scholarly journals UAV-Assisted Wide Area Multi-Camera Space Alignment Based on Spatiotemporal Feature Map

2021 ◽  
Vol 13 (6) ◽  
pp. 1117
Author(s):  
Jing Li ◽  
Yuguang Xie ◽  
Congcong Li ◽  
Yanran Dai ◽  
Jiaxin Ma ◽  
...  
Keyword(s):  
Large Scale ◽  
Superior Performance ◽  
Wide Area ◽  
Feature Map ◽  
Map Construction ◽  
Wide Range ◽  
Spatiotemporal Feature ◽  
Ground Point ◽  
Matching Strategy ◽  
Ground Monitoring

In this paper, we investigate the problem of aligning multiple deployed camera into one united coordinate system for cross-camera information sharing and intercommunication. However, the difficulty is greatly increased when faced with large-scale scene under chaotic camera deployment. To address this problem, we propose a UAV-assisted wide area multi-camera space alignment approach based on spatiotemporal feature map. It employs the great global perception of Unmanned Aerial Vehicles (UAVs) to meet the challenge from wide-range environment. Concretely, we first present a novel spatiotemporal feature map construction approach to represent the input aerial and ground monitoring data. In this way, the motion consistency across view is well mined to overcome the great perspective gap between the UAV and ground cameras. To obtain the corresponding relationship between their pixels, we propose a cross-view spatiotemporal matching strategy. Through solving relative relationship with the above air-to-ground point correspondences, all ground cameras can be aligned into one surveillance space. The proposed approach was evaluated in both simulation and real environments qualitatively and quantitatively. Extensive experimental results demonstrate that our system can successfully align all ground cameras with very small pixel error. Additionally, the comparisons with other works on different test situations also verify its superior performance.

scholarly journals Adversarial domain translation networks enable fast and accurate large-scale atlas-level single-cell data integration

2021 ◽  
Author(s):  
Jia Zhao ◽  
Gefei Wang ◽  
Jingsi Ming ◽  
Zhixiang Lin ◽  
Yang Wang ◽  
...  
Keyword(s):  
Single Cell ◽  
Rna Sequencing ◽  
Large Scale ◽  
Superior Performance ◽  
Brain Atlas ◽  
Unified Framework ◽  
Fine Grained ◽  
Wide Range ◽  
Shared Information ◽  
Single Nucleus

The rapid emergence of large-scale atlas-level single-cell RNA-sequencing (scRNA-seq) datasets from various sources presents remarkable opportunities for broad and deep biological investigations through integrative analyses. However, harmonizing such datasets requires integration approaches to be not only computationally scalable, but also capable of preserving a wide range of fine-grained cell populations. We created Portal, a unified framework of adversarial domain translation to learn harmonized representations of datasets. With innovation in model and algorithm designs, Portal achieves superior performance in preserving biological variation during integration, while having significantly reduced running time and memory compared to existing approaches, achieving integration of millions of cells in minutes with low memory consumption. We demonstrate the efficiency and accuracy of Portal using diverse datasets ranging from mouse brain atlas projects, the Tabula Muris project, and the Tabula Microcebus project. Portal has broad applicability and in addition to integrating multiple scRNA-seq datasets, it can also integrate scRNA-seq with single-nucleus RNA-sequencing (snRNA-seq) data. Finally, we demonstrate the utility of Portal by applying it to the integration of cross-species datasets with limited shared-information between them, and are able to elucidate biological insights into the similarities and divergences in the spermatogenesis process between mouse, macaque, and human.

scholarly journals DICOM Imaging Router: An Open Deep Learning Framework for Classification of Body Parts from DICOM X-ray Scans

2021 ◽  
Author(s):  
Hieu H. Pham ◽  
Dung V. Do ◽  
Ha Q. Nguyen
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Imaging Modality ◽  
The Body ◽  
Superior Performance ◽  
Body Parts ◽  
Deep Convolutional Neural Networks ◽  
X Ray ◽  
Wide Range ◽  
Dicom Imaging

