Pixel-based Analysis Research Articles

Automatic detection of building roofs from point clouds produced by the dense image matching technique

ABSTRACTThree-dimensional (3D) spatial information of object points is a vital requirement for many disciplines. Laser scanning technology and techniques based on image matching have been used extensively to produce 3D dense point clouds. These data are used frequently in various applications, such as the generation of digital surface model (DSM)/digital terrain model (DTM), extracting objects (e.g., buildings, trees, and roads), 3D modelling, and detecting changes. The aim of this study was to extract the building roof points automatically from the 3D point cloud data created via the image matching techniques with optical aerial images (with red, green, and blue band (RGB) and infrared (IR)). In the first stage of the study, as an alternative to laser scanning technology, which is more expensive than optical imaging systems, the 3D point clouds were produced by matching high-resolution images using a Semi Global Matching algorithm. The normalized difference vegetation index (NDVI) values for each point were calculated using the spectral information (RGB + IR) in the 3D point cloud data, and the points that represented the vegetation cover were determined using these values. In the second stage, existing ground and non-ground points that were free of vegetation cover were determined within the point cloud. Subsequently, only the points on the roof of the building were detected automatically using the proposed algorithm. Thus, points of the roofs of buildings located in areas with different topographic characteristics were detected automatically detected using only images. It was determined that the average values of correctness (Corr), completeness (Comp), and quality (Q) of the pixel-based accuracy analysis metrics were 95%, 98%, and 93%, respectively, in the selected test areas. According to the results of the accuracy analysis, it is clear that the proposed algorithm is very successful in automatic extraction of building roof points.

MONITORING AND PREDICTING LAND USE-LAND COVER (LULC) CHANGES WITHIN AND AROUND KRAU WILDLIFE RESERVE (KWR) PROTECTED AREA IN MALAYSIA USING MULTI-TEMPORAL LANDSAT DATA

Natural and anthropogenic activities surrounding a Protected Area (PA) may cause its natural area to change in terms of Land Use-Land Cover (LULC). Thus, there is need of environmental change monitoring within and around PA because of its significant values to ecosystem at conservation scales. Effects and influences of local community within and around PA turn into the major problems for natural resource and conservations management as well as environmental impact assessment. Ascertaining the complex interface in relations to changes and its driving factors over period of time within and around PA is significant in order to predict future LULC changes, build alternative scenarios and serve as tools for decision making. The main objective of this work was to evaluate temporal change detection and prediction of LULC as well as the trends of changes from 1989 to 2016 within and around Krau Wildlife Reserve (KWR). The cloud issues were mitigated by producing cloud free image and object-based image analysis (OBIA) was adopted after a comparison with pixel-based analysis for overall accuracy and kappa statistics. The comparison of classified maps had produced a satisfactory results of overall accuracies of 91%, 86% and 90% for 1989, 2004 and 2016 respectively. The natural/dense forest between periods of 1989-2016 was decreased whereas built-up and agricultural/sparse forest were increased. The simulation model of Land Change Modeler (LCM) was utilized with digital elevation model (DEM) and past LULC maps to project future LULC pattern using Markov chain. The predicted map trend showed an increase of dense forest converted to agricultural/sparse forest in the north-western, and urban/built-up in east-southern part of KWR. The study is important for the conservation of habitat species and monitoring the current status of the KWR

Object-based multiscale method for SAR image change detection

This paper proposed an object-based multiscale method for synthetic aperture radar (SAR) image change detection based on the statistical model. Rather than the pixel-based analysis conducted in the traditional way, the object-based image analysis was employed to take a collection of pixels as the unit of analysis, which reduced small spurious changes and was less strict relative to registration. In addition, a multiscale concept was adopted to exhibit the inherent multiscale characteristics of the target. To achieve object-based, multiscale change detection results, the multidate segmentation was performed on two temporal SAR images and extended to a set of suitable scales. Then, the Edgeworth series expansion was employed to estimate the probability density function, and the Kullback–Leibler divergence was adopted to calculate the distance between pairs of pixel collections. Next, the divergence index maps were divided into changed and unchanged classes to obtain change detection results for each scale. Finally, the subresults were combined to obtain a more accurate detection result. The experimental results obtained using real data demonstrated the effectiveness of the proposed method.

Correction: Diffusion weighted imaging in patients with rectal cancer: Comparison between Gaussian and non-Gaussian models

[This corrects the article DOI: 10.1371/journal.pone.0184197.].

