Accuracy Evaluation of Dense Matching Techniques for Casting Part Dimensional Verification

Gorka Kortaberria; Unai Mutilba; Eneko Gomez-Acedo; Alberto Tellaeche; Rikardo Minguez

doi:10.3390/s18093074

Accuracy Evaluation of Dense Matching Techniques for Casting Part Dimensional Verification

Sensors ◽

10.3390/s18093074 ◽

2018 ◽

Vol 18 (9) ◽

pp. 3074

Author(s):

Gorka Kortaberria ◽

Unai Mutilba ◽

Eneko Gomez-Acedo ◽

Alberto Tellaeche ◽

Rikardo Minguez

Keyword(s):

Optical Sensors ◽

Large Scale ◽

Image Data ◽

Production Costs ◽

Manufacturing Processes ◽

Accuracy Evaluation ◽

Dense Matching ◽

Component Supplier ◽

Evaluation Exercise ◽

Matching Techniques

Product optimization for casting and post-casting manufacturing processes is becoming compulsory to compete in the current global manufacturing scenario. Casting design, simulation and verification tools are becoming crucial for eliminating oversized dimensions without affecting the casting component functionality. Thus, material and production costs decrease to maintain the foundry process profitable on the large-scale component supplier market. New measurement methods, such as dense matching techniques, rely on surface texture of casting parts to enable the 3D dense reconstruction of surface points without the need of an active light source as usually applied with 3D scanning optical sensors. This paper presents the accuracy evaluation of dense matching based approaches for casting part verification. It compares the accuracy obtained by dense matching technique with already certified and validated optical measuring methods. This uncertainty evaluation exercise considers both artificial targets and key natural points to quantify the possibilities and scope of each approximation. Obtained results, for both lab and workshop conditions, show that this image data processing procedure is fit for purpose to fulfill the required measurement tolerances for casting part manufacturing processes.

Download Full-text

Large-Scale Road Network Congestion Pattern Analysis and Prediction Using Deep Convolutional Autoencoder

Sustainability ◽

10.3390/su13095108 ◽

2021 ◽

Vol 13 (9) ◽

pp. 5108

Author(s):

Navin Ranjan ◽

Sovit Bhandari ◽

Pervez Khan ◽

Youn-Sik Hong ◽

Hoon Kim

Keyword(s):

Traffic Congestion ◽

Network Architecture ◽

Road Network ◽

Large Scale ◽

Pattern Analysis ◽

Image Data ◽

Urban Life ◽

Prediction Algorithm ◽

Rapid Urbanization ◽

Convolutional Autoencoder

The transportation system, especially the road network, is the backbone of any modern economy. However, with rapid urbanization, the congestion level has surged drastically, causing a direct effect on the quality of urban life, the environment, and the economy. In this paper, we propose (i) an inexpensive and efficient Traffic Congestion Pattern Analysis algorithm based on Image Processing, which identifies the group of roads in a network that suffers from reoccurring congestion; (ii) deep neural network architecture, formed from Convolutional Autoencoder, which learns both spatial and temporal relationships from the sequence of image data to predict the city-wide grid congestion index. Our experiment shows that both algorithms are efficient because the pattern analysis is based on the basic operations of arithmetic, whereas the prediction algorithm outperforms two other deep neural networks (Convolutional Recurrent Autoencoder and ConvLSTM) in terms of large-scale traffic network prediction performance. A case study was conducted on the dataset from Seoul city.

Download Full-text

NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

Applied Sciences ◽

10.3390/app11104426 ◽

2021 ◽

Vol 11 (10) ◽

pp. 4426

Author(s):

Chunyan Ma ◽

Ji Fan ◽

Jinghao Yao ◽

Tao Zhang

Keyword(s):

Action Recognition ◽

Large Scale ◽

Short Term Memory ◽

Evaluation Criteria ◽

Image Data ◽

Basketball Player ◽

Basketball Players ◽

Convolutional Network ◽

Atomic Actions ◽

New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

Download Full-text

Optical Navigation Sensor for Runway Relative Positioning of Aircraft during Final Approach

Sensors ◽

10.3390/s21062203 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2203

Author(s):

Antal Hiba ◽

Attila Gáti ◽

Augustin Manecy

Keyword(s):

Optical Sensors ◽

Inertial Sensor ◽

Image Data ◽

Flight Test ◽

Image Features ◽

Wide Field ◽

Test Results ◽

Wide Field Of View ◽

Final Approach ◽

Marker Detection

Precise navigation is often performed by sensor fusion of different sensors. Among these sensors, optical sensors use image features to obtain the position and attitude of the camera. Runway relative navigation during final approach is a special case where robust and continuous detection of the runway is required. This paper presents a robust threshold marker detection method for monocular cameras and introduces an on-board real-time implementation with flight test results. Results with narrow and wide field-of-view optics are compared. The image processing approach is also evaluated on image data captured by a different on-board system. The pure optical approach of this paper increases sensor redundancy because it does not require input from an inertial sensor as most of the robust runway detectors.

