Search results

This paper aims to propose an automatic imaging network design to improve the efficiency and accuracy of automated construction progress monitoring. The proposed method will address two shortcomings of the previous studies, including the large number of captured images required and the incompleteness and inaccuracy of generated as-built models.

Using the proposed method, the number of required images is minimized in two stages. In the first stage, the manual photogrammetric network design is used to decrease the number of camera stations considering proper constraints. Then the image acquisition is done and the captured images are used to generate 3D points cloud model. In the second stage, a new software for automatic imaging network design is developed and used to cluster and select the optimal images automatically, using the existing dense points cloud model generated before, and the final optimum camera stations are determined. Therefore, the automated progress monitoring can be done by imaging at the selected camera stations to produce periodic progress reports.

The achieved results show that using the proposed manual and automatic imaging network design methods, the number of required images is decreased by 65 and 75 per cent, respectively. Moreover, the accuracy and completeness of points cloud reconstruction is improved and the quantity of performed work is determined with the accuracy, which is close to 100 per cent.

It is believed that the proposed method may present a novel and robust tool for automated progress monitoring using unmanned aerial vehicles and based on photogrammetry and computer vision techniques. Using the proposed method, the number of required images is minimized, and the accuracy and completeness of points cloud reconstruction is improved.

To generate the points cloud reconstruction based on close-range photogrammetry principles, more than hundreds of images must be captured and processed, which is time-consuming and labor-intensive. There has been no previous study to reduce the large number of required captured images. Moreover, lack of images in some areas leads to an incomplete or inaccurate model. This research resolves the mentioned shortcomings.

This work presents a system based on an ensemble of Convolutional Neural Networks (CNNs) and descriptors for bioimage classification that has been validated on different datasets of color images. The proposed system represents a very simple yet effective way of boosting the performance of trained CNNs by composing multiple CNNs into an ensemble and combining scores by sum rule. Several types of ensembles are considered, with different CNN topologies along with different learning parameter sets. The proposed system not only exhibits strong discriminative power but also generalizes well over multiple datasets thanks to the combination of multiple descriptors based on different feature types, both learned and handcrafted. Separate classifiers are trained for each descriptor, and the entire set of classifiers is combined by sum rule. Results show that the proposed system obtains state-of-the-art performance across four different bioimage and medical datasets. The MATLAB code of the descriptors will be available at https://github.com/LorisNanni.

Rebar is the prime component of reinforced concrete structures, and rebar monitoring is a time-consuming and technical job. With the emergence of the fourth industrial revolution, the construction industry practices have evolved toward digitalization. Still, hesitation remains among stakeholders toward the adoption of advanced technologies and one of the significant reasons is the unavailability of knowledge frameworks and implementation guidelines. This study aims to investigate technical factors impacting automated monitoring of rebar for the understanding, confidence gain and effective implementation by construction industry stakeholders.

A structured study pipeline has been adopted, which includes a systematic literature collection, semistructured interviews, pilot survey, questionnaire survey and statistical analyses via merging two techniques, i.e. structural equation modeling and relative importance index.

The achieved model highlights “digital images” and “scanning” as two main categories being adopted for automated rebar monitoring. Moreover, “external influence”, “data-capturing”, “image quality”, and “environment” have been identified as the main factors under “digital images”. On the other hand, “object distance”, “rebar shape”, “occlusion” and “rebar spacing” have been highlighted as the main contributing factors under “scanning”.

The study provides a base guideline for the construction industry stakeholders to gain confidence in automated monitoring of rebar via vision-based technologies and effective implementation of the progress-monitoring processes. This study, via structured data collection, performed qualitative and quantitative analyses to investigate technical factors for effective rebar monitoring via vision-based technologies in the form of a mathematical model.

The unique nature of the construction sector makes it fall behind other sectors in terms of productivity. Monitoring construction productivity is crucial for the construction project's success. Current practices for construction productivity monitoring are time-consuming, manned and error prone. Although previous studies have been implemented toward reducing these limitations, a gap still exists in the automated monitoring of construction productivity.

This study aims to investigate and assess the different techniques used for monitoring productivity in building construction projects. Therefore, a mixed review methodology (bibliometric analysis and systematic review) was adopted. All the related publications were collected from different databases, which were further screened to get the most relevant based on the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) criteria.