Combining pixel and object based image analysis of ultra-high resolution multibeam bathymetry and backscatter for habitat mapping in shallow marine waters

Habitat mapping data are increasingly being recognised for their importance in underpinning marine spatial planning. The ability to collect ultra-high resolution (cm) multibeam echosounder (MBES) data in shallow waters has facilitated understanding of the fine-scale distribution of benthic habitats in these areas that are often prone to human disturbance. Developing quantitative and objective approaches to integrate MBES data with ground observations for predictive modelling is essential for ensuring repeatability and providing confidence measures for habitat mapping products. Whilst supervised classification approaches are becoming more common, users are often faced with a decision whether to implement a pixel based (PB) or an object based (OB) image analysis approach, with often limited understanding of the potential influence of that decision on final map products and relative importance of data inputs to patterns observed. In this study, we apply an ensemble learning approach capable of integrating PB and OB Image Analysis from ultra-high resolution MBES bathymetry and backscatter data for mapping benthic habitats in Refuge Cove, a temperate coastal embayment in south-east Australia. We demonstrate the relative importance of PB and OB seafloor derivatives for the five broad benthic habitats that dominate the site. We found that OB and PB approaches performed well with differences in classification accuracy but not discernible statistically. However, a model incorporating elements of both approaches proved to be significantly more accurate than OB or PB methods alone and demonstrate the benefits of using MBES bathymetry and backscatter combined for class discrimination.

The potentials of Sentinel-2 and LandSat-8 data in green infrastructure extraction, using object based image analysis (OBIA) method

ABSTRACTGreen infrastructure (GI) mapping and monitoring is crucial in urban areas, and remote sensing is widely used to accomplish the task. Improved moderate resolution Sentinel-2A (10 m) and LandSat-8 (15 m) images, in place of commercial satellite images, enable GI mapping with little to no cost. Considering so, the objective of this paper is to evaluate the potential of GI feature extraction of Sentinel-2A (S2) and LandSat-8 (L8) (freely available images) using the Object Based Image Analysis (OBIA) method. The advantage of using OBIA over pixel-based analysis has been investigated primarily with very high resolution images. Using OBIA, bottom up (i.e. Multiresolution) and top down (i.e. Spectral Difference) segmentation were implemented using eCognition to obtain image objects for both S2 and L8 images. Then, rule-based classification was performed to extract GI areas from the objects. NDVI, NDWI, NIR/R ratios were utilized in rule set development, after several trial and error process. Both S2 and L8 provided acceptable extraction of GI for urban areas. However, with an overall accuracy of 71.24%, S2 was more effective when extracting GI areas. Shadows along roads and high rise buildings caused some inaccuracy in classification.

Coastal wetland change detection using high spatial resolution KOMPSAT-2 imagery

Coastal wetlands store terrestrial carbon and conserve biodiversity, thus playing an essential ecological role. Reliable regional-scale assessments of wetland dynamics, such as analysis of land use and land cover (LULC), and coastal monitoring, provide important hydrographical and socio-geographical information. Remote sensing images, such as Earth Observation satellite data, are useful for examining temporal LULC changes and providing environmental monitoring data. This study presents a method of mapping and monitoring changes in coastal LULC using classified multispectral images acquired by the Korea Multi-Purpose Satellite-2 (KOMPSAT-2). Wetland changes are monitored in three different protected tidal flats areas on the coastal boundary of the Korean Peninsula with the Yellow Sea, for the period of 2008 - 2015. High overall accuracy and Kappa coefficient values for the accuracy assessment indicate the suitability of LULC classification using high spatial resolution KOMPSAT imagery, even when an unsupervised classification approach is adopted. The LULC maps were analyzed and evaluated using post-classification change detection methods. Results showed spatial decreases of 6 and 20% for mixed forest and wetlands in the Gyeonggi area, respectively, but no significant changes over time for Jeonbuk and Jeonnam. There was a 12% increase in developed areas for Gyeonggi but only 1.9 and 6% for Jeonbuk and Jeonnam, respectively. LULC change is thus easily identified through a pixel-based analysis of multispectral KOMPSAT-2 images over time. Such data are useful for environmental and policy managers when developing advanced coastal management strategies.

Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis

Efficient methodologies for mapping croplands are an essential condition for the implementation of sustainable agricultural practices and for monitoring crops periodically. The increasing spatial and temporal resolution of globally available satellite images, such as those provided by Sentinel-2, creates new possibilities for generating accurate datasets on available crop types, in ready-to-use vector data format. Existing solutions dedicated to cropland mapping, based on high resolution remote sensing data, are mainly focused on pixel-based analysis of time series data. This paper evaluates how a time-weighted dynamic time warping (TWDTW) method that uses Sentinel-2 time series performs when applied to pixel-based and object-based classifications of various crop types in three different study areas (in Romania, Italy and the USA). The classification outputs were compared to those produced by Random Forest (RF) for both pixel- and object-based image analysis units. The sensitivity of these two methods to the training samples was also evaluated. Object-based TWDTW outperformed pixel-based TWDTW in all three study areas, with overall accuracies ranging between 78.05% and 96.19%; it also proved to be more efficient in terms of computational time. TWDTW achieved comparable classification results to RF in Romania and Italy, but RF achieved better results in the USA, where the classified crops present high intra-class spectral variability. Additionally, TWDTW proved to be less sensitive in relation to the training samples. This is an important asset in areas where inputs for training samples are limited.

Fast Ca2+ responses in astrocyte end-feet and neurovascular coupling in mice.

Cerebral blood flow (CBF) is regulated by the activity of neurons and astrocytes. Understanding how these cells control activity-dependent increases in CBF is crucial to interpreting functional neuroimaging signals. The relative importance of neurons and astrocytes is debated, as are the functional implications of fast Ca2+ changes in astrocytes versus neurons. Here, we used two-photon microscopy to assess Ca2+ changes in neuropil, astrocyte processes, and astrocyte end-feet in response to whisker pad stimulation in mice. We also developed a pixel-based analysis to improve the detection of rapid Ca2+ signals in the subcellular compartments of astrocytes. Fast Ca2+ responses were observed using both chemical and genetically encoded Ca2+ indicators in astrocyte end-feet prior to dilation of arterioles and capillaries. A low dose of the NMDA receptor antagonist (5R,10s)-(+)-5-methyl-10,11-dihydro-5H-dibenzo[a,d]cyclohepten-5,10-imine-hydrogen-maleate (MK801) attenuated fast Ca2+ responses in the neuropil and astrocyte processes, but not in astrocyte end-feet, and the evoked CBF response was preserved. In addition, a low dose of 4,5,6,7-tetrahydroisoxazolo[5,4-c]pyridin-3-ol (THIP), an agonist for the extrasynaptic GABAA receptor (GABAA R), increased CBF responses and the fast Ca2+ response in astrocyte end-feet but did not affect Ca2+ responses in astrocyte processes and neuropil. These results suggest that fast Ca2+ increases in the neuropil and astrocyte processes are not necessary for an evoked CBF response. In contrast, as local fast Ca2+ responses in astrocyte end-feet are unaffected by MK801 but increase via GABAA R-dependent mechanisms that also increased CBF responses, we hypothesize that the fast Ca2+ increases in end-feet adjust CBF during synaptic activity.

A comparative analysis of pixel- and object-based detection of landslides from very high-resolution images

A comparative analysis of landslides detected by pixel-based and object-oriented analysis (OOA) methods was performed using very high-resolution (VHR) remotely sensed aerial images for the San Juan La Laguna, Guatemala, which witnessed widespread devastation during the 2005 Hurricane Stan. A 3-band orthophoto of 0.5m spatial resolution together with a 115 field-based landslide inventory were used for the analysis. A binary reference was assigned with a zero value for landslide and unity for non-landslide pixels. The pixel-based analysis was performed using unsupervised classification, which resulted in 11 different trial classes. Detection of landslides using OOA includes 2-step K-means clustering to eliminate regions based on brightness; elimination of false positives using object properties such as rectangular fit, compactness, length/width ratio, mean difference of objects, and slope angle. Both overall accuracy and F-score for OOA methods outperformed pixel-based unsupervised classification methods in both landslide and non-landslide classes. The overall accuracy for OOA and pixel-based unsupervised classification was 96.5% and 94.3%, respectively, whereas the best F-score for landslide identification for OOA and pixel-based unsupervised methods: were 84.3% and 77.9%, respectively.Results indicate that the OOA is able to identify the majority of landslides with a few false positive when compared to pixel-based unsupervised classification.

