检索结果-内蒙古大学图书馆

Spatio-temporal deep learning models for tip force estimation during needle insertion

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2019年第9期14卷 1485-1493页

作者： Gessert, Nils Priegnitz, Torben Saathoff, Thore Antoni, Sven-Thomas Meyer, David Hamann, Moritz Franz Juenemann, Klaus-Peter Otte, Christoph Schlaefer, Alexander Hamburg Univ Technol Inst Med Technol Hamburg Germany Univ Hosp Schleswig Holstein Dept Urol Kiel Germany

Purpose Precise placement of needles is a challenge in a number of clinical applications such as brachytherapy or biopsy. Forces acting at the needle cause tissue deformation and needle deflection which in turn may lead to misplacement or injury. Hence, a number of approaches to estimate the forces at the needle have been proposed. Yet, integrating sensors into the needle tip is challenging and a careful calibration is required to obtain good force estimates. Methods We describe a fiber-optic needle tip force sensor design using a single OCT fiber for measurement. The fiber images the deformation of an epoxy layer placed below the needle tip which results in a stream of 1D depth profiles. We study different deep learning approaches to facilitate calibration between this spatio-temporal image data and the related forces. In particular, we propose a novel convGRU-CNN architecture for simultaneous spatial and temporal data processing. Results The needle can be adapted to different operating ranges by changing the stiffness of the epoxy layer. Likewise, calibration can be adapted by training the deep learning models. Our novel convGRU-CNN architecture results in the lowest mean absolute error of 1.59 +/- 1.3mN and a cross-correlation coefficient of 0.9997 and clearly outperforms the other methods. Ex vivo experiments in human prostate tissue demonstrate the needle's application. Conclusions Our OCT-based fiber-optic sensor presents a viable alternative for needle tip force estimation. The results indicate that the rich spatio-temporal information included in the stream of images showing the deformation throughout the epoxy layer can be effectively used by deep learning models. Particularly, we demonstrate that the convGRU-CNN architecture performs favorably, making it a promising approach for other spatio-temporal learning problems.

关键词： Force estimation optical coherence tomography Convolutional GRU Convolution neural network Needle placement

来源：评论

学校读者我要写书评

暂无评论

Planogram Design Analytics using Image Processing

Planogram Design Analytics using Image Processing

引用

computing, Analytics and networks (Indo-Taiwan ICAN), Indo – Taiwan 2nd International Conference on

作者： Eesha Goel Kulbhushan Sharma Technology Team Denave India Private Limited Noida India

ISBN: (数字)9781728149998

ISBN: (纸本)9781728150000

A planogram is a tool for visual merchandising of retail stores. It displays a detailed view of the retail store with the major intent for product placement. The planogram is highly useful for examining the point of sale as it demonstrates the exact positioning of products. Two major benefits are there for building planograms while planning the store layout such as maximizing sales and space of the retail *** important part of Planogram management is to read planogram drawings and images and convert these to representational data in CSV or database *** this part, Contour analysis of image using OpenCV along with combination of text detection and recognition is performed using Connectionist Text Proposal network and Convolutional Recurrent neural network deep learning models respectively. The proposed planogram design analytics system is implemented using real data. The customer had tested the system as per different cases. The feedback obtained from them confirms that the system meets the requirements to their satisfaction.

关键词： Text recognition optical character recognition software Layout Feature extraction Data mining Proposals Machine learning

来源：评论

学校读者我要写书评

暂无评论

High-Performance Object Detection for optical Remote Sensing Images with Lightweight Convolutional neural networks

High-Performance Object Detection for Optical Remote Sensing...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Jia Liu Renhua Liu Kaijun Ren Xiaoyong Li Jianjian Xiang Shaohua Qiu School of Computer Science China University of Geosciences Wuhan China College of Meteorology and Oceanography National University of Defense Technology Changsha China National Key Laboratory of Science and Technology on Vessel Integrated Power System Naval University of Engineering Wuhan China

