21,673 Hits in 6.9 sec

Motion Prediction Model Using Adaptive Neuro Fuzzy Network (ANFN) and Probabilistic Neural Network (PNN) Algorithm in 4-Dimensional Computed Tomography (4DCT) Images

J. Vijayaraj, D. Loganathan
2020 International Journal of Current Research and Review  
Methods: The proposed system illustrates a novel predicting model using Adaptive Neuro-Fuzzy Network combined with probabilistic neural networks.  ...  Objective: Novel method to prevent and predict lung cancer as well as to identify the most significant genetic and environmental factors has to be developed.  ...  In real-time, the prediction is both temporal and spatial are estimated on ground truth for a longer time of about 5.5 min.  ... 
doi:10.31782/ijcrr.2020.122328 fatcat:fbxef4zgm5h4zgstfacbk3574u

PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer [article]

Xuzhe Zhang, Xinzi He, Jia Guo, Nabil Ettehadi, Natalie Aw, David Semanek, Jonathan Posner, Andrew Laine, Yun Wang
2021 arXiv   pre-print
In this study, we introduced a novel MRI synthesis framework - Pyramid Transformer Net (PTNet). PTNet consists of transformer layers, skip-connections, and multi-scale pyramid representation.  ...  Despite the success of MRI collection and analysis for adults, it is a challenge for researchers to collect high-quality multimodal MRIs from developing infants mainly because of their irregular sleep  ...  The brain structures, functions, and neural pathways that develop during this time lay the foundation for the people we will become.  ... 
arXiv:2105.13993v1 fatcat:awx3j6nqavcsjohda22x6mgzoa

Scanning the Issue

Azim Eskandarian
2021 IEEE transactions on intelligent transportation systems (Print)  
This paper proposes a novel robust path-following strategy for autonomous road vehicles based on type-2 fuzzy PID neural network (PIDT2FNN) method coupled to an extended Kalman filter-based fuzzy neural  ...  density map and estimate the number of people more accurately.  ...  Dini The SAPIENT system is a real-time monitoring and control infrastructure for air traffic management.  ... 
doi:10.1109/tits.2021.3098395 fatcat:s7r5jkvwbfe2hntml6gylicktq

Multi-sensor People Counting [chapter]

Daniel Hernández-Sosa, Modesto Castrillón-Santana, Javier Lorenzo-Navarro
2011 Lecture Notes in Computer Science  
An accurate estimation of the number of people entering / leaving a controlled area is an interesting capability for automatic surveillance systems.  ...  In this paper we present a novel configuration of a multi-sensor system combining both visual and range data specially suited for troublesome scenarios such as public transportation.  ...  [2] introduced a method for people counting in crowded environments as bus or train gates.  ... 
doi:10.1007/978-3-642-21257-4_40 fatcat:ngo5mr64w5hnpkm5rvo5wso77a

Editorial Message from the Editor-in-Chief

João Manuel R. S. Tavares
2019 Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization  
real-time freehand 3D US imaging system that can obtain volume reconstruction and visualisation during data acquisition in real-time level; 10) Yepes-Calderon et al. introduced a new CT-based pipeline  ...  fracture reduction process are introduced and discussed by Jiménez-Pérez et al.; 3) Moraes et al. proposed and evaluated a novel isosurface rendering method for medical images improved by automatic texture  ... 
doi:10.1080/21681163.2019.1591722 fatcat:wehmcoib6rdvjdcxsnmhkiksfm

A High-Computational Efficiency Human Detection and Flow Estimation Method Based on TOF Measurements

Weihang Wang, Peilin Liu, Rendong Ying, Jun Wang, Jiuchao Qian, Jialu Jia, Jiefeng Gao
2019 Sensors  
This paper presents a fast real-time human detection and flow estimation method using depth images captured by a top-view TOF camera.  ...  Taking full advantage of the distance information implied in the depth image, we achieve high-accuracy human detection and people counting with accuracy of 97.73% and significantly reduce the running time  ...  In this paper, we present a real-time framework for human detection and flow estimation using top-view TOF camera measurements.  ... 
doi:10.3390/s19030729 fatcat:mr7viq75bfdr3nzn2qvnz7nism

Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot

Kuisong Zheng, Feng Wu, Xiaoping Chen
2021 Sensors  
In general, the proposed approach runs in real-time and performs much better than traditional methods.  ...  To tackle these problems, (1) we propose a novel deep learning-based method, which uses the deep neural network in a sliding window fashion to effectively classify every single point of a laser scan. (  ...  Inference To decrease the number of points needed to be classified during inference time, the jump distance clustering method is applied to split a laser scan into groups of beams.  ... 
doi:10.3390/s21030961 pmid:33535488 fatcat:ge4vqzozjzfejon5lyxejym7a4

Octree-based fusion for realtime 3D reconstruction

Ming Zeng, Fukai Zhao, Jiaxiang Zheng, Xinguo Liu
2013 Graphical Models  
To further reduce the computation time, the octree is organized into four layers, called top layer, branch layer, middle layer and data layer.  ...  This paper proposes an octree-based surface representation for KinectFusion, a realtime reconstruction technique of in-door scenes using a low-cost moving depth camera and a commodity graphics hardware  ...  Acknowledgements We would like to thank the anonymous reviewers for their valuable comments, and thank Bo Jiang, Zizhao Wu and Xuan Cheng for proof reading and video editing.  ... 
doi:10.1016/j.gmod.2012.09.002 fatcat:yoinnd7jvjeyxiyiubqen4pr4i