Identifying city PV roof resource based on Gabor filter

To identify a city’s PV roof resources, the area and ownership distribution of residential buildings in an urban district should be assessed. To achieve this assessment, remote sensing data analysing is a promising approach. Urban building roof area estimation is a major topic for remote sensing image information extraction. There are normally three ways to solve this problem. The first way is pixel-based analysis, which is based on mathematical morphology or statistical methods; the second way is object-based analysis, which is able to combine semantic information and expert knowledge; the third way is signal-processing view method. This paper presented a Gabor filter based method. This result shows that the method is fast and with proper accuracy.

Comprehensive two-dimensional gas chromatography in combination with pixel-based analysis for fouling tendency prediction

Fouling tendencies of a series of gas condensates were evaluated using comprehensive two-dimensional gas chromatography with flame ionization detection and sulfur chemiluminescence detection. A pixel-based approach was applied in order to identify parts of the chromatograms which were associated with the reactor coil fouling. Particular emphasis is given in this work to evaluate several feature selection methodologies along with various data preprocessing procedures. It was found that both aspects were crucial for studying the fouling tendencies and, as part of the subsequent partial least squares model development, predominantly the feature selection. Based on the flame ionization detector chromatograms and using the RReliefF algorithm for feature selection, a partial least squares regression model with one latent variable resulted in a root mean square error of the cross-validation of 0.65gdeposit/6h (17%). Based on the sulfur chemiluminescence detector chromatograms, the F-statistics feature selection generated a slightly better partial least squares regression model compared to using RReliefF, thus generating a model using one latent variable with a root mean square error of the cross-validation of 0.81gdeposit/6h (21%). Heavy aromatic compounds and heavy sulfur containing compounds were negatively associated with the fouling rate. Both were crucial in developing a partial least squares model with good prediction power, however, worked independently as predictors.

Performance evaluation strategy for cool roof based on pixel dependent variable in multiple spatial regressions

Performance evaluation for cool roof has been mainly based on field sampling, which relies on attributes of an area at one point in time, reflecting an emphasis on the small number of in situ data. One of the major disadvantages of traditional field monitoring is that it is costly, laborious and time consuming due to the large number of samples required. Acknowledging these constraints, this research was inspired by the fact that pixel of remotely-sensed imagery could play a key role in presenting rooftop temperature remarkably due to thermal sensitivity channel. The aim of this research is primarily intended to show how to evaluate energy saving performance of color changing roof, based on pixel of remotely-sensed imagery, together with multiple spatial regressions. An empirical study for a case study site was suggested to demonstrate how a standard remote sensing and multiple spatial regression approach can be used to assist in monitoring performance of cool roof based on thermal pixel in terms of various specific settings such as season, sunset, sunrise timing, solar facing and sitting orientation etc. It is expected that the pixel-based analysis would make it possible to identify area-wide patterns of cool roof performance subject to many different type of artificial structures, which cannot be acquired by traditional field sampling. This research will be used as a valuable reference in implementing performance evaluation for color roofing since the quantitative data generated from remote sensing and multiple spatial regressions can present area-wide visual evidences by permanent record.

Toward Abnormal Trajectory and Event Detection in Video Surveillance

In this paper, we present a unified approach for abnormal behavior detection and group behavior analysis in video scenes. Existing approaches for abnormal behavior detection do either use trajectory-based or pixel-based methods. Unlike these approaches, we propose an integrated pipeline that incorporates the output of object trajectory analysis and pixel-based analysis for abnormal behavior inference. This enables to detect abnormal behaviors related to speed and direction of object trajectories, as well as complex behaviors related to finer motion of each object. By applying our approach on three different data sets, we show that our approach is able to detect several types of abnormal group behaviors with less number of false alarms compared with existing approaches.

Small FDIRC designs

In this article11The paper was presented at the RICH 2016 conference, Bled, Slovenia, September 2016. we explore the angular resolution limits attainable in small FDIRC designs taking advantage of the new highly pixelated detectors that are now available. Since the basic FDIRC design concept attains its particle separation performance mostly in the angular domain as measured by two-dimensional pixels, this paper relies primarily on a pixel-based analysis, with additional chromatic corrections using the time domain, requiring single photon timing resolution at a level of 100–200ps only. This approach differs from other modern DIRC design concepts such as TOP or TORCH detectors,22See presentation at this conference. whose separation performances rely more strongly on time-dependent analyses. We find excellent single photon resolution with a geometry where individual bars are coupled to a single plate, which is coupled in turn to a cylindrical lens focusing camera.

Extraction optimization and pixel-based chemometric analysis of semi-volatile organic compounds in groundwater

Combined dual extraction steps provided high enrichment factors and separation of peaks from unresolved complex mixtures in groundwaters. For the first time, pixel-based analysis of summed extracted ion chromatograms (sEIC's) was used for the characterization of semi-VOCs.

