检索结果-内蒙古大学图书馆

Speckle reduction with trained nonlinear diffusion filtering

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Feng, Wensen Chen, Yunjin School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16 GrazA-8010 Austria

Speckle reduction is a prerequisite for many image processing tasks in synthetic aperture radar (SAR) images, as well as all coherent images. In recent years, predominant state-of-the-art approaches for despeckling are usually based on nonlocal methods which mainly concentrate on achieving utmost image restoration quality, with relatively low computational efficiency. Therefore, in this study we aim to propose an efficient despeckling model with both high computational efficiency and high recovery quality. To this end, we exploit a newly-developed trainable nonlinear reaction diffusion(TNRD) framework which has proven a simple and effective model for various image restoration problems. In the original TNRD applications, the diffusion network is usually derived based on the direct gradient descent scheme. However, this approach will encounter some problem for the task of multiplicative noise reduction exploited in this study. To solve this problem, we employed a new architecture derived from the proximal gradient descent method. Taking into account the speckle noise statistics, the diffusion process for the despeckling task is derived. We then retrain all the model parameters in the presence of speckle noise. Finally, optimized nonlinear diffusion filtering models are obtained, which are specialized for despeckling with various noise levels. Experimental results substantiate that the trained filtering models provide comparable or even better results than state-of-the-art nonlocal approaches. Meanwhile, our proposed model merely contains convolution of linear filters with an image, which offers high level parallelism on GPUs. As a consequence, for images of size 512 × 512, our GPU implementation takes less than 0.1 seconds to produce state-of-the-art despeckling performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Computational efficiency

The interactive image: A media archaeology approach

学校读者我要写书评

暂无评论

The interactive image: A media archaeology approach

ACM SIGGRAPH 2017 Art Gallery - International Conference on computer graphics and Interactive Techniques, SIGGRAPH 2017

作者： Bravo, Esteban García Burbano, Andrés Byrd, Vetria L. Forbes, Angus G. Purdue University Department of Computer Graphics Technology West LafayetteIN47907 United States Universidad de Los Andes Department of Design Cra 1 No. 18A-12 Bogotá111711 Colombia University of Illinois at Chicago Electronic Visualization Laboratory Department of Computer Science M/C 152 851 S Morgan Room 1120 ChicagoIL60607 United States

ISBN: (纸本)9781450349987

This paper examines the history of the influential Interactive Image computer graphics showcase, which took place at museum and conference venues from 1987 to 1988. The authors present a preliminary exploration of the historical contexts that led to the creation of this exhibition by the Electronic Visualization Lab (EVL), which included the integrated efforts of both artists and computer scientists. In addition to providing historical details about this event, the authors introduce a media archaeology approach for examining the cultural and technological contexts in which this event is situated. © 2017 Esteban García Bravo, Andr's Burbano, Vetria L. Byrd, Angus G. Forbes.

关键词： Exhibitions

In-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in ultrasound acquisitions of the liver with two specialists in internal medicine

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Egger, Jan Schmalstieg, Dieter Bettac, Lucas Hänle, Mark Hann, Alexander Chen, Xiaojun Gräter, Tilmann Egger, Jan Zoller, Wolfram G. Hann, Alexander Institute for Computer Graphics Vision Graz University of Technology Graz Austria Dept. of Internal Medicine I Ulm University Ulm Germany School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Dept. of Diagnostic and Interventional Radiology Ulm University Ulm Germany BioTechMed-Graz Graz Austria Dept. of Internal Medicine and Gastroenterology Katharinenhospital Stuttgart Germany

The manual outlining of hepatic metastasis in (US) ultrasound acquisitions from patients suffering from pancreatic cancer is common practice. However, such pure manual measurements are often very time consuming, and the results repeatedly differ between the raters. In this contribution, we study the in-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in US images of the liver with two specialists in Internal Medicine. Thereby, evaluating the approach with over one hundred different acquisitions of metastases. The two physicians or the algorithm had never assessed the acquisitions before the evaluation. In summary, the physicians first performed a pure manual outlining followed by an algorithmic segmentation over one month later. As a result, the experts satisfied in up to ninety percent of algorithmic segmentation results. Furthermore, the algorithmic segmentation was much faster than manual outlining and achieved a median Dice Similarity Coefficient (DSC) of over eighty percent. Ultimately, the algorithm enables a fast and accurate segmentation of liver metastasis in clinical US images, which can support the manual outlining in daily practice. Copyright © 2018, The Authors. All rights reserved.

关键词： Graphic methods

Learning to assign orientations to feature points

学校读者我要写书评

暂无评论

Learning to assign orientations to feature points

2016 IEEE Conference on computer Vision and Pattern Recognition, CVPR 2016

作者： Yi, Kwang Moo Verdie, Yannick Fua, Pascal Lepetit, Vincent Switzerland Institute for Computer Graphics and Vision Graz University of Technology Austria

ISBN: (纸本)9781467388511

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point. Our method improves feature point matching upon the state-of-the art and can be used in conjunction with any existing rotation sensitive descriptors. To avoid the tedious and almost impossible task of finding a target orientation to learn, we propose to use Siamese networks which implicitly find the optimal orientations during training. We also propose a new type of activation function for Neural Networks that generalizes the popular ReLU, maxout, and PReLU activation functions. This novel activation performs better for our task. We validate the effectiveness of our method extensively with four existing datasets, including two non-planar datasets, as well as our own dataset. We show that we outperform the state-of-the-art without the need of retraining for each dataset.