Download Full-text

Extraction of short chain chitooligosaccharides from fungal biomass and their use as promoters of arbuscular mycorrhizal symbiosis

Scientific Reports ◽

10.1038/s41598-021-83299-6 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Andrea Crosino ◽

Elisa Moscato ◽

Marco Blangetti ◽

Gennaro Carotenuto ◽

Federica Spina ◽

...

Keyword(s):

Fungal Biomass ◽

Large Scale ◽

Low Cost ◽

Trichoderma Viride ◽

Arbuscular Mycorrhizal ◽

Am Fungi ◽

Production Costs ◽

Short Chain ◽

Mycorrhizal Symbiosis ◽

Major Interest

AbstractShort chain chitooligosaccharides (COs) are chitin derivative molecules involved in plant-fungus signaling during arbuscular mycorrhizal (AM) interactions. In host plants, COs activate a symbiotic signalling pathway that regulates AM-related gene expression. Furthermore, exogenous CO application was shown to promote AM establishment, with a major interest for agricultural applications of AM fungi as biofertilizers. Currently, the main source of commercial COs is from the shrimp processing industry, but purification costs and environmental concerns limit the convenience of this approach. In an attempt to find a low cost and low impact alternative, this work aimed to isolate, characterize and test the bioactivity of COs from selected strains of phylogenetically distant filamentous fungi: Pleurotus ostreatus, Cunninghamella bertholletiae and Trichoderma viride. Our optimized protocol successfully isolated short chain COs from lyophilized fungal biomass. Fungal COs were more acetylated and displayed a higher biological activity compared to shrimp-derived COs, a feature that—alongside low production costs—opens promising perspectives for the large scale use of COs in agriculture.

Download Full-text

Electrochemically induced structural reconstruction in promoting Zn storage performances of CaMn3O6 cathode for superior long life aqueous Zn-ion battery

Journal of Materials Chemistry A ◽

10.1039/d1ta03708k ◽

2021 ◽

Author(s):

peisheng guo ◽

gongzheng yang ◽

Chengxin Wang

Keyword(s):

Energy Storage ◽

Large Scale ◽

Storage Systems ◽

Low Cost ◽

Zinc Ion ◽

Manufacturing Processes ◽

Energy Storage Systems ◽

Long Life

Aqueous zinc-ion batteries (AZIBs) have been regarded as alternative and promising large-scale energy storage systems due to their low cost, convenient manufacturing processes, and high safety. However, their development was...

Download Full-text

Towards pixel-to-pixel deep nucleus detection in microscopy images

BMC Bioinformatics ◽

10.1186/s12859-019-3037-5 ◽

2019 ◽

Vol 20 (1) ◽

Cited By ~ 3

Author(s):

Fuyong Xing ◽

Yuanpu Xie ◽

Xiaoshuang Shi ◽

Pingjun Chen ◽

Zizhao Zhang ◽

...

Keyword(s):

Neural Networks ◽

Large Scale ◽

Deep Neural Networks ◽

Image Data ◽

Fine Tuning ◽

Cell Detection ◽

Imaging Protocol ◽

Microscopy Image ◽

Microscopy Images ◽

Target Data

Abstract Background Nucleus or cell detection is a fundamental task in microscopy image analysis and supports many other quantitative studies such as object counting, segmentation, tracking, etc. Deep neural networks are emerging as a powerful tool for biomedical image computing; in particular, convolutional neural networks have been widely applied to nucleus/cell detection in microscopy images. However, almost all models are tailored for specific datasets and their applicability to other microscopy image data remains unknown. Some existing studies casually learn and evaluate deep neural networks on multiple microscopy datasets, but there are still several critical, open questions to be addressed. Results We analyze the applicability of deep models specifically for nucleus detection across a wide variety of microscopy image data. More specifically, we present a fully convolutional network-based regression model and extensively evaluate it on large-scale digital pathology and microscopy image datasets, which consist of 23 organs (or cancer diseases) and come from multiple institutions. We demonstrate that for a specific target dataset, training with images from the same types of organs might be usually necessary for nucleus detection. Although the images can be visually similar due to the same staining technique and imaging protocol, deep models learned with images from different organs might not deliver desirable results and would require model fine-tuning to be on a par with those trained with target data. We also observe that training with a mixture of target and other/non-target data does not always mean a higher accuracy of nucleus detection, and it might require proper data manipulation during model training to achieve good performance. Conclusions We conduct a systematic case study on deep models for nucleus detection in a wide variety of microscopy images, aiming to address several important but previously understudied questions. We present and extensively evaluate an end-to-end, pixel-to-pixel fully convolutional regression network and report a few significant findings, some of which might have not been reported in previous studies. The model performance analysis and observations would be helpful to nucleus detection in microscopy images.

