scholarly journals Efficient Shape Estimation of Transparent Microdefects with Manifold Learning and Regression on a Set of Saturated Images

2020 ◽  
Vol 10 (1) ◽  
pp. 385
Author(s):  
Yuanlong Deng ◽  
Xizhou Pan ◽  
Xiaopin Zhong
Keyword(s):  
Three Dimensional ◽  
Measurement Data ◽  
Estimation Method ◽  
Support Vector ◽  
Measuring Instruments ◽  
Imaging Data ◽  
Shape Estimation ◽  
Data Set ◽  
3D Shape ◽  
Accuracy Requirement

In the industry of polymer film products such as polarizers, measuring the three-dimensional (3D) contour of the transparent microdefects, the most common defects, can crucially affect what further treatment should be taken. In this paper, we propose an efficient method for estimating the 3D shape of defects based on regression by converting the problem of direct measurement into an estimation problem using two-dimensional imaging. The basic idea involves acquiring structured-light saturated imaging data on transparent microdefects; integrating confocal microscopy measurement data to create a labeled data set, on which dimensionality reduction is performed; using support vector regression on a low-dimensional small-set space to establish the relationship between the saturated image and defects’ 3D attributes; and predicting the shape of new defect samples by applying the learned relationship to their saturated images. In the discriminant subspace, the manifold of saturated images can clearly show the changing attributes of defects’ 3D shape, such as depth and width. The experimental results show that the mean relative error (MRE) of the defect depth is 3.64% and the MRE of the defect width is 1.96%. The estimation time consumed in the Matlab platform is less than 0.01 s. Compared with precision measuring instruments such as confocal microscopes, our estimation method greatly improves the efficiency of quality control and meets the accuracy requirement of automated defect identification. It is therefore suitable for complete inspection of products.

Harmonic Analysis on Low Quality Tidal Data

2014 ◽  
Author(s):  
Joost den Haan
Keyword(s):  
Harmonic Analysis ◽  
Three Dimensional ◽  
Measurement Data ◽  
Tidal Energy ◽  
Energy Yield ◽  
Profile Measurement ◽  
Current Profile ◽  
Tidal Power ◽  
Data Set ◽  
Tidal Forcing

The aim of the study is to devise a method to conservatively predict a tidal power generation based on relatively short current profile measurement data sets. Harmonic analysis on a low quality tidal current profile measurement data set only allowed for the reliable estimation of a limited number of constituents leading to a poor prediction of tidal energy yield. Two novel, but very different approaches were taken: firstly a quasi response function is formulated which combines the currents profiles into a single current. Secondly, a three dimensional vectorial tidal forcing model was developed aiming to support the harmonic analysis with upfront knowledge of the actual constituents. The response based approach allowed for a reasonable prediction. The vectorial tidal forcing model proved to be a viable start for a full featuring numerical model; even in its initial simplified form it could provide more insight than the conventional tidal potential models.

scholarly journals A dynamic zone estimation method using cumulative voxels for autonomous driving

2017 ◽  
Vol 14 (1) ◽  
pp. 172988141668713 ◽  
Author(s):  
Seongjo Lee ◽  
Seoungjae Cho ◽  
Sungdae Sim ◽  
Kiho Kwak ◽  
Yong Woon Park ◽  
...  
Keyword(s):  
High Speed ◽  
Moving Objects ◽  
Three Dimensional ◽  
Estimation Method ◽  
Autonomous Driving ◽  
Significant Feature ◽  
Data Set ◽  
Ground Truth Data ◽  
Unmanned Vehicle ◽  
Space Data

Obstacle avoidance and available road identification technologies have been investigated for autonomous driving of an unmanned vehicle. In order to apply research results to autonomous driving in real environments, it is necessary to consider moving objects. This article proposes a preprocessing method to identify the dynamic zones where moving objects exist around an unmanned vehicle. This method accumulates three-dimensional points from a light detection and ranging sensor mounted on an unmanned vehicle in voxel space. Next, features are identified from the cumulative data at high speed, and zones with significant feature changes are estimated as zones where dynamic objects exist. The approach proposed in this article can identify dynamic zones even for a moving vehicle and processes data quickly using several features based on the geometry, height map and distribution of three-dimensional space data. The experiment for evaluating the performance of proposed approach was conducted using ground truth data on simulation and real environment data set.