关键词： computer vision

ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rad, Mahdi Roth, Peter M. Lepetit, Vincent Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Laboratoire Bordelais de Recherche en Informatique Université de Bordeaux Bordeaux France

To be robust to illumination changes when detecting objects in images, the current trend is to train a Deep Network with training images captured under many different lighting conditions. Unfortunately, creating such a training set is very cumbersome, or sometimes even impossible, for some applications such as 3D pose estimation of specific objects, which is the application we focus on in this paper. We therefore propose a novel illumination normalization method that lets us learn to detect objects and estimate their 3D pose under challenging illumination conditions from very few training samples. Our key insight is that normalization parameters should adapt to the input image. In particular, we realized this via a Convolutional Neural Network trained to predict the parameters of a generalization of the Difference-of-Gaussians method. We show that our method significantly outperforms standard normalization methods and demonstrate it on two challenging 3D detection and pose estimation problems. Copyright © 2017, The Authors. All rights reserved.

关键词： Object detection

3D vision guided robotic charging station for electric and plug-in hybrid vehicles

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Mišeikis, Justinas Rüther, Matthias Walzel, Bernhard Hirz, Mario Brunner, Helmut Department of Informatics Universityof Oslo Oslo Norway Graz University of Technology Institute for Computer Graphics and Vision Graz Austria Graz University of Technology Institute for Automotive Engineer-ing Graz Austria

Electric vehicles (EVs) and plug-in hybrid vehicles (PHEVs) are rapidly gaining popularity on our roads. Besides a comparatively high purchasing price, the main two problems limiting their use are the short driving range and inconvenient charging process. In this paper we address the following by presenting an automatic robot-based charging station with 3D vision guidance for plugging and unplugging the charger. First of all, the whole system concept consisting of a 3D vision system, an UR10 robot and a charging station is presented. Then we show the shape-based matching methods used to successfully identify and get the exact pose of the charging port. The same approach is used to calibrate the camera-robot system by using just known structure of the connector plug and no additional markers. Finally, a three-step robot motion planning procedure for plug-in is presented and functionality is demonstrated in a series of successful experiments. Copyright © 2017, The Authors. All rights reserved.

关键词： Plug-in hybrid vehicles

Feature mapping for learning fast and accurate 3D pose inference from synthetic images

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rad, Mahdi Oberweger, Markus Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Laboratoire Bordelais de Recherche en Informatique Université de Bordeaux Bordeaux France

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome. However, synthetic images do not resemble real images exactly, and using them for training can result in suboptimal performance. It was recently shown that for exemplar-based approaches, it is possible to learn a mapping from the exemplar representations of real images to the exemplar representations of synthetic images. In this paper, we show that this approach is more general, and that a network can also be applied after the mapping to infer a 3D pose: At run-time, given a real image of the target object, we first compute the features for the image, map them to the feature space of synthetic images, and finally use the resulting features as input to another network which predicts the 3D pose. Since this network can be trained very effectively by using synthetic images, it performs very well in practice, and inference is faster and more accurate than with an exemplar-based approach. We demonstrate our approach on the LINEMOD dataset for 3D object pose estimation from color images, and the NYU dataset for 3D hand pose estimation from depth maps. We show that it allows us to outperform the state-of-the-art on both datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Mapping

Integration of the HTC vive into the medical platform MeVisLab

学校读者我要写书评

暂无评论

Integration of the HTC vive into the medical platform MeVisL...

SPIE Medical Imaging 2017

作者： Egger, Jan Gall, Markus Wallner, Jürgen Boechat, Pedro Hann, Alexander Li, Xing Chen, Xiaojun Dieter Schmalstieg Graz University of Technology Institute for Computer Graphics and Vision Graz AustriaBioTechMed-Graz Graz Austria Medical University of Graz Department of Maxillofacial Surgery Graz Austria Ulm University Department of Internal Medicine I Ulm Germany Shanghai Jiao Tong University School of Mechanical Engineering Shanghai China

Estimation of formal verification cost using regression machine learning 18

学校读者我要写书评

暂无评论

Estimation of formal verification cost using regression mach...

18th IEEE International High Level Design Validation and Test Workshop, HLDVT 2016

作者： Mandouh, Eman El Wassal, Amr G. Mentor Graphics Corporation Design Verification Technology Egypt Computer Engineering Department Cairo University Egypt

ISBN: (纸本)9781509042708

Formal Verification is a computationally expensive step in the verification of today's complex hardware designs. Effective results can be obtained from formal runs by planning ahead the effort and cost that are required for them. Additionally estimating in-advance the expected formal's complexity promotes a lot of potential tricks and clever setup techniques to overcome the initial push-button capacity limitation of the formal verifies and improve their capabilities to handle designs with higher complexity. This paper illustrates the application of regression machine learning (ML) techniques to build an estimation model for the cost of formal verification. Up to 10,000 formal verification runs on RTL designs with good varieties of design/properties attributes are used to learn the relationship between HW designs and the final formal cost in terms of formal run time. We demonstrate the use of Ridge-Regression to decide on the bias-variance trade-off during the regression-model design step as well as the application of Lasso-Regression for the feature selection phase. Finally a comparison between the proposed multiple linear regression approach and another non-parametric K-nearest neighbors kernel based regression technique is done to conclude on the presented work. Our results indicate how the proposed model managed to estimate with reasonable error ratio the expected formal verification effort for new-to-verify HW designs. © 2016 IEEE.

关键词： Formal verification