Infrastructure, such as buildings, bridges, pavement, etc., needs to be examined periodically to maintain its reliability and structural health. Visual signs of cracks and depressions indicate stress and wear and tear over time, leading to failure/collapse if these cracks are located at critical locations, such as in load-bearing joints. Manual inspection is carried out by experienced inspectors who require long inspection times and rely on their empirical and subjective knowledge. This lengthy process results in delays that further compromise the infrastructure’s structural integrity. To address this limitation, this study proposes a deep learning (DL)-based autonomous crack detection method using the convolutional neural network (CNN) technique. To improve the CNN classification performance for enhanced pixel segmentation, 40,000 RGB images were processed before training a pretrained VGG16 architecture to create different CNN models. The chosen methods (grayscale, thresholding, and edge detection) have been used in image processing (IP) for crack detection, but not in DL. The study found that the grayscale models (F1 score for 10 epochs: 99.331%, 20 epochs: 99.549%) had a similar performance to the RGB models (F1 score for 10 epochs: 99.432%, 20 epochs: 99.533%), with the performance increasing at a greater rate with more training (grayscale: +2 TP, +11 TN images; RGB: +2 TP, +4 TN images). The thresholding and edge-detection models had reduced performance compared to the RGB models (20-epoch F1 score to RGB: thresholding −0.723%, edge detection −0.402%). This suggests that DL crack detection does not rely on colour. Hence, the model has implications for the automated crack detection of concrete infrastructures and the enhanced reliability of the gathered information.
This paper aims at providing a descriptive view of the lowfrequency sea level changes around the northern Australian coastline. Twenty years of sea level observations from multi-mission satellite altimetry and tide gauges are used to characterize sea level trends and inter-annual variability over the study region. The results show that the interannual sea level fingerprint in the northern Australian coastline is closely related to El Niño Southern Oscillation (ENSO) and Madden-Julian Oscillation (MJO) events, with the greatest influence on the Gulf Carpentaria, Arafura Sea, and the Timor Sea. The basin average of 14 tide-gauge time series is in strong agreement with the basin average of the altimeter data, with a root mean square difference of 18 mm and correlation coefficient of 0.95. The rate of sea level rise (6.3 ± 1.4 mm/yr) estimated from tide gauges is slightly higher than that (6.1 ± 1.3 mm/yr) from altimetry in the time interval 1993-2013, which can vary with the length of the time interval. Here we provide new insights into examining the significance of sea level trends by applying the nonparametric Mann-Kendall test. This test is applied to assess if the trends are significant (upward or downward). Apart from a positive rate of sea level rise, trends are not statistically significant in this region due to the effects of natural variability. The findings suggest that altimetric trends are not significant along the coasts and some parts of the Gulf Carpentaria (14°S-8°S), where geophysical corrections (e.g., ocean tides) cannot be estimated accurately and altimeter measurements are contaminated by reflections from the land.
This paper suggests a new algorithm for automatic building point cloud filtering based on the Z coordinate histogram. This operation aims to select the roof class points from the building point cloud, and the suggested algorithm considers the general case where high trees are associated with the building roof. The Z coordinate histogram is analyzed in order to divide the building point cloud into three zones: the surrounding terrain and low vegetation, the facades, and the tree crowns and/or the roof points. This operation allows the elimination of the first two classes which represent an obstacle toward distinguishing between the roof and the tree points. The analysis of the normal vectors, in addition to the change of curvature factor of the roof class leads to recognizing the high tree crown points. The suggested approach was tested on five datasets with different point densities and urban typology. Regarding the results’ accuracy quantification, the average values of the correctness, the completeness, and the quality indices are used. Their values are, respectively, equal to 97.9%, 97.6%, and 95.6%. These results confirm the high efficacy of the suggested approach.
