Object-based Approach Research Articles

Comparison of spectral indices extracted from Sentinel-2 images to map plastic covered greenhouses through an object-based approach

ABSTRACT One of the most important challenges of agriculture today is increasing its productivity gains, while controlling its environmental footprint. Because of that plastic covered greenhouses (PCG) mapping via remote sensing is receiving a great attention throughout this century. In this study, a fair comparison was carried out in four PCG study areas around the world to test 14 spectral indices mainly focused on the detection of plastic. To the best knowledge of the authors, this is the first research that fairly compares all these spectral indices in such variable number of study sites. The applied OBIA approach was based on the combined use of very high-resolution satellite data (Deimos-2 pansharpened images) to address the segmentation process and Sentinel-2 time series to compute the spectral indices. When dealing with Sentinel-2 single images, the Plastic GreenHouse Index (PGHI) stood out among all the indices tested in the study areas dedicated to the cultivation of vegetables, such as the cases of Almería (Spain), Agadir (Morocco) and Antalya (Turkey). Better Overall Accuracy (OA) values of 94.09%, 92.27%, 92.77% and 92.17% were achieved for Almería, Agadir, Bari and Antalya study sites, respectively, when using statistical seasonal spectral indices based on Sentinel-2 time series, being the maximum and mean values of PGHI (MAX (PGHI) and MEAN (PGHI)) the best ranked. Meanwhile, the PCG area of Bari (Italy), with a monoculture in vineyards, presented the worst and most irregular results.

Object-Based Verification of GSI EnKF and Hybrid En3DVar Radar Data Assimilation and Convection-Allowing Forecasts within a Warn-on-Forecast Framework

Abstract The Center for Analysis and Prediction of Storms has recently developed capabilities to directly assimilate radar reflectivity and radial velocity data within the GSI-based ensemble Kalman filter (EnKF) and hybrid ensemble three-dimensional variational (En3DVar) system for initializing convective-scale forecasts. To assess the performance of EnKF and hybrid En3DVar with different hybrid weights (with 100%, 20%, and 0% of static background error covariance corresponding to pure 3DVar, hybrid En3DVar, and pure En3DVar) for assimilating radar data in a Warn-on-Forecast framework, a set of data assimilation and forecast experiments using the WRF Model are conducted for six convective storm cases of May 2017. Using an object-based verification approach, forecast objects of composite reflectivity and 30-min updraft helicity swaths are verified against reflectivity and rotation track objects in Multi-Radar Multi-Sensor data on space and time scales typical of National Weather Service warnings. Forecasts initialized by En3DVar or the best performing EnKF ensemble member produce the highest object-based verification scores, while forecasts from 3DVar and the worst EnKF member produce the lowest scores. Averaged across six cases, hybrid En3DVar using 20% static background error covariance does not improve forecasts over pure En3DVar, although improvements are seen in some individual cases. The false alarm ratios of EnKF members for both composite reflectivity and updraft helicity at the initial time are lower than those from variational methods, suggesting that EnKF analysis reduces spurious reflectivity and mesocyclone objects more effectively.

Spatial verification of a regional ensemble precipitation forecasting system at the Hydrometeorological Research Center of the Russian Federation using a free verification package, MET

Ensemble weather forecasting is a necessary tool for assessing the probabilities of weather events, alternative scenarios of their development, and forecast uncertainties. At the Hydrometeorological Research Center of the Russian Federation, a regional high-resolution ensemble system is under development with a grid mesh of 2.2 km for the central region of Russia. Consequently, developing a state-of-the-art ensemble verification system is of high priority. In this work, preliminary results of a high-resolution ensemble verification system are given for precipitation as an example. The system includes both standard probability scores and some novel spatial scores. A method for object-based diagnostic evaluation, MODE, is used as the main object-based approach. The system is based on a free verification package, METplus. Examples of scores are given.