ISBN: (纸本)9781728176499;9781728176505

Convolutional neural network (CNN)-based object detection for optical remote sensing images has achieved higher accuracy compared with traditional detection methods with handcrafted features. However, the deep and large CNNs make it hard to be deployed in real-time scenarios with limited computation, storage, power and bandwidth resources, for example, data processing onboard airborne, satellites and unmanned aerial vehicles for search and rescue. Therefore, in this paper we present a high-performance object detection approach for optical remote sensing images. Based on the widely used Faster R-CNN framework, we integrate state-of-the-art lightweight CNNs as backbone to extract features, slim the heavy-head architecture of two-stage detector by reducing dimensions of features, and fine-tune our models with NWPU VHR-10 optical remote sensing dataset. Besides, the multi-threading for CPU and detection in batches for GPU are deployed to enhance the throughput of detectors and utilization of multi-core CPU and many-core GPU. Experiments show that our presented detection approach can significantly reduce the model size, computation complexity and detection time, while maintaining competitive accuracy. Specifically, the one with ShuffleNet-v2 and slimmed features has achieved a highest mean average precision of 94.39%, a lowest computational complexity of 18.97 Giga floating point operations, a highest detection speed of 90.10 frames per second (fps) for GPU and 3.07 fps for CPU, corresponding to speedups of 6.94X and 13.26X compared with the baseline on the benchmarked system, with a model size of 13.6 MB. Moreover, it further improves the efficiency and achieves 4.98 fps on CPU with 4 threads, and 200.24 fps on GPU with a batch size of 32.

关键词： Computational modeling Graphics processing units Object detection optical computing Detectors optical fiber networks optical detectors

来源：评论

学校读者我要写书评

暂无评论

Dense Convolutional networks for Efficient Video Analysis 5

Dense Convolutional Networks for Efficient Video Analysis

引用

5th International Conference on Control, Automation and Robotics (ICCAR)

作者： Jin, Tian He, Zhihao Basu, Amlan Soraghan, John Di Caterina, Gaetano Petropoulakis, Lykourgos Hangzhou Shargoo Data Technol Co Ltd CeSIP Royal Coll Bldg Hangzhou Peoples R China Univ Strathclyde CeSIP Royal Coll Bldg Glasgow Lanark Scotland

ISBN: (纸本)9781728133263

Over the past few years various Convolutional neural networks (CNNs) based models exhibited certain human-like performance in a range of image processing problems. Video understanding, action classification, gesture recognition has become a new stage for CNNs. The typical approach for video analyse is based on 2DCNN to extract feature map from a single frame and through 3DCNN or LSTM to merging spatiotemporal information, some approaches will add optical flow on the other branch and then post-hoc fusion. Normally the performance is proportional to the model complexity, as the accuracy keeps improving, the problem is also evolved from accuracy to model size, computing speed, model availability. In this paper, we present a lightweight network architecture framework to learn spatiotemporal feature from video. Our architecture tries to merge long-term content in any network feature map. Keeping the model as small and as fast as possible while maintaining accuracy.

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

Proposing algorithm for detecting car number plate using SVM and WPOD-NET models

Proposing algorithm for detecting car number plate using SVM...

引用

International Conference on Advanced computing and Applications (ACOMP)

作者： Phat Nguyen Huu Cuong Vu Quoc Thang Nguyen Vu Hieu Nguyen Trong Quang Tran Minh Trung Nguyen Dac School of Electronics and Telecommunications Hanoi University of Science and Technology (HUST) Hanoi Vietnam National Institute of Patent and Technology Exploitation Vietnamese Ministry of Science and Technology Hanoi Vietnam Faculty of Computer Science and Engineering Ho Chi Minh City University of Technology (HCMUT) Vietnam National University Ho Chi Minh City (VNU-HCM) Hochiminh Vietnam School of Engineering Pedagogy Hanoi University of Science and Technology (HUST) Hanoi Vietnam

ISBN: (数字)9781728181677

ISBN: (纸本)9781728181684

Nowadays, although there are various methods to detect car registration numbers, most approaches are focused on the frontal view of the plate in fair conditions of the environment. This paper proposes an algorithm to detect the car number in different angle views and various weather conditions. Our salient contribution is applying a new Convolution neural network (CNN) capable of detecting and adjusting distorted license plates. They would then be processed in the optical Character Recognition step-using Support Vector Machine (SVM)-to get the result of numbers and characters on the plate. Our experiment results indicate that the algorithm performs well in unconstrained scenarios with two types of car plates in Vietnam: rectangle and square. The percentage of correct detecting and recognizing the car number plate is 95.1% when testing 1000 samples in various realistic scenarios.