This paper presents an innovative approach to the automatic modeling of buildings composed of rotational surfaces, based exclusively on airborne LiDAR point clouds. The proposed approach starts by detecting the gravity center of the building's footprint. A thin point slice parallel to one coordinate axis around the gravity center was considered, and a vertical cross-section was rotated around a vertical axis passing through the gravity center, to generate the 3D building model. The constructed model was visualized with a matrix composed of three matrices, where the same dimensions represented the X, Y, and Z Euclidean coordinates. Five tower point clouds were used to evaluate the performance of the proposed algorithm. Then, to estimate the accuracy, the point cloud was superimposed onto the constructed model, and the deviation of points describing the building model was calculated, in addition to the standard deviation. The obtained standard deviation values, which express the accuracy, were determined in the range of 0.21 m to 1.41 m. These values indicate that the accuracy of the suggested method is consistent with approaches suggested previously in the literature. In the future, the obtained model could be enhanced with the use of points that have considerable deviations. The applied matrix not only facilitates the modeling of buildings with various levels of architectural complexity, but it also allows for local enhancement of the constructed models.
The north of Australia is known for its complex tidal system, where the highest astronomical tides (HATs) reach 12 m. This paper investigates the tidal behaviour in this region by developing spectral climatology for tide gauge and altimetry data. Power spectral density analysis is applied to detect the magnitude of ocean tides in 20 years of sea-level data from multimission satellite altimeters and tide gauges. The spectra of altimetry sea level anomaly (SLA) time series have their strongest peaks centred at approximately 2.11, 5.88, and 7.99 cycles per year (cpy), corresponding to the diurnal and semidiurnal tidal constituents K1, M2, and O1, respectively. Closer to the coastline, the spectra peak at high-frequency overtide and shallow-water constituents such as M4, MK4, and MK3. There have been many large, high-frequency spectral peaks near the coastline, indicating the difficulty of predicting tidal signals by coastal altimetry. Similar to altimetry observations, there are dominant semidiurnal and diurnal tidal peaks in tide gauge SLA time series accompanying a number of overtides. The semidiurnal and diurnal peaks are mostly higher on the northwest coast of Australia compared with the north and northeast coast. The results from both altimetry and tide gauges indicate that tidal range increases with increasing continental shelf.
Machine Learning (ML) applications on Light Detection And Ranging (LiDAR) data have provided promising results and thus this topic has been widely addressed in the literature during the last few years. This paper reviews the essential and the more recent completed studies in the topography and surface feature identification domain. Four areas, with respect to the suggested approaches, have been analyzed and discussed: the input data, the concepts of point cloud structure for applying ML, the ML techniques used, and the applications of ML on LiDAR data. Then, an overview is provided to underline the advantages and the disadvantages of this research axis. Despite the training data labelling problem, the calculation cost, and the undesirable shortcutting due to data downsampling, most of the proposed methods use supervised ML concepts to classify the downsampled LiDAR data. Furthermore, despite the occasional highly accurate results, in most cases the results still require filtering. In fact, a considerable number of adopted approaches use the same data structure concepts employed in image processing to profit from available informatics tools. Knowing that the LiDAR point clouds represent rich 3D data, more effort is needed to develop specialized processing tools.
Sea level rise is an important and topical issue in the South Pacific region and needs an urgent assessment of trends for informed decision making. This paper presents mean sea level trend assessment using harmonic analysis and a hybrid deep learning (DL) model based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique, Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU) and Neighbourhood Component Analysis (NCA) to build a highly accurate sea level forecasting model for three small islands (Fiji, Marshall Island and Papua New Guinea (PNG)) in the South Pacific. For a 20-year period, the estimated mean sea level rise per year from the harmonic computation is obtained: 112 mm for PNG, 98 mm for Marshall Island and 52 mm for Fiji. The DL procedure uses climate and environment-based remote sensing satellite (MODIS, GLDAS-2.0, MODIS TERRA, MERRA-2) predictor variables with tide gauge base mean sea level (MSL) data for model training and development for forecasting. The developed CEEMDAN-CNN-GRU as the objective model is benchmarked by comparison to the hybrid model without data decomposition, CNN-GRU and standalone models, Decision Trees (DT) and Support Vector Regression (SVR). All model performances are evaluated using reliable statistical metrics. The CEEMDAN-CNN-GRU shows superior accuracy when compared with other standalone and hybrid models. It shows an accuracy of >96% for correlation coefficient and an error of <1% for all study sites.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.