CT Imaging Evolution of Novel Coronavirus Pneumonia during Hospitalization

Abdulfatah Hassan Maqul, Allauddin Barak, Yili Zhang, Youmin Guo
2020 Open Journal of Radiology  
Object: To evaluate CT Features on serial thin-section computed tomographic (CT) scans in patients with conventional Novel Coronavirus Pneumonia (COVID-19) for the period during which they remained hospitalized  ...  Majority of patients had a normal white blood cell count, and normal lymphocyte count although there were patients with leucopenia and lymphocytopenia.  ...  Statistical Methods SPSS 22.0 statistical software was used for analysis. Frequency and rate were used for counting data.  ... 
doi:10.4236/ojrad.2020.103013 fatcat:6ivxpmoqnjbzfj4iumamu7si7i

Counting Fish and Dolphins in Sonar Images Using Deep Learning [article]

Stefan Schneider, Alex Zhuang
2020 arXiv   pre-print
Our method can be used to lower costs and expedite the data analysis of fish and dolphin abundance to real-time along the Amazon river and river systems worldwide.  ...  We propose a novel approach to calculating fish abundance using deep learning for fish and dolphin estimates from sonar images taken from the back of a trolling boat.  ...  The images are constructed in real time by a side-scan sonar that is able to scan a sweeping angle of 60 degrees within the water.  ... 
arXiv:2007.12808v1 fatcat:prvdywdp5vcr7dcy6bgs3v64mq

Fully Convolutional Neural Networks for Crowd Segmentation [article]

Kai Kang, Xiaogang Wang
2014 arXiv   pre-print
In this paper, we propose a fast fully convolutional neural network (FCNN) for crowd segmentation.  ...  Based on FCNN, a multi-stage deep learning is proposed to integrate appearance and motion cues for crowd segmentation.  ...  (a) A typical structure for patch-by-patch scanning method.(b) A typical CNN structure for regression problem. (c) Our proposed FCNN network. (d) The output maps of a high-level fusion layer in FCNN.  ... 
arXiv:1411.4464v1 fatcat:tvsshs7cifa3ba2idanzy3mycu

Livestock detection and counting using CNN

Harsha M. V., Karthik J. Bharadwaj, Lohith Raj S. N.
2021 International journal of advanced scientific research and management  
This project develops an algorithm to detect the animals and to count them. Since there are a large number of animals personally identifying and counting them will be a very difficult task.  ...  This application classifies livestock animals based on the pictures fed by live camera so we can monitor and keep count of them more correctly.  ...  This project is designed to be a real-time system that solves the problem and improves efficiency, accuracy and it is affordable. Fig. 1 . 1 Fig. 1.  ... 
doi:10.36282/ijasrm/6.11.2021.1843 fatcat:f5nfun5bprgbvkxnkoayp2xa6u

A new clustering method for the diagnosis of CoVID19 using medical images

Himanshu Mittal, Avinash Chandra Pandey, Raju Pal, Ashish Tripathi
2021 Applied intelligence (Boston)  
In this method, a novel variant of a gravitational search algorithm is employed for obtaining optimal clusters.  ...  For the same, literature has witnessed that medical imaging plays a vital role, and tools using supervised methods have promising results.  ...  Therefore, this paper presents a novel variant of GSA, improved GSA (IGSA), to enhance the vicinity to optimal solutions.  ... 
doi:10.1007/s10489-020-02122-3 pmid:34764580 pmcid:PMC7823179 fatcat:56b6asmgirhqblaw3p52qf2vl4

DeepMMSA: A Novel Multimodal Deep Learning Method for Non-small Cell Lung Cancer Survival Analysis [article]

Yujiao Wu, Jie Ma, Xiaoshui Huang, Sai Ho Ling, Steven Weidong Su
2021 arXiv   pre-print
To improve the survival prediction accuracy and help prognostic decision-making in clinical practice for medical experts, we for the first time propose a multimodal deep learning method for non-small cell  ...  The conventional methods for lung cancer survival analysis normally utilize clinical data and only provide a statistical probability.  ...  It can be broadly classified into non-small cell lung cancer (NSCLC), counting for 85% and small cell lung cancer (SCLC), counting for the remaining 15%. Lung cancer has a poor prognosis.  ... 
arXiv:2106.06744v1 fatcat:27xdqaauina6po7aalwe4bnw3m

Human View Synthesis using a Single Sparse RGB-D Input [article]

Phong Nguyen, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung
2021 arXiv   pre-print
We show our method generates high-quality novel views of synthetic and real human actors given a single sparse RGB-D input.  ...  Novel view synthesis for humans in motion is a challenging computer vision problem that enables applications such as free-viewpoint video.  ...  the cur- 3dMD 4D scans people in motion.  ... 
arXiv:2112.13889v2 fatcat:u6e2uuinxra2lnrknjmrcsd6yq
« Previous Showing results 1 — 15 out of 21,673 results