AbstractX-ray imaging in Digital Imaging and Communications in Medicine (DICOM) format is the most commonly used imaging modality in clinical practice, resulting in vast, non-normalized databases. This leads to an obstacle in deploying artificial intelligence (AI) solutions for analyzing medical images, which often requires identifying the right body part before feeding the image into a specified AI model. This challenge raises the need for an automated and efficient approach to classifying body parts from X-ray scans. Unfortunately, to the best of our knowledge, there is no open tool or framework for this task to date. To fill this lack, we introduce a DICOM Imaging Router that deploys deep convolutional neural networks (CNNs) for categorizing unknown DICOM X-ray images into five anatomical groups: abdominal, adult chest, pediatric chest, spine, and others. To this end, a large-scale X-ray dataset consisting of 16,093 images has been collected and manually classified. We then trained a set of state-of-the-art deep CNNs using a training set of 11,263 images. These networks were then evaluated on an independent test set of 2,419 images and showed superior performance in classifying the body parts. Specifically, our best performing model (i.e., MobileNet-V1) achieved a recall of 0.982 (95% CI, 0.977– 0.988), a precision of 0.985 (95% CI, 0.975–0.989) and a F1-score of 0.981 (95% CI, 0.976–0.987), whilst requiring less computation for inference (0.0295 second per image). Our external validity on 1,000 X-ray images shows the robustness of the proposed approach across hospitals. These remarkable performances indicate that deep CNNs can accurately and effectively differentiate human body parts from X-ray scans, thereby providing potential benefits for a wide range of applications in clinical settings. The dataset, codes, and trained deep learning models from this study will be made publicly available on our project website at https://vindr.ai/datasets/bodypartxr.

scholarly journals LoRa Communications as an Enabler for Internet of Drones towards Large-Scale Livestock Monitoring in Rural Farms

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5044
Author(s):  
Mehran Behjati ◽  
Aishah Binti Mohd Noh ◽  
Haider A. H. Alobaidy ◽  
Muhammad Aidiel Zulkifley ◽  
Rosdiadee Nordin ◽  
...  
Keyword(s):  
Data Collection ◽  
Monitoring System ◽  
Large Scale ◽  
Service Providers ◽  
Wide Area ◽  
Management Approach ◽  
Communication Link ◽  
Reliable Communication ◽  
Wide Range ◽  
Smart Farming

Currently, smart farming is considered an effective solution to enhance the productivity of farms; thereby, it has recently received broad interest from service providers to offer a wide range of applications, from pest identification to asset monitoring. Although the emergence of digital technologies, such as the Internet of Things (IoT) and low-power wide-area networks (LPWANs), has led to significant advances in the smart farming industry, farming operations still need more efficient solutions. On the other hand, the utilization of unmanned aerial vehicles (UAVs), also known as drones, is growing rapidly across many civil application domains. This paper aims to develop a farm monitoring system that incorporates UAV, LPWAN, and IoT technologies to transform the current farm management approach and aid farmers in obtaining actionable data from their farm operations. In this regard, an IoT-based water quality monitoring system was developed because water is an essential aspect in livestock development. Then, based on the Long-Range Wide-Area Network (LoRaWAN®) technology, a multi-channel LoRaWAN® gateway was developed and integrated into a vertical takeoff and landing drone to convey collected data from the sensors to the cloud for further analysis. In addition, to develop LoRaWAN®-based aerial communication, a series of measurements and simulations were performed under different configurations and scenarios. Finally, to enhance the efficiency of aerial-based data collection, the UAV path planning was optimized. Measurement results showed that the maximum achievable LoRa coverage when operating on-air via the drone is about 10 km, and the Longley–Rice irregular terrain model provides the most suitable path loss model for the scenario of large-scale farms, and a multi-channel gateway with a spreading factor of 12 provides the most reliable communication link at a high drone speed (up to 95 km/h). Simulation results showed that the developed system can overcome the coverage limitation of LoRaWAN® and it can establish a reliable communication link over large-scale wireless sensor networks. In addition, it was shown that by optimizing flight paths, aerial data collection could be performed in a much shorter time than industrial mission planning (up to four times in our case).

Electron microscopy study of reactively sputter-deposited Ti/N films on silicon

1992 ◽  
Vol 50 (2) ◽  
pp. 1362-1363
Author(s):  
V. C. Kannan ◽  
A. K. Singh ◽  
R. B. Irwin ◽  
S. Chittipeddi ◽  
F. D. Nkansah ◽  
...  
Keyword(s):  
Integrated Circuits ◽  
Large Scale ◽  
Hexagonal Phase ◽  
Microscopy Study ◽  
Electron Microscopy Study ◽  
Process Conditions ◽  
Tin Films ◽  
Wide Range ◽  
Fcc Phase ◽  
Circuits Vlsi

Titanium nitride (TiN) films have historically been used as diffusion barrier between silicon and aluminum, as an adhesion layer for tungsten deposition and as an interconnect material etc. Recently, the role of TiN films as contact barriers in very large scale silicon integrated circuits (VLSI) has been extensively studied. TiN films have resistivities on the order of 20μ Ω-cm which is much lower than that of titanium (nearly 66μ Ω-cm). Deposited TiN films show resistivities which vary from 20 to 100μ Ω-cm depending upon the type of deposition and process conditions. TiNx is known to have a NaCl type crystal structure for a wide range of compositions. Change in color from metallic luster to gold reflects the stabilization of the TiNx (FCC) phase over the close packed Ti(N) hexagonal phase. It was found that TiN (1:1) ideal composition with the FCC (NaCl-type) structure gives the best electrical property.