关键词： Support vector machines optical filters Wireless sensor networks optical distortion Filtering algorithms Automobiles optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

Video Object Detection Base on RGB and optical Flow Analysis 2

Video Object Detection Base on RGB and Optical Flow Analysis

引用

2nd China Symposium on Cognitive computing and Hybrid Intelligence, CCHI 2019

作者： Zhang, Shunyao Wang, Tian Wang, Chuanyun Wang, Yan Shan, Guangcun Snoussi, Hichem School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science Shenyang Aerospace University Shenyang China School of Instrumentation Science and Opto-electronic Engineering Beihang University Beijing China Institute Charles Delaunay LM2SFRE CNRS 2019 University of Technology of Troyes Troyes France

ISBN: (纸本)9781728140919

Although the image object detection technology developed quickly, the object detection in videos has special conditions such as motion blur, video defocus, part occlusion, rare posture, and needs to keep the target detection result consistent in time. It cannot apply image object detection models directly on videos. In this paper, we proposed the video object detection method based on the YOLO-v3 together with the FlowNet 2.0 optical flow extraction network to make full use of the information of the consistent video frames. The proposed Flow-guided Partial Warp method operates at the feature map level to make the detection result more accurate. In order to solve the motion blur influence of background, the optical flow compression by bilinear interpolation can minimize the influence. Meanwhile, the proposed method also uses the frame skipping to avoid the repeated use of convolutional neural networks in frames with little change, which reduces the consumption of computing resources and speeds up the running of the model. In addition, this paper also attempts to use the autonomous vehicles simulator as the input data of the video target detection algorithm. Finally, after testing in some typical scenarios, the detection results of most scenes are obviously improved after using optical flow guidance and aggregation feature maps. © 2019 IEEE.

关键词： optical flows

来源：评论

学校读者我要写书评

暂无评论

Learning Temporal Information From A Single Image For AU Detection 14

Learning Temporal Information From A Single Image For AU Det...

引用

14th IEEE International Conference on Automatic Face and Gesture Recognition (FG)

作者： Yang, Huiyuan Yin, Lijun SUNY Binghamton Dept Comp Sci Binghamton NY 13902 USA

ISBN: (纸本)9781728100890

Automatic Facial Action Units ( AUs) detection is the recognition of the facial appearance changes caused by the contraction or relaxation of one or more related facial muscles. Compared to the sequence-based methods, a decreased performance is observed for the static image-based AU detection, due to the loss of temporal information. To solve this problem, we propose a novel method that implicitly learns temporal information from a single image for AU detection by adding a hidden optical-flow layer to concatenate two Convolutional neural networks ( CNNs) models: optical-flow net ( OF-Net) and AU detection net ( AU-Net). The OF-Net is designed to estimate the facial appearance changes ( optical flow) from a single input image through unsupervised learning. The AU-Net accepts the estimated optical-flow as input and predicts the AU occurrence. By training both OF-Net and AU-Net jointly, our model achieves better performance than training them separately, as the AU-Net provides semantic constraints for the optical-flow learning and helps generate more meaningful optical-flow. In return, the estimated optical-flow, which reflects facial appearance changes, benefits the AU-Net. Our proposed method has been evaluated on two benchmarks: BP4D and DISFA, and the experiments show significant performance improvement as compared to the state-of-the-art methods.