Download Full-text

Metric Accuracy Evaluation of Dense Matching Algorithms in Archeological Applications

Geoinformatics FCE CTU ◽

10.14311/gi.6.34 ◽

2011 ◽

Vol 6 ◽

pp. 275-282 ◽

Cited By ~ 2

Author(s):

C. Re ◽

S. Robson ◽

R. Roncella ◽

M Hess

Keyword(s):

Laser Scanner ◽

Medium Size ◽

Accuracy Evaluation ◽

Software Packages ◽

Dense Matching ◽

Laser Scanners ◽

Surface Models ◽

University College London ◽

Archaeological Artifacts ◽

Archaeological Objects

In the cultural heritage field the recording and documentation of small and medium size objects with very detailed Digital Surface Models (DSM) is readily possible by through the use of high resolution and high precision triangulation laser scanners. 3D surface recording of archaeological objects can be easily achieved in museums; however, this type of record can be quite expensive. In many cases photogrammetry can provide a viable alternative for the generation of DSMs. The photogrammetric procedure has some benefits with respect to laser survey. The research described in this paper sets out to verify the reconstruction accuracy of DSMs of some archaeological artifacts obtained by photogrammetric survey. The experimentation has been carried out on some objects preserved in the Petrie Museum of Egyptian Archaeology at University College London (UCL). DSMs produced by two photogrammetric software packages are compared with the digital 3D model obtained by a state of the art triangulation color laser scanner. Intercomparison between the generated DSM has allowed an evaluation of metric accuracy of the photogrammetric approach applied to archaeological documentation and of precision performances of the two software packages.

Download Full-text

Techno-Economic Assessment of Solar-Driven Steam Gasification of Biomass for Large-Scale Hydrogen Production

Processes ◽

10.3390/pr9030462 ◽

2021 ◽

Vol 9 (3) ◽

pp. 462

Author(s):

Houssame Boujjat ◽

Sylvain Rodat ◽

Stéphane Abanades

Keyword(s):

Solar Energy ◽

Large Scale ◽

Biomass Gasification ◽

Sensitivity Study ◽

H2 Production ◽

Steam Gasification ◽

Economic Feasibility ◽

Production Costs ◽

Concentrated Solar Energy ◽

Land Cost

Solar biomass gasification is an attractive pathway to promote biomass valorization while chemically storing intermittent solar energy into solar fuels. The economic feasibility of a solar gasification process at a large scale for centralized H2 production was assessed, based on the discounted cash-flow rate of return method to calculate the minimum H2 production cost. H2 production costs from solar-only, hybrid and conventional autothermal biomass gasification were evaluated under various economic scenarios. Considering a biomass reference cost of 0.1 €/kg, and a land cost of 12.9 €/m2, H2 minimum price was estimated at 2.99 €/kgH2 and 2.48 €/kgH2 for the allothermal and hybrid processes, respectively, against 2.25 €/kgH2 in the conventional process. A sensitivity study showed that a 50% reduction in the heliostats and solar tower costs, combined with a lower land cost of below 0.5 €/m2, allowed reaching an area of competitiveness where the three processes meet. Furthermore, an increase in the biomass feedstock cost by a factor of 2 to 3 significantly undermined the profitability of the autothermal process, in favor of solar hybrid and solar-only gasification. A comparative study involving other solar and non-solar processes led to conclude on the profitability of fossil-based processes. However, reduced CO2 emissions from the solar process and the application of carbon credits are definitely in favor of solar gasification economics, which could become more competitive. The massive deployment of concentrated solar energy across the world in the coming years can significantly reduce the cost of the solar materials and components (heliostats), and thus further alleviate the financial cost of solar gasification.

