the entire set. The classification and regression tree-decision tree (CART-DT) model performed best in the estimation of the PPCs in the PeITCs, in which, when estimating the Car, the calibration coefficient of determination (R2C) was 0.843, the calibration root mean square error (RMSEC) was 0.084, the calibration residual prediction deviation (RPDC) was 2.525, the validation coefficient of determination (R2V) was 0.670, the validation root mean square error (RMSEV) was 0.251, the validation residual prediction deviation (RPDV) was 1.741. (4) Qualitative comparison of spectral reflectance and NDVI values between GF-6 multispectral imagery and Parrot Sequoia+ multispectral image on the 172 PeITCs can show the reliability of Parrot Sequoia+ multispectral image. The comparison results of five PeITCs relative health degree judged by field vision judgment, measured SPAD value, predicted value of Chl (Chlpre), the red edge value calculated by ZY1-02D (ZY1-02Dred edge) and the Carotenoid Reflection Index 2 (CRI2) value calculated by ZY1-02D (ZY1-02DCRI2) can further prove the scientificity of inversion results to a certain extent. These results indicate that multispectral UAV images can be applied for quantitative inversion of PPC in PeITC, which could provide an indicator for the construction of a Populus euphratica individual tree health evaluation indicator system based on UAV remote sensing technology in the next step.

Monitoring the change of Turkey’s tourism city Antalya’s Konyaaltı shoreline with multi-source satellite and meteorological data

Uncontrolled tourism activities cause the destruction of nature and deterioration of the ecological balance. Since coastal areas are both economically and socially important, monitoring shoreline changes has become one of the important research areas. Monitoring short-term and long-term changes in coastal areas is important to prevent damages that may occur due to natural and human factors and protect the shorelines. In this study, which is an important tourist city of Antalya, Turkey, and the world, coastal changes using historical and recent satellite data have been analyzed. The focus of the study is to analyze long-term coastal change with Landsat data and the data obtained every 5 years between 1985 and 2020 and to analyze short-term change with annual Sentinel-2 data between 2015 and 2020. In the study, water areas on the coastline were determined by object-based classification and multiresolution segmentation method with the Modified Normalized Difference Water Index (MNDWI). The obtained shorelines were analyzed with the Digital Shoreline Analysis System (DSAS) tool and the changes in the coastal areas were determined statistically. Five-year and 35-year changes were compared with Linear Regression Rate (LRR) and End Point Rate (EPR) analyses. As a result of the study, when the Pearson’s r value between EPR and LRR was examined, r was found 0.916 and 0.944 for 5-year and 35-year data, respectively. Spatial resolution in satellite images is vital for shoreline detection. However, the most optimal way to detect long-term changes in the shoreline is to use Landsat data. Although the spatial resolution of Landsat data, it has been observed that the power to analyze annual variation differences is lower than Sentinel-2.

An Object-Based Genetic Programming Approach for Cropland Field Extraction

Cropland fields are the basic spatial units for agricultural management, and information about their distribution is critical for analyzing agricultural investments and management. However, the extraction of cropland fields of smallholder farms is a challenging task because of their irregular shapes and diverse spectrum. In this paper, we proposed a new object-based Genetic Programming (GP) approach to extract cropland fields. The proposed approach used the multiresolution segmentation (MRS) method to acquire objects from a very high resolution (VHR) image, and extracted spectral, shape and texture features as inputs for GP. Then GP was used to automatically evolve the optimal classifier to extract cropland fields. The results show that the proposed approach has obtained high accuracy in two areas with different landscape complexities. Further analysis show that the GP approach significantly outperforms five commonly used classifiers, including K-Nearest Neighbor (KNN), Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). By using different numbers of training samples, GP can maintain high accuracy with any volume of samples compared to other classifiers.

