检索结果-内蒙古大学图书馆

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Gregory Rogez J.J. Guerrero Carlos Orrite Computer Vision Lab University of Zaragoza Spain Robotics Perception and Real Time Group University of Zaragoza Spain

We present a view-invariant human feature extractor (shape+pose) for pedestrian monitoring in man-made environments. Our approach can be divided into 2 steps: firstly, a series of view-based models is built by discretizing the viewpoint with respect to the camera into several training views. During the online stage, the Homography that relates the image points to the closest and most adequate training plane is calculated using the dominant 3D directions. The input image is then warped to this training view and processed using the corresponding view-based model. After model fitting, the inverse transformation is performed on the resulting human features obtaining a segmented silhouette and a 2D pose estimation in the original input image. Experimental results demonstrate our system performs well, independently of the direction of motion, when it is applied to monocular sequences with high perspective effect.

关键词： Humans Feature extraction Cameras Shape Legged locomotion Application software computer vision Image segmentation Surveillance Proposals

来源：评论

学校读者我要写书评

暂无评论

Effect of Field of View in Stereovision-Based Visual Homing

Effect of Field of View in Stereovision-Based Visual Homing

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Damian Lyons Luca DelSignore Benjamin Barriage Robotics and Computer Vision Lab Fordham University Bronx NY Fordham University New York NY US

Navigation is challenging for an autonomous robot operating in an unstructured environment. Visual homing is an AI local navigation technique used to direct a robot to a previously seen location, and is inspired by biological models. Most visual homing uses a panoramic camera. Prior work has shown that exploiting depth cues in homing from, e.g., a stereo-camera, leads to improved performance. However, many stereo-cameras have a limited field of view (FOV). We present a stereovision database methodology for visual homing. We use two databases we have collected, one indoor and one outdoor, to evaluate the effect of FOV on the performance of our homing with stereovision algorithm. Based on over 120,000 homing trials, we show that contrary to intuition, a panoramic field of view does not necessarily lead to the best performance, and we discuss the implications of this.

关键词： Visualization Cameras Robot kinematics Visual databases Navigation

来源：评论

学校读者我要写书评

暂无评论

MULTI-CAMERA POSITIONING FOR AUTOMATED TRACKING SYSTEMS IN DYNAMIC ENVIRONMENTS

引用

International Journal of Information Acquisition 2010年第3期7卷 225-242页

作者： YI YAO CHUNG-HAO CHEN BESMA ABIDI DAVID PAGE ANDREAS KOSCHAN MONGI ABIDI Visualization and Computer Vision Lab GE Global Research USA Department of Mathematics and Computer Science North Carolina Central University USA Imaging Robotics and Intelligent Systems Lab University of Tennessee Knoxville USA

Most existing camera placement algorithms focus on coverage and/or visibility analysis, which ensures that the object of interest is visible in the camera's field of view (FOV). According to recent literature, handoff safety margin is introduced to sensor planning so that sufficient overlapped FOVs among adjacent cameras are reserved for successful and smooth target transition. In this paper, we investigate the sensor planning problem when considering the dynamic interactions between moving targets and observing cameras. The probability of camera overload is explored to model the aforementioned interactions. The introduction of the probability of camera overload also considers the limitation that a given camera can simultaneously monitor or track a fixed number of targets and incorporates the target's dynamics into sensor planning. The resulting camera placement not only achieves the optimal balance between coverage and handoff success rate but also maintains the optimal balance in environments with various target densities. The proposed camera placement method is compared with a reference algorithm by Erdem and Sclaroff. Consistently improved handoff success rate is illustrated via experiments using typical office floor plans with various target densities.

关键词： Sensor planning visual surveillance multiple camera systems camera handoff

来源：评论

学校读者我要写书评

暂无评论

On the complexity of computing equilibria for nonsymmetric analog networks

On the complexity of computing equilibria for nonsymmetric a...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： D.A. Miller S.W. Sucker Computer Vision and Robotics Laboratory Research Center of Intelligent Machines McGill University Montreal Canada Comput. Vision & Robotics Lab. McGill Univ. Montreal Que. Canada

The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if the amplifiers are piecewise-linear, then such networks are instances of a game-theoretic model known as polymatrix games. Equilibria for the latter may be computed by vertex pivoting algorithms similar to the simplex method for linear programming, which are in practice of low order polynomial complexity. These algorithms appear to be the only ones both guaranteed to work and which are polynomial in practice. These results suggest that networks with few nonstable equilibria would be computationally attractive.< >

关键词： Analog computers computer networks Polynomials Biology computing NP-hard problem computer vision Physics computing Piecewise linear techniques Intelligent robots Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Global semantic description of objects based on prototype theory

arXiv

引用

arXiv 2019年

作者： Pino, Omar Vidal Nascimento, Erickson R. Campos, Mario F.M. Universidade Federal de Minas Gerais Computer Science Department Computer Vision and Robotics Lab Belo Horizonte Minas Gerais Brazil

In this paper, we introduce a novel semantic description approach based on Prototype Theory foundations. Inspired by the human approach used for representing categories, we propose a Computational Prototype Model (CPM) that encodes and stores the central semantic meaning of the object’s category: the semantic prototype. Also, we introduce a Prototype-based Description Model that encodes the semantic of an object while describing its features using our CPM model. Our description method uses semantic prototypes computed by convolutional neural network (CNN) classification models to create discriminative signatures that describe an object highlighting its most distinctive features within the category. Our experiments show that: i) the proposed CPM model (semantic prototype + distance metric) successfully describes the internal semantic structure of objects categories;ii) our semantic distance metric can be understood as object visual typicality score within a category;and iii) our descriptor encoding is semantically interpretable and significantly outperforms other image global encodings in clustering and classification tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Conditional Sequential Modulation for Efficient Global Image Retouching 16th

Conditional Sequential Modulation for Efficient Global Image...