Download Full-text

Planting Systems for Modern Olive Growing: Strengths and Weaknesses

Agriculture ◽

10.3390/agriculture11060494 ◽

2021 ◽

Vol 11 (6) ◽

pp. 494

Author(s):

Riccardo Lo Bianco ◽

Primo Proietti ◽

Luca Regni ◽

Tiziano Caruso

Keyword(s):

Large Scale ◽

New Technologies ◽

Production Costs ◽

Biotic And Abiotic Stress ◽

Short Term ◽

Mediterranean Countries ◽

Social Concerns ◽

The World ◽

Fruit Growing ◽

Cultivar Diversity

The objective of fully mechanizing olive harvesting has been pursued since the 1970s to cope with labor shortages and increasing production costs. Only in the last twenty years, after adopting super-intensive planting systems and developing appropriate straddle machines, a solution seems to have been found. The spread of super-intensive plantings, however, raises serious environmental and social concerns, mainly because of the small number of cultivars that are currently used (basically 2), compared to over 100 cultivars today cultivated on a large scale across the world. Olive growing, indeed, insists on over 11 million hectares. Despite its being located mostly in the Mediterranean countries, the numerous olive growing districts are characterized by deep differences in climate and soil and in the frequency and nature of environmental stress. To date, the olive has coped with biotic and abiotic stress thanks to the great cultivar diversity. Pending that new technologies supporting plant breeding will provide a wider number of cultivars suitable for super-intensive systems, in the short term, new growing models must be developed. New olive orchards will need to exploit cultivars currently present in various olive-growing areas and favor increasing productions that are environmentally, socially, and economically sustainable. As in fruit growing, we should focus on “pedestrian olive orchards”, based on trees with small canopies and whose top can be easily reached by people from the ground and by machines (from the side of the top) that can carry out, in a targeted way, pesticide treatments, pruning and harvesting.

Download Full-text

Seeding metrics for image velocimetry performances in rivers

10.5194/egusphere-egu21-9229 ◽

2021 ◽

Author(s):

Silvano Fortunato Dal Sasso ◽

Alonso Pizarro ◽

Sophie Pearce ◽

Ian Maddock ◽

Matthew T. Perks ◽

...

Keyword(s):

Spatial Distribution ◽

Optical Sensors ◽

Large Scale ◽

Surface Flow ◽

Surface Velocity ◽

Seeding Density ◽

Earth System ◽

Science Data ◽

Image Velocimetry ◽

Hydraulic Conditions

Optical sensors coupled with image velocimetry techniques are becoming popular for river monitoring applications. In this context, new opportunities and challenges are growing for the research community aimed to: i) define standardized practices and methodologies; and ii) overcome some recognized uncertainty at the field scale. At this regard, the accuracy of image velocimetry techniques strongly depends on the occurrence and distribution of visible features on the water surface in consecutive frames. In a natural environment, the amount, spatial distribution and visibility of natural features on river surface are continuously challenging because of environmental factors and hydraulic conditions. The dimensionless seeding distribution index (SDI), recently introduced by Pizarro et al., 2020a,b and Dal Sasso et al., 2020, represents a metric based on seeding density and spatial distribution of tracers for identifying the best frame window (FW) during video footage. In this work, a methodology based on the SDI index was applied to different study cases with the Large Scale Particle Image Velocimetry (LSPIV) technique. Videos adopted are taken from the repository recently created by the COST Action Harmonious, which includes 13 case study across Europe and beyond for image velocimetry applications (Perks et al., 2020). The optimal frame window selection is based on two criteria: i) the maximization of the number of frames and ii) the minimization of SDI index. This methodology allowed an error reduction between 20 and 39% respect to the entire video configuration. This novel idea appears suitable for performing image velocimetry in natural settings where environmental and hydraulic conditions are extremely challenging and particularly useful for real-time observations from fixed river-gauged stations where an extended number of frames are usually recorded and analyzed.&#160;References Dal Sasso S.F., Pizarro A., Manfreda S.,&#160;Metrics for the Quantification of Seeding Characteristics to Enhance Image Velocimetry Performance in Rivers.&#160;Remote Sensing,&#160;12, 1789 (doi: 10.3390/rs12111789), 2020.Perks M. T., Dal Sasso S. F., Hauet A., Jamieson E., Le Coz J., Pearce S., &#8230;Manfreda S, Towards harmonisation of image velocimetry techniques for river surface velocity observations. Earth System Science Data, https://doi.org/10.5194/essd-12-1545-2020, 12(3), 1545 &#8211; 1559, 2020.Pizarro A., Dal Sasso S.F., Manfreda S.,&#160;Refining image-velocimetry performances for streamflow monitoring: Seeding metrics to errors minimisation,&#160;Hydrological Processes, (doi: 10.1002/hyp.13919), 1-9, 2020.Pizarro A., Dal Sasso S.F., Perks M. and Manfreda S., Identifying the optimal spatial distribution of tracers for optical sensing of stream surface flow, Hydrology and Earth System Sciences, 24, 5173&#8211;5185, (10.5194/hess-24-5173-2020), 2020.

Download Full-text