scholarly journals Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera

2021 ◽  
Vol 11 (21) ◽  
pp. 10463
Author(s):  
Jun-Hyeon Kim ◽  
Jong-Ho Nam

The proportion of welding work in total man-hours required for shipbuilding processes has been perceived to be significant, and welding man-hours are greatly affected by working posture. Continuous research has been conducted to identify the posture in welding by utilizing the relationship between man-hours and working posture. However, the results that reflect the effect of the welding posture on man-hours are not available. Although studies on posture recognition based on depth image analysis are being positively reviewed, welding operation has difficulties in image interpretation because an external obstacle caused by arcs exists. Therefore, any obstacle element must be removed in advance. This study proposes a method to acquire work postures using a low-cost RGB-D camera and recognize the welding position through image analysis. It removes obstacles that appear as depth holes in the depth image and restores the removed part to the desired state. The welder’s body joints are extracted, and a convolution neural network is used to determine the corresponding welding position. The restored image showed significantly improved recognition accuracy. The proposed method acquires, analyzes, and automates the recognition of welding positions in real-time. It can be applied to all areas where image interpretation is difficult due to obstacles.

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1356
Author(s):  
Linda Christin Büker ◽  
Finnja Zuber ◽  
Andreas Hein ◽  
Sebastian Fudickar

With approaches for the detection of joint positions in color images such as HRNet and OpenPose being available, consideration of corresponding approaches for depth images is limited even though depth images have several advantages over color images like robustness to light variation or color- and texture invariance. Correspondingly, we introduce High- Resolution Depth Net (HRDepthNet)—a machine learning driven approach to detect human joints (body, head, and upper and lower extremities) in purely depth images. HRDepthNet retrains the original HRNet for depth images. Therefore, a dataset is created holding depth (and RGB) images recorded with subjects conducting the timed up and go test—an established geriatric assessment. The images were manually annotated RGB images. The training and evaluation were conducted with this dataset. For accuracy evaluation, detection of body joints was evaluated via COCO’s evaluation metrics and indicated that the resulting depth image-based model achieved better results than the HRNet trained and applied on corresponding RGB images. An additional evaluation of the position errors showed a median deviation of 1.619 cm (x-axis), 2.342 cm (y-axis) and 2.4 cm (z-axis).


Materials ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 1543
Author(s):  
Francisca Guadalupe Cabrera-Covarrubias ◽  
José Manuel Gómez-Soberón ◽  
Carlos Antonio Rosas-Casarez ◽  
Jorge Luis Almaral-Sánchez ◽  
Jesús Manuel Bernal-Camacho

The porosity of mortars with recycled ceramic aggregates (10, 20, 30, 50, and 100% as a replacement of natural aggregate) was evaluated and analyzed using three different techniques. The results of gas adsorption (N2), Scanning Electron Microscopy (SEM) image analysis and open porosity allowed establishing the relationship between the recycled aggregate content and the porosity of these mortars, as well as the relationship between porosity and the physical and mechanical properties of the mortars: absorption, density, compressive strength, modulus of elasticity, and drying shrinkage. Using the R2 coefficient and the equation typology as criteria, additional data such as Brunauer, Emmett, and Teller (BET) surface area (N2 adsorption) established significant correlations with the mentioned properties; with SEM image analysis, no explanatory relationships could be established; and with open porosity, revealing relationships were established (R2 > 0.9). With the three techniques, it was confirmed that the increase in porosity is related to the increase in the amount of ceramic aggregate; in particular with gas adsorption (N2) and open porosity. It was concluded that the open porosity technique can explain the behavior of these recycled mortars with more reliable data, in a simple and direct way, linked to its establishment with a more representative sample of the mortar matrix.