Comparison of the Estimated Result of Ecosystem Service Value Using Pixel-based and Object-based Analysis

Comparison of the Estimated Result of Ecosystem Service Value Using Pixel-based and Object-based Analysis

Who Recognized Fake Image Better: A Comparison Study between Human and Computer

Along with the rapid development of multimedia and information technology in the recent years, a large number of photos and videos can be easily created and distributed by each and every member of our society. Some of these images are genuine, while some others have gone through modifications. Although the creation and posting of edited photographs in media are basically not prohibited, it becomes a problem when they are used improperly. Until now, the common practice in Indonesia when assessing whether an image has been modified or is original is still heavily dependent on human expert assessment that could be subjective. This research offers an alternative solution that is objective by developing a systematic image analysis method for distinguishing between original and modified image. The method utilizes high-level feature, namely the metadata of the image file, to differentiate between original and modified image. A prototype system was implemented in Visual Basic as a desktop application. The application used MS Windows GDI+. This prototype application can be used as a reliable and faster means to assist in fake image detection. However, as metadata-based analysis only detects whether a photograph has possibly been edited and it does not show which part of the photograph has been manipulated, future work includes development of pixel-based analysis approach.

Quantitative imaging by pixel-based contrast-enhanced ultrasound reveals a linear relationship between synovial vascular perfusion and the recruitment of pathogenic IL-17A-F+IL-23+ CD161+ CD4+ T helper cells in psoriatic arthritis joints.

To develop quantitative imaging biomarkers of synovial tissue perfusion by pixel-based contrast-enhanced ultrasound (CEUS), we studied the relationship between CEUS synovial vascular perfusion and the frequencies of pathogenic T helper (Th)-17 cells in psoriatic arthritis (PsA) joints. Eight consecutive patients with PsA were enrolled in this study. Gray scale CEUS evaluation was performed on the same joint immediately after joint aspiration, by automatic assessment perfusion data, using a new quantification approach of pixel-based analysis and the gamma-variate model. The set of perfusional parameters considered by the time intensity curve includes the maximum value (peak) of the signal intensity curve, the blood volume index or area under the curve, (BVI, AUC) and the contrast mean transit time (MTT). The direct ex vivo analysis of the frequencies of SF IL17A-F+CD161+IL23+ CD4+ T cells subsets were quantified by fluorescence-activated cell sorter (FACS). In cross-sectional analyses, when tested for multiple comparison setting, a false discovery rate at 10%, a common pattern of correlations between CEUS Peak, AUC (BVI) and MTT parameters with the IL17A-F+IL23+ - IL17A-F+CD161+ - and IL17A-F+CD161+IL23+ CD4+ T cells subsets, as well as lack of correlation between both peak and AUC values and both CD4+T and CD4+IL23+ T cells, was observed. The pixel-based CEUS assessment is a truly measure synovial inflammation, as a useful tool to develop quantitative imaging biomarker for monitoring target therapeutics in PsA.

Classification of Land Use on Sand-Dune Topography by Object-Based Analysis, Digital Photogrammetry, and GIS Analysis in the Horqin Sandy Land, China

Previous field research on the Horqin Sandy Land (China), which has suffered from severe desertification during recent decades, revealed how land use on a sand-dune topography affects both land degradation and restoration. This study aimed to depict the spatial distribution of local land use in order to shed more light on previous field findings regarding policies on a broader scale. We performed the following analyses with Panchromatic Remote-sensing Instrument for Stereo Mapping (PRISM) and Advanced Visible and Near Infrared Radiometer type 2 (AVNIR-2) images of Advanced Land Observing Satellite (ALOS): (1) object-based classification to discriminate preliminary classification of land-use types that were approximately differentiated by ordinary pixel-based analysis with spectral information; (2) digital photogrammetry to generate a digital surface model (DSM) with adequately high accuracy to represent undulating sand-dune topography; (3) geographic information system (GIS) analysis to classify major topographic types with the digital surface model (DSM); and (4) overlay of the two classification results to depict the local land-use types. The overall accuracies of the object-based and GIS-based classifications were high, at 93% (kappa statistic: 0.84) and 89% (kappa statistic: 0.81), respectively. The resultant local land-use map represents areas covered in previous field studies, showing where and how land degradation and restoration are likely to occur. This research can contribute to future environmental surveys, models, and policies in the study area.