A detailed review was performed, and it was found that traditional methods, computer vision-based and photogrammetry are the most adopted data acquisition for productivity monitoring of building projects, respectively. Machine learning algorithms (ANN, SVM) and BIM were integrated with monitoring tools and technologies to enhance the automated monitoring performance in construction productivity. Also, it was observed that current studies did not cover all the complex construction job sites and they were applied based on a small sample of construction workers and machines separately.

This review paper contributes to the literature on construction management by providing insight into different productivity monitoring techniques.

This paper aims to present error compensation based on surface reconstruction to improve the positioning accuracy of industrial robots.

In previous research, it has been proved that the positioning error of industrial robots is continuous on the two-dimensional manifold of six-joint space. The point cloud generated by positioning error data can be used to fit the continuous surfaces, which makes it possible to apply surface reconstruction on error compensation. The moving least-squares interpolation and the B-spline method are used for the error surface reconstruction.

The results of experiments and simulations validate the effectiveness of error compensation by the moving least-squares interpolation and the B-spline method.

The proposed methods can control the average of compensated positioning error within 0.2 mm, which meets the requirement of a tolerance (±0.5 mm) for fastener hole drilling in aircraft assembly.

The error surface reconstruction based on the B-spline method has great superiority because fewer sample points are needed to use this method than others while keeping the compensation accuracy at the same level. The control points of the B-spline error surface can be adjusted with measured data, which can be applied for the error prediction in any temperature field.

The great value of offline identification of machine parameters is when the machine manufacturer does not provide its parameters. Most machine control strategies require parameter values, and some circumstances in the industrial sector only require offline identification. This paper aims to present a new offline method for estimating induction motor parameters based on least squares and a salp swarm algorithm (SSA).

The central concept is to use the classic least squares (LS) method to acquire the majority of induction machine (IM) constant parameters, followed by the SSA method to obtain all parameters and minimize errors.

The obtained results showed that the LS method gives good results in simulation based on the assumption that the measurements are noise-free. However, unlike in simulations, the LS method is unable to accurately identify the machine’s parameters during the experimental test. On the contrary, the SSA method proves higher efficiency and more precision for IM parameter estimation in both simulations and experimental tests.

After performing a primary identification using the technique of least squares, the initial intention of this study was to apply the SSA for the purpose of identifying all of the machine’s parameters and minimizing errors. These two approaches use the same measurement from a simple running test of an IM, and they offer a quick processing time. Therefore, this combined offline strategy provides a reliable model based on the identified parameters.

The purpose of this study is to monitor the progress of construction activities in an automated way by using sensor-based technologies for tracking multiple resources that are used in building construction.

An automated on-site progress monitoring approach was proposed and a proof-of-concept prototype was developed, followed by a field experimentation study at a high-rise building construction site. The developed approach was used to integrate sensor data collected from multiple resources used in different steps of an activity. It incorporated the domain-specific heuristics that were related to the site layout conditions and method of activity.

The prototype estimated the overall progress with 95% accuracy. More accurate and up-to-date progress measurement was achieved compared to the manual approach, and the need for visual inspections and manual data collection from the field was eliminated. Overall, the field experiments demonstrated that low-cost implementation is possible, if readily available or embedded sensors on equipment are used.

Previous studies either monitored one particular piece of equipment or the developed approaches were only applicable to limited activity types. This study demonstrated that it is technically feasible to determine progress at the site by fusing sensor data that are collected from multiple resources during the construction of building superstructure. The rule-based reasoning algorithms, which were developed based on a typical work practice of cranes and hoists, can be adapted to other activities that involve transferring bulk materials and use cranes and/or hoists for material handling.

The understandable recent trend in sensor design has been to exploit the rapid advance in digital electronics to reduce reliance on analogue circuits. In contrast to this general trend some researchers have been inspired by biological systems to design smart imaging sensors based upon collective analogue computation in networks of resistors. This has resulted in sensor designs which efficiently extract information from a large volume of data whilst reducing manufacturing costs by improving yield.

Light field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.

This work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).

In three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.

(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.