检索结果-内蒙古大学图书馆

Long Term Safety Area Tracking (LT-SAT) with online failure detection and recovery for robotic minimally invasive surgery

引用

MEDICAL image ANALYSIS 2018年 45卷 13-23页

作者： Penza, Veronica Du, Xiaofei Stoyanov, Danail Forgione, Antonello Mattos, Leonardo S. De Momi, Elena Politecn Milan Dept Elect Informat & Bioengn Pzza L Da Vinci 32 I-20133 Milan Italy Ist Italiano Tecnol Dept Adv Robot Via Morego 30 I-16163 Genoa Italy UCL Ctr Med Image Comp Dept Comp Sci London England Osped Niguarda Ca Granda Pzza Osped Maggiore 3 I-20162 Milan Italy

Despite the benefits introduced by robotic systems in abdominal Minimally Invasive Surgery (MIS), major complications can still affect the outcome of the procedure, such as intra-operative bleeding. One of the causes is attributed to accidental damages to arteries or veins by the surgical tools, and some of the possible risk factors are related to the lack of sub-surface visibilty. Assistive tools guiding the surgical gestures to prevent these kind of injuries would represent a relevant step towards safer clinical procedures. However, it is still challenging to develop computer vision systems able to fulfill the main requirements: (i) long term robustness, (ii) adaptation to environment/object variation and (iii) real time processing. The purpose of this paper is to develop computer vision algorithms to robustly track soft tissue areas (Safety Area, SA), defined intra-operatively by the surgeon based on the real-time endoscopic images, or registered from a pre-operative surgical plan. We propose a framework to combine an optical flow algorithm with a tracking-by-detection approach in order to be robust against failures caused by: (i) partial occlusion, (ii) total occlusion, (iii) SA out of the field of view, (iv) deformation, (v) illumination changes, (vi) abrupt camera motion, (vii), blur and (viii) smoke. A Bayesian inference-based approach is used to detect the failure of the tracker, based on online context information. A Model Update Strategy (MUpS) is also proposed to improve the SA re-detection after failures, taking into account the changes of appearance of the SA model due to contact with instruments or image noise. The performance of the algorithm was assessed on two datasets, representing ex-vivo organs and in-vivo surgical scenarios. Results show that the proposed framework, enhanced with MUpS, is capable of maintain high tracking performance for extended periods of time (similar or equal to 4 min - containing the aforementioned events) with high precisi

关键词： Long-term tissue tracking Tracking failure detection Model Update Strategy Robotic minimally invasive surgery

来源：评论

学校读者我要写书评

暂无评论

Improve the Frequency Identification in SSVEP based BCI systems with Moving Windows Algorithm

Improve the Frequency Identification in SSVEP based BCI Syst...

引用

International conference on Control, Instrumentation, and Automation

作者： Arian Yousefiankalareh Mohammad Ali Manoochehri Seyed Alireza Khoshnevis Sandeep Reddy Surakanti Mechanical Engineering Department Tarbiat Modares University Tehran Iran Electrical Engineering Department Yazd University Yazd Iran Electrical Engineering Department University of South Florida Tampa USA

ISBN: (数字)9781728158150

ISBN: (纸本)9781728158167

Most processing methods used in SSVEP-based BCI systems use fixed time windows for frequency identification. Due to the variable nature of the EEG signal timing, the use of fixed time windows is not appropriate. In this paper, a new algorithm for floating windows is proposed and evaluated with CCA and LASSO frequency detection methods. The results show that the use of the moving window algorithm for LASSO and CCA methods improves the maximum percentage of frequency identification accuracy by 3.76% and 6.25% respectively. Furthermore, this method decreases the frequency identification time to 0.55 seconds and 0.79 seconds compared to the fixed window algorithm. Advantages such as being able to apply to all frequency recognition methods, increasing the frequency identification accuracy at a certain time of processing compared to fixed windows, adding unlabeled state and adaptability based on system requirements make this algorithm one of the best candidates for SSVEP-based BCI systems.

关键词： Electroencephalography Microsoft Windows Classification algorithms Harmonic analysis image coding Instruments Automation

来源：评论

学校读者我要写书评

暂无评论

Mobile Microscopic device to detect parasitical cell-related diseases using Machine Learning 6

Mobile Microscopic device to detect parasitical cell-related...

引用

6th IEEE Int Conf on Future Internet of Things and Cloud (W-FiCloud) / 15th Int Conf on Mobile Web and Intelligent Information systems (MobiWis) / 4th Int Conf on Big Data Innovations and Applications (Innovate-Data)

作者： Khan, Aishah Khalil, Ashraf Hajjdiab, Hassan Abu Dhabi Univ Coll Engn Abu Dhabi U Arab Emirates

ISBN: (纸本)9781538678107

The objective of this mobile hand-held microscopic device is to provide aid to people residing in developing countries with early detection of various blood and gastrointestinal diseases. This device is created using a cell scope attached to the camera lens of the phone. The detection of disease is done using image processing algorithms which are stored on a cloud based server to generate reports and efficiently send results to the end user. The main goal behind the device is to create a revolution in the world of technology and healthcare by facilitating easier approaches of disease detection and prevention in rural areas.

关键词： mobile microscope healthcare malaria image pre processing neural networks feature extraction classification

来源：评论

学校读者我要写书评

暂无评论

Speed Optimization of the AES Algorithm Using Pipeline Hardware Architecture

Speed Optimization of the AES Algorithm Using Pipeline Hardw...

引用

International conference on Communication and Electronics systems (ICCES)

作者： Dheeraj Punia Brahmjit Singh School of VLSI Design and Embedded Systems NIT Kurukshetra Kurukshetra India NIT Kurukshetra Kurukshetra India

ISBN: (数字)9781728112619

ISBN: (纸本)9781728112626

Secure encryption algorithms with advanced key executive techniques constantly help to achieve privacy, verification, and security of the data and curtail the overheads of the system. Currently, the prominent cryptographic technique is the Advance Encryption Standard (AES). The 128-bit pipelined cipher AES components adopt the symmetric-block cipher algorithm for encryption of the data. Our application achieves a high-level of encryption of 25.6 Gbps with an effective inter-and-intra-round layout. This module is designed on Xilinx ISE® Design Suite 14.7 and optimized for faster conversion speeds as the module is based on the pipeline architecture to perform the repeated array of operations known as the round. The designed module is suitable for high-security data communication, image processing, and other embedded applications. Pipelined architecture reduces the time associated with each encryption process and decreases the total time it takes for a plaintext block to encrypt.

关键词： Encryption conferences Throughput Hardware Ciphers Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Gradient Fusion Operators for Vector-Valued image processing 4th

Gradient Fusion Operators for Vector-Valued Image Processing

引用

10th conference of the European-Society-for-Fuzzy-Logic-and-Technology (EUSFLAT) / 16th International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets (IWIFSGN)

作者： Lopez-Molina, Carlos Montero, Javier Bustince, Humberto De Baets, Bernard Univ Publ Navarra Dept Automat & Computac Pamplona Spain Univ Complutense Madrid Fac Math Madrid Spain CSIC UCM Geosci Inst IGEO Madrid Spain Univ Ghent Dept Math Modelling Stat & Bioinformat KERMIT Ghent Belgium

ISBN: (纸本)9783319668246;9783319668239

While classical image processing algorithms were designed for scalar-valued (binary or grayscale) images, new technologies have made it commonplace to work with vector-valued ones. These technologies can involve new types of sensors, as in remote sensing, but also mathematical models leading to an increased cardinality at each pixel. This work analyzes the role of first-order differentiation in vector-valued images;specifically, we explore a novel operator to produce a 2D vector from a Jacobian matrix, in order to represent the variation in a vector-valued image as a planar feature.

关键词： Vector-valued images Differentiation Jacobian matrix Information fusion

来源：评论

学校读者我要写书评

暂无评论

A flexible system for gesture based human-robot interaction 51

A flexible system for gesture based human-robot interaction

引用

51st CIRP conference on Manufacturing systems (CIRP CMS)

作者： Tellaeche, Alberto Kildal, Johan Maurtua, Inaki IK4 Tekniker Calle Inaki Goenaga 5 Eibar Gipuzkoa Spain

In industrial collaborative robotics, operators and robots perform complex tasks working together without physical barriers. Under this premise, the availability of a flexible, robust and fast interaction system between the robot and the workers is a necessity. Human beings use voice and gestures to achieve a natural interaction. Taking into account the environmental conditions usually present in workshops with noise and poor lighting conditions, combining both communication channels can contribute to make the interaction more robust. This research work presents a solution to define, setup and run a flexible and robust gesture interaction system to integrate in collaborative robotics applications. (C) 2018 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the 51st CIRP conference on Manufacturing systems.

关键词： Robust gesture detection Human-Robot collaboration image processing machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep multi-spectral registration using invariant descriptor learning 25

Deep multi-spectral registration using invariant descriptor ...

引用

25th IEEE International conference on image processing, ICIP 2018

作者： Ofir, Nati Silberstein, Shai Levi, Hila Rozenbaum, Dani Keller, Yosi Duvdevani Bar, Sharon Elbit Systems Bar-Ilan University Computer Vision and Algorithms Ltd Weizmann Institute Israel

ISBN: (纸本)9781479970612

In this work, we propose a deep-learning approach for aligning cross-spectral images. Our approach utilizes a learned descriptor invariant to different spectra. Multi-modal images of the same scene capture different characteristics and therefore their registration is challenging. To that end, we developed a feature-based approach for registering visible (viS) to Near-Infra-Red (NIR) images. Our scheme detects corners by Harris and matches them by a patch-metric learned on top of a network trained using the CIFAR-10 dataset. As our experiments demonstrate, we achieve accurate alignment of cross-spectral images with sub-pixel accuracy. Comparing to contemporary state-of-the-art, our approach is more accurate in the task of viS to NIR registration. © 2018 IEEE.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Automating and Optimizing the Design Process of Solar Module Installation and Providing Necessary Forecasts using Machine Learning Algorithm 2018

Automating and Optimizing the Design Process of Solar Module...

引用

10th International conference on Machine Learning and Computing (ICMLC)

作者： Shende, Prasad Mehendarge, Shivani Goel, Anubhav Kasturkar, Vaishnavi Chougule, Sachin Takalikar, Mukta Pune Inst Comp Technol Dept Comp Engn Pune Maharashtra India Inteliment Technol India Pvt Ltd India Pune Maharashtra India

ISBN: (纸本)9781450363532

Solar energy is the most readily available and the cheapest form of energy available. In a data-driven world of today, the data analysis tools combined with machine learning algorithms and sensors can be used to analyze and crunch data to solve various problems plaguing the solar industry. Designing a system that recognizes the accurate positions for installing the PV modules on a rooftop, predict the power production capacity of the solar power plant and also manage the maintenance cycles, will not only help in minimizing the losses due to installation at improper places but also will increase the efficiency of the plant and reduce the cost of electricity production as a whole. This paper aims at using machine learning algorithms and image analysis tools to find the proper areas wherein the PV modules can be installed so as to maximize the production and at the same time predicting and visualizing the maintenance cycles of the power plant. The paper also aims to provide relevant data points for prediction of weather and power, which will be tabulated in a user-friendly way for further analytics.

关键词： Artificial intelligence image processing and computer vision connectism and neural nets genetic algorithms un- supervised learning and data management systems

来源：评论

学校读者我要写书评

暂无评论

Onboard smart surveillance for micro-UAV swarm: an experimental study 8

Onboard smart surveillance for micro-UAV swarm: an experimen...

引用

8th IEEE Annual International conference on Cyber Technology in Automation, Control, and Intelligent systems (IEEE-CYBER)

作者： Zhao, Kuang Zhou, Yong Zhou, Zhengyuan Tang, Dengqing Chang, Yuan Fang, Qiang Zhou, Han Hu, Tianjiang Natl Univ Def Technol Coll Mechatron & Automat Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781538670576

In this paper, a smart approach is proposed and developed to enable micro-UAV surveillance with extremely limited onboard computation resources. Recently, a few algorithms have been proposed to detect ground vehicles from UAV aerial vision views. But most of them are processed via air-ground communication and abundant ground computing platforms. However, this study concentrates on the onboard processing scheme of detection and classification on ground moving vehicles by one flying micro UAV. A unified scheme of saliency detection and shallow convolution neural network classification makes a compatible surveillance performance with the only onboard processor. Under such circumstances, an experimental study is conducted on the developed micro-UAV onboard surveillance approach. The experimental results show that the proposed approach can definitely detect and classify at less six kinds of ground moving vehicles up to similar to 14 fps with only limited onboard computation. This work demonstrates practical feasibility for online vision processing of micro-UAV swarm surveillance on ground objects.

关键词： autonomous aerial vehicles convolutional neural nets image classification microrobots neurocontrollers object detection robot vision surveillance Neurocontrollers Microbots robot vision Object detection image classification Ground vehicles dike swarms Slow moving vehicles

来源：评论

学校读者我要写书评

暂无评论

Large Margin Deep Networks for Classification 32

Large Margin Deep Networks for Classification

引用

32nd conference on Neural Information processing systems (NIPS)

作者： Elsayed, Gamaleldin F. Krishnan, Dilip Mobahi, Hossein Regan, Kevin Bengio, Samy Google Res Salt Lake City UT 84102 USA

We present a formulation of deep learning that aims at producing a large margin classifier. The notion of margin, minimum distance to a decision boundary, has served as the foundation of several theoretically profound and empirically successful results for both classification and regression tasks. However, most large margin algorithms are applicable only to shallow models with a preset feature representation;and conventional margin methods for neural networks only enforce margin at the output layer. Such methods are therefore not well suited for deep networks. In this work, we propose a novel loss function to impose a margin on any chosen set of layers of a deep network (including input and hidden layers). Our formulation allows choosing any l(p) norm (p > 1) on the metric measuring the margin. We demonstrate that the decision boundary obtained by our loss has nice properties compared to standard classification loss functions. Specifically, we show improved empirical results on the MNIST, CIFAR-10 and imageNet datasets on multiple tasks: generalization from small training sets, corrupted labels, and robustness against adversarial perturbations. The resulting loss is general and complementary to existing data augmentation (such as random/adversarial input transform) and regularization techniques such as weight decay, dropout, and batch norm.(2 )

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：