检索结果-内蒙古大学图书馆

European Signal Processing Conference

作者： Ruxandra Tapu Titus Zaharia Institut Mines-Telecom/Telecom SudParis ARTEMIS Department

ISBN: (纸本)9781467310680

In this paper we propose a method for automatic structuring of video documents. The video is firstly segmented into shots based on a scale space filtering graph partition method. For each detected shot the associated static summary is developed using a leap key-frame extraction method. Based on the representative images obtained, we introduce next a combined spatial and temporal video attention model that is able to recognize moving salient objects. The proposed approach extends the state-of-the-art image region based contrast saliency with a temporal attention model. Different types of motion presented in the current shot are determined using a set of homographic transforms, estimated by recursively applying the ransac algorithm on the interest point correspondence. Finally, a decision is taken based on the combined spatial and temporal attention models. The experimental results validate the proposed framework and demonstrate that our approach is effective for various types of videos, including noisy and low resolution data.

关键词： Saliency maps Temporal attention model Homography transform ransac algorithm Videotapes pixel Visualization shot Noise region of an image

来源：评论

学校读者我要写书评

暂无评论

FAST AUTOMATED SEGMENTATION OF FEMORAL HEADS IN FLUOROSCOPIC X-RAY IMAGES

FAST AUTOMATED SEGMENTATION OF FEMORAL HEADS IN FLUOROSCOPIC...

引用

8th IEEE International Symposium on Biomedical Imaging (ISBI) - From Nano to Macro

作者： Wang, Lei Kohnen, Michael Friman, Ola Hahn, Horst K. Fraunhofer MEVIS Inst Med Image Comp Bremen Germany Stryker Leibinger GmbH & Co KG Freiburg Germany

ISBN: (纸本)9781424441280

In fluoroscopic tracking for fractured femur bone fixation, a precise identification of the femoral head provides valuable guidance for positioning the implant instruments such as nails and screws. Noise, occlusions and weak edges challenge the task of automatically segmenting the femoral head. In this paper, a fast and fully automated method to precisely delineate the femoral head in fluoroscopic X-ray images is presented. The proposed method comprises two stages: First, a candidate circle detection stage using a set of curved Gabor filters and a Gabor-based Hough transform is applied to estimate a few candidate circles approximating the femoral head. Second, a fine circle determination stage extracts the target circle from the candidates by analyzing the anatomical features of the femoral head and its spatial relation to the acetabulum. The validity and robustness of the method were tested on a set of 1184 fluoroscopic images from different vendors.

关键词： Femoral head segmentation Gabor filter Hough transform ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Obstacle detection for patrol robot using Bumblebee2 stereo vision system

引用

3rd International Conference on Measuring Technology and Mechatronics Automation (ICMTMA 2011)

作者： Xie Xing-zhe Wang Heng Luo Qian-you SW Univ Sci & Technol Sch Informat Engn Robot Lab Mianyang 621010 Sichuan Peoples R China

ISBN: (纸本)9783037850190

This paper employs Bumblebee2 stereo vision system to detect the obstacles for patrol robot in substation environment. Firstly, with the selected points in the disparity image, the ground plane is calculated by the ransac (Random Sample Consensus) algorithm. And then, the local occupancy grid map is built for patrol robot, and the obstacles are detected through connected component analysis method. The actual test in substation environment verified the reliability of the system.

关键词： patrol robot ransac algorithm connected component analysis occupancy grid map

来源：评论

学校读者我要写书评

暂无评论

AN IMPROVED SEGMENTATION APPROACH FOR PLANAR SURFACES FROM UNSTRUCTURED 3D POINT CLOUDS

引用

PHOTOGRAMMETRIC RECORD 2010年第129期25卷 5-23页

作者： Awwad, Tarek M. Zhu, Qing Du, Zhiqiang Zhang, Yeting Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan Peoples R China

The extraction of object features from massive unstructured point clouds with different local densities, especially in the presence of random noisy points, is not a trivial task even if that feature is a planar surface. Segmentation is the most important step in the feature extraction process. In practice, most segmentation approaches use geometrical information to segment the 3D point cloud. The features generally include the position of each point (X, Y and Z), locally estimated surface normals and residuals of best fitting surfaces;however, these features could be affected by noisy points and in consequence directly affect the segmentation results. Therefore, massive unstructured and noisy point clouds also lead to bad segmentation (over-segmentation, under-segmentation or no segmentation). While the ransac (random sample consensus) algorithm is effective in the presence of noise and outliers, it has two significant disadvantages, namely, its efficiency and the fact that the plane detected by ransac may not necessarily belong to the same object surface;that is, spurious surfaces may appear, especially in the case of parallel-gradual planar surfaces such as stairs. The innovative idea proposed in this paper is a modi. cation for the ransac algorithm called Seq-NV-ransac. This algorithm checks the normal vector (NV) between the existing point clouds and the hypothesised ransac plane, which is created by three random points, under an intuitive threshold value. After extracting the first plane, this process is repeated sequentially (Seq) and automatically, until no planar surfaces can be extracted from the remaining points under the existing threshold value. This prevents the extraction of spurious surfaces, brings an improvement in quality to the computed attributes and increases the degree of automation of surface extraction. Thus the best fit is achieved for the real existing surfaces.

