A method is introduced for detecting changes from point clouds that avoids registration. For many applications, changes are detected between two scans of the same scene obtained at different times. Traditionally, these scans are aligned to a common coordinate system having the disadvantage that this registration step introduces additional errors. In addition, registration requires stable targets or features. To avoid these issues, we propose a change detection method based on so-called baselines. Baselines connect feature points within one scan. To analyze changes, baselines connecting corresponding points in two scans are compared. As feature points either targets or virtual points corresponding to some reconstructable feature in the scene are used. The new method is implemented on two scans sampling a masonry laboratory building before and after seismic testing, that resulted in damages in the order of several centimeters. The centres of the bricks of the laboratory building are automatically extracted to serve as virtual points. Baselines connecting virtual points and/or target points are extracted and compared with respect to a suitable structural coordinate system. Changes detected from the baseline analysis are compared to a traditional cloud to cloud change analysis demonstrating the potential of the new method for structural analysis.
Elderly people with acute respiratory failure (ARF) have prolonged length of hospital stay (LOS) and high mortality rates. Malnutrition is negatively correlated with these LOS and mortality. However, no tools have been used to detect the risk of malnutrition and assist in designing nutritional support for these patients. The geriatric nutritional risk index (GNRI) is reported as a novel tool for evaluating the risk of malnutrition. The aim of this study is to explore the relationship of the GNRI score with mortality and LOS in elderly patients with ARF. Data of elderly patients diagnosed with ARF were retrieved from the Medical Information Mart for Intensive Care III (MIMIC-III) database. A total of 1250 patients were divided into two groups based on their GNRI score: the malnutrition risk group (GNRI ≤ 98) and no risk group (GNRI > 98). The primary endpoints of this study were hospital mortality and hospital LOS. The higher GNRI score was associated with lower hospital mortality and shorter hospital LOS. Odds ratio (OR) for hospital mortality of patients with nutritional risk (GNRI ≤ 98) was 1.264 (95% CI:1.067-1.497) in the adjusted model. Patients with GNRI ≤98 had longer hospital LOS (adjusted OR: 1.142, 95%CI: 1.044-1.250) compared with those with GNRI > 98. Subgroup analysis showed that higher GNRI was only significantly associated with lower hospital mortality in the patients that did not undergo mechanical ventilator (MV) treatment (adjusted OR: 0.985, 95% CI: 0.977-0.992, P < 0.01). Kaplan-Meier curve analysis showed that the 90-day survival was significantly lower in the group with nutrition risk (GNRI≤98) compared with the no risk group (GNRI > 98, p < 0.05). These findings imply that GNRI is a useful prognostic tool in elderly patients with ARF.
26 July 2024 in International Journal of Applied Earth Observation and Geoinformation
Automatically and accurately reconstructing the overhead wires of railway from airborne laser scanning (ALS) data are an efficient way of railway monitoring to ensure stable and safety transportation services. However, due to the complex structure of the overhead wires, it is challenging to extract these wires using the existing methods. This work proposes a workflow for railway overhead wire reconstruction using deep learning for wire identification collaborating with the RANdom SAmple Consensus (RANSAC) algorithm for wire reconstruction. First, data augmentation and ground points down-sampling are performed to facilitate the issues caused by insufficient and non-uniformity of LiDAR points. Then, a network incorporating with PointNet model is proposed to segment wires, pylons and ground points. The proposed network is composed of a Geometry Feature Extraction (GFE) module and a Neighborhood Information Aggregation (NIA) module. These two modules are introduced to encode and describe the local geometric features. Therefore, the capability of the model to discriminate geometric details is enhanced. Finally, a wire individualization and multi-wire fitting algorithm is proposed to reconstruct the overhead wires. A number of experiments are conducted using ALS point cloud data of railway scenarios. The results show that the accuracy and MIoU for wire identification are 96.89% and 82.56%, respectively, which demonstrates a better performance compared to the existing methods. The overall reconstruction accuracy is 96% over the study area. Furthermore, the presented strategy also demonstrated its applicability to high-voltage powerline scenarios.
The use of a terrestrial laser scanner is examined to measure the changes of rock slopes subject to a wave attack test. Real scenarios are simulated in a water flume facility using a wave attack experiment representing a storm of 3000 waves. The stability of two rock slopes of different steepness was evaluated under the set conditions. For quantification of the changes of the slopes after the wave attack test, terrestrial laser scanning was used to acquire dense 3D point cloud data sampling for slope geometries before and after the wave attack experiment. After registration of the two scans, representing situations before and after the wave attack, the cloud-to-cloud distance was determined to identify areas in the slopes that were affected. Then, a range image technique was introduced to generate a raster image to facilitate a change analysis. Using these raster images, volume change was estimated as well. The results indicate that the area around the artificial coast line is most strongly affected by wave attacks. Another interesting phenomenon considers the change in transport direction of the rocks between the two slopes: from seaward transport for the steeper slope to landward transport for the milder slope. Using the range image technique, the work in this article shows that terrestrial laser scanning is an effective and feasible method for change analysis of long and narrow rock slopes.
The use of Terrestrial Laser Scanning (TLS) data for structural analysis is gaining growing interest. This paper is focused on a new method for detecting local structural changes in masonry walls investigated with TLS technology, which is accurate and capable to obtain dense 3D coordinates of point clouds for the measured objects. The kernel of the method is the definition of a structural change descriptor based on a baseline network. Baselines connect feature points of each brick with its adjacent bricks within one scan. To analyze changes, the baseline vectors in the baseline network of each brick are compared with the unique standard baseline network matrix, computed on those bricks without apparent damage. This paper also describes intermediate steps of the procedure, namely the TLS data acquisition, a coordinate transformation for the point cloud, and the segmentation of bricks and mortar for further extraction of individually labelled bricks. Furthermore, it illustrates the performance of the proposed baseline-based method with a validation experiment at the Stevin laboratory of Delft University of Technology. From the analysis of this experiment, interesting results were obtained: the changes along the X axis are more significant than those along the Z axis, while the changes along the Y axis only happened within the same rows of bricks of the wall. By comparing the results obtained by manually picking the brick centers, the accuracy of the proposed methodology was proved with the maximum difference value of ~4 mm.