Robotica ◽  
2021 ◽  
pp. 1-19
Author(s):  
Shengjie Wang ◽  
Kun Wang ◽  
Chunsong Zhang ◽  
Jian S Dai

Abstract A kinetostatic approach applied to the design of a backflip strategy for quadruped robots is proposed in this paper. Inspired by legged animals and taking the advantage of the leg workspace, this strategy provides an optimal design idea for the low-cost quadruped robots to achieve self-recovery after overturning. Through kinetostatic and energy analysis, a four-stepped backflip strategy based on the selected rotation axis with minimum energy is proposed, with a process of selection, lifting, rotating, and protection. The kinematic factors that affect the backflip are investigated, along with the relationship between the design parameters of the leg and trunk being analyzed. At the end of this paper, the strategy is validated by a simulation and experiments with a prototype called DRbot, demonstrating that the strategy endows the robot a strong self-recovery ability in various terrains.


2021 ◽  
Author(s):  
Samantha Richardson ◽  
Samira Al Hinai ◽  
Jesse Gitaka ◽  
Will Mayes ◽  
Mark Lorch ◽  
...  

<p>Routine monitoring of available soil nutrients is required to better manage agricultural land<sup>1</sup>, especially in many lower and middle income countries (LMICs). Analysis often still relies on laboratory-based equipment, meaning regular monitoring is challenging.<sup>2</sup> The limited number of in situ sensors that exist are expensive or have complex workflows, thus are not suitable in LMICs, where the need is greatest.<sup>3</sup> We aim to develop a simple-to-use, low-cost analysis system that enable farmers to directly monitor available nutrients and pH on-site, thus making informed decisions about when and where to apply fertilisers.</p><p>We combine nutrient extraction via a cafetiere-based filtration system with nutrient readout on a paper microfluidic analysis device (PAD) employing colour producing reactions that can be captured via a smartphone camera through an app. Image analysis of colour intensity permits quantitation of analytes. We initially focus on key nutrients (phosphate, nitrate) and pH analysis.</p><p>For extraction of phosphate, we mixed soil and water in the cafetiere and quantified the extracted phosphate via phosphomolybdenum blue chemistry. For example, for 5 g of soil, a water volume of about 160 mL led to optimum extraction. Active mixing, by pushing coffee filter plunger up and down, aided extraction. A mixing period of 3 min yielded maximum extraction; this time period was deemed suitable for an on-site workflow.</p><p>Following nutrient extraction, a simple-to-use readout system is required. For this, we developed colourimetric paper-based microfluidic devices; these are simply dipped into the decanted soil supernatant from the cafetiere and wick fluids based on capillary forces. Chemical reagents are pre-stored in reaction zones, created by patterning cellulose with wax barriers. Our devices contain multiple paper layers with different reagents; these are folded, laminated and holes cut for sample entry. Following the required incubation time, the developed colour is captured using a smartphone. This constitutes a portable detector, already available to envisaged end users, even in LMICs. We have previously developed an on-paper reaction for monitoring phosphates in fresh water in the mg L<sup>-1</sup> working range, with readout after an incubation period of 3 min. This method was adapted here to enable storage at ambient temperatures up to 1 week by incorporating additional acidic reagents. Further pad devices were developed in our group for colour-based readout of nitrate, involving a two-step reaction chemistry. Within a relatively short incubation period (≤8 min) a pink coloured was formed following reduction of nitrate to nitrite with zinc and subsequent reaction to form an azo-dye. This system achieved detection in the low mg L<sup>-1</sup> range. Moreover, a pad to monitor pH was developed, employing chlorophenol red indicator, with linear response achieved over the relevant pH 5-7 range.  </p><p>Our analysis workflow combines a simple-to-use cafetiere-based extraction method with paper microfluidic colour readout and smart-phone detector. This has the potential to enable farmers to monitor nutrients in soils on-site. Future work will aim at integrating multiple analytes into a single analysis card and to automate image analysis.</p><p>[1] <em>Europ. J. Agronomy</em>, 55, 42–52, <strong>2014.</strong></p><p>[2] <em>Nutr. Cycling Agroecosyst.,</em> 109, 77-102, <strong>2017.</strong></p><p>[3] Sens Actuators B, 30, 126855, <strong>2019.</strong></p>


2021 ◽  
pp. 1-15
Author(s):  
PHUC VAN PHAN

Public governance and income inequality relationship is complex and debatable. This paper examines the extent to which the quality of local governance affects inequality in Vietnam spanning the 2006–2016 period. I apply a generalized method of moments (GMM) estimators to a dynamic panel data extracted from the Vietnam’s provincial competitiveness index and the Vietnam household living standard surveys. The findings are that there is a positive inequality — corruption link but no statistically significant correlation coefficient between the overall level of governance and income disparity. The study, therefore, suggests that the Vietnamese Government at all levels should consider both more effective legal practices and economic low-cost solutions to mitigate corruption.


