Search

The authors previously published positive peer-reviewed (21 raters using the Terzis scale) and photogrammetric (Emotrics) outcomes in patients who had undergone two-stage lower lip reanimations up to 2018. Other series have published surgeon and peer-rated results, but we know of only two (n=12) that have assessed patients' views using patient satisfaction surveys. This paper presents patient-rated outcomes (PROMS) in an 11-year series of both single and two-stage anterior belly of digastric muscle (ABDM) lower lip reanimations. Demographics, paralysis characteristics, operative details, and complications were recorded. Patients were telephoned and requested to complete the Glasgow Benefit Inventory (GBI) to assess patient-rated outcomes. Thirty-two patients were eligible (mean age 36.4 years). Twenty-one (63.6%) completed the GBI (mean score +33.3). More patients reported benefit than detriment (95.2% vs 4.8%). Complications were infrequent and included three cases of superficial infections and one of dermatitis. Four patients (12.5%) underwent minor revisions, mostly lipofilling of lip notches. The median (range) duration of follow up was 2.8 (0.3 - 8.5) years. ABDM transfer for lower lip reanimation is a safe, low morbidity procedure that enhances the psychological wellbeing of patients with facial palsy.

In obstructive sleep apnea (OSA), the upper airway is obstructed during sleep due to obesity and/or posterior collapse of the tongue root. Maxillofacial morphological abnormalities increase the risk of OSA in the Asian population. This study sought to elucidate whether three-dimensional (3D) photogrammetry measurements correlate with the severity of OSA irrespective of sex and degree of obesity.A prospective pilot study was performed, in which 37 consecutive adult patients (M/F = 28/9) underwent polysomnography and 3D photogrammetry in the supine position for the diagnosis of OSA. Measurements obtained from 3D photogrammetry included mandibular width (Mw), mandibular length (Ml), mandibular depth (Md), mandibular width-length angle (Mwla), and mandibular area (Ma). The effects of sex and body mass index (BMI) on the measurements and their association with the apnea-hypopnea index (AHI) were statistically analyzed. The inter-rater reliability of the measurements was evaluated using intraclass correlation coefficients (ICC).Mwla (R = 0.73, p 0.01), Mw (R = 0.39, p 0.05), and Md (R = -0.34, p 0.05) were significantly correlated with the severity of OSA. On multivariate analysis, Mwla (p 0.01) and Md (p 0.05) remained independent factors for AHI after adjusting for sex, age, BMI, and neck circumference. In addition, diagnosability analysis revealed that Mwla was useful for identifying the presence of OSA (AHI ≥5) (cutoff: 78.6°, sensitivity: 0.938, specificity: 0.800, area under the curve: 0.931). The ICC was0.9, showing high reliability.This study suggests that Mwla measured using 3D photogrammetry can predict the presence of OSA and correlates with the severity of OSA, independent of obesity and sex.

INTRODUCTION This study aimed to evaluate changes in facial size and shape in children and their relationship to the changes in height and weight. METHODS One hundred and thirteen healthy children aged between 6 and 13��years were followed annually for 2 consecutive years. The facial morphology was captured in 12-month intervals (from T1 to T2 and from T2 to T3) using a 3-dimensional stereophotogrammetric optical scanner; the body height and weight were recorded simultaneously. The changes in facial size and shape were analyzed with geometric morphometrics. Multiple regression mixed-effects models were exploited for evaluation of the association between the changes of facial size or shape and age at the beginning of the observation, gender, and change of height and weight. RESULTS The centroid size (reflecting facial size) increased from T1 to T2 and T2 to T3 in boys and girls. In contrast, the facial shape did not change during both 12-month observation periods (T1 to T2 and T2 to T3) either in boys or girls. Of 2 multiple regression mixed-effects models, only the model with the change of natural logarithm of centroid size as a dependent variable was statistically significant (P��

Feature matching is a fundamental and important task in many applications of remote sensing and photogrammetry. Remote sensing images often involve complex spatial relationships due to the ground relief variations and imaging viewpoint changes. Therefore, using a pre-defined geometrical model will probably lead to inferior matching accuracy. In order to find good correspondences, we propose a simple yet efficient deep learning network, which we term the ``local structure visualization-attention'' network (LSV-ANet). Our main aim is to transform outlier detection into a dynamic visual similarity evaluation. Specifically, we first map the local spatial distribution into a regular grid as descriptor LSV, and then customized a spatial SCale Attention (SCA) module and a spatial STructure Attention (STA) module, which explicitly allows structure manipulation and scale selection of LSV within the network. Finally, the embedded SCA and STA deduce optimal LSV for solving feature matching task by training the LSV-ANet end-to-end. In order to demonstrate the robustness and universality of our LSV-ANet, extensive experiments on various real image pairs for general feature matching are conducted and compared against eight state-of-the-art methods. The experiment results demonstrate the superiority of our method over state of the art.

Automatic building extraction from high-resolution remote sensing images plays an important role in many application fields, such as the urban planning and photogrammetry. However, the complex background and large variety in building appearances in high-resolution remote sensing images make the building instance extraction challenging. In this study, we propose a novel two-stage instance segmentation network named gated spatial memory and centroid-aware network (GSMC) to handle these problems. Two new modules, including a gated spatial memory module (GSM) and a centroid-aware head (CH), are developed in our GSMC. The GSM is a top-down spatial structure and semantic information transmission module, where two gates including an input gate and a state gate are designed to strengthen the important features and replenish the lacking information. The CH is a new task head for regressing the geometric center of each instance, which can help to promote the accurate and complete recognition for irregularly shaped buildings. Experiments on the WHU Aerial data set, the WHU Satellite data set, and the Massachusetts Building data set demonstrate that the proposed GSMC can achieve consistently superior performances when compared with the recent state-of-the-art deep learning methods.

The purpose of this paper was to determine the usability of unmanned hydrographic drones and photogrammetric techniques during the conduct of work, the results of which are potentially to serve as navigational materials in areas that, due to their characteristics, make it impossible to carry out research using crew vessels and direct shoreline determination. In order to prepare and carry out the measurement campaign with the greatest possible accuracy and safety, the authors of the article decided to determine the shoreline of the analyzed reservoir using photogrammetric methods. The use of satellite images allowed the border between land and water to be identified as precisely as possible, which had a direct impact on the accuracy of relating depth data to their location on Earth's globe. Use of unmanned vessels and orthophotos can find practical application when navigating vessels during maneuvers required high precision.

