检索结果-内蒙古大学图书馆

2006 17th British Machine vision Conference, BMVC 2006

作者： Murphy-Chutorian, Erik Trivedi, Mohan Computer Vision and Robotics Research Laboratory University of California San Diego United States

ISBN: (纸本)1904410146

In this paper we introduce the NDS-Forest data structure, which can be used for the calculation and representation of Maximally Stable Extremal Regions in real-time video. In contrast to the standard MSER algorithm, the NDS-Forest stores information about the extremal regions as they are formed, making it unnecessary to regrow the regions from seed pixels. Using the NDS-Forest structure, we describe a system that uses MSERs in an automobile for face registration, segmentation, and pose estimation of the driver.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Facial action coding using multiple visual cues and a hierarchy of particle filters

Facial action coding using multiple visual cues and a hierar...

引用

2006 Conference on computer vision and Pattern Recognition Workshops

作者： McCall, Joel C. Trivedi, Mohan M. Computer Vision and Robotics Research Laboratory University of California San Diego United States

ISBN: (纸本)0769526462

In this paper we present a framework for tracking non-rigid facial landmarks by combining various visual cues at multiple levels of detail. Using a probabilistic framework consisting of a hierarchy of particle filters, we are able to track individual facial landmarks using multiple visual cues at the local level, as well as tracking results at more coarse level of detail. This allows for the fusion of global and local cues in an efficient and robust manner. Testing is performed by tracking and classifying facial action codes obtained from the Cohn-Kanade AU-Coded Facial Expression Database. © 2006 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Balanced optical flow refinement by bidirectional constraint

Balanced optical flow refinement by bidirectional constraint

引用

作者： Choi, Jongwon Kim, Hyeongwoo Oh, Tae-Hyun Kweon, In So Robotics and Computer Vision Laboratory Korea Advanced Institute of Science and Technology Korea Republic of

ISBN: (纸本)9781479957514

We present an efficient optical flow refinement approach based on a bidirectional flow consistency. Our method is an add-on component that improves the existing optical flow estimation to be balanced between forward and backward flows. Most of the state-of-the-art optical flow methods only consider unidirectional motion vectors from a source image to a target image, which can make the estimated flow inconsistent with its backward estimation. The inconsistency can be reduced by considering the bidirectional motion when the optical flow is estimated, but it would be very hard for most of the typical optical flow methods and impossible for some of them. To solve this problem, we propose a sampling-based optimization method for efficiently refining the optical flows with a bidirectional constraint. By evaluating on Middle-bury benchmark and public large displacement datasets, we validate the effectiveness of our method quantitatively and qualitatively and for accuracy. © 2014 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Rank-based multisensory fusion in multitarget video tracking

Rank-based multisensory fusion in multitarget video tracking

引用

IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2005

作者： Lyons, Damian M. Hsu, D. Frank Robotics and Computer Vision Laboratory Department of Computer and Information Science Fordham University Bronx NY 10458

ISBN: (纸本)0780393856

An attractive approach to improve tracking performance for visual surveillance is to use information from multiple visual sensory cues such as position, color, shape, etc. Previous work in fusion for tracking has tended to focus on fusion by numerically combining the scores assigned by each cue. We argue that for video scenes with many targets in a crowded situation, the splitting and merging of regions associated with targets, and the subsequent dramatic changes in cue values and reliabilities, renders this form of fusion less effective. In this paper we present experimental results showing that use of cue rank information in fusion produces a significantly better tracking result in crowded scenes. We also present a formalization of this fusion problem as a step in understanding why this effect occurs and how to build a tracking system that exploits it. © 2005 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

CURVATURE CONSISTENCY IMPROVES LOCAL SHADING ANALYSIS

CVGIP-IMAGE UNDERSTANDING

引用

CVGIP-IMAGE UNDERSTANDING 1992年第1期55卷 95-105页

作者： FERRIE, FP LAGARDE, J Computer Vision and Robotics Laboratory McGill Research Centre for Intelligent Machines McGill University Montréal Québec Canada H3A 2A7

This paper describes how a surface reconstruction algorithm, based on minimizing the variation of surface curvature, can be used to stabilize and correct the results of local shading analysis. What is novel about this approach is that it is viewpoint independent and applicable to any process that can provide estimates of local surface orientation. The assumptions used in formulating the minimization are derived from standard differential geometry. When applied as a second stage of processing after local shading analysis, the algorithm can recover a close approximation of the true surface orientation under realistic assumptions about image noise. Results are presented that show the performance of the algorithm on synthetic and real data. In particular, they demonstrate how this form of reconstruction can compensate for some of the shape distortion incurred in local shading analysis.

