- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Im2Fit: Fast 3D Model Fitting and Anthropometrics using Single Consumer Depth Camera and Synthetic Data
摘要： Recent advances in consumer depth sensors have created many opportunities for human body measurement and modeling. Estimation of 3D body shape is particularly useful for fashion e-commerce applications such as virtual try-on or fit personalization. In this paper, we propose a method for capturing accurate human body shape and anthropometrics from a single consumer grade depth sensor. We first generate a large dataset of synthetic 3D human body models using real-world body size distributions. Next, we estimate key body measurements from a single monocular depth image. We combine body measurement estimates with local geometry features around key joint positions to form a robust multi-dimensional feature vector. This allows us to conduct a fast nearest-neighbor search to every sample in the dataset and return the closest one. Compared to existing methods, our approach is able to predict accurate full body parameters from a partial view using measurement parameters learned from the synthetic dataset. Furthermore, our system is capable of generating 3D human mesh models in real-time, which is significantly faster than methods which attempt to model shape and pose deformations. To validate the efficiency and applicability of our system, we collected a dataset that contains frontal and back scans of 83 clothed people with ground truth height and weight. Experiments on real-world dataset show that the proposed method can achieve real-time performance with competing results achieving an average error of 1.9 cm in estimated measurements.
关键词： real-time performance,anthropometrics,consumer depth camera,synthetic data,3D model fitting
更新于2025-09-23 15:21:01
-
Kinetics of crystallization in 13.2Li2O-67.6SiO2-14.49Al2O3-3.3TiO2-0.4BaO-0.97ZnO glass ceramic powder: Part I: A model-free vs. model-fitting approach
摘要： Crystallization kinetics of lithium aluminosilicate glass powder has been investigated by model-free and model–fitting methods. Non-isothermal experiments were carried out using differential scanning calorimetry (DSC) to monitor crystallization behavior. Model-free activation energy has been calculated based on Ozawa-Flynn-wall (OFW), Kissinger-Akahira-Sunose (KAS) and Friedman (FR) methods during crystallization progress. Although activation energy does not significantly differ between the models (400 to 470 kJ/mol), partial Avrami coefficient n(α) varies considerably with rate and crystallization progress. A better description of the crystallization behavior could be observed by the comparison of model-free and model fitting methods. The conformity of one model has been approved with comparison of theoretical DSC curve and experimental results. Finally, a model which can more accurately describe the crystallization behavior of this material was suggested.
关键词： aluminosilicate,Kinetics,model-free,model-fitting,lithium,crystallization.
更新于2025-09-19 17:15:36
-
The OCS method of seeding point detection using visible vision for large-diameter sapphire single crystal growth via the Kyropoulos method
摘要： The seeding process is vital in the preparation of large-diameter sapphire single crystal. It is the key to detect the seeding point during the seeding process. The OCS method is proposed in the paper to detect the seeding point. The OCS method improves the detection method of spoke pattern center propsed by Churl Min Kim, based on this, and the convergence model of spoke pattern center is fitted, sothat the real seeding point is detected. In the experiment, the OCS method is verified by comparing with the traditional manual seeding method (operated by skilled seeding technologists) and the method proposed by Churl Min Kim. The OCS method has the same effect as the traditional artificial seeding method and can reduce the number of attempts in a single seeding experiment. Compared with the method propsed by Churl Min Kim, the OCS method can meet the needs of actual industrial production in terms of the number of successful seeding, the number of seeding attempts and the average seeding time.
关键词： Skeletonizing,Seeding point detection,Convergence model fitting,Observation Convergence Seeding (OCS),Coner detection,ROI locking
更新于2025-09-19 17:15:36
-
Device Parameter Extraction for Loss Analysis of Silicon Solar Cells Based on Intelligent Model Fitting
摘要： A fully automated and rigorous loss analysis routine that provides a breakdown of the loss components occurring in silicon solar cells is presented in this work. The routine combines large-area two-dimensional modeling and smart auto-fitting routines with luminescence imaging. This allows the spatially resolved information in luminescence images to be analyzed to extract recombination parameters partitioned by regions (e.g. wafer edge, under metal contacts, over passivated areas), as well as the spatial distribution of contact resistance. After these cell parameters have been extracted, a loss analysis of open-circuit voltage can be performed by simulating the open-circuit condition and examining the various recombination currents, and a loss analysis of fill factor can be performed by successively turning off the effects of factors that degrade it in simulation. The technique is demonstrated on a multicrystalline silicon PERC solar cell.