Semantic segmentation is important for the understanding of subdecimeter aerial images. In recent years, deep convolutional neural networks (DCNNs) have been used widely for semantic segmentation in the field of remote sensing. However, because of the highly complex subdecimeter resolution of aerial images, inseparability often occurs among some geographic entities of interest in the spectral domain. In addition, the semantic segmentation methods based on DCNNs mostly obtain context information using extra information within the added receptive field. However, the context information obtained this way is not explicit. We propose a novel class-constraint coarse-to-fine attentional (CCA) deep network, which enables the formation of class information constraints to obtain explicit long-range context information. Further, the performance of subdecimeter aerial image semantic segmentation can be improved, particularly for fine-structured geographic entities. Based on coarse-to-fine technology, we obtained a coarse segmentation result and constructed an image class feature library. We propose the use of the attention mechanism to obtain strong class-constrained features. Consequently, pixels of different geographic entities can adaptively match the corresponding categories in the class feature library. Additionally, we employed a novel loss function, CCA-loss to realize end-to-end training. The experimental results obtained using two popular open benchmarks, International Society for Photogrammetry and Remote Sensing (ISPRS) 2-D semantic labeling Vaihingen data set and Institute of Electrical and Electronics Engineers (IEEE) Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest Zeebrugge data set, validated the effectiveness and superiority of our proposed model. The proposed method achieved state-of-the-art performance on the IEEE GRSS Data Fusion Contest Zeebrugge data set.

Ecosystem restoration has been practiced for over a century and is increasingly supported by the emergent applied science of restoration ecology. A prerequisite for successful ecosystem restoration is determining meaningful and measurable goals. This requires tools to monitor success in a standardized way. Photogrammetry uses images to reconstruct landscapes and organisms in three dimensions, enabling non-invasive measurement of key success indicators with unprecedented accuracy. We propose photogrammetry can improve restoration success by: (i) facilitating measurable goals; (ii) innovating and standardizing indicators of success; and (iii) standardizing monitoring. While the case we present is specific to coral reefs, photogrammetry has enormous potential to improve restoration practice in a wide range of ecosystems.

Multi-sensor data fusion has recently gained a wide attention within the Geomatics research community, as it helps overcome the limitations of a single sensor and enables a complete 3D model for the structure and a better object classification. This study develops a data fusion algorithm, which optimally combines sensor data from a terrestrial and an unmanned aerial system (UAS) to obtain an improved and a complete 3D mapping model of a structure. Terrestrial laser scanner (TLS) data are collected for the exterior of a building along with the DJI Phantom 4 Pro and terrestrial close-range Sony α7R camera images. A number of ground control points and targets are established throughout the scanned building for the photogrammetric process and scans registration. Different point cloud datasets are generated from the TLS, UAS and the terrestrial Sony camera images. The created point clouds from each individual sensor and the fused point clouds are used in different forms, namely the original, denoised and subsampled point clouds. The denoised point cloud dataset is generated through the application of the statistical outlier remover (SOR) filter on the original point clouds. The relative precision of the 3D models is investigated using the multiscale model-to-model cloud comparison (M3C2) method. The TLS-based 3D model is used as a reference. It is found that the precision of the Sony-based 3D model is higher than the other two models for the original and denoised datasets. The fused Sony/UAS-based model provides a complete 3D model with precision higher than the UAS-based model.

Driver eye height and object height are key factors in the derivation of basic parameters for safe and economically efficient highway design. In this work, previous approaches to the measurement of these values were critically reviewed and the changes in them over time were investigated. Previous methods of measurement were found to have considerable limitations in terms of coverage or accuracy. A new approach was thus developed for the naturalistic recording of a sample of vehicles using the principles of photogrammetry – the first time this approach has been used for all vehicle types. A field survey on a typical single-carriageway UK trunk road was undertaken and the driver eye and object heights of vehicles using the route were recorded. This work confirms the consumer trend for larger vehicles with a consequential increase in driver eye height and object height. It was found that the values used in current design standards are conservative and robust, but potential exists for further review. The results of this study will be useful to roads authorities internationally in defining their own highway design standards.

Thermal infrared (TIR) images acquired from Unmanned Aircraft Vehicles (UAV) are gaining scientific interest in a wide variety of fields. However, the reconstruction of three-dimensional (3D) point clouds utilizing consumer-grade TIR images presents multiple drawbacks as a consequence of low-resolution and induced aberrations. Consequently, these problems may lead photogrammetric techniques, such as Structure from Motion (SfM), to generate poor results. This work proposes the use of RGB point clouds estimated from SfM as the input for building thermal point clouds. For that purpose, RGB and thermal imagery are registered using the Enhanced Correlation Coefficient (ECC) algorithm after removing acquisition errors, thus allowing us to project TIR images into an RGB point cloud. Furthermore, we consider several methods to provide accurate thermal values for each 3D point. First, the occlusion problem is solved through two different approaches, so that points that are not visible from a viewing angle do not erroneously receive values from foreground objects. Then, we propose a flexible method to aggregate multiple thermal values considering the dispersion from such aggregation to the image samples. Therefore, it minimizes error measurements. A naive classification algorithm is then applied to the thermal point clouds as a case study for evaluating the temperature of vegetation and ground points. As a result, our approach builds thermal point clouds with up to 798,69% more point density than results from other commercial solutions. Moreover, it minimizes the build time by using parallel computing for time-consuming tasks. Despite obtaining larger point clouds, we report up to 96,73% less processing time per 3D point.

This study was conducted to compare the performance of three different spatial analysis models: Inverse Distance Weighted (IDW), Ordinary Kriging,­­ and Regularized Spline interpolation technique to determine the best fit model representing Peak Ground Acceleration (PGA) in West Java Province, Indonesia. The three models are commonly used in spatial visualization, but have different calculation methods. The calculations were performed using available formulas while the spatial modeling was conducted using the algorithms in GIS software. Meanwhile, the accuracy of the spatial model and factual calculation was determined through the Root Mean Square Error (RMSE). The results showed differences for both spatial distribution and maximum and minimum values for each model. However, IDW was observed to be the model which approaches the factual value of the PGA calculation as indicated by its RMSE value of 0.772352 in comparison with the 7.169879 (Ordinary Kriging) and 1.140802 (Regularized Spline).

