检索结果-内蒙古大学图书馆

作者： Oh, Sangmin Hoogs, Anthony Perera, Amitha Cuntoor, Naresh Chen, Chia-Chih Lee, Jong Taek Mukherjee, Saurajit Aggarwal, J.K. Lee, Hyungtae Davis, Larry Swears, Eran Wang, Xioyang Ji, Qiang Reddy, Kishore Shah, Mubarak Vondrick, Carl Pirsiavash, Hamed Ramanan, Deva Yuen, Jenny Torralba, Antonio Song, Bi Fong, Anesco Roy-Chowdhury, Amit Desai, Mita

ISBN: (纸本)9781457703942

We introduce a new large-scale video dataset designed to assess the performance of diverse visual event recognition algorithms with a focus on continuous visual event recognition (CVER) in outdoor areas with wide coverage. Previous datasets for action recognition are unrealistic for real-world surveillance because they consist of short clips showing one action by one individual [15, 8]. Datasets have been developed for movies [11] and sports [12], but, these actions and scene conditions do not apply effectively to surveillance videos. Our dataset consists of many outdoor scenes with actions occurring naturally by non-actors in continuously captured videos of the real world. The dataset includes large numbers of instances for 23 event types distributed throughout 29 hours of video. This data is accompanied by detailed annotations which include both moving object tracks and event examples, which will provide solid basis for large-scale evaluation. Additionally, we propose different types of evaluation modes for visual recognition tasks and evaluation metrics along with our preliminary experimental results. We believe that this dataset will stimulate diverse aspects of computer vision research and help us to advance the CVER tasks in the years ahead. © 2011 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Imprecise probability as a linking mechanism between deep learning, symbolic cognition and local feature detection in vision processing

Imprecise probability as a linking mechanism between deep le...

引用

Lecture Notes in computer Science

作者： Goertzel, Ben Novamente LLC United States

ISBN: (纸本)9783642228865

A novel approach to computer vision is outlined, involving the use of imprecise probabilities to connect a deep learning based hierarchical vision system with both local feature detection based preprocessing and symbolic cognition based guidance. The core notion is to cause the deep learning vision system to utilize imprecise rather than single-point probabilities, and use local feature detection and symbolic cognition to affect the confidence associated with particular imprecise probabilities, thus modulating the amount of credence the deep learning system places on various observations and guiding its pattern recognition/formation activity. The potential application to the hybridization of the DeSTIN, SIFT and OpenCog systems is described in moderate detail. The underlying ideas are even more broadly applicable, to any computer vision approach with a significant probabilistic component which satisfies certain broad criteria. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Music Score Binarization Based on Domain Knowledge

引用

5th Iberian Conference on pattern recognition and Image Analysis (IbPRIA)

作者： Pinto, Telmo Rebelo, Ana Giraldi, Gilson Cardoso, Jaime S. Univ Porto INESC Porto Fac Engn Porto Portugal Natl Lab Sci Comp Petropolis Brazil

ISBN: (纸本)9783642212567;9783642212574

Image binarization is a common operation in the preprocessing stage in most Optical Music recognition (OMR) systems. The choice of an appropriate binarization method for handwritten music scores is a difficult problem. Several works have already evaluated the performance of existing binarization processes in diverse applications. However, no goal-directed studies for music sheets documents were carried out. This paper presents a novel binarization method based in the content knowledge of the image. The method only needs the estimation of the staffline thickness and the vertical distance between two stafflines. This information is extracted directly from the gray level music score. The proposed binarization procedure is experimentally compared with several state of the art methods.

关键词： computer vision Image Processing Optical Music recognition

来源：评论

学校读者我要写书评

暂无评论

On fast deep nets for AGI vision

On fast deep nets for AGI vision

引用

Lecture Notes in computer Science

作者： Schmidhuber, Jurgen Cireşan, Dan Meier, Ueli Masci, Jonathan Graves, Alex Swiss AI Lab IDSIA University of Lugano SUPSI Switzerland

ISBN: (纸本)9783642228865

Artificial General Intelligence will not be general without computer vision. Biologically inspired adaptive vision models have started to outperform traditional pre-programmed methods: our fast deep / recurrent neural networks recently collected a string of 1st ranks in many important visual pattern recognition benchmarks: IJCNN traffic sign competition, NORB, CIFAR10, MNIST, three ICDAR handwriting competitions. We greatly profit from recent advances in computing hardware, complementing recent progress in the AGI theory of mathematically optimal universal problem solvers. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Event recognition based on bag of local space-time interest points' features

Event recognition based on bag of local space-time interest ...

引用

4th International Workshop on Advanced Computational Intelligence, IWACI 2011

作者： Zhai, Chuan-Min Guo, Yi-Lan Du, Ji-Xiang Department of Computer Science and Technology Huaqiao University Xiamen China

ISBN: (纸本)9781612843735

This paper proposes a novel method based on bag of local space-time interest points' features to recognize and retrieval complex events in real movies. In this method, an individual video sequence is represented as a bag of local space-time features then we integrate such bag-of-feature with SVM for recognition events. Local space-time features are introduced to capture the local events in video and can be adapted to size and velocity of the pattern of the event. To evaluate effectiveness of this method, this paper uses the public Hollywood dataset, in this dataset the shot sequences has collected from 32 different Hollywood movies and it includes 8 event classes. The presented result justify the proposed method explicitly improve the average accuracy and average precision compared to other relative approaches. © 2011 IEEE.