Three-dimensional echocardiography

2016 ◽  
Author(s):  
Luigi P. Badano ◽  
Roberto M. Lang ◽  
Alexandra Goncalves
Keyword(s):  
Three Dimensional ◽  
Digital Processing ◽  
Surface Rendering ◽  
Imaging Data ◽  
Data Set ◽  
Clinical Scenarios ◽  
Dimensional Echocardiography ◽  
Three Dimensional Echocardiography ◽  
Two Dimensional Echocardiography ◽  
Echocardiographic Technique

The advent of fully-sampled matrix array transthoracic transducers has enabled advanced digital processing and improved image formation algorithms and brought three-dimensional echocardiography (3DE) technology into clinical practice. Currently, 3DE is recognized as an important echocardiographic technique, demonstrated to be superior to two-dimensional echocardiography in various clinical scenarios. This chapter focuses on the technology of 3DE matrix transducers, physics of 3D imaging, data set acquisition (multiplane, real-time, full-volume, zoom, and colour), and display (volume rendering, surface rendering and multislice) modalities. The chapter also addresses the issues of training in 3DE, and main clinical indications and reporting of transthoracic and transoesophageal 3DE.

Estimation of Crowd Density Based on Adaptive LBP

2014 ◽  
Vol 998-999 ◽  
pp. 864-868 ◽  
Author(s):  
Yue Li ◽  
Tao Zou ◽  
Peng Chen
Keyword(s):  
Support Vector Machine ◽  
Density Estimation ◽  
Characteristic Point ◽  
Hessian Matrix ◽  
Three Dimensional ◽  
Estimation Method ◽  
Support Vector ◽  
Density Level ◽  
Dynamic Texture ◽  
Crowd Density

In recent years, mass incidents occurred frequently. In order to identify and warn the incidents proactively and timely. To this problem, we propose an algorithm based on adaptive LBP to estimate the crowd density. Firstly, use three-dimensional Hessian matrix to detect characteristic point. Secondly, use improved adaptive LBP to extract the dynamic texture and analyze it, then get the local feature. Thirdly, learn for global characteristic vectors, and then estimate the density level with support vector machine (SVM). Through simulation comparison, the density estimation method is more accurate and more real-time.

Investigation of Periodically Unsteady Flow in a Radial Pump by CFD Simulations and LDV Measurements

2010 ◽  
Vol 133 (1) ◽  
Author(s):  
Jianjun Feng ◽  
Friedrich-Karl Benra ◽  
Hans Josef Dohmen
Keyword(s):  
Unsteady Flow ◽  
Stokes Equations ◽  
Three Dimensional ◽  
Measurement Data ◽  
Load Condition ◽  
Navier Stokes ◽  
Complex Flow ◽  
Data Set ◽  
Vaned Diffuser ◽  
Radial Pump

The periodically unsteady flow fields in a low specific speed radial diffuser pump have been investigated both numerically and experimentally for the design condition (Qdes) and also one part-load condition (0.5Qdes). Three-dimensional, unsteady Reynolds-averaged Navier–Stokes equations are solved on high-quality structured grids with the shear stress transport turbulence model by using the CFD (computational fluid dynamics) code CFX-10. Furthermore, two-dimensional laser Doppler velocimetry (LDV) measurements are successfully conducted in the interaction region between the impeller and the vaned diffuser, in order to capture the complex flow with abundant measurement data and to validate the CFD results. The analysis of the obtained results has been focused on the behavior of the periodic velocity field and the turbulence field, as well as the associated unsteady phenomena due to the unsteady interaction. In addition, the comparison between CFD and LDV results has also been addressed. The blade orientation effects caused by the impeller rotation are quantitatively examined and detailedly compared with the turbulence effect. This work offers a good data set to develop the comprehension of the impeller-diffuser interaction and how the flow varies with relative impeller position to the diffuser in radial diffuser pumps.

scholarly journals Abnormal Water Quality Monitoring Based on Visual Sensing of Three-Dimensional Motion Behavior of Fish

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1179
Author(s):  
Shuhong Cheng ◽  
Kaopeng Zhao ◽  
Dianfan Zhang
Keyword(s):  
Water Quality ◽  
Three Dimensional ◽  
Water Quality Monitoring ◽  
Quality Monitoring ◽  
Support Vector ◽  
Motion Trajectory ◽  
Integrated Learning ◽  
Monitoring Method ◽  
Data Set ◽  
Extreme Gradient Boosting

