检索结果-内蒙古大学图书馆

5th International Symposium on Multispectral Image Processing and pattern recognition

作者： Lv, Meibo Zi, Fang Li, Yanjun Zhang, Ke Zhao, Dawei Northwest Polytech Univ Coll Astronaut Xian 710072 Peoples R China

ISBN: (纸本)9780819469502

Information given by a single-waveband imaging sensor doesn't satisfy the battlefield's needs. Many excellent characteristics of biotic vision are gradually applied in the design of intelligent imaging-guided missile. Combined with the function of lateral inhibition network in vision, a schematic diagram of intelligent infrared imaging-guided guidance head is proposed. Enlightened by the large field (LF) and small field (SF) of fly, the paralleled implement scheme of spatial double mode is proposed. A physical model of infrared imaging guidance head is given. The guidance head simulates the whole imaging progress of fly's ommateum. And its field of view is 360 degrees. Then the synthetical application flow on imaging guidance referenced fly's vision system is proposed. The exploring study is beneficial and referenced to the design of intending imaging-guided system.

关键词： vision bionics imaging guidance head design

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Node Splitting for Random Forest Construction

Semi-supervised Node Splitting for Random Forest Constructio...

引用

26th IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Liu, Xiao Song, Mingli Tao, Dacheng Liu, Zicheng Zhang, Luming Chen, Chun Bu, Jiajun Zhejiang Univ Coll Comp Sci Hangzhou Zhejiang Peoples R China Univ Technol Sydney Ctr Quantum Computat & Intelligent Syst Sydney NSW 2007 Australia Microsoft Res Redmond WA USA

ISBN: (纸本)9780769549897

Node splitting is an important issue in Random Forest but robust splitting requires a large number of training samples. Existing solutions fail to properly partition the feature space if there are insufficient training data. In this paper, we present semi-supervised splitting to overcome this limitation by splitting nodes with the guidance of both labeled and unlabeled data. In particular we derive a non-parametric algorithm to obtain an accurate quality measure of splitting by incorporating abundant unlabeled data. To avoid the curse of dimensionality, we project the data points from the original high-dimensional feature space onto a low-dimensional subspace before estimation. A unified optimization framework is proposed to select a coupled pair of subspace and separating hyperplane such that the smoothness of the subspace and the quality of the splitting are guaranteed simultaneously. The proposed algorithm is compared with state-of-the-art supervised and semi-supervised algorithms for typical computer vision applications such as object categorization and image segmentation. Experimental results on publicly available datasets demonstrate the superiority of our method.

关键词： computer vision learning (artificial intelligence) nonparametric statistics optimisation pattern classification random processes

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Dictionary for Single Image Super-resolution

Multi-scale Dictionary for Single Image Super-resolution

引用

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Zhang, Kaibing Gao, Xinbo Tao, Dacheng Li, Xuelong Xidian Univ Sch EE Xian 710071 Peoples R China Univ Technol Sydney QCIS Sydney NSW 2007 Australia Univ Technol Sydney FEIT Sydney NSW 2007 Australia Chinese Acad Sci Xian Inst Opt & Precis Mech Xian 710119 Peoples R China

ISBN: (纸本)9781467312288

Reconstruction- and example-based super-resolution (SR) methods are promising for restoring a high-resolution (HR) image from low-resolution (LR) image(s). Under large magnification, reconstruction-based methods usually fail to hallucinate visual details while example-based methods sometimes introduce unexpected details. Given a generic LR image, to reconstruct a photo-realistic SR image and to suppress artifacts in the reconstructed SR image, we introduce a multi-scale dictionary to a novel SR method that simultaneously integrates local and non-local priors. The local prior suppresses artifacts by using steering kernel regression to predict the target pixel from a small local area. The non-local prior enriches visual details by taking a weighted average of a large neighborhood as an estimate of the target pixel. Essentially, these two priors are complementary to each other. Experimental results demonstrate that the proposed method can produce high quality SR recovery both quantitatively and perceptually.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention

Beyond bottom-up: Incorporating task-dependent influences in...

引用

IEEE Conference on computer vision and pattern recognition

作者： Peters, Robert J. Itti, Laurent Univ Southern Calif Dept Comp Sci Los Angeles CA 90089 USA Univ Southern Calif Dept Neurosci Los Angeles CA 90089 USA Univ Southern Calif Dept Psychol Los Angeles CA 90089 USA

ISBN: (纸本)9781424411795

A critical function in both machine vision and biological vision systems is attentional selection of scene regions worthy of further analysis by higher-level processes such as object recognition. Here we present the first model of spatial attention that (1) can be applied to arbitrary static and dynamic image sequences with interactive tasks and (2) combines a general computational implementation of both bottom-up (BU) saliency and dynamic top-down (TD) task relevance;the claimed novelty lies in the combination of these elements and in the fully computational nature of the model. The BU component computes a saliency map from 12 low-level multi-scale visual features. The TD component computes a low-level signature of the entire image, and learns to associate different classes of signatures with the different gaze patterns recorded from human subjects performing a task of interest. We measured the ability of this model to predict the eye movements of people playing contemporary video games. We found that the TD model alone predicts where humans look about twice as well as does the BU model alone;in addition, a combined BU*TD model performs significantly better than either individual component. Qualitatively, the combined model predicts some easy-to-describe but hard-to-compute aspects of attentional selection, such as shifting attention leftward when approaching a left turn along a racing track. Thus, our study demonstrates the advantages of integrating BU factors derived from a saliency map and TD factors learned from image and task contexts in predicting where humans look while performing complex visually-guided behavior.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Keypoint descriptors for matching across multiple image modalities and non-linear intensity variations

Keypoint descriptors for matching across multiple image moda...

引用

IEEE Conference on computer vision and pattern recognition

作者： Kelman, Avi Sofka, Michal Stewart, Charles V. Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA

ISBN: (纸本)9781424411795

In this paper we investigate the effect of substantial inter-image intensity changes and changes in modality on the performance of keypoint detection, description, and matching algorithms in the context of image registration. In doing so, we modify widely-used keypoint descriptors such as SIFT and shape contexts, attempting to capture the insight that some structural information is indeed preserved between images despite dramatic appearance changes. These extensions include (a) pairing opposite-direction gradients in the formation of orientation histograms and (b) focusing on edge structures only. We also compare the stability of MSER, Laplacian-of-Gaussian, and Harris corner keypoint location detection and the impact of detection errors on matching results. Our experiments on multimodal image pairs and on image pairs with significant intensity differences show that indexing based on our modified descriptors produces more correct matches on difficult pairs than current techniques at the cost of a small decrease in performance on easier pairs. This extends the applicability of image registration algorithms such as the Dual-Bootstrap which rely on correctly matching only a small number of keypoints.

关键词： pattern matching

来源：评论

学校读者我要写书评

暂无评论

Target detection based on hierarchical saliency feature model

Target detection based on hierarchical saliency feature mode...

引用

5th International Symposium on Multispectral Image Processing and pattern recognition

作者： Wang, Yuehuan Lan, Qian Zhang, Tianxu Huazhong Univ Sci & Technol State Key Lab Multi Spectral Informat Proc Techno Inst Pattern Recognit & Artificial Intelligence Wuhan 430074 Peoples R China

ISBN: (纸本)9780819469502

A target description model based on hierarchical saliency feature and target detection based on the model are proposed, which integrates bottom-up and top-down vision attention mechanisms together. Some saliency features of target are extracted on multi-scale, such as local symmetry, corner and so on, which are then processed hierarchically. This makes detection process much simpler and robust. Experiments demonstrate that the approach proposed is effective.

关键词： attention mechanism hierarchical saliency feature target detection

来源：评论

学校读者我要写书评

暂无评论

Towards General Purpose vision Systems: An End-to-End Task-Agnostic vision-Language Architecture

Towards General Purpose Vision Systems: An End-to-End Task-A...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Gupta, Tanmay Kamath, Amita Kembhavi, Aniruddha Hoiem, Derek PRIOR Allen Inst AI Seattle WA 98103 USA Univ Illinois Urbana IL 61801 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept' transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.

关键词： Training computer vision Visualization Machine vision computer architecture Object detection Network architecture

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral detection of citrus damage with Mahalanobis kernel classifier

引用

ELECTRONICS LETTERS 2007年第20期43卷 1082-1084页

作者： Gomez, J. Blasco, J. Molto, E. Camps-Valls, G. Inst Valenciano Invest Agr Valencia 46113 Spain Univ Valencia Dept Elect Engn Valencia Spain

Presented is a full computer vision system for the identification of post-harvest damage in citrus packing houses. The method is based on the combined use of hyperspectral images and the Mahalanobis kernel classifier. More accurate and reliable results compared to other methods are obtained in several scenarios and acquired images.

关键词： Mathematical analysis computer vision Image processing pattern recognition systems Numerical analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient new-view synthesis using pairwise dictionary priors

Efficient new-view synthesis using pairwise dictionary prior...

引用

IEEE Conference on computer vision and pattern recognition

作者： Woodford, O. J. Reid, I. D. Fitzgibbon, A. W. Univ Oxford Dept Engn Sci Parks Rd Oxford OX1 3PJ England Microsoft Res Cambridge England

ISBN: (纸本)9781424411795

New-view synthesis (NVS) using texture priors (as opposed to surface-smoothness priors) can yield high quality results, but the standard formulation is in terms of large-clique Markov Random Fields (MRFs). Only local optimization methods such as iterated conditional modes, which are prone to fall into local minima close to the initial estimate, are practical for solving these problems. In this paper we replace the large-clique energies with pairwise potentials, by restricting the patch dictionary for each clique to image regions suitable for that clique. This enables for the first time the use of a global optimization method, such as tree-reweighted message passing, to solve the NVS problem with image-based priors. We employ a robust, truncated quadratic kernel to reject outliers caused by occlusions, specularities and moving objects, within our global optimization. Because the MRF optimization is thus fast, computing the unary potentials becomes the new performance bottleneck. An additional contribution of this paper is a novel, fast method for enumerating color modes of the per-pixel unary potentials, despite the non-convex nature of our robust kernel. We compare the results of our technique with other rendering methods, and discuss the relative merits and flaws of regularizing color, and of local versus global dictionaries.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Cast shadow removal combining local and global features

Cast shadow removal combining local and global features

引用

IEEE Conference on computer vision and pattern recognition

作者： Liu, Zhou Huang, Kaiqi Tan, Tieniu Wang, Liangsheng Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China

ISBN: (纸本)9781424411795

In this paper, we present a method using pixel-level information, local region-level information and global-level information to remove shadow. At the pixel-level, we employ GMM to model the behavior of cast shadow for every pixel in the HSV color space, as it can deal with complex illumination conditions. However, unlike the GMM for background which can obtain sample every frame, this model for shadow needs more frames to get the same number of sample, because shadow may not appear at the same pixel for each frame. Therefore, it will take a long time to converge. To overcome this drawback, we use the local region-level information to get more samples and global-level information to improve a preclassifier and then, by using it, we get samples which are more likely to be shadow. Also, at the local region-level, we use Markov random fields to represent dependencies between the label of single pixel and labels of its neighborhood. Moreover, to make global level information more robust, tracking information is used. Experimental results show that the proposed method is efficient and robust.

关键词： Feature 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：