Using an object-based machine learning ensemble approach to upscale evapotranspiration measured from eddy covariance towers in a subtropical wetland

Accurate prediction of evapotranspiration (ET) in wetlands is critical for understanding the coupling effects of water, carbon, and energy cycles in terrestrial ecosystems. Multiple years of eddy covariance (EC) tower ET measurements at five representative wetland ecosystems in the subtropical Big Cypress National Preserve (BCNP), Florida (USA) provide a unique opportunity to assess the performance of the Moderate Resolution Imaging Spectroradiometer (MODIS) ET operational product MOD16A2 and upscale tower measured ET to generate local/regional wetland ET maps. We developed an object-based machine learning ensemble approach to evaluate and map wetland ET by linking tower measured ET with key predictors from MODIS products and meteorological variables. The results showed MOD16A2 had poor performance in characterizing ET patterns and was unsatisfactory for estimating ET over four wetland communities where Nash-Sutcliffe model Efficiency (NSE) was less than 0.5. In contrast, the site-specific machine learning ensemble model had a high predictive power with a NSE larger than 0.75 across all EC sites. We mapped the ET rate for two distinctive seasons and quantified the prediction diversity to identify regions easier or more challenging to estimate from model-based analyses. An integration of MODIS products and other datasets through the machine learning upscaling paradigm is a promising tool for local wetland ET mapping to guide regional water resource management.

An object-based sparse representation model for spatiotemporal image fusion

Many algorithms have been proposed for spatiotemporal image fusion on simulated data, yet only a few deal with spectral changes in real satellite images. An innovative spatiotemporal sparse representation (STSR) image fusion approach is introduced in this study to generate global dense high spatial and temporal resolution images from real satellite images. It aimed to minimize the data gap, especially when fine spatial resolution images are unavailable for a specific period. The proposed approach uses a set of real coarse- and fine-spatial resolution satellite images acquired simultaneously and another coarse image acquired at a different time to predict the corresponding unknown fine image. During the fusion process, pixels located between object classes with different spectral responses are more vulnerable to spectral distortion. Therefore, firstly, a rule-based fuzzy classification algorithm is used in STSR to classify input data and extract accurate edge candidates. Then, an object-based estimation of physical constraints and brightness shift between input data is utilized to construct the proposed sparse representation (SR) model that can deal with real input satellite images. Initial rules to adjust spatial covariance and equalize spectral response of object classes between input images are introduced as prior information to the model, followed by an optimization step to improve the STSR approach. The proposed method is applied to real fine Sentinel-2 and coarse Landsat-8 satellite data. The results showed that introducing objects in the fusion process improved spatial detail, especially over the edge candidates, and eliminated spectral distortion by preserving the spectral continuity of extracted objects. Experiments revealed the promising performance of the proposed object-based STSR image fusion approach based on its quantitative results, where it preserved almost 96.9% and 93.8% of the spectral detail over the smooth and urban areas, respectively.

Detecting and mapping karst landforms using object-based image analysis: Case study: Takht-Soleiman and Parava Mountains, Iran

This study presents a novel, semi-automated approach for integrating decision rules and object-based image analysis (OBIA) methods for identifying and mapping karst zones and landforms. We developed a multi-resolution segmentation approach using an Approximate Gaussian function to compute the degree of fuzzy memberships of object-based features and applied it to Sentinel-2 satellite images and a digital elevation model. The object based features and decision rules were applied to identify and detect karst landforms in the semi-automated approach. The efficiency of each technique was examined based on two case studies in Takht-Soleiman and Parava-Biston in Iran using a fuzzy synthetic evaluation (FSE) approach and ground control points. The validation of the karst landform detection and delineation yielded high accuracies for the six prominent landforms, namely Dolin (96.8%), Ouvala (99.2%), Lapiez (95.1%), Canyon (98.3%), Polje (96.1%) and Karren (97.4%), respectively. Based on the research outcome, we conclude that the combined use of spatial (e.g. shape index, compactness, asymmetry), spectral (e.g. brightness, mean and standard deviation) and textural (grey-level co-occurrence matrix, GLCM) features allows us to detect and map karst landforms efficiently. This fuzzy rule object-based approach can enhance the accuracy of geomorphological and geological maps and allows for a regular update of the usually labor-intensive geological mapping campaigns.

Semi-Automated, Object-Based Tomography of Dislocation Structures.