引用

16th European Conference on computer vision, ECCV 2020

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT - SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030586003

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1 × 1 convolution, CSRNet only contains less than 37 k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. © 2020, Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Software mode changes for continuous motion tracking 1st

Software mode changes for continuous motion tracking

引用

1st International Workshop on Self-Adaptive Software, IWSAS 2000

作者： Karuppiah, Deepak Deegan, Patrick Araujo, Elizeth Yang, Yunlei Holness, Gary Zhu, Zhigang Lerner, Barbara Grupen, Roderic Riseman, Edward Dept. of Computer Science Computer Vision Research Laboratory University of Massachusetts AmherstMA01003 United States Dept. of Computer Science Laboratory for Perceptual Robotics University of Massachusetts AmherstMA01003 United States Dept. of Computer Science Lab. for Advanced Software Eng. Research University of Massachusetts AmherstMA01003 United States

ISBN: (纸本)3540416552

Robot control in nonlinear and nonstationary run-time environments presents challenges to traditional software methodologies. In particular, robot systems in "open" domains can only be modeled probabilistically and must rely on run-time feedback to detect whether hardware/software configurations are adequate. Modifications must be effected while guaranteeing critical performance properties. Moreover, in multi-robot systems, there are typically many ways in which to compensate for inadequate performance. The computational complexity of high dimensional sensorimotor systems prohibits the use of many traditional centralized methodologies. We present an application in which a redundant sensor array, distributed spatially over an office-like environment can be used to track and localize a human being while reacting at run-time to various kinds of faults, including: hardware failure, inadequate sensor geometries, occlusion, and bandwidth limitations. Responding at run-time requires a combination of knowledge regarding the physical sensorimotor device, its use in coordinated sensing operations, and high- level process descriptions. We present a distributed control architecture in which run-time behavior is both preanalyzed and recovered empirically to inform local scheduling agents that commit resources autonomously subject to process control specifications. Preliminary examples of system performance are presented from the UMass Self-Adaptive Software (SAS) platform. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Facial landmark localization and feature extraction for therapeutic face exercise classification

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2014年 458卷 179-194页

作者： Lanz, Cornelia Olgay, Birant Sibel Denzler, Joachim Gross, Horst-Michael Neuroinformatics and Cognitive Robotics Lab Ilmenau University of Technology Ilmenau Germany Computer Vision Group Friedrich Schiller University Jena Jena Germany

ISBN: (纸本)9783662449103

In this work, we examine landmark localization and feature extraction approaches for the unexplored topic of therapeutic facial exercise recognition. Our goal is to automatically discriminate nine therapeutic exercises that have been determined in cooperation with speech therapists. We use colour, 2.5D and 3D image data that was recorded using Microsoft’s Kinect. Our features comprise statistical descriptors of the face surface curvature as well as characteristic profiles that are derived from face landmarks. For the nine facial exercises, we yield an average recognition accuracy of about 91% in conjunction with manually labeled landmarks. Additionally, we introduce a combined method for automatic landmark localization and compare the results to landmark positions obtained from Active Appearance Model fitting as well as manual labeling. The combined localization method exhibits increased robustness in comparison to AAMs. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Pixel Attention 16th

Efficient Image Super-Resolution Using Pixel Attention

引用

Workshops held at the 16th European Conference on computer vision, ECCV 2020

作者： Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030670696

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one—SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its two-branch architecture and attention scheme. While the second one—U-PA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model—PAN could achieve similar performance as the lightweight networks—SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at https://***/zhaohengyuan1/PAN. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Supervised learning of hidden and non-hidden 0-order affordances and detection in real scenes

Supervised learning of hidden and non-hidden 0-order afforda...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Aitor Aldoma Federico Tombari Markus Vincze Vision4Robotics Group Automation and Control Institute University of Technology Vienna Austria Computer Vision Lab DEIS-ARCES University of Bologna Italy

The ability to perceive possible interactions with the environment is a key capability of task-guided robotic agents. An important subset of possible interactions depends solely on the objects of interest and their position and orientation in the scene. We call these object-based interactions 0-order affordances and divide them among non-hidden and hidden whether the current configuration of an object in the scene renders its affordance directly usable or not. Conversely to other works, we propose that detecting affordances that are not directly perceivable increase the usefulness of robotic agents with manipulation capabilities, so that by appropriate manipulation they can modify the object configuration until the seeked affordance becomes available. In this paper we show how 0-order affordances depending on the geometry of the objects and their pose can be learned using a supervised learning strategy on 3D mesh representations of the objects allowing the use of the whole object geometry. Moreover, we show how the learned affordances can be detected in real scenes obtained with a low-cost depth sensor like the Microsoft Kinect through object recognition and 6D0F pose estimation and present results for both learning on meshes and detection on real scenes to demonstrate the practical application of the presented approach.

关键词： Solid modeling Robots Training Design automation Histograms Object recognition Computational modeling

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：