关键词： Silicon wafer solar cells,model fitting,loss analysis,multivariate regression,luminescence imaging
更新于2025-09-12 10:27:22
-
Determination of the Optimal State of Dough Fermentation in Bread Production by Using Optical Sensors and Deep Learning
摘要： Dough fermentation plays an essential role in the bread production process, and its success is critical to producing high-quality products. In Germany, the number of stores per bakery chain has increased within the last years as well as the trend to finish the bakery products local at the stores. There is an unsatisfied demand for skilled workers, which leads to an increasing number of untrained and inexperienced employees at the stores. This paper proposes a method for the automatic monitoring of the fermentation process based on optical techniques. By using a combination of machine learning and superellipsoid model fitting, we have developed an instance segmentation and parameter estimation method for dough objects that are positioned inside a fermentation chamber. In our method we measure the given topography at discrete points in time using a movable laser sensor system that is located at the back of the fermentation chamber. By applying the superellipsoid model fitting method, we estimated the volume of each object and achieved results with a deviation of approximately 10% on average. Thereby, the volume gradient is monitored continuously and represents the progress of the fermentation state. Exploratory tests show the reliability and the potential of our method, which is particularly suitable for local stores but also for high volume production in bakery plants.
关键词： fermentation monitoring,optical sensor,superellipsoid model fitting,process automation,quality inspection,deep learning
更新于2025-09-12 10:27:22
-
Estimation of photovoltaic generation forecasting models using limited information
摘要： This work deals with the problem of estimating a photovoltaic generation forecasting model in scenarios where measurements of meteorological variables (i.e., solar irradiance and temperature) at the plant site are not available. A novel algorithm for the estimation of the parameters of the well-known PVUSA model of a photovoltaic plant is proposed. Such a method is characterized by a low computational complexity, and efficiently exploits only power generation measurements, a theoretical clear-sky irradiance model, and temperature forecasts provided by a meteorological service. The proposed method is validated on real data.
关键词： Model fitting,Photovoltaic generation,Energy systems,Forecasting
更新于2025-09-12 10:27:22
-
Waveguide dispersion curves identification at low-frequency using two actuators and phase perturbations
摘要： Dispersion curves of fluid-filled elastic-tubes are used for non-destructive measurement of material acoustic properties. The underlying physics leads to a singular numerical procedure when several modes or long-wavelength scenarios take part in the tube dynamics. The literature describes several methods to identify dispersion curves that require a large ratio of samples per length. Described is a method to enrich the amount of available information of an otherwise ill-posed problem, by multiple boundary phase perturbations at each excitation frequency. The method uses two actuators, one at either end of the waveguide to produce different relative phases, followed by a nonlinear model fitting procedure. Presented are a model-based derivation and experimental verification of the proposed approach on an air-filled elastic-tube. The latter shows the capability of the method to recover the dispersion curves even for very weak structural-acoustic coupling and at low frequencies. The portrayed scheme can be applied on various waveguides by using two actuators and only a single sensor, and hence makes dispersion curve estimation realistic in formerly inaccessible cases.
关键词： non-destructive measurement,phase perturbations,nonlinear model fitting,dispersion curves,acoustic properties,fluid-filled elastic-tubes
更新于2025-09-11 14:15:04
-
[IEEE 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) - Washington, DC (2018.4.4-2018.4.7)] 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) - Segmentation of cell nuclei using intensity-based model fitting and sequential convex programming
摘要： We introduce a convex model-based approach for the segmentation of cell nuclei, which exploits both shape and intensity information. The model is directly fitted to the image intensities. Previous shape-based approaches either are not globally optimal or require prior binarization of an image. Our approach relies on a fast second-order optimization scheme to solve a sequence of convex programs and estimate the globally optimal solution based on the image intensities. Model fitting is performed within image regions which are determined by exploiting the local image structure. We evaluated our approach using fluorescence microscopy images of two different cell types and performed a quantitative comparison with previous methods.
关键词： model fitting,Fluorescence microscopy,convex optimization,cell segmentation
更新于2025-09-09 09:28:46