The characterization of the three-dimensional arrangement of dislocations is important for many analyses in materials science. Dislocation tomography in transmission electron microscopy is conventionally accomplished through intensity-based reconstruction algorithms. Although such methods work successfully, a disadvantage is that they require many images to be collected over a large tilt range. Here, we present an alternative, semi-automated object-based approach that reduces the data collection requirements by drawing on the prior knowledge that dislocations are line objects. Our approach consists of three steps: (1) initial extraction of dislocation line objects from the individual frames, (2) alignment and matching of these objects across the frames in the tilt series, and (3) tomographic reconstruction to determine the full three-dimensional configuration of the dislocations. Drawing on innovations in graph theory, we employ a node-line segment representation for the dislocation lines and a novel arc-length mapping scheme to relate the dislocations to each other across the images in the tilt series. We demonstrate the method for a dataset collected from a dislocation network imaged by diffraction-contrast scanning transmission electron microscopy. Based on these results and a detailed uncertainty analysis for the algorithm, we discuss opportunities for optimizing data collection and further automating the method.

(Un)constructed, Reconstructed and Deconstructed Again. An Examination of the Context, Reconstruction and Display Possibilities of Five Lace Panels for Use on a Gown, c. 1900–1910, at the MoMu Fashion Museum in Antwerp

This article studies five shaped panels of Duchesse de Bruxelles lace, part of the collection of the MoMu Fashion Museum in Antwerp. These handmade panels were created c. 1900 but never fashioned into a gown and, consequently, never worn. The first part of this article uses an object-based approach to examine how the panels might have looked if they had been constructed into a gown, what type of gown this would have been, to what occasions it would have been worn and by whom. In 2021, the renovated MoMu reopened with, in addition to its space for temporary exhibitions, a permanent display showing highlights from the museum collection. This unconstructed gown being a highlight of its historical lace collection, the museum is currently considering how to best exhibit it. The second part of this article therefore examines different display possibilities, ranging from a full reconstruction, to a deconstructed display, to the possibility of replication — all the while keeping in mind the ethics of conservation-restoration and display, and what it means to exhibit fashion.

An Object-Based Approach to Map Young Forest and Shrubland Vegetation Based on Multi-Source Remote Sensing Data

Many remote sensing studies have individually addressed afforestation, forest disturbance and forest regeneration, and considered land use history. However, no single study has simultaneously addressed all of these components that collectively constitute successional stages and pathways of young forest and shrubland at large spatial extents. Our goal was to develop a multi-source, object-based approach that utilized the strengths of Landsat (large spatial extent with good temporal coverage), LiDAR (vegetation height and vertical structure), and aerial imagery (high resolution) to map young forest and shrubland vegetation in a temperate forest. Further, we defined young forest and shrubland vegetation types in terms of vegetation height and structure, to better distinguish them in remote sensing for ecological studies. The multi-source, object-based approach provided an area-adjusted estimate of 42,945 ha of young forest and shrubland vegetation in Connecticut with overall map accuracy of 88.2% (95% CI 2.3%), of which 20,953 ha occurred in complexes ≥2 ha in size. Young forest and shrubland vegetation constituted 3.3% of Connecticut’s total land cover and 6.3% of forest cover as of 2018. Although the 2018 estimates are consistent with those of the past 20 years, concerted efforts are needed to restore, maintain, or manage young forest and shrubland vegetation in Connecticut.

Change of land use / land cover in kurdistan region of Iraq: A semi-automated object-based approach

During the conflict and in the years afterward, the Kurdistan Region of Iraq (KRI) saw substantial changes in land use. The mapping and monitoring of land use/land cover (LULC) is critical for its long-term development and natural resource management. Therefore in this study, we developed a semi-automated object-based land use/land cover classification to identify and quantify LULC changes and change detection analysis in the Kurdistan Region of Iraq for the period 1990 to 2020 using Landsat satellite data (TM, ETM+, and OLI). To determine the optimum segmentation scales for each phase, we first applied and evaluated different scales of a multi-resolution segmentation technique. After that, spatial (digital elevation information) and spectral information were combined in an object-based image analysis (OBIA) technique. For each LULC class, object features were found. We then used the standard nearest neighbor (SNN) approach to derive their individual properties. Field data and validation units collected from high resolution Google earth pro and historical maps in SAS planet open source were used to conduct accuracy evaluations based on the error matrix and kappa coefficient for each reference year. With overall accuracies ranging from 86.072% to 88.9% and Kappa coefficients of 0.845–0.878, ten LULCs were effectively recorded. After that, a post classification comparison was used to perform a change analysis. The findings demonstrated that LULC change trends were notably different, as all categories were altered at different times throughout the study. Strikingly, 52.1% of the land use/land cover in the Kurdistan Region has changed between 1990 and 2020. All changes corresponded to the KRI's own challenges throughout the last three decades. The OBIA-based approaches and features, we conclude, have a lot of potential for LULC mapping and monitoring. The results shall support state institutions and experts to manage the land in a more controlled way.