Geomatics engineering (GIS, GPS, Remote sensing, and photogrammetry) offers a lower cost and faster prediction of the threat of landslides to road traffic safety. They reduce the cost and the time needed for the monitoring of the active sliding land areas around the highways. The objective is to assess the potential of geomatics engineering in deciding slope failure occurrence after landslide to insure traffic safety. Several types of geomatics data (GPS, Photogrammetry, high resolution satellite images) will be used to predict the threat of landslides on the highway. Landslides around the highways lead to dangerous accidents, significant economic loss and disruption of traffic flow. As a case study, we considered unstable area with continuous landslides where a major highway is traversing and suffers from yearly disruption and accidents due to landslides. An area around the North Highway (Amman-Jerash highway) which connects the capital Amman to three important governorates Irbid, Jerash and Ajloun was studied and analysed using Geomatics engineering techniques to predict its stability after land slide. This highway traverses a mountainous area with repeated unpredicted dangerous landslides after the rainy season. Landslides cause tremendous problems to this artery highway and sometimes corrupt traffic for months. The late landslides occurred in 2017 and 2019 caused massive destruction and disruption of the traffic flow. For the sake of comparison with the used classical methods, the results of land stability detection obtained from geomatics processing were compared with those obtained by the classical methods (based on field and laboratory works). The results (obtained from the use of geomatics techniques) completely agreed with the geo-technique, geologic and water studies using data obtained from the Ministry of Public Works and Housing (MPWH). As a result, Geomatics techniques provided the same detection results faster and at lower cost.

This study aims to produce accurate geospatial 3D data from unmanned aerial vehicle (UAV) images. An image of a ≈ 0.05 km2 area of the Najran University campus in Najran, Saudi Arabia, was captured using a DJI Mavic Pro Platinum drone. Agisoft Metashape and Pix4dmapper programs were used to generate the solution. The horizontal and vertical accuracies of the obtained UAV solution were computed by comparing the coordinates of 21 ground control points (GCPs) with coordinates measured using the RTK GPS method. The accuracy of the four different GCP configurations was evaluated using both software packages. The root mean square error (RMSE) was calculated for some checkpoints. The generated model achieved the 2015 ASPRS accuracy standards for digital geospatial data, while horizontal RMSE values were 4–6 cm and vertical accuracy was 5–6 cm. The horizontal and vertical RMSE values were twice and three times the GSD, respectively.

A cost-effective approach is described for sharing virtual fossil specimens through 3D digitisation using readily available hardware and software. Modern digitization methods such as this can support continued research when it would otherwise be limited by travel restrictions, such as during the Covid-19 pandemic. A Hewlett-Packard structured light scanner pro s3 system using HP3D scan software pro v5 was used to scan the fossils and the data shared through cloud storage, thereby facilitating the first description of dinosaurs from Ireland.

BACKGROUND The extent of facial involvement in positional plagiocephaly is only little investigated so far. Investigation methods that take into account the challenging anatomical conditions and growth of infants' faces are desirable. In this study, the authors established a new three-dimensional photogrammetry quantification method evaluating pretherapeutic and posttherapeutic facial asymmetry in positional plagiocephaly. Furthermore, a facial asymmetry index was established and evaluated. METHODS Three-dimensional photographs of 100 children undergoing treatment with head orthoses were analyzed by constructing a standardized interindividual coordinate system. Defining landmarks, section planes, and point coordinates with a computer-aided design software, both sides of the faces were compared. Facial asymmetry was quantified by measuring differences between left and right sides and pretherapeutic and posttherapeutic changes in each patient. The facial asymmetry index was calculated by putting the absolute differences in relation with the coordinates of the nonaffected side. RESULTS Present results indicate that positional plagiocephaly results in a distinct facial asymmetry (range, -3.8 to 9.6 mm) in nearly all spatial directions and facial regions. Helmet therapy led to a significant reduction (p < 0.05) of intraindividual facial asymmetry (median change in facial asymmetry index, -1.9 to 3.1 percent). However, no correlation of the Cranial Vault Asymmetry Index and facial asymmetry (Spearman rank correlation coefficient, ρ = -0.09 to 0.47) has been seen. According to these results, severe occipital deformation does not necessarily provoke distinct facial asymmetry. CONCLUSIONS Present three-dimensional photogrammetry method allows the longitudinal quantification of facial involvement in positional plagiocephaly. Asymmetry has been determined in all facial regions. The facial asymmetry decreased through helmet therapy but was not eliminated completely.

Unmanned aerial vehicles (UAVs), which have made a name for themselves in photogrammetry studies in recent years, provide users with integrated camera systems. Identifying interior orientation parameters, such as focal coordinates, focal length and distortions, is an essential requirement for camera systems used for photogrammetric purposes. This process, which is called camera calibration, is offered automatically by software from the library. Another important known calibration method is self-calibration. Calibrating cameras by creating 2D or 3D test areas is a troublesome and grueling option. However, it is the most commonly accepted way in terms of accuracy. In this study, images were taken in different test areas (2D and 3D) to perform the calibrations of the cameras integrated on two different UAVs, namely DJI Phantom 4 Pro and Parrot Anafi. The calibration parameters determined from the images taken were compared with the calibration parameters obtained by the self-calibration method, and block adjustment was performed with ground control points marked in the study area. In order to perform performance analysis, the root-mean-square error (RMSE) was determined from the control points. In conclusion, it was determined that the results of both the calibrations obtained with the test fields and those obtained with self-calibration were acceptable.

Unmanned aerial vehicle (UAV) photogrammetry without ground control points (GCPs) can effectively improve production efficiency and reduce production costs; this method is especially advantageous in areas that are difficult for people to reach. However, there are a series of problems in UAV photogrammetry without GCPs. One of the main problems is that the accurate camera parameters cannot be obtained through the on-the-job calibration method; furthermore, the inaccurate principal distance will have a serious impact on the elevation accuracy of object points. The other one is that the projection deformation and earth curvature also have impacts on the elevation accuracy, when the mapping task is carried out in the map projection frame. This article explains the specific reasons of elevation errors and proposes an effective solution. First, the camera self-calibration is performed in a geocentric frame with control strips. Then, the exterior orientation elements of the images are calculated in the map projection frame without control strips. Finally, the elevation errors that are caused by the map projection deformation and the earth’s curvature are corrected. The experimental results show that the proposed method can achieve accurate mapping, and the elevation accuracy has been significantly improved.