关键词： feature extraction fit to reality normal vectors planar surfaces ransac algorithm segmentation terrestrial laser scanner unstructured 3D point clouds

来源：评论

学校读者我要写书评

暂无评论

MZmine 2: Modular framework for processing, visualizing, and analyzing mass spectrometry-based molecular profile data

引用

BMC BIOINFORMATICS 2010年第1期11卷 1-11页

作者： Pluskal, Tomas Castillo, Sandra Villar-Briones, Alejandro Oresic, Matej OIST Cell Unit G0 Okinawa Japan VTT Tech Res Ctr Finland Espoo Finland

Background: Mass spectrometry (MS) coupled with online separation methods is commonly applied for differential and quantitative profiling of biological samples in metabolomic as well as proteomic research. Such approaches are used for systems biology, functional genomics, and biomarker discovery, among others. An ongoing challenge of these molecular profiling approaches, however, is the development of better data processing methods. Here we introduce a new generation of a popular open-source data processing toolbox, MZmine 2. Results: A key concept of the MZmine 2 software design is the strict separation of core functionality and data processing modules, with emphasis on easy usability and support for high-resolution spectra processing. Data processing modules take advantage of embedded visualization tools, allowing for immediate previews of parameter settings. Newly introduced functionality includes the identification of peaks using online databases, MSn data support, improved isotope pattern support, scatter plot visualization, and a new method for peak list alignment based on the random sample consensus (ransac) algorithm. The performance of the ransac alignment was evaluated using synthetic datasets as well as actual experimental data, and the results were compared to those obtained using other alignment algorithms. Conclusions: MZmine 2 is freely available under a GNU GPL license and can be obtained from the project website at: http://***/. The current version of MZmine 2 is suitable for processing large batches of data and has been applied to both targeted and non-targeted metabolomic analyses.

关键词： Mass Spectrometry Data Peak List Peak Picking Master List ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust and accurate iris segmentation in very noisy iris images

引用

IMAGE AND VISION COMPUTING 2010年第2期28卷 246-253页

作者： Li, Peihua Liu, Xiaomin Xiao, Lijuan Song, Qi Heilongjiang Univ Sch Comp Sci & Technol Harbin 150080 Hei Long Jiang Peoples R China

Iris segmentation plays an important role in an accurate iris recognition system. In less constrained environments where iris images are captured at-a-distance and on-the-move, iris segmentation becomes much more difficult due to the effects of significant variation of eye position and size, eyebrows, eyelashes, glasses and contact lenses, and hair, together with illumination changes and varying focus condition. This paper contributes to robust and accurate iris segmentation in very noisy images. Our main contributions are as follows: (1) we propose a limbic boundary localization algorithm that combines K-Means clustering based on the gray-level co-occurrence histogram and an improved Hough transform, and, in possible failures, a complementary method that uses skin information;the best localization between this and the former is selected. (2) An upper eyelid detection approach is presented, which combines a parabolic integro-differential operator and a ransac (RANdom SAmple Consensus)-like technique that utilizes edgels detected by a one-dimensional edge detector. (3) A segmentation approach is presented that exploits various techniques and different image information, following the idea of focus of attention, which progressively detects the eye, localizes the limbic and then pupillary boundaries, locates the eyelids and removes the specular highlight. The proposed method was evaluated in the UBIRIS.v2 testing database by the NICE.I organizing committee. We were ranked #4 among all participants according to the evaluation results. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Iris segmentation Integro-differential operator K-Means clustering ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

The Study of Target Points Center Extracting and Matching in Calibration

The Study of Target Points Center Extracting and Matching in...

引用

2nd International Conference on Functional Manufacturing Technologies

作者： Zhou Bo Wang Dongping Yang Jian Heilongjiang Inst Sci & Technol Comp & Informat Engn Coll Harbin 150027 Peoples R China

ISBN: (纸本)9780878492374

It's important to extract target points center from image in computer vision quickly and accurately. The center extract with the raw gradient information in the neighborhood of the target points boundary to get the parameters of the ellipse, avoids the intermediate stage of precisely extracting individual edge points. Moreover, under the dual space representation, the ellipse parameter can easily be calculated from the dual conic with the qualification of the ellipse, and the ellipse center will be got at the same time. Then, the ransac algorithm is used to match the pair of corresponding points between the calibration image and the calibration plate. The experiment and application result shows that the method is efficiently.

关键词： Matching Ellipse Center Extracting ransac algorithm Camera Calibration

来源：评论

学校读者我要写书评

暂无评论

New moving target detection algorithm

引用

Guangdian Gongcheng/Opto-Electronic Engineering 2008年第9期35卷 11-16页

作者： Zhang, Heng Li, Li-Chun Yu, Qi-Feng College of Aerospace and Materials Engineering National Univ. of Defense Technology Changsha 410073 China

For the important problem of moving target detection on a moving platform, an ego motion compensation algorithm is presented based on the Gabor feature descriptions. After compensating the camera ego motion, it is able to detect the relative moving targets to the camera efficiently. The interesting points are detected by the scale-space theory firstly. Then the feature description for every interesting point is created according to its character scale and character angle. And the coarse matching results are obtained by cross-match. At last, the transform model is estimated by the Random Sample Consensus (ransac) algorithm. Experimental results show that the new method can effectively and accurately detect the moving targets on the moving platform.

关