The Use of C-Band and X-Band SAR with Machine Learning for Detecting Small-Scale Mining

Illicit small-scale mining occurs in many tropical regions and is both environmentally and socially hazardous. The aim of this study was to determine whether the classification of Synthetic Aperture Radar (SAR) imagery could detect and map small-scale mining in Ghana by analyzing multi-temporal filtering applied to three SAR datasets and testing five machine-learning classifiers. Using an object-based image analysis approach, we were successful in classifying water bodies associated with small-scale mining. The multi-temporally filtered Sentinel-1 dataset was the most reliable, with kappa coefficients at 0.65 and 0.82 for the multi-class classification scheme and binary-water classification scheme, respectively. The single-date Sentinel-1 dataset has the highest overall accuracy, at 90.93% for the binary water classification scheme. The KompSAT-5 dataset achieved the lowest accuracy at an overall accuracy of 80.61% and a kappa coefficient of 0.61 for a binary-water classification scheme. The experimental results demonstrated that it is possible to classify water as a proxy to identify illegal mining activities and that SAR is a potentially accurate and reliable solution for the detection of SSM in tropical regions such as Ghana. Therefore, using SAR can assist local governments in regulating small-scale mining activities by providing specific spatial information on the whereabouts of small-scale mining locations.

Comparative Assessment of Pixel and Object-Based Approaches for Mapping of Olive Tree Crowns Based on UAV Multispectral Imagery

Pixel-based (PB) and geographic-object-based (GEOBIA) classification approaches allow the extraction of different objects from multispectral images (MS). The primary goal of this research was the analysis of UAV imagery applicability and accuracy assessment of MLC and SVM classification algorithms within PB and GEOBIA classification approaches. The secondary goal was to use different accuracy assessment metrics to determine which of the two tested classification algorithms (SVM and MLC) most reliably distinguishes olive tree crowns and which approach is more accurate (PB or GEOBIA). The third goal was to add false polygon samples for Correctness (COR), Completeness (COM) and Overall Quality (OQ) metrics and use them to calculate the Total Accuracy (TA). The methodology can be divided into six steps, from data acquisition to selection of the best classification algorithm after accuracy assessment. High-quality DOP (digital orthophoto) and UAVMS were generated. A new accuracy metric, called Total Accuracy (TA), combined both false and true positive polygon samples, thus providing a more comprehensive insight into the assessed classification accuracy. The SVM (GEOBIA) was the most reliable classification algorithm for extracting olive tree crowns from UAVMS imagery. The assessment carried out indicated that application of GEOBIA-SVM achieved a TACOR of 0.527, TACOM of 0.811, TAOQ of 0.745, Overall Accuracy (OA) of 0.926 or 0.980 and Area Under Curve (AUC) value of 0.904 or 0.929. The calculated accuracy metrics confirmed that the GEOBIA approach (SVM and MLC) achieved more accurate olive tree crown extraction than the PB approach (SVM and MLC) if applied to classifying VHR UAVMS imagery. The SVM classification algorithm extracted olive tree crowns more accurately than MLC in both approaches. However, the accuracy assessment has proven that PB classification algorithms can also achieve satisfactory accuracy.