Structure from Motion (SfM) is key to mixed computer vision and photogrammetry applications. However, the fast-growing needs for large-scale SfM bring challenges to current SfM solutions. Unlike traditional global and incremental SfM solutions, hierarchical SfM approaches demonstrate promising potential in effectively reconstructing large-scale image sets by dividing the image set into multiple image clusters, reconstructing each cluster separately, and gradually merging partial models into a complete model. However, current hierarchical SfM approaches still suffer from the following problems: accurate image clustering without ancillary information; automatic quality evaluation of each reconstruction unit and unreliable partial reconstruction removal; effective and efficient reconstruction of each image cluster; robust and accurate cluster merging considering the merging order and the handling of images taken with the same camera but divided into different clusters. These unstable factors limit the robustness and accuracy of hierarchical SfM approaches on different unstructured image sets. To systematically improve the performance of hierarchical SfM, we propose a novel robust hierarchical structure from motion (RHSfM) method for large-scale image sets, which does not rely on any additional information, such as Global Positioning System (GPS) and Inertial Navigation System (INS). (1) We develop an automatic image clustering method based on image correlation and present a dynamic adjustment strategy, obtaining reliable image clustering results. (2) We remove the poor reconstructions by introducing multiple quality evaluation standards. (3) We put forward a fast incremental SfM algorithm that optimizes the image adding mode with an image pre-screening strategy and gets rid of the dependence by the proposed dynamic adjustment strategy. (4) We achieve accurate cluster merging by creating an optimal merging list and employing a stepwise global optimization strategy that merges structures first and then cameras. Significantly, the entire process is fully automated with only a few input parameters, and the final result is not sensitive to these parameters. We verify our method on various real image sets that cover different image conditions, different scenes, and different image scales, especially two large-scale image sets with 121,506 and 153,396 images, respectively. The experimental results reveal that our approach outperforms the state-of-the-art SfM systems Colmap, 3DF Samantha, and Metashape in terms of robustness, accuracy, and efficiency. In particular, only our method successfully reconstructed all the seven challenging datasets. For the five datasets that the other systems can also reconstruct, our method obtains the highest accuracy, which is 25 percent better than the best result of the comparable methods on average; for the remaining two datasets, the accuracy of our method is higher than 0.75 pixels. Moreover, the efficiency of our method is about 18, 4.85, and 0.25 times faster than Colmap, 3DF Samantha, and Metashape averagely on the experimental image sets, respectively. After all, our contribution provides a comprehensive and practical solution for large-scale SfM.

In this paper, we propose a model-driven method that reconstructs LoD-2 building models following a "decomposition-optimization-fitting" paradigm. The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a "three-step" polygon extraction method, followed by a novel grid-based decomposition method that decomposes the complex and irregularly shaped building polygons to tightly combined elementary building rectangles ready to fit elementary building models. We have optionally introduced OpenStreetMap (OSM) and Graph-Cut (GC) labeling to further refine the orientation of 2D building rectangle. The 3D modeling step takes building-specific parameters such as hip lines, as well as non-rigid and regularized transformations to optimize the flexibility for using a minimal set of elementary models. Finally, roof type of building models s refined and adjacent building models in one building segment are merged into the complex polygonal model. Our proposed method has addressed a few technical caveats over existing methods, resulting in practically high-quality results, based on our evaluation and comparative study on a diverse set of experimental datasets of cities with different urban patterns., 16 figures, 31 pages

BACKGROUND Human cadavers are an essential component of anatomy education. However, access to cadaveric specimens and laboratory facilities is limited in most parts of the world. Hence, new innovative approaches and accessible technologies are much needed to enhance anatomy training. OBJECTIVE To provide a practical method for 3-dimensional (3D) visualization of cadaveric specimens to maximize the utility of these precious educational materials. METHODS Embalmed cadaveric specimens (cerebrum, brain stem, and cerebellum) were used. The 3D models of cadaveric specimens were built by merging multiple 2-dimensional photographs. Pictures were taken with standard mobile devices (smartphone and tablet). A photogrammetry program (Qlone®, 2017-2020, EyeCue Vision Technologies Ltd, Yokneam, Israel), an all-in-one 3D scanning and augmented reality technology, was then used to convert the images into an integrated 3D model. RESULTS High-resolution 360-degree 3D models of the cadaveric specimens were obtained. These models could be rotated and moved freely on different planes, and viewed from different angles with varying magnifications. Advanced editing options and the possibility for export to virtual- or augmented-reality simulation allowed for better visualization. CONCLUSION This inexpensive, simple, and accessible method for creating 360-degree 3D cadaveric models can enhance training in neuroanatomy and allow for a highly realistic surgical simulation environment for neurosurgeons worldwide.

Coastal erosion has become an issue globally. As the sea level continues to rise due to global warming, projections are that erosion would increase. To address the issue sustainably, relevant scientific information such as sediment transport and shoreline dynamics is required at local scales. Over the years, erosion at the eastern coast of Ghana has been mainly evaluated using low-resolution imagery due to the challenges in retrieving high-resolution data in the nearshore region. An unmanned aerial vehicle (UAV) approach was used to assess beach evolution on a seasonal and short-term basis between May 2018 and December 2019. Using the UAV approach, shoreline changes, sediment volume changes, and profile elevation parameters were extracted for the Dzita beach of Ghana. Shoreline changes indicated the dominance of erosion during the first and third phases (May 2018–December 2018 and June 2019–December 2019, respectively) at a rate of −7.23 ± 0.23 and −4.85 ± 0.23 m/yr, whereas the second phase (January 2019–June 2019) showed accretion of +8.44 ± 0.23 m/yr. Beach profiles from the first, second, and third phases had steep and gentle slopes, respectively. From these observations, it was recommended that soft engineering approaches such as beach nourishment should be implemented to protect the shoreline and strict prevention of nearshore sand mining and gravel mining. It is also possible that the beach could go through a cycle of changes. Further studies using this same approach should be done as well as probing into other parameters such as nearshore bathymetry to have a better understanding of beach dynamics as envisaged.

The paper deals with the calibration of a non-metric digital camera Nikon EOS 6D with a 50 mm lens that could be adapted as a potential UAV sensor for the purposes of aerial inspections. The determination of the internal orientation parameters and the image errors of the non-metric digital camera involved self-calibration with Agisoft Metashape software solving the network of the images obtained from different test fields: a chessboard field, a professional laboratory field and a spatially diverse research area. The results of the control measurement for the examined object distance of 6 meters do not differ significantly. The RMSE from the control measurement for the second analyzed object distance of 15 meters was calculated on the basis of the internal orientation elements. The images from the laboratory field, the spatial test area and the chessboard field were used, and the obtained results amounted to 7.9, 9.9 and 11.5 mm, respectively. The conducted studies showed that in the case of very precise photogrammetric measurements performed by means of the Nikon EOS 6D camera equipped with a 50 mm lens, it is optimal to conduct calibration in a laboratory test field. The greatest RMSE errors were recorded for the control images with the elements of the internal camera orientation calculated on the basis of the chessboard area. The results of the experiments clearly show a relation between the accuracy of the Nikon EOS 6D camera calibrations and the percentage of the frame area filled with the test field. This explains why the weakest calibration results were obtained from the chessboard test field.