Variational-Scale Segmentation for Multispectral Remote-Sensing Images Using Spectral Indices

Many studies have focused on performing variational-scale segmentation to represent various geographical objects in high-resolution remote-sensing images. However, it remains a significant challenge to select the most appropriate scales based on the geographical-distribution characteristics of ground objects. In this study, we propose a variational-scale multispectral remote-sensing image segmentation method using spectral indices. Real scenes in remote-sensing images contain different types of land cover with different scales. Therefore, it is difficult to segment images optimally based on the scales of different ground objects. To guarantee image segmentation of ground objects with their own scale information, spectral indices that can be used to enhance some types of land cover, such as green cover and water bodies, were introduced into marker generation for the watershed transformation. First, a vector field model was used to determine the gradient of a multispectral remote-sensing image, and a marker was generated from the gradient. Second, appropriate spectral indices were selected, and the kernel density estimation was used to generate spectral-index marker images based on the analysis of spectral indices. Third, a series of mathematical morphology operations were used to obtain a combined marker image from the gradient and the spectral index markers. Finally, the watershed transformation was used for image segmentation. In a segmentation experiment, an optimal threshold for the spectral-index-marker generation method was identified. Additionally, the influence of the scale parameter was analyzed in a segmentation experiment based on a five-subset dataset. The comparative results for the proposed method, the commonly used watershed segmentation method, and the multiresolution segmentation method demonstrate that the proposed method yielded multispectral remote-sensing images with much better performance than the other methods.

Using canopy height model derived from UAV imagery as an auxiliary for spectral data to estimate the canopy cover of mixed broadleaf forests.

Canopy cover is an important structural trait that is frequently used in forest inventories to assess sustainability as well as many other important aspects of forest stands. Remote sensing data is more effective and suitable for canopy cover estimating than traditional field measurements such as sample plots, especially at broad scales. Measurement and mapping this attribute in fine-scale is a difficult task. Aerial imagery using unmanned aerial vehicle (UAV) has been recognized as an excellent tool to estimate canopy attributes. In this study, we compared the potential of using digital hemispherical photography (DHP), digital cover photography (DCP), UAV RGB data, and canopy height model (CHM) for estimation of canopy cover of mix broad-leaved forest on seven different stands. The canopy cover was measured from two digital canopy photographic methods, including DHP (as the reference method) and DCP. The stand orthophotos were segmented using a multi-resolution image segmentation method. Afterward, the classification in two classes of the canopy cover and the non-canopy cover was conducted using minimum distance classification to estimate canopy cover. The CHM layer was generated based on the SfM algorithm and utilized in the canopy cover estimation in each stand as auxiliary data. The results showed a slight improvement when we used the CHM as auxiliary data. Overall, the results showed that the efficiency of the ground digital canopy photographic methods (zenith view) in multi-storied and dense forests is the lowest. In return, our method for digital aerial canopy photography (object-based canopy segmentation and classification) is simple, quick, efficient, and cost-effective.

Exploration of Semantic Geo-Object Recognition Based on the Scale Parameter Optimization Method for Remote Sensing Images

Image segmentation is of significance because it can provide objects that are the minimum analysis units for geographic object-based image analysis (GEOBIA). Most segmentation methods usually set parameters to identify geo-objects, and different parameter settings lead to different segmentation results; thus, parameter optimization is critical to obtain satisfactory segmentation results. Currently, many parameter optimization methods have been developed and successfully applied to the identification of single geo-objects. However, few studies have focused on the recognition of the union of different types of geo-objects (semantic geo-objects), such as a park. The recognition of semantic geo-objects is likely more crucial than that of single geo-objects because the former type of recognition is more correlated with the human perception. This paper proposes an approach to recognize semantic geo-objects. The key concept is that a single geo-object is the smallest component unit of a semantic geo-object, and semantic geo-objects are recognized by iteratively merging single geo-objects. Thus, the optimal scale of the semantic geo-objects is determined by iteratively recognizing the optimal scales of single geo-objects and using them as the initiation point of the reset scale parameter optimization interval. In this paper, we adopt the multiresolution segmentation (MRS) method to segment Gaofen-1 images and tested three scale parameter optimization methods to validate the proposed approach. The results show that the proposed approach can determine the scale parameters, which can produce semantic geo-objects.

Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images

Road networks are one of the main urban features. Therefore, road parts extraction from high-resolution remotely sensed imagery and updated road database are beneficial for many GIS applications. However, owing to the presence of various types of obstacles in the images, such as shadows, cars, and trees, with similar transparency and spectral values as road class, achieving accurate road extraction using different classification and segmentation methods is still difficult. This paper proposes an integrated method combining segmentation and classification methods with connected components analysis to extract road class from orthophoto images. The proposed technique is threefold. First, multiresolution segmentation method was applied to segment images. Then, the main classification methods, namely, decision trees (DT), k-nearest neighbors (KNN), and support vector machines (SVM), were implemented based on spectral, geometric, and textural information to classify the obtained results into two classes: road and non-road. Three main accuracy evaluation measures, such as recall, precision, and F1-score, were evaluated to determine the performance of the proposed method, with respective average values of 87.62%, 89.71%, and 88.61%, respectively, for DT; 86.61%, 88.17%, and 87.30%, respectively, for KNN; and 89.83%, 89.52%, and 89.67%, respectively, for SVM. Finally, connected components labelling was used to extract road component parts, and morphological operation was employed to delete non-road parts and noises and improve the performance. These results were also compared with other prior works, which confirmed that the integrated method is an effective road extraction technique.

Extraction of lake water area by using Multi-source Satellite Data

With remote sensing resolution data from Landsat-8, GF-1 and Sentinel-1 as the data sources, we used the object-oriented multi-resolution segmentation method to extract the area of Po Lake in Anhui. First, the multi-resolution segmentation method is used to segment the object, and then rule sets are established to extract areas of water bodies on three maps to calculate the area of lake water. The research result shows that the object-oriented multi-resolution segmentation method can realize efficient extraction of open water areas and facilitate disaster monitoring and emergency response.

Detailed Urban Land Use Land Cover Classification at the Metropolitan Scale Using a Three-Layer Classification Scheme

Urban Land Use/Land Cover (LULC) information is essential for urban and environmental management. It is, however, very difficult to automatically extract detailed urban LULC information from remote sensing imagery, especially for a large urban area. Medium resolution imagery, such as Landsat Thematic Mapper (TM) data, cannot uncover detailed LULC information. Further, very high resolution (VHR) satellite imagery, such as IKONOS and QuickBird data, can only be applied to a small area, largely due to the data unavailability and high computation cost. As a result, little research has been conducted to extract detailed urban LULC information for a large urban area. This study, therefore, developed a three-layer classification scheme for deriving detailedurban LULC information by integrating newly launched Chinese GF-1 (medium resolution) and GF-2 (very high resolution) satellite imagery and synthetically incorporating geometry, texture, and spectral information through multi-resolution image segmentation and object-based image classification (OBIA). Homogeneous urban LULC types such as water bodies or large areas of vegetation could be derived from GF-1 imagery with 16 m and 8 m spatial resolutions, while heterogeneous urban LULC types such as industrial buildings, residential buildings, and roads could be extracted from GF-2 imagery with 3.2 m and 0.8 m spatial resolutions. The multi-resolution segmentation method and a random forest algorithm were employed to perform image segmentation and object-based image classification, respectively. An analysis of the results suggests an overall accuracy of 0.89 and 0.87 were achieved for the second and third level urban LULC classification maps, respectively. Therefore, the three-layer classification scheme has the potential to derive high accuracy urban LULC information through integrating medium and high-resolution remote sensing imagery.

A spatiotemporal cube model for analyzing satellite image time series: Application to land-cover mapping and change detection

Satellite image time series (SITS) data have been widely used in resource investigations and environmental monitoring. However, three characteristics of geographic objects (i.e., spatiotemporal heterogeneity, spatiotemporal correlation and scale characteristics) pose great challenges to SITS analysis; while, existing studies ignore these characteristics, leading to unsatisfactory SITS analysis results including land-cover classification and change detection. Aiming at integratively measuring and expressing these three characteristics, this study proposes a spatiotemporal cube model and a spatiotemporal multi-resolution segmentation (ST-MRS) method for analyzing SITS. First, the novel spatiotemporal model, ST-cube, is introduced to reduce the spectral heterogeneity in spatial and temporal domains. Both spatial and temporal heterogeneities are considered and defined while constructing the spatiotemporal segmentation model. Second, the ST-MRS method is proposed by extending the existing mono-temporal MRS method into spatiotemporal domain to segment SITS into relatively homogeneous ST-cubes. Third, a novel unsupervised method is developed to evaluate the segmentation results of the ST-MRS method. In experiments, we apply this method to Shunyi District in Beijing, China, generate ST-cubes at different spatiotemporal scales, and compare our method with existing ones for SITS classification. Furthermore, the intra-annual seasonal changes of land covers are detected based on ST-cubes classification results. The results indicate the effectiveness and superiority of the ST-cubes in representing geographic objects and analyzing spatiotemporal characteristics over existing pixel- and object-based methods, contributing to a wider range of applications and analysis of SITS.