关键词： Image Processing

来源：评论

学校读者我要写书评

暂无评论

Multiscale Convolutional Transformer with Diverse-aware Feature Learning for Motor Imagery EEG Decoding

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hang, Wenlong Wang, Junliang Liang, Shuang Lei, Baiying Wang, Qiong Li, Guanglin Chen, Badong Qin, Jing Nanjing Tech University College of Computer Nanjing211816 China Nanjing Tech University Information Engineering Nanjing211816 China Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing210023 China Shenzhen University School of Biomedical Engineering Shenzhen518060 China Guangdong Provincial Key Laboratory of Computer Vision Shenzhen518055 China Virtual Reality Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences Shenzhen518055 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hong Kong Polytechnic University School of Nursing Hung Hom Hong Kong

Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interfaces (BCIs) have significant potential in improving motor function for neurorehabilitation. Despite recent advancements, learning diversified EEG features across different frequency ranges remains a significant challenge, as the homogenization of feature representations often limits the generalization capabilities of EEG decoding models for BCIs. In this paper, we propose a novel multiscale convolutional transformer framework for EEG decoding that integrates multiscale convolution, transformer, and diverse-aware feature learning scheme (MCTD) to tackle the above challenge. Specifically, we first capture multiple frequency features using dynamic one-dimensional temporal convolution with different kernel lengths. Subsequently, we incorporate convolutional layers and transformers with a contrastive learning scheme to extract discriminative local and global EEG features within a single frequency range. To mitigate the homogenization of features extracted from different frequency ranges, we propose a novel decorrelation regularization. It enables multiscale convolutional transformers produce less correlated features with each other, thereby enhancing the overall expressiveness of EEG decoding model. The performance of MCTD is evaluated on four public MI-based EEG datasets, including the BCI competition III 3a and IV 2a, the BNCI 2015- 001, and the OpenBMI. For the average Kappa/Accuracy scores, MCTD obtains improvements of 3.58%/2.68%, 3.09%/2.20%, 2.33%/1.54%, and 4.44%/2.22%, over the state-of-the-art method on four EEG datasets, respectively. Experimental results demonstrate that our method exhibits superior performance. © 2016 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

PART DECOMPOSITION OF OBJECTS FROM SINGLE VIEW LINE DRAWINGS

CVGIP-IMAGE UNDERSTANDING

引用

CVGIP-IMAGE UNDERSTANDING 1992年第1期55卷 73-83页

作者： BERGEVIN, R LEVINE, MD Computer Vision and Robotics Laboratory McGill Research Centre for Intelligent Machines McGill University Montréal Québec Canada H3A 2A7

We describe an algorithm for segmenting a 3D object into its constituent volumetric parts from a single 2D line drawing. This algorithm is part of the bottom-up line drawing description process of PARVO, a generic object recognition system. In PARVO, an object is recognized as being a member of a class defined by qualitative geometrical properties and topological structure. Similarity between different 3D views of any member of a given class is a result of building coarse part-based structural descriptions from limited information. A preliminary stage to part segmentation of an object consists of extracting viewpoint-invariant and nonaccidental features from the line drawing. The segmentation process itself is described as a hierarchical decomposition of the line drawing on the basis of pairs of high-concavity points in its silhouette. The pairing of these so-called segmentation points rests on (i) an object visibility model describing the generic structures present in any line drawing satisfying our assumptions, and (ii) the feature instances extracted from the specific line drawing analyzed. First, we discuss the properties of the line drawings in the domain of PARVO. From them, geometrical models of important line drawing features may be developed. The latter are used both as cues in the segmentation process and as precursors to the representation from which part structure is understood.

关键词： Pattern Recognition

来源：评论

学校读者我要写书评

暂无评论

A REAL-TIME IMPLEMENTATION OF STRUCTURE ESTIMATION USING IMAGE STREAMS 6

A REAL-TIME IMPLEMENTATION OF STRUCTURE ESTIMATION USING IMA...

引用

CONF ON SENSOR FUSION 6

作者： DALMIA, AK TRIVEDI, MM Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee Knoxville 37996-2100 TN United States

ISBN: (纸本)0819413240

The computation of 3-D structure from motion using a monocular sequence of images in the paradigm of active vision is investigated in this paper. Robotic tasks such as navigation, manipulation, and object recognition all require 3-D description of scene. The 3-D description for these tasks varies in resolution, accuracy, robustness, range, and time. In developing such a system, it must have the capability to actively control the imaging parameters so that a 3-D description sufficient enough for that task is generated. The objective of this paper is to investigate a strategy suitable for fast and active 3-D structure estimation. First, the process of 3-D structure estimation in the paradigm of active vision is discussed. Second, implication of image streams in 3-D structure computation is analyzed. The three approaches to structure from motion, feature based, optical flow based, and spatial and temporal gradient based, are reviewed for their efficacy in fast and active estimation of 3-D structure. Finally, a pipeline based implementation of a spatial and temporal gradient based approach is presented alongwith detailed experimental analysis. © 1993 SPIE. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

SIMULATION AND ANIMATION OF SENSOR-DRIVEN ROBOTS

引用

IEEE TRANSACTIONS ON robotics AND AUTOMATION 1994年第5期10卷 684-704页

作者： CHEN, CX TRIVEDI, MM BIDLACK, CR Computer Vision and Robotics Research Laboratory the Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA Artificial Intelligence Laboratory College of Engineering University of Michigan Ann Arbor MI USA

Most simulation and animation systems utilized in robotics are concerned with simulation of the robot and its environment without simulation of sensors. These systems have difficulty in handling robots that utilize sensory feedback in their operation. In this paper, a new design of an environment for simulation, animation, and visualization of sensor-driven robots is presented. As sensor technology advances, increasing numbers of robots are equipped with various types of sophisticated sensors. The main goal of creating the visualization environment is to aid the automatic robot programming and off-line programming capabilities of sensor-driven robots. The software system will help the users visualize the motion and reaction of the sensor-driven robot under their control program. Therefore, the efficiency of the software development is increased, the reliability of the software and the operation safety of the robot are ensured, and the cost of new software development is reduced. Conventional computer-graphics-based robot simulation and animation software packages lack of capabilities for robot sensing simulation. This paper describes a system designed to overcome this deficiency.

关键词： Animation Robot sensing systems robotics and automation Visualization Robot programming Software safety Computational modeling computer simulation Automatic programming Software systems

来源：评论

学校读者我要写书评

暂无评论

AN ACTIVE vision SYSTEM FOR DEPTH EXTRACTION USING MULTI-PRIMITIVE HIERARCHICAL STEREO ANALYSIS AND MULTIPLE DEPTH CUES

AN ACTIVE VISION SYSTEM FOR DEPTH EXTRACTION USING MULTI-PRI...

引用

CONF ON SENSOR FUSION AND AEROSPACE APPLICATIONS

作者： MARAPANE, SB TRIVEDI, MM Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee Knoxville 37996-2100 TN United States

ISBN: (纸本)0819411922

Binocular stereo, vergence stereo, and depth from focus have been extensively studied in isolation in the past for extraction of depth. These passive approaches have there oivn strengths and limitations. All these cues differ in their input image requirements, computational requirements, and the quality and nature of results they provide. None of them by themselves is sufficient to reliably extract depth information from a wide variety of scenes. It is evident an integrated system ivhich employs multiple cues and exploits their strengths would be most critical for developing a robust depth extraction system. Active vision paradigm alloivs us to develop such a system where various depth cues cooperate to derive the 3-D structure of the scene. In this, the integration would be accomplished by active intelligent control of the acquisition processes tightly coupled to the analysis of image data. One of the uniqueness of our integration approach is that while previous approaches have used a single primitive stereo system, typically edgel based, we have chosen a novel multi-primitive hierarchical(MPH) system. In MPH model, stereo analysis is performed in multiple stages, incorporating multiple primitives, utilizing a hierarchical control strategy. The MPH stereo system consists of three integrated subsystems: region based analysis module;linear edge segment based analysis module;and edgel based stereo analysis module. The use of regions and edge segments in addition to the edgel based analysis add a new dimension to the extraction of depth from stereo images. In fact, even in an integrated multiple cue based system, an edgel based binocular stereo approach alone is insufficient to process a variety of scenes. The reliance of different primitives at various levels makes MPH stereo analysis ideal for use in an integrated multiple cue based depth extraction system. © 1993 SPIE. All rights reserved.

关键词： Extraction

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：