The objective of our study is the evaluation of the 3D modeling of buildings and the extraction of structural elements from point clouds obtained using two acquisition techniques (drone and terrestrial laser scanner), as well as the evaluation of the usefulness of their integration. The drone shooting mission was carried using the DJI Phantom 3 Professional and the Sony EXMOR 1/2.3" CMOS RGB camera. For the TLS scanning mission, 9 scanning stations were performed using the FARO Focus S350 laser scanner.To allow the fusion of the two point clouds obtained from drone imagery and TLS, an alignment step is applied. This step was performed using the Iterative Closest Point algorithm. Segmentation was performed using the adapted RANSAC algorithm on point clouds obtained from the drone mission and the TLS mission as well as on the merged point cloud in order to extract structural elements of the building such as windows, doors and stairs. Analysis of the results emphasizes the importance of TLS and drone in 3D modeling. TLS gave better results than the drone in extracting structural elements. This work confirms the importance of complementarity between these two technologies to produce detailed, complete and precise 3D models.

Photogrammetry-based method is gaining popularity in many fields. One of the main tasks of photogrammetry is to identify the homologous points in multiple images, which is commonly referred to as the corresponding problem. Coded targets are often placed on the surfaces of the targeted objects and have been widely used as a reliable method for solving the corresponding problem in photogrammetry for high-accuracy three-dimensional measurements. Automated recognition and identification of coded targets are of great importance in the coded target-based photogrammetry. However, false coded target identifications are inevitable due to large perspective distortion, unfavorable lighting conditions, and low-resolution, low-quality images, etc. As a result, manual corrections are often required, which are tedious, prone to error, and inefficient. In this paper, a faster R-CNN-based method has been proposed to recognize coded targets. Then, a table method has been developed to automatically identify and reject the falsely identified coded targets by taking advantages of the prior knowledge of the geometric arrangement of the coded targets. Based on that, missing coded targets can be recovered using either interpolation or extrapolation method. The effectiveness and accuracy of the proposed method are validated by implementing it into three-dimensional reconstruction of soil specimens during triaxial testing in geotechnical engineering. Experimental validation results indicate that the proposed method can achieve accurate and efficient coded target recognition and identification.

Video surveillance camera (VSC) is an important source of information during investigations especially if used as a tool for the extraction of verified and reliable forensic measurements. In this study, some aspects of human height extraction from VSC video frames are analyzed with the aim of identifying and mitigating error sources that can strongly affect the measurement. More specifically, those introduced by lens distortion are present in wide-field-of-view lens such as VSCs. A weak model, which is not able to properly describe and correct the lens distortion, could introduce systematic errors. This study focuses on the aspect of camera calibration to verify human height extraction by Amped FIVE software, which is adopted by the Forensic science laboratories of Carabinieri Force (RaCIS), Italy. A stable and reliable approach of camera calibration is needed since investigators have to deal with different cameras while inspecting the crime scene. The performance of the software in correcting distorted images is compared with a technique of single view self-calibration. Both approaches were applied to several frames acquired by a fish-eye camera and then measuring the height of five different people. Moreover, two actual cases, both characterized by common low-resolution and distorted images, were also analyzed. The height of four known persons was measured and used as reference value for validation. Results show no significant difference between the two calibration approaches working with fish-eye camera in test field, while evidence of differences was found in the measurement on the actual cases.

We present a new aerial image dataset, named ESPADA, intended for the training of deep neural networks for depth image estimation from a single aerial image. Given the difficulty of creating aerial image datasets containing image pairs of chromatic images related to their depth images, simulators such as AirSim have been proposed to generate synthetic images from photorealistic scenes. The latter enables the generation of thousands of images that can be used to train and evaluate neural models. However, we argue that synthetic photorealistic aerial image datasets can be improved by adding images generated from photogrammetric models imported into the simulator, thus enabling a less artificial generation of both chromatic and depth images. To assess the quality of these images, we compare the performance of 4 deep neural networks whose pre-trained models and code for re-training are publicly available. We also use ORB-SLAM, in its RGB-D version, to indirectly assess the estimated depth image. To accomplish this, chromatic images from 3 aerial videos and their depth images, estimated with the networks trained with ESPADA, are fed into ORB-SLAM. The estimated camera pose is compared against the trajectory retrieved from the GPS flight trajectory. Our results indicate that images generated from photogrammetric models improve the performance of depth estimation from a single aerial image.

To solve problems in 3D modelling, including unclear 3D edges in point clouds, lack of geometric semantics, confusing topological relations between 3D models, and low degree of automation in traditional model-driven 3D modelling, a method for high-accuracy and automatic monomer 3D modelling must be developed. This paper is the first to propose a 3D modelling strategy, called combining data-and-model-driven 3D modelling (CDMD3DM), for small regular objects in indoor scenes using RGB-D data. The proposed method’s workflow is as follows: generation of initial 3D point cloud data using data-driven Kinect v2; segmentation of point cloud data, based on deep learning, that improves the accuracy and automation of geometric model recognition; definition of the initial model-driven parameters based on the instance segmentation results; optimization of geometric model parameters, based on generalized point photogrammetry theory, to generate monomer models in indoor scenes to overcome the shortcomings of confusing topological relationships and inaccurate 3D model edges; and finally, fusion of the results of data-driven and model-driven 3D modelling. The experimental results demonstrate that CDMD3DM is feasible, automatic, more accurate, more reliable, semantically richer and capable of producing clearer topological relationships than current 3D modelling results using indoor RGB-D data. These outcomes promote interdisciplinary integration between computer vision and photogrammetry.

Increases in the social sector of open data and online mapping technologies are starting new chances for interactive mapping in many research applications. Mobile crowd sensing is an application that gathers data from a network of conscientious volunteers and implements it for a public benefit which is very helpful for collecting related information during the COVID-19 situation. The paper aims to demonstrate the concept of #Safe Mapping Platform which followed a framework of opensource technology and implementation aspects. The #Safe Mapping Platform was established for self-tracking and self-risk managing by integrating GIS opensource technologies, location-based services, and LINE application. The developed platform can be adapted to the public for self-tracking and self-risk managing in any health issues in the future.