Unsupervised segmentation parameter selection using the local spatial statistics for remote sensing image segmentation

Image segmentation is a key issue in geographic object-based image analysis, thus determining the appropriate segmentation parameter is a prerequisite to allowing for obtaining accurate segmentation. In this study, an unsupervised segmentation parameter selection method using the local spatial statistics was proposed for achieving the automatic parameter optimization of image segmentation. The two measure of within-segment homogeneity (WSH) and between-segment heterogeneity (BSH) were calculated using local spatial statistics approach, and then integrated into a global value for indicating the overall segmentation quality. In addition, the contribution of the common boundary between each segment and one of its neighboring segments was considered in BSH calculation for obtaining a more objective evaluation. For this experiment, the multi-resolution segmentation (MRS) method was used as a segmentation algorithm and GF-1 image used as test data. The measure analysis experiment of the proposed method showed BSH is more sensitive to under-segmentation. The visual and discrepancy measures results of the proposed method compared with the other four methods revealed that the proposed method is more potential to recognize the proper segmentation parameter with the purpose of allowing for obtaining segmentations with high quality.

A Hierarchical Multiscale Super-Pixel-Based Classification Method for Extracting Urban Impervious Surface Using Deep Residual Network From WorldView-2 and LiDAR Data

High-resolution optical imagery can provide detailed information of urban land objects for impervious surface extraction, while airborne light detection and ranging (LiDAR) data can provide height features of land objects. Therefore, synergistic use of high-resolution imagery and LiDAR data is considered as an effective method to improve impervious surfaces extraction. In this paper, a novel hierarchical multiscale super-pixel-based classification method is proposed and applied to the urban impervious surfaces extraction from WorldView-2 and normalized digital surface model (nDSM) images derived from airborne LiDAR data. Three subsets in rural, rural–urban, and urban subsets are selected as the study areas. First, we split nonground and ground objects based on nDSM thresholds. Second, a hierarchical multiresolution segmentation method is used to generate nonground and ground super pixels. Then, we determine the multiscale input images based on the size of super pixels. Third, we construct optimal deep residual network (ResNet) and Spatial Pyramid Pooling (SPP-net) to train the model using multiscale input images. Finally, we use our deep models to predict hierarchically total super pixels in three subsets and generate the classification and impervious surfaces results. Our proposed method adopts hierarchical classification based on LiDAR nDSM height, which significantly improves the impervious surfaces extraction accuracies. Then, the deep residual network is applied further on multispectral and height fused data to extract urban impervious surfaces. Moreover, we propose an adaptive method to determine multiscale input images based on the segmentation of super pixels, which are inputs into the ResNet+SPP-net to train the deep model. Our proposed method reduces the uncertainty of multiscale input images and extracts better multiscale features. The results of the experiment show that our proposed method has a significant superiority to traditional pixel-based method and single scale method for urban impervious surfaces extraction.

Multiscale and Multifeature Segmentation of High-Spatial Resolution Remote Sensing Images Using Superpixels with Mutual Optimal Strategy

High spatial resolution (HSR) image segmentation is considered to be a major challenge for object-oriented remote sensing applications that have been extensively studied in the past. In this paper, we propose a fast and efficient framework for multiscale and multifeatured hierarchical image segmentation (MMHS). First, the HSR image pixels were clustered into a small number of superpixels using a simple linear iterative clustering algorithm (SLIC) on modern graphic processing units (GPUs), and then a region adjacency graph (RAG) and nearest neighbors graph (NNG) were constructed based on adjacent superpixels. At the same time, the RAG and NNG successfully integrated spectral information, texture information, and structural information from a small number of superpixels to enhance its expressiveness. Finally, a multiscale hierarchical grouping algorithm was implemented to merge these superpixels using local-mutual best region merging (LMM). We compared the experiments with three state-of-the-art segmentation algorithms, i.e., the watershed transform segmentation (WTS) method, the mean shift (MS) method, the multiresolution segmentation (MRS) method integrated in commercial software, eCognition9, on New York HSR image datasets, and the ISPRS Potsdam dataset. Computationally, our algorithm was dozens of times faster than the others, and it also had the best segmentation effect through visual assessment. The supervised and unsupervised evaluation results further proved the superiority of the MMHS algorithm.

Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images

Image segmentation is an important process and a prerequisite for object-based image analysis. Thus, evaluating the performance of segmentation algorithms is essential to identify effective segmentation methods and to optimize the scale. In this paper, we propose an unsupervised evaluation (UE) method using the area-weighted variance (WV) and Jeffries-Matusita (JM) distance to compare two image partitions to evaluate segmentation quality. The two measures were calculated based on the local measure criteria, and the JM distance was improved by considering the contribution of the common border between adjacent segments and the area of each segment in the JM distance formula, which makes the heterogeneity measure more effective and objective. Then the two measures were presented as a curve when changing the scale from 8 to 20, which can reflect the segmentation quality in both over- and under-segmentation. Furthermore, the WV and JM distance measures were combined by using three different strategies. The effectiveness of the combined indicators was illustrated through supervised evaluation (SE) methods to clearly reveal the segmentation quality and capture the trade-off between the two measures. In these experiments, the multiresolution segmentation (MRS) method was adopted for evaluation. The proposed UE method was compared with two existing UE methods to further confirm their capabilities. The visual and quantitative SE results demonstrated that the proposed UE method can improve the segmentation quality.

Particle Swarm Optimization for Object-Based Feature Selection of VHSR Satellite Images

With the advent of very high spatial resolution (VHSR) satellite imagery, object-based classification (OBC) has attracted a great deal of attention in the remote sensing community. However, due to the numerous spectral, textural, and structural features which can be extracted for each object, feature selection is needed to address the curse-of-dimensionality issue. In this letter, a new wrapper object-based feature (OBF) selection method was applied in order to select the best combination of spectral, textural, and structural OBFs. In the first step, the image is segmented into objects using the multiresolution segmentation method. Subsequently, OBFs are extracted for each object. Last, optimal OBFs are selected using the proposed method based on particle swarm optimization (PSO) combined with the minimum distance classifier. Two VHSR remotely sensed images, acquired by a WorldView-2 sensor, were used to test the proposed method. The results of the experiment indicated that OBC using optimal OBFs led to significant improvement over the case where all extracted features were used. Furthermore, PSO has a better performance than do the three metaheuristic optimization algorithms: genetic algorithm, artificial bee colony, and honey-bee mating, according to the technique of order of preference by similarity to ideal solution analysis.

Extraction of Terraces on the Loess Plateau from High-Resolution DEMs and Imagery Utilizing Object-Based Image Analysis

Abstract: Terraces are typical artificial landforms on the Loess Plateau, with ecological functions in water and soil conservation, agricultural production, and biodiversity. Recording the spatial distribution of terraces is the basis of monitoring their extent and understanding their ecological effects. The current terrace extraction method mainly relies on high-resolution imagery, but its accuracy is limited due to vegetation coverage distorting the features of terraces in imagery. High-resolution topographic data reflecting the morphology of true terrace surfaces are needed. Terraces extraction on the Loess Plateau is challenging because of the complex terrain and diverse vegetation after the implementation of “vegetation recovery”. This study presents an automatic method of extracting terraces based on 1 m resolution digital elevation models (DEMs) and 0.3 m resolution Worldview-3 imagery as auxiliary information used for object-based image analysis (OBIA). A multi-resolution segmentation method was used where slope, positive and negative terrain index (PN), accumulative curvature slope (AC), and slope of slope (SOS) were determined as input layers for image segmentation by correlation analysis and Sheffield entropy method. The main classification features based on DEMs were chosen from the terrain features derived from terrain factors and texture features by gray-level co-occurrence matrix (GLCM) analysis; subsequently, these features were determined by the importance analysis on classification and regression tree (CART) analysis. Extraction rules based on DEMs were generated from the classification features with a total classification accuracy of 89.96%. The red band and near-infrared band of images were used to exclude construction land, which is easily confused with small-size terraces. As a result, the total classification accuracy was increased to 94%. The proposed method ensures comprehensive consideration of terrain, texture, shape, and spectrum characteristics, demonstrating huge potential in hilly-gully loess region with similarly complex terrain and diverse vegetation covers.