2019 ◽  
Vol 13 (1) ◽  
pp. 47-61
Author(s):  
Guenther Retscher ◽  
Jonathan Kleine ◽  
Lisa Whitemore

Abstract More and more sensors and receivers are found nowadays in smartphones which can enable and improve positioning for Location-based Services and other navigation applications. Apart from inertial sensors, such as accelerometers, gyroscope and magnetometer, receivers for Wireless Fidelity (Wi-Fi) and GNSS signals can be employed for positioning of a mobile user. In this study, three trilateration methods for Wi-Fi positioning are investigated whereby the influence of the derivation of the relationship between the received signal strength (RSS) and the range to an Access Points (AP) are analyzed. The first approach is a straightforward resection for point determination and the second is based on the calculation of the center of gravity in a triangle of APs while weighting the received RSS. In the third method a differential approach is employed where as in Differential GNSS (DGNSS) corrections are derived and applied to the raw RSS measurements. In this Differential Wi-Fi (DWi-Fi) method, reference stations realized by low-cost Raspberry Pi units are used to model temporal RSS variations. In the experiments in this study two different indoor environments are used, one in a laboratory and the second in the entrance of an office building. The results of the second and third approach show position deviations from the ground truth of around 2 m in dependence of the geometrical point location. Furthermore, the transition between GNSS positioning outdoors and Wi-Fi localization indoors in the entrance area of the building is studied.


2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Borja Millan ◽  
Santiago Velasco-Forero ◽  
Arturo Aquino ◽  
Javier Tardaguila

This paper describes a new methodology for noninvasive, objective, and automated assessment of yield in vineyards using image analysis and Boolean model. Image analysis, as an inexpensive and noninvasive procedure, has been studied for this purpose, but the effect of occlusions from the cluster or other organs of the vine has an impact that diminishes the quality of the results. To reduce the influence of the occlusions in the estimation, the number of berries was assessed using the Boolean model. To evaluate the methodology, three different datasets were studied: cluster images, manually acquired vine images, and vine images captured on-the-go using a quad. The proposed algorithm estimated the number of berries in cluster images with a root mean square error (RMSE) of 20 and a coefficient of determination (R2) of 0.80. Vine images manually taken were evaluated, providing 310 grams of mean error and R2=0.81. Finally, images captured using a quad equipped with artificial light and automatic camera triggering were also analysed. The estimation obtained applying the Boolean model had 610 grams of mean error per segment (three vines) and R2=0.78. The reliability against occlusions and segmentation errors of the Boolean model makes it ideal for vineyard yield estimation. Its application greatly improved the results when compared to a simpler estimator based on the relationship between cluster area and weight.


Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7410
Author(s):  
Ruey-Ching Twu ◽  
Kai-Hsuan Li ◽  
Bo-Lin Lin

A low-cost polyethylene terephthalate fluidic sensor (PET-FS) is demonstrated for the concentration variation measurement on fluidic solutions. The PET-FS consisted of a triangular fluidic container attached with a birefringent PET thin layer. The PET-FS was injected with the test liquid solution that was placed in a common path polarization interferometer by utilizing a heterodyne scheme. The measured phase variation of probe light was used to obtain the information regarding the concentration change in the fluidic liquids. The sensor was experimentally tested using different concentrations of sodium chloride solution showing a sensitivity of 3.52 ×104 deg./refractive index unit (RIU) and a detection resolution of 6.25 × 10−6 RIU. The estimated sensitivity and detection resolutions were 5.62 × 104 (deg./RIU) and 6.94 × 10−6 RIU, respectively, for the hydrochloric acid. The relationship between the measured phase and the concentration is linear with an R-squared value reaching above 0.995.


Sign in / Sign up

Export Citation Format

Share Document