Conventional methods for measuring the deformational response of geosynthetics, such as the linear variable differential transformers (LVDTs), strain gauges, and extensometers have several limitations in fully determining the complete strain distribution in geosynthetics. This paper presents a multi-camera based photogrammetric method to track the 3D full-field displacements of geosynthetics during tensile tests. The proposed method extends the conventional one-camera based photogrammetry for static object measurements to multi-camera-based photogrammetry for object measurements with continuous movements or deformations. It is non-contact, cost-effective, highly accurate, and capable of measuring the 3D full-field displacements of the geosynthetics. A tensile test on a geogrid specimen was performed to verify the effectiveness and accuracy of the proposed photogrammetric method. The results from the tensile tests using both the proposed method and conventional methods, such as machine-controlled displacement measurements and extensometer, were presented and compared. It was observed that the average absolute difference between the proposed photogrammetric method and the machine-controlled movements of the bottom clamp was 0.25%, and the average absolute error was 0.038 mm. The average difference in measurements made by the proposed method and extensometer was 0.07%. It was further found that the proposed method can provide more comprehensive input, such as the complete strain and modulus distributions in the geosynthetics, for a probability-based geosynthetics design.

Detailed, accurate, and frequent mapping of land cover are the prerequisite regarding areas of reclaimed mines and the development of sustainable project-level for goals. Mine reclamation is essential as the extractive organizations are bounded by-laws that have been established by stakeholders to ensure that the mined areas are properly restored. As databases at the mines area become outdated, an automated process of upgrading is needed. Currently, there are only few studies regarding mine reclamation which has less potential of land cover classification using Unmanned Aerial Vehicle (UAV) photogrammetry with Deep learning (DL). This paper aims to employ the classification of land cover for monitoring mine reclamation using DL from the UAV photogrammetric results. The land cover was classified into five classes, comprising: 1) trees, 2) shadow, 3) grassland, 4) barren land, and 5) others (as undefined). To perform the classification using DL, the UAV photogrammetric results, orthophoto and Digital Surface Model (DSM) were used. The effectiveness of both results was examined to verify the potential of land cover classification. The experimental findings showed that effective results for land cover classification over test area were obtained by DL through the combination of orthophoto and DSM with an Overall Accuracy of 0.904, Average Accuracy of 0.681, and Kappa index of 0.937. Our experiments showed that land cover classification from combination orthophoto with DSM was more precise than using orthophoto only. This research provides framework for conducting an analytical process, a UAV approach with DL based evaluation of mine reclamation with safety, also providing a time series information for future efforts to evaluate reclamation. The procedure resulting from this research constitutes approach that is intended to be adopted by government organizations and private corporations so that it will provide accurate evaluation of reclamation in timely manner with reasonable budget.

В процессе автоматизации решения прикладных измерительных задач, в том числе на базе фотограмметрических методов, возникает проблема соответствия измерительной системы объекту и условиям измерения. Для того чтобы измерительная система позволяла заранее оценить возможность получения достоверных результатов, а также наилучшим образом подстраивалась под условия измерения, необходимо наличие специализированных алгоритмов и моделей. В общем случае такие модели ориентированы на квалифицированных технических специалистов, обладающих необходимыми знаниями в области информационных технологий. Особенностью применения фотограмметрических измерительных систем в лесной и металлургической промышленности является низкая квалификация пользователей в сфере информационных технологий, что обуславливается характером выполняемых работ и условиями привлечения. Данный фактор не позволяет решить задачу подстройки системы традиционными методами, в которых процессом настройки управляет пользователь. В этой связи в статье предлагается модель и алгоритм формирования измерительной системы по первичным входным данным, в котором процессом настройки управляет сама система. In the process of automating the solution of applied measurement tasks, including on the basis of photogrammetric methods, there is a problem of compliance of the measurement system with the object and measurement conditions. In order for the measuring system to assess in advance the possibility of obtaining reliable results, as well as to best adapt to the conditions of measurement, it is necessary to have specialized algorithms and models. In general, such models are aimed at qualified technicians with the necessary knowledge in the field of information technology. A feature of the application of photogrammetric measurement systems in the forestry and metallurgical industry is the low qualification of users in the field of information technology, which is determined by the nature of the work performed and the conditions of attraction. This factor does not solve the problem of adjusting the system by traditional methods in which the user controls the configuration process. In this regard, the article proposes a model and algorithm for forming a measuring system from primary input data, in which the system itself controls the adjustment process.

Постановка задачи. Одной из актуальных научно-технических задач в строительстве является совершенствование методов мониторинга состояния строительных конструкций (в том числе в стесненных условиях работы) при строительстве уникальных сооружений и объектов незавершенного строительства, обеспечивающих надежный контроль их качества, устойчивости и безопасности. Довольно часто возникают условиях, при которых нет возможности выполнить полноценный мониторинг отдельных видов деформаций строительных конструкций традиционными методами. Требуется разработка универсальных, надежных и удобных методов контроля различных геометрических параметров сооружения с целью своевременного принятия мер по обеспечению стабильности и устойчивости сооружения, чтобы исключить переход сооружения в ограниченно работоспособное или в аварийное состояние. Результаты и выводы. Предложенные в работе методы определения деформаций и качества изготовления строительных конструкций с использованием метрической фотосъемки позволяют провести полноценный мониторинг их технического состояния с необходимой точностью. Все перечисленные в статье способы контроля отрабатывались и проверялись на зданиях и сооружениях законсервированной Воронежской атомной станции теплоснабжения. Statement of the problem. One of the urgent scientific and technical problems facing construction is the improvement of methods for monitoring the state of building structures (including under confined working conditions) during the construction of unique structures and objects of unfinished construction, ensuring reliable control of their quality, stability and safety. Oftentimes, conditions arise where it is impossible to perform a full types of deformations of building structures using traditional methods. It is required to develop universal, reliable and convenient methods for controlling various geometric parameters of the structure in order to take timely measures to ensure the stability and stability of the structure in order to exclude the transition of the structure to a partially operable or emergency state. Results and conclusions. The suggested methods for determining deformations and the quality of manufacturing of building structures using metric photography make it possible to conduct a full-fledged monitoring of their technical condition with the required accuracy. All the control methods listed in the article were developed and tested on the buildings and structures of the mothballed Voronezh nuclear heat supply station.