OBCD-HH: an object-based change detection approach using multi-feature non-seed-based region growing segmentation

OBCD-HH: an object-based change detection approach using multi-feature non-seed-based region growing segmentation

Desert landform detection and mapping using a semi-automated object-based image analysis approach

Traditional landform modeling approaches are labor-intensive and time-consuming. We proposed and developed a semi-automated object-based image analysis (OBIA) rule set approach for desert landforms detection and mapping. Sentinel-2 image and digital elevation model (DEM) were acquired for the study area. The multi-resolution segmentation algorithm was employed on the datasets to select relevant features to define appropriate segmentation scales for all landform categories. Object-based rule sets were then employed using spatial (DEM and its derivatives, e.g., slope, aspect, and hillshade) and spectral information for semi-automated classification of the desert landforms. Desert landforms are detected and classified into four classes: saline dome, barchan, playa, and dune. The Fuzzy Synthetic Evaluation (FSE) technique was applied in concert with the error matrix to validate the accuracy of the classification results based on field data, Google Earth, and geological maps. Our findings demonstrated the highest confidence of overall accuracy (OA) 96.21%, 92.58%, 95.99%, and 95.05% respectively, for the saline dome, barchan, playa, and dune. Results showed the strong potential of the rule-based OBIA remote sensing approach for desert landform detection and delineation. Results further demonstrated the efficiency of spatial and spectral features for desert landforms detection and delineation.

Feature-Based Approach to Change Detection of Small Objects from High-Resolution Satellite Images

This paper proposes a new approach to small-object change detection from high-resolution satellite images. We propose using feature points that can be quickly extracted from satellite images as a suitable unit of change for small objects and to reduce false alarms. We can perform feature-based change detection by extracting features from previous and recent images and by estimating change based on change magnitude of the features. We estimate the magnitude by calculating pixel-based change magnitude, and counting the ratio of changed pixels around the extracted features. We apply feature matching and determine matched features as unchanged ones. The remaining feature points are judged as changed or unchanged based on their change magnitude. We tested our approach with three Kompsat-3A image sets with a ground sampling distance of 50 cm. We showed that our approach outperformed the pixel-based approach by producing a higher precision of 88.7% and an accuracy of 86.1% at a fixed false alarm rate of 10%. Our approach is unique in the sense that the feature-based approach applying computer vision methods is newly proposed for change detection. We showed that our feature-based approach was less noisy than pixel-based approaches. We also showed that our approach could compensate for the disadvantages of supervised object-based approaches by successfully reducing the number of change candidates. Our approach, however, could not handle featureless objects, and may increase the number of undetected objects. Future studies will handle this issue by devising more intelligent schemes for merging pixel-based and feature-based change detection results.

Paddy lands detection using Landsat-8 satellite images and object-based classification in Rasht city, Iran

Rice is one of the most important food staples in many countries, particularly Iran. Because irrigated rice production differs from other agricultural fields, this study developed a paddy field mapping model based on phenological aspects, various satellite sensor data, and an object-based approach. This study uses the phonological features of rice plants as well as annual data on land surface temperature (LST) to produce the paddy map. The core remote sensing data consists of the yearly LST from MODIS and multi-temporal Landsat-8 satellite imagery. The detection of phenological characteristics and the selection of relevant Landsat images were made possible by analyzing the LST time series with Google Earth Engine. After that, object-based image classification and fuzzy functions are used to create flexible and comprehensible rules for discovering paddy fields in Rasht, Iran. Data such as the digital elevation model (DEM) and spectral indices including NDVI, EVI, and LSWI were employed to improve the object-based classification. Due to the unique properties of paddy lands, a DEM of 12.5 m obtained from the ALOS PALSAR sensor could help distinguish paddy lands from other vegetation. A comparison finally made between the object-based and pixel-based classification methods showed that the former is more accurate. Overall accuracy and kappa coefficient for the pixel-based classification approach were 92% and 0.89, respectively, whereas overall accuracy and kappa coefficient for the object-based classification method were 94% and 0.92, respectively. Eventually, the producer's accuracy of the paddy class has increased from 88% to 94%.