THE SOME QUESTIONS OF AUTONOMOUS MOTION AND MANAGEMENT OF LAND-MOBILE ROBOTIC COMPLEXES FOR UKRAINIAN GROUND FORCESE

2019 ◽  
pp. 53-58
Author(s):  
О. Кravchuk ◽  
V. Symonenkov ◽  
I. Symonenkova ◽  
O. Hryhorev
Keyword(s):  
Large Scale ◽  
Armed Forces ◽  
Distributed Information ◽  
Wide Range ◽  
Highly Effective ◽  
Information Management Systems ◽  
Robotic Devices ◽  
Principles And Standards ◽  
And Control ◽  
The Eu

Today, more than forty countries of the world are engaged in the development of military-purpose robots. A number of unique mobile robots with a wide range of capabilities are already being used by combat and intelligence units of the Armed forces of the developed world countries to conduct battlefield intelligence and support tactical groups. At present, the issue of using the latest information technology in the field of military robotics is thoroughly investigated, and the creation of highly effective information management systems in the land-mobile robotic complexes has acquired a new phase associated with the use of distributed information and sensory systems and consists in the transition from application of separate sensors and devices to the construction of modular information subsystems, which provide the availability of various data sources and complex methods of information processing. The purpose of the article is to investigate the ways to increase the autonomy of the land-mobile robotic complexes using in a non-deterministic conditions of modern combat. Relevance of researches is connected with the necessity of creation of highly effective information and control systems in the perspective robotic means for the needs of Land Forces of Ukraine. The development of the Armed Forces of Ukraine management system based on the criteria adopted by the EU and NATO member states is one of the main directions of increasing the effectiveness of the use of forces (forces), which involves achieving the principles and standards necessary for Ukraine to become a member of the EU and NATO. The inherent features of achieving these criteria will be the transition to a reduction of tasks of the combined-arms units and the large-scale use of high-precision weapons and land remote-controlled robotic devices. According to the views of the leading specialists in the field of robotics, the automation of information subsystems and components of the land-mobile robotic complexes can increase safety, reliability, error-tolerance and the effectiveness of the use of robotic means by standardizing the necessary actions with minimal human intervention, that is, a significant increase in the autonomy of the land-mobile robotic complexes for the needs of Land Forces of Ukraine.

Stirring and aeration system for the upgrading of small waste water treatment plants

1994 ◽  
Vol 29 (12) ◽  
pp. 149-156 ◽  
Author(s):  
Marcus Höfken ◽  
Katharina Zähringer ◽  
Franz Bischof
Keyword(s):  
Waste Water ◽  
Water Treatment ◽  
Large Scale ◽  
Waste Water Treatment ◽  
Water Treatment Plants ◽  
Waste Water Treatment Plants ◽  
Basic Fluid ◽  
Aeration System ◽  
Technical Realization ◽  
Wide Range

A novel agitating system has been developed which allows for individual or combined operation of stirring and aeration processes. Basic fluid mechanical considerations led to the innovative hyperboloid design of the stirrer body, which ensures high efficiencies in the stirring and the aeration mode, gentle circulation with low shear forces, excellent controllability, and a wide range of applications. This paper presents the basic considerations which led to the operating principle, the technical realization of the system and experimental results in a large-scale plant. The characteristics of the system and the differences to other stirring and aeration systems are illustrated. Details of the technical realization are shown, which conform to the specific demands of applications in the biological treatment of waste water. Special regard is given to applications in the upgrading of small compact waste water treatment plants.

Thin structure of heterogeneous and multiphase fluid flows

2012 ◽  
Vol 9 (1) ◽  
pp. 175-180
Author(s):  
Yu.D. Chashechkin
Keyword(s):  
Large Scale ◽  
Fundamental System ◽  
Fluid Flows ◽  
Regular Solutions ◽  
Flow Models ◽  
Group Methods ◽  
Wide Range ◽  
Thin Structure ◽  
Multiphase Fluid ◽  
Complete Solutions

According to the results of visualization of streams, the existence of structures in a wide range of scales is noted: from galactic to micron. The use of a fundamental system of equations is substantiated based on the results of comparing symmetries of various flow models with the usage of theoretical group methods. Complete solutions of the system are found by the methods of the singular perturbations theory with a condition of compatibility, which determines the characteristic equation. A comparison of complete solutions with experimental data shows that regular solutions characterize large-scale components of the flow, a rich family of singular solutions describes formation of the thin media structure. Examples of calculations and observations of stratified, rotating and multiphase media are given. The requirements for the technique of an adequate experiment are discussed.