Influence of footwear on posture in athletes is poorly documented despite its potential impact on biomechanics and injury risk. The aim of this study was to investigate effects of different footwear geometries on comfort and posture on a cohort of 48 elite rugby players. Spine posture was characterized by photogrammetry, while center of pressure was measured by means of a force platform. Three different footwear outsoles architectures (one rugby shoe with flat outsole, one rugby shoe with a 10 mm heel rise and foot arch support, and a running shoe with a 10mm heel rise and foot arch support) were compared to non-shod in randomized order. Then comfort felt at the level of foot and spine was also estimated by subjective questionnaires. Compared to the flat rugby model, both other models induced significantly (p

This paper presents a unique study to reveal the effect of the mounting system of the linear variable differential transformer (LVDT) on the mechanical property tests of timber materials. This effect has been overlooked in the past but proven to be significant enough that will distort the measurements completely if the displacement is relatively small. The reason for causing this error is because the LVDT is not directly measuring targeting points on a sample, instead, the LVDT is measuring the distance between one point on the stop-end (where the tip rested on) and the holder. The wrong common sense hopes that this point on the stop-end and holder reliably following the movement of the sample points. But this study reveals that it is not always the case with the aid from the photogrammetry method. The messages of this paper are simple but alertly useful and, important: 1) the mounting system and the method of installation of the LVDTs have a significant impact on the actual displacement measurement in a mechanical properties test of timber materials. It should be carefully designed and validated before the actual test; 2) the displacement distribution is not uniform across the timber sample. This should be taken into account when selecting the mounting points of the LVDTs. Testing standards should consider this effect when recommending displacement transducers to be used in a timber-related test.

Increasingly, drone-based photogrammetry has been used to measure size and body condition changes in marine megafauna. A broad range of platforms, sensors, and altimeters are being applied for these purposes, but there is no unified way to predict photogrammetric uncertainty across this methodological spectrum. As such, it is difficult to make robust comparisons across studies, disrupting collaborations amongst researchers using platforms with varying levels of measurement accuracy. Here we built off previous studies quantifying uncertainty and used an experimental approach to train a Bayesian statistical model using a known-sized object floating at the water’s surface to quantify how measurement error scales with altitude for several different drones equipped with different cameras, focal length lenses, and altimeters. We then applied the fitted model to predict the length distributions and estimate age classes of unknown-sized humpback whales Megaptera novaeangliae, as well as to predict the population-level morphological relationship between rostrum to blowhole distance and total body length of Antarctic minke whales Balaenoptera bonaerensis. This statistical framework jointly estimates errors from altitude and length measurements from multiple observations and accounts for altitudes measured with both barometers and laser altimeters while incorporating errors specific to each. This Bayesian model outputs a posterior predictive distribution of measurement uncertainty around length measurements and allows for the construction of highest posterior density intervals to define measurement uncertainty, which allows one to make probabilistic statements and stronger inferences pertaining to morphometric features critical for understanding life history patterns and potential impacts from anthropogenically altered habitats.

The increasing use of digital technologies can provide significant benefits to the excavation and interpretative process in archaeology. Yet, despite major developments in the last two decades, dig...

Background Being able to accurately assess the 3D architecture of plant canopies can allow us to better estimate plant productivity and improve our understanding of underlying plant processes. This is especially true if we can monitor these traits across plant development. Photogrammetry techniques, such as structure from motion, have been shown to provide accurate 3D reconstructions of monocot crop species such as wheat and rice, yet there has been little success reconstructing crop species with smaller leaves and more complex branching architectures, such as chickpea. Results In this work, we developed a low-cost 3D scanner and used an open-source data processing pipeline to assess the 3D structure of individual chickpea plants. The imaging system we developed consists of a user programmable turntable and three cameras that automatically captures 120 images of each plant and offloads these to a computer for processing. The capture process takes 5–10 min for each plant and the majority of the reconstruction process on a Windows PC is automated. Plant height and total plant surface area were validated against “ground truth” measurements, producing R2 > 0.99 and a mean absolute percentage error Conclusions Our results show that it is possible to use low-cost photogrammetry techniques to accurately reconstruct individual chickpea plants, a crop with a complex architecture consisting of many small leaves and a highly branching structure. We hope that our use of open-source software and low-cost hardware will encourage others to use this promising technique for more architecturally complex species.

Documentation is a key step for cognition of cultural heritage, and also a requisite for conservation and adaptive reuse actions. Petroleum reservoir of Mashhad (constructed in 1925) was documented by means of Drone images. The photogrammetric documentation was aimed at provision of 3D models and as a dataset for the creation of BIM models. These data-enriched models could be used on Digital Twin platforms for monitoring and operational purposes, a concept that is becoming increasingly relevant in the field of cultural heritage conservation. The discussion of this process demonstrates that the dense matching of drone images may generate centimeter-level precision and can provide a proper basis for BIM and Digital Twin platforms. The capability of this system will help the community in sustainable development in order to preserve the monuments and determine the appropriate urban use in heritage buildings.

The paper points the attention to some hidden parts of metric surveys, that usually are not enough documented in scientific papers but in technical reposts. Reporting encountered challenges and discussing identified technical solutions and methodologies to overcome bottlenecks and operative issues, highlights the novelty of the presented experience from a technical viewpoint. The overall approach has been reported taking care of describing technical details and present case study’s implementation of the applied techniques. Integrating GNSS control Networks and topographic tools to design, implement and perform a rigorous topographic survey methodology in describing built heritage, which is one of the modern geomatics’ advancements, has been depicted. An ad hoc datum has been designed to guarantee a clear compliance both to cartographic standards and architectural representations in 1:50 to 1:100 graphical output scale.

Archaeological sites in urban areas are often poorly integrated with the modern urban fabric and appear as “trenches” at a lower level than the road. They become neglected and unvalued places. The study of archaeological ruins in urban centres must involve archaeologists and architects to integrate restoration, enhancement and improvement of physical and visual accessibility projects. New digital technologies can improve these activities thanks to 3D models, “digital replicas” that allow even remote study (especially during a pandemic). The paper presents the case study of a private Roman-imperial bath in Catania. The open-air site is located at a depth of 3 metres above the road level and is not exploited. Our study consisted of historical-bibliographical research, direct and SfM surveys that allowed creating a high-resolution textured 3D model. We have extracted orthophotos and sections for geometric and technical-constructive analyses and recognition of decay from this model. We drew up an archaeological restoration and valorisation design. In addition, we imported the model into the Sketchfab portal. So, we enriched the mesh with information from the analyses employing specific tags about annotations, 2D drawings, historical and technical-scientific information. In this way, the model becomes an interactive document to monitor over time the conservation state, validate the restoration design and contribute to the valorisation of the site. This is an easy tool of exchange between all involved users (researchers, professions and students). Thus, the digital replica also represents a very high potential for dissemination purposes.