In the context of the problem of water pollution, the movement characteristics and patterns of fish under normal water quality and abnormal water quality are clearly different. This paper proposes a biological water quality monitoring method combining three-dimensional motion trajectory synthesis and integrated learning. The videos of the fish movement are captured by two cameras, and the Kuhn-Munkres (KM) algorithm is used to match the target points of the fish body. The Kalman filter is used to update the current state and find the optimal tracking position as the tracking result. The Kernelized Correlation Filters (KCF) algorithm compensates the targets that are lost in the tracking process and collision or occlusion in the movement process, reducing the errors caused by illumination, occlusion and water surface fluctuation effectively. This algorithm can directly obtain the target motion trajectory, avoiding the re-extraction from the centroid point in the image sequence, which greatly improves the efficiency. In order to avoid the one-sidedness of the two-dimensional trajectory, the experiment combines the pixel coordinates of different perspectives into three-dimensional trajectory pixel coordinates, so as to provide a more authentic fish swimming trajectory. We then select a representative positive and negative sample data set; the number of data sets should have symmetry. The base classifier capable of identifying different water quality is obtained by training. Finally, support vector machine(SVM), eXtreme Gradient Boosting (XGBoost) and pointnet based classifiers are combined into strong classifiers through integrated learning. The experimental results show that the integrated learning model can reflect the water quality effectively and accurately under the three-dimensional trajectory pixel coordinates of fish, and the recognition rate of water quality is above 95%.

Assessment of the quality of the ozone measurements from the Odin/SMR instrument using data assimilation

2007 ◽  
Vol 85 (11) ◽  
pp. 1209-1223 ◽  
Author(s):  
S Massart ◽  
A Piacentini ◽  
D Cariolle ◽  
L El Amraoui ◽  
N Semane
Keyword(s):  
Data Assimilation ◽  
Transport Model ◽  
Three Dimensional ◽  
The Other ◽  
Measuring Instruments ◽  
Atmospheric Measurements ◽  
Data Set ◽  
Ozone Data ◽  
Using Data

Space-based remote-sensing instruments providing atmospheric measurements have different time and space resolutions, and coverage. This makes the direct comparison of the measurements very difficult. Data assimilation has proven to be a far more powerful tool than simple interpolation techniques to create three-dimensional analyzed fields for a given data set. In this paper, we describe how the assimilation of ozone data from the Odin/SMR instrument can be used to assess its precisions and biases against other ozone-measuring instruments. To assess the quality of Odin/SMR ozone retrievals by MOLIERE-5 against ozonesondes, Envisat/MIPAS, Earth Probe/TOMS, and UARS/HALOE data, we use a three-dimensional variational assimilation scheme applied to the Météo-France MOCAGE chemistry transport model. The MOCAGE-PALM assimilation system has been already used by Météo-France and CERFACS to analyse the Envisat/MIPAS data for the ASSET intercomparison exercise. We have further developed and calibrated the configuration of this system to better account for the Odin/SMR ozone profiles. The upgraded system is used to assimilate the Odin/SMR ozone during the August 2003 – November 2003 period and intercomparisons are made with the other ozone measuring techniques. The Odin/SMR analysis and the other ozone data sets are in good agreement at mid and high latitudes, while in the lower tropical stratosphere, we found a positive bias of the Odin/SMR, Envisat/MIPAS, and Earth Probe/TOMS data compared to measurements from UARS/HALOE and ozonesondes. The precision of Odin/SMR ozone retrievals in terms of standard deviation is about 20% in the tropics, below 10% at high southern latitudes, and below 5% at high northern latitudes. PACS No.: 82.33.Tb

scholarly journals Calibration-Free Cuffless Blood Pressure Estimation Based on a Population With a Diverse Range of Age and Blood Pressure

2021 ◽  
Vol 3 ◽  
Author(s):  
Syunsuke Yamanaka ◽  
Koji Morikawa ◽  
Hiroshi Morita ◽  
Ji Young Huh ◽  
Osamu Yamamura
Keyword(s):  
Blood Pressure ◽  
Standard Deviation ◽  
Transit Time ◽  
Cuff Pressure ◽  
Estimation Method ◽  
Pulse Transit Time ◽  
International Standards ◽  
Support Vector ◽  
Data Set ◽  
Diverse Range