Classification of Medicinal Plants Astragalus Mongholicus Bunge and Sophora Flavescens Aiton Using GaoFen-6 and Multitemporal Sentinel-2 Data

Accurate information regarding cultivated areas of medicinal plants is useful for taking macro-level decisions for medicinal plant management and contingency plans. In this study, the capabilities and limitations of mapping Astragalus mongholicus Bunge and Sophora flavescens Aiton using GaoFen-6 and multitemporal Sentinel-2 data were assessed through a case study in Naiman Banner, Inner Mongolia, China. First, an object-based approach was used to produce a cropland mask based on the GaoFen-6 images. Then, different spectral indices were generated from multitemporal Sentinel-2 imagery acquired in 2019, and a temporal phonological pattern analysis was conducted. Subsequently, optimal feature selection was carried out for each of the crops (Astragalus mongholicus Bunge, Sophora flavescens Aiton and Zea mays L.). The selection was performed by sorting all features according to their global separability index and removing those whose contribution to the model accuracy was negligible. Finally, the medicinal crops were distinguished using the random forest classification algorithm. An overall accuracy and a kappa coefficient of 94.51% and 0.90 were achieved, respectively, demonstrating that the synergistic use of time series GaoFen-6 and Sentinel-2 data were more suitable for Astragalus mongholicus Bunge and Sophora flavescens Aiton mapping.

Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning

Unsupervised multimodal change detection is a practical and challenging topic that can play an important role in time-sensitive emergency applications. To address the challenge that multimodal remote sensing images cannot be directly compared due to their modal heterogeneity, we take advantage of two types of modality-independent structural relationships in multimodal images. In particular, we present a structural relationship graph representation learning framework for measuring the similarity of the two structural relationships. Firstly, structural graphs are generated from preprocessed multimodal image pairs by means of an object-based image analysis approach. Then, a structural relationship graph convolutional autoencoder (SR-GCAE) is proposed to learn robust and representative features from graphs. Two loss functions aiming at reconstructing vertex information and edge information are presented to make the learned representations applicable for structural relationship similarity measurement. Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations and two difference images are generated based on the similarity levels. After obtaining the difference images, an adaptive fusion strategy is presented to fuse the two difference images. Finally, a morphological filtering-based postprocessing approach is employed to refine the detection results. Experimental results on five datasets with different modal combinations demonstrate the effectiveness of the proposed method.

Biases in the Prediction of Convective Storm Characteristics with a Convection Allowing Ensemble

Abstract The severity, duration, and spatial extent of thunderstorm impacts are related to convective storm mode. This study assesses the skill of the High-Resolution Rapid Refresh Ensemble (HRRR-E) and its deterministic counterpart (HRRRv4) at predicting convective mode and storm macrophysical properties using 35 convective events observed during the 2020 warm season across the eastern United States. Seven cases were selected from each of five subjectively determined convective organization modes: tropical cyclones, mesoscale convective systems (MCSs), quasi-linear convective systems, clusters, and cellular convection. These storm events were assessed using an object-based approach to identify convective storms and determine their individual size. Averaged across all 35 cases, both the HRRR-E and HRRRv4 predicted storm areas were generally larger than observed, with this bias being a function of storm lifetime and convective mode. Both modeling systems also underpredicted the rapid increase in storm counts during the initiation period, particularly for the smaller-scale storm modes. Interestingly, performance of the HRRRv4 differed from that of the HRRR-E, with the HRRRv4 generally having a larger bias in total storm area than the HRRR-E due to HRRRv4 predicting up to 66% more storm objects than the HRRR-E. The HRRR-E accurately predicted the convective mode 65% of the time, with complete misses being very rare (<5% of the time overall). However, an evaluation of rank histograms across all 35 cases revealed that the HRRR-E tended to be underdispersive when predicting storm size for all but the MCS mode.

Abnormality Identification in Video Surveillance System using DCT

In the present world, video surveillance methods play a vital role in observing the activities that take place across secured and unsecured environment. The main aim with which a surveillance system is deployed is to spot abnormalities in specific areas like airport, military, forests and other remote areas, etc. A new block-based strategy is represented in this paper. This strategy is used to identify unusual circumstances by examining the pixel-wise frame movement instead of the standard object-based approaches. The density and also the speed of the movement is extorted by utilizing optical flow. The proposed strategy recognizes the unusual movement and differences by using discrete cosine transform coefficient. Our goal is to attain a trouble-free block-based Discrete Cosine Transform (DCT) strategy that promotes real-time abnormality detection. The proposed approach has been evaluated against an airport dataset and the outcome of unusual happenings occurred in is evaluated and reported.