The proposed research aims at a comparison of the main historical surveys conducted on the Porta Palatina by different authors, with the data of a current digital survey. Through a work of redrawing and superimposition of information deducted from historical drawings, the analysis will highlight the consistency, discrepancies and inconsistencies of these drawings compared to the current state of the artefact. Therefore, the instrumental survey, necessary for the subsequent stages of graphical analysis, was carried out using photogrammetric techniques and Metashape software.The drawings taken into consideration for this work are those by Sangallo (1494–1497 ca.), by Palladio (1566 ca.), by Promis (1869) and by D'Andrade (1883): they constitute a very interesting documentary heritage, although heterogeneous, in which qualitative drawings (Sangallo), scaled drawings (D'Andrade), measured drawings (in vicentine’s feet for Palladio, in meters for Promis) alternate.

Cultural heritage preservation via 3D digitization is becoming more and more important. Besides conventional buildings and landmarks, many technical instruments and artifacts, which belong to tech heritage (TH), are also of great importance, historically and didactically. Gyroscopes, which can be dated back for 200 years, are fascinating instruments with complex structures and different working principles. With such properties, any 3D digitization of Gyroscopes could not be realized by simply using conventional solutions of photogrammetry or laser scanning. In our work, we introduce photogrammetry, endoscopy and computed tomography (CT) for an integrated 3D digitization solution. Though photogrammetry has been widely used for the purpose of cultural heritage preservation, 3D reconstructions using the other two sensor systems have their own challenges. For an endoscope, a pre-calibration solution has been put forward and the Structure-from-Motion (SfM) process has been optimized to deal with the drift caused by a long imaging trajectory. Regarding the CT 3D reconstruction, we mainly focus on the 3D representation’s completeness and the denoising process. In the section of data integration, we designed different methods according to the characteristics of the objects as well as the 3D models from different sonsors. In case of limited overlap between the pair of point clouds, the Gauss-Helmert model with manually picked control points is applied for the estimation of the transformation matrix. CT point clouds, which hold only the intensity values representing the material attenuation, could be integrated with photogrammetry data via a surface color mapping method using the photogrammetric images or the primitive based corresponding virtual control points. Through our research, the concept of integrating photogrammetry, endoscopy and CT for 3D digitization of Gyroscopes is validated. Furthermore, advantages and disadvantages involved in the complete process are discussed and a solid foundation has been laid for further research.

This paper presents a comparative approach between a digital documentation workflow using contemporary tools versus a traditional documentation technique for Felix Candela's hyperbolic paraboloid (hypar) modern heritage building: Cosmic Rays Pavilion. This documentation was undertaken to better understand the building’s structure, its evolution, and to assess the performance of this concrete structure for future seismic and damage analysis. Furthermore, the paper discusses the challenges related to producing a Heritage Building Information Model (HBIM) of this building using point cloud data in Autodesk’s Revit BIM-authoring software. This project states the importance of a parallel study between the traditional and the contemporary documentation methods; which led to discoveries about the current state of the extrados in the hypar after several earthquakes. Upon analyzing the HBIM and comparing it to the historical drawings, a gap was discovered between the moisture barrier membrane and the concrete shell. Visualizing the building in 3D provides a deeper and more accurate understanding of the current state of this pavilion and is one of many advantages of using digital technologies. The insights provided by digital documentation techniques and analyzing the historical images of the pavilion showed that the curvature of the pavilion has been modified over time. The results imply two hypotheses. First, the curvature profile has been altered due to earthquakes. Second, the modification is due to improper maintenance of the pavilion, namely, multiple additions of the membrane layers. This could not have been detected by solely relying on traditional documentation techniques.

O presente trabalho visa discutir o uso de métodos de aquisição de dados geotécnicos de maciços rochosos. A área de estudo é uma pedreira de brita desativada, localizada na cidade de Belo Horizonte (Minas Gerais, Brasil), onde afloram gnaisses migmatizados, com constante queda de blocos. Os métodos de aquisição empregados foram o tradicional mapeamento de talude e o levantamento remoto por fotogrametria digital terrestre. A classificação de maciços Slope Mass Rating (SMR) foi aplicada. Os resultados evidenciaram diferenças nos ranges de detecção de estruturas e a fotogrametria se mostrou mais completa, com mais dados de descontinuidades do que o mapeamento tradicional, com exceção das estruturas oblíquas ao talude. Esta deficiência se explica pelo fato do talude estudado ser subvertical, sem reentrâncias e saliências, que permitem muitas vezes a detecção dos traços de descontinuidades e não dos planos. Contudo, mesmo nestes casos, a fotogrametria mostrou-se importante, por permitir a caracterização de todo talude, impossível pelo método tradicional. A classificação SMR mostrou baixos valores, indicando instabilidade por rupturas planares e em cunha do maciço em alguns pontos, o que coincide com as frequentes quedas de blocos.

In this paper, we present a case study that performs an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event. Multi-temporal oblique photogrammetry images are collected with 3D point clouds generated at different stages of the demolition. The geometric accuracy of the generated point clouds has been evaluated against both airborne and terrestrial LiDAR point clouds, achieving an average distance of 12 cm and 16 cm for roof and facade respectively. We propose a hierarchical volumetric change detection framework that unifies multi-temporal UAV images for pose estimation (free of ground control points), reconstruction, and a coarse-to-fine 3D density change analysis. This work has provided a solution capable of addressing change detection on full 3D time-series datasets where dramatic scene content changes are presented progressively. Our change detection results on the building demolition event have been evaluated against the manually marked ground-truth changes and have achieved an F-1 score varying from 0.78 to 0.92, with consistently high precision (0.92 - 0.99). Volumetric changes through the demolition progress are derived from change detection and have shown to favorably reflect the qualitative and quantitative building demolition progression., 28 pages, 9 figures

In real-world applications (e.g., change detection), annotating images is very expensive. To build effective deep learning models in these applications, deep few-shot learning methods have been developed and prove to be a robust approach in small training data. The analysis of building change detection from high spatial resolution remote sensing observations is important research in photogrammetry, computer vision, and remote sensing nowadays, which can be widely used in a variety of real-world applications, such as map updating. As manual high resolution image interpretation is expensive and time-consuming, building change detection methods are of high interest. The interest in developing building change detection approaches from optical remote sensing images is rapidly increasing due to larger coverages, and lower costs of optical images. In this study, we focus on building change detection analysis on a small set of building change from different regions that sit in several cities. In this paper, a new deep few-shot learning method is proposed for building change detection using Monte Carlo dropout and remote sensing observations. The setup is based on a small dataset, including bitemporal optical images labeled for building change detection., Comment: 5 pages, 3 figures