Integrative Data Analysis from a Unifying Research Synthesis Perspective

2018 ◽  
Author(s):  
Eun-Young Mun ◽  
Anne E. Ray
Keyword(s):  
Data Analysis ◽  
Large Scale ◽  
Research Synthesis ◽  
Alcohol Intervention ◽  
Data Set ◽  
Integrative Data Analysis ◽  
Level Data ◽  
Model Complex ◽  
Wide Range ◽  
Individual Participant

Integrative data analysis (IDA) is a promising new approach in psychological research and has been well received in the field of alcohol research. This chapter provides a larger unifying research synthesis framework for IDA. Major advantages of IDA of individual participant-level data include better and more flexible ways to examine subgroups, model complex relationships, deal with methodological and clinical heterogeneity, and examine infrequently occurring behaviors. However, between-study heterogeneity in measures, designs, and samples and systematic study-level missing data are significant barriers to IDA and, more broadly, to large-scale research synthesis. Based on the authors’ experience working on the Project INTEGRATE data set, which combined individual participant-level data from 24 independent college brief alcohol intervention studies, it is also recognized that IDA investigations require a wide range of expertise and considerable resources and that some minimum standards for reporting IDA studies may be needed to improve transparency and quality of evidence.

Quantum Optomechanics and Nanomechanics

2020 ◽  
Keyword(s):  
Gravitational Wave ◽  
Summer School ◽  
Large Scale ◽  
Quantum Noise ◽  
Foundations Of Quantum Mechanics ◽  
Wide Range ◽  
Measurement Laser ◽  
Quantum Limits ◽  
Quantum Optomechanics ◽  
Quantum Ground State

The Les Houches Summer School 2015 covered the emerging fields of cavity optomechanics and quantum nanomechanics. Optomechanics is flourishing and its concepts and techniques are now applied to a wide range of topics. Modern quantum optomechanics was born in the late 70s in the framework of gravitational wave interferometry, initially focusing on the quantum limits of displacement measurements. Carlton Caves, Vladimir Braginsky, and others realized that the sensitivity of the anticipated large-scale gravitational-wave interferometers (GWI) was fundamentally limited by the quantum fluctuations of the measurement laser beam. After tremendous experimental progress, the sensitivity of the upcoming next generation of GWI will effectively be limited by quantum noise. In this way, quantum-optomechanical effects will directly affect the operation of what is arguably the world’s most impressive precision experiment. However, optomechanics has also gained a life of its own with a focus on the quantum aspects of moving mirrors. Laser light can be used to cool mechanical resonators well below the temperature of their environment. After proof-of-principle demonstrations of this cooling in 2006, a number of systems were used as the field gradually merged with its condensed matter cousin (nanomechanical systems) to try to reach the mechanical quantum ground state, eventually demonstrated in 2010 by pure cryogenic techniques and a year later by a combination of cryogenic and radiation-pressure cooling. The book covers all aspects—historical, theoretical, experimental—of the field, with its applications to quantum measurement, foundations of quantum mechanics and quantum information. Essential reading for any researcher in the field.

scholarly journals A Self-Spatial Adaptive Weighting Based U-Net for Image Segmentation

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 348
Author(s):  
Choongsang Cho ◽  
Young Han Lee ◽  
Jongyoul Park ◽  
Sangkeun Lee
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Feature Maps ◽  
Data Set ◽  
Feature Map ◽  
Adaptive Weighting ◽  
Spatially Adaptive ◽  
Wide Range ◽  
Decoder Architecture

Semantic image segmentation has a wide range of applications. When it comes to medical image segmentation, its accuracy is even more important than those of other areas because the performance gives useful information directly applicable to disease diagnosis, surgical planning, and history monitoring. The state-of-the-art models in medical image segmentation are variants of encoder-decoder architecture, which is called U-Net. To effectively reflect the spatial features in feature maps in encoder-decoder architecture, we propose a spatially adaptive weighting scheme for medical image segmentation. Specifically, the spatial feature is estimated from the feature maps, and the learned weighting parameters are obtained from the computed map, since segmentation results are predicted from the feature map through a convolutional layer. Especially in the proposed networks, the convolutional block for extracting the feature map is replaced with the widely used convolutional frameworks: VGG, ResNet, and Bottleneck Resent structures. In addition, a bilinear up-sampling method replaces the up-convolutional layer to increase the resolution of the feature map. For the performance evaluation of the proposed architecture, we used three data sets covering different medical imaging modalities. Experimental results show that the network with the proposed self-spatial adaptive weighting block based on the ResNet framework gave the highest IoU and DICE scores in the three tasks compared to other methods. In particular, the segmentation network combining the proposed self-spatially adaptive block and ResNet framework recorded the highest 3.01% and 2.89% improvements in IoU and DICE scores, respectively, in the Nerve data set. Therefore, we believe that the proposed scheme can be a useful tool for image segmentation tasks based on the encoder-decoder architecture.

Sign in / Sign up

Export Citation Format

Share Document