关键词： computer vision Conferences Feature extraction pattern recognition Video sequences Visualization Vocabulary

来源：评论

学校读者我要写书评

暂无评论

A Two-Phase Test Sample Sparse Representation Method for Use With Face recognition

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2011年第9期21卷 1255-1262页

作者： Xu, Yong Zhang, David Yang, Jian Yang, Jing-Yu Harbin Inst Technol Shenzhen Grad Sch Biocomp Res Ctr Shenzhen 518055 Peoples R China Hong Kong Polytech Univ Dept Comp Kowloon Hong Kong Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing 210094 Peoples R China

In this paper, we propose a two-phase test sample representation method for face recognition. The first phase of the proposed method seeks to represent the test sample as a linear combination of all the training samples and exploits the representation ability of each training sample to determine M "nearest neighbors" for the test sample. The second phase represents the test sample as a linear combination of the determined M nearest neighbors and uses the representation result to perform classification. We propose this method with the following assumption: the test sample and its some neighbors are probably from the same class. Thus, we use the first phase to detect the training samples that are far from the test sample and assume that these samples have no effects on the ultimate classification decision. This is helpful to accurately classify the test sample. We will also show the probability explanation of the proposed method. A number of face recognition experiments show that our method performs very well.

关键词： computer vision face recognition pattern recognition sparse representation transform methods

来源：评论

学校读者我要写书评

暂无评论

Object recognition with hierarchical kernel descriptors

Object recognition with hierarchical kernel descriptors

引用

作者： Bo, Liefeng Lai, Kevin Ren, Xiaofeng Fox, Dieter University of Washington United States Computer Vision Lab University of Central Florida Orlando FL United States Intel Labs Seattle United States

ISBN: (纸本)9781457703942

Kernel descriptors [1] provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object recognition tasks. However, best results with kernel descriptors are achieved using efficient match kernels in conjunction with nonlinear SVMs, which makes it impractical for large-scale problems. In this paper, we propose hierarchical kernel descriptors that apply kernel descriptors recursively to form image-level features and thus provide a conceptually simple and consistent way to generate image-level features from pixel attributes. More importantly, hierarchical kernel descriptors allow linear SVMs to yield state-of-the-art accuracy while being scalable to large datasets. They can also be naturally extended to extract features over depth images. We evaluate hierarchical kernel descriptors both on the CIFAR10 dataset and the new RGB-D Object Dataset consisting of segmented RGB and depth images of 300 everyday objects. © 2011 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A Munkres Particle Swarm optimization algorithm for point pattern matching

A Munkres Particle Swarm optimization algorithm for point pa...

引用

2011 International Conference on Human Health and Biomedical Engineering, HHBE 2011

作者： Zhou, You Wei, Wei Yu, Chong Sun, Ying Xing, Chong Shen, Wei Shi, Xiaohu College of Computer Science and Technology Jilin University Changchun 130012 China

ISBN: (纸本)9781612847269

Particle Swarm Optimization combines with Munkres algorithm is proposed for Point pattern Matching in three dimensions. Point pattern Matching is a fundamental aspect of many fields in computer vision and pattern recognition. The point pattern matching technique could be described as finding an optimal transformation for one point pattern to the other under some measures. The proposed algorithm can be used to perform reliable matching between two different views of an object or scene. A new formula is proposed and used as a reasonable fitness function. The advantages of Munkres and Particle Swarm optimization are used and combined together in this paper. The simulated results show that the new algorithm is very effective. © 2011 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Multi-camera calibration based on an invariant pattern

引用

computerS & GRAPHICS-UK 2011年第2期35卷 198-207页

作者： Loaiza, Manuel E. Raposo, Alberto B. Gattass, Marcelo Pontifical Catholic Univ Rio de Janeiro Dept Informat Tecgraf Comp Graph Technol Grp Rio De Janeiro Brazil

In this paper we present a method for the calibration of multiple cameras based on the extraction and use of the physical characteristics of a one-dimensional invariant pattern which is defined by four collinear markers. The advantages of this kind of pattern stand out in two key steps of the calibration process. In the initial step of camera calibration methods, related to sample points capture, the proposed method takes advantage of using a new technique for the capture and recognition of a robust sample of projective invariant patterns, which allows to capture simultaneously more than one invariant pattern in the tracking area and recognize each pattern individually as well as each marker that composes them. This process is executed in real time while capturing our sample of calibration points in the cameras of our system. This new feature allows to capture a more numerous and robust set of sample points than other patterns used for multi-camera calibration methods. In the last step of the calibration process, related to camera parameters' optimization, we explore the collinearity feature of the invariant pattern and add this feature in the camera parameters optimization model. This approach obtains better results in the computation of camera parameters. We present the results obtained with the calibration of two multi-camera systems using the proposed method and compare them with other methods from the literature. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Processing image Structure from motion Camera calibration Projective invariant patterns computer vision

来源：评论

学校读者我要写书评

暂无评论

Study on interaction behaviors of micro-autonomous vehicles

Study on interaction behaviors of micro-autonomous vehicles

引用

International Workshop on Assurance in Distributed Systems and Networks

作者： Li, Deyi Wang, Xiaodong He, Wen Guo, Mu Zhang, Tianlei Dept. Computer Science and Technology Tsinghua University Bejing China

ISBN: (纸本)9780769543499

Autonomous vehicles are very hot research area which advance artificial intelligent, pattern recognition, computer vision, sensor fusion and control theory. In the paper we demonstrate a kind of micro-autonomous vehicle, describing hardware and software architectures, perception system and control method-cloud control. Our goal is study interaction behaviors between autonomous vehicles and how to take appropriate measure to avoid driving conditions hazardous. We propose a new control alogrithm-cloud control algorithm and experiments show cloud control algorithm has good performance and flexibility.

关键词： pattern recognition

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：