This study presents a new blood pressure (BP) estimation algorithm utilizing machine learning (ML). A cuffless device that can measure BP without calibration would be precious for portability, continuous measurement, and comfortability, but unfortunately, it does not currently exist. Conventional BP measurement with a cuff is standard, but this method has various problems like inaccurate BP measurement, poor portability, and painful cuff pressure. To overcome these disadvantages, many researchers have developed cuffless BP estimation devices. However, these devices are not clinically applicable because they require advanced preparation before use, such as calibration, do not follow international standards (81060-1:2007), or have been designed using insufficient data sets. The present study was conducted to combat these issues. We recruited 127 participants and obtained 878 raw datasets. According to international standards, our diverse data set included participants from different age groups with a wide variety of blood pressures. We utilized ML to formulate a BP estimation method that did not require calibration. The present study also conformed to the method required by international standards while calculating the level of error in BP estimation. Two essential methods were applied in this study: (a) grouping the participants into five subsets based on the relationship between the pulse transit time and systolic BP by a support vector machine ensemble with bagging (b) applying the information from the wavelet transformation of the pulse wave and the electrocardiogram to the linear regression BP estimation model for each group. For systolic BP, the standard deviation of error for the proposed BP estimation results with cross-validation was 7.74 mmHg, which was an improvement from 17.05 mmHg, as estimated by the conventional pulse-transit-time-based methods. For diastolic BP, the standard deviation of error was 6.42 mmHg for the proposed BP estimation, which was an improvement from 14.05mmHg. The purpose of the present study was to demonstrate and evaluate the performance of the newly developed BP estimation ML method that meets the international standard for non-invasive sphygmomanometers in a population with a diverse range of age and BP.

scholarly journals Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

2020 ◽  
Author(s):  
Cung Lian Sang ◽  
Bastian Steinhagen ◽  
Jonas Dominik Homburg ◽  
Michael Adams ◽  
Marc Hesse ◽  
...  
Keyword(s):  
Machine Learning ◽  
Indoor Localization ◽  
Measurement Data ◽  
Ultra Wideband ◽  
Line Of Sight ◽  
Support Vector ◽  
Case Scenario ◽  
Worst Case ◽  
Data Set ◽  
Worst Case Scenario

In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

A 3D Shape-Measuring System for Assessing Strawberry Fruits

2018 ◽  
Vol 12 (3) ◽  
pp. 395-404 ◽  
Author(s):  
Nobuo Kochi ◽  
Takanari Tanabata ◽  
Atsushi Hayashi ◽  
Sachiko Isobe ◽  
◽  
...  
Keyword(s):  
Measurement Accuracy ◽  
Three Dimensional ◽  
Measurement Data ◽  
Measuring System ◽  
Shape Features ◽  
3D Shape ◽  
3D Objects ◽  
Reliable Assessment ◽  
Large Measurement ◽  
Time Required

Plant shape measurements have conventionally been conducted in plant science by classifying their shape features, by measuring their widths and lengths with a Vernier caliper, or by similar methods. Those measurements rely heavily on human senses and manual labor, making it difficult to acquire massive data. Additionally, they are prone to large measurement differences. To cope with those problems of conventional measuring methods, we are developing a three-dimensional (3D) shape-measuring system using images and a reliable assessment technique. 3D objects enable us to assess and measure shape features with high accuracy and to automatically measure volume, which conventional methods cannot. Thus, our new system is capable of automatically and efficiently measuring objects. Our goal is to obtain wide acceptance of our method at actual research sites. Unlike industrial products, it is difficult to properly assess the measurements of plants because of their object fluctuations and shape complexities. This paper describes our automatic 3D shape-measuring system, the method for assessing measurement accuracy, and the assessment results. The measurement accuracy of the developed system for strawberry fruits is 0.6 mm or less for 90% or more of the fruit and 0.3 mm or less for 80%. This evidence supports the system’s capability of shape assessment. The developed system can fully automate photographing, measuring, and modeling objects and can semi-automatically analyze them, reducing the time required for the entire process from the conventional time of 6–7 h to 1.5 h. The developed system is designed for users with no technical knowledge so that they can easily use it to acquire 3D measurement data on plants. Thus, we intend to expand measurable objects from strawberry fruits to other plants and their parts, including leaves, stalks, and flowers

Sign in / Sign up

Export Citation Format

Share Document