关键词： optical imaging Gold optical losses optical computing Estimation optical network units

来源：评论

学校读者我要写书评

暂无评论

Temporal Interlacing network

arXiv

引用

arXiv 2020年

作者： Shao, Hao Qian, Shengju Liu, Yu Tsinghua University SenseTime X-Lab Chinese University of Hong Kong

For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal convolution. However, these pipelines consume enormous computing resources due to the alternately learning process for spatial and temporal information. One natural question is whether we can embed the temporal information into the spatial one so the information in the two domains can be jointly learned once-only. In this work, we answer this question by presenting a simple yet powerful operator – temporal interlacing network (TIN). Instead of learning the temporal features, TIN fuses the two kinds of information by interlacing spatial representations from the past to the future, and vice versa. A differentiable interlacing target can be learned to control the interlacing process. In this way, a heavy temporal model is replaced by a simple interlacing operator. We theoretically prove that with a learnable interlacing target, TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with 6x less latency on 6 challenging benchmarks. These results push the state-of-the-art performances of video understanding by a considerable margin. Not surprising, the ensemble model of the proposed TIN won the 1st place in the ICCV19 - Multi Moments in Time challenge. Code is made available to facilitate further research.1 Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

基于深度学习的人体动作识别方法

引用

计算机工程与设计 2020年第4期41卷 1153-1157页

作者：沈西挺于晟董瑶董永峰张泽伟河北工业大学人工智能与数据科学学院天津300401 河北工业大学河北省大数据计算重点实验室天津300401

对基于机器视觉的人体动作识别的成果进行研究,为提高视频数据集中人体动作的识别率,提出一种改进的深度网络模型。采用稠密光流方法处理数据,结合二维卷积神经网络(2DCNN)、三维卷积神经网络(3DCNN)和长短期记忆神经网络(LSTM)对动作... 详细信息

对基于机器视觉的人体动作识别的成果进行研究,为提高视频数据集中人体动作的识别率,提出一种改进的深度网络模型。采用稠密光流方法处理数据,结合二维卷积神经网络(2DCNN)、三维卷积神经网络(3DCNN)和长短期记忆神经网络(LSTM)对动作特征进行提取,利用Softmax分类器识别分类。通过KTH数据集进行实验对比验证,分析结果表明,改进模型相比其它已有模型具有更高的识别率,动作识别效果更优。

关键词：人体动作识别深度学习 KTH数据集卷积神经网络稠密光流

来源：评论

学校读者我要写书评

暂无评论

Belief Propagation with Deep Unfolding for High-Dimensional Inference in Communication Systems

Belief Propagation with Deep Unfolding for High-Dimensional ...

引用

作者： Lian, Mengke Duke University

学位级别：Ph.D.

High-dimensional probability distributions are important objects in a wide variety of applications for example, most prediction and inference applications focus on computing the posterior marginal of a subset of variables conditioned on observations of another subset of variables. In practice, this is untractable due to the curse of dimensionality. In some problems, high-dimensional joint probability distributions can be represented by factor graphs. For such problems, belief propagation (BP) is a polynomial-time algorithm that provides an efficient approximation of the posterior marginals, and it is exact if the factor graph does not contain cycles. With rapid improvements in machine learning over the past decade, using machine learning techniques to optimize system parameters is an emerging field in communication research. This thesis considers applying BP for communication systems, and focuses on incorporating domain knowledge into machine learning models. For compressive sensing, two variants of relaxed belief propagation (RBP) algorithm are proposed. One improves the stability over a larger class of measurement matrices and the other reduces the computational complexity when measurement matrix is in the product of several sparse matrices. For optical communication, the non-linear Schrodinger equation is solved by modeling the signal in each step of split-step Fourier method as a multivariate complex Gaussian distribution. Then, the parameters of the Gaussian are tracked through in digital back-propagation. For recursive decoding for Reed-Muller codes, the algebraic structure of the code is utilized and a recursive BP approach for redundant factor graphs is developed for near-optimal decoding. Finally, we use deep unfolding to unroll BP decoding as a recursive neural network and introduce the idea of a the parameter adaptive network to learn the relation between channel SNR and optimal BP weight factors.

关键词： Engineering belief propagation channel coding compressed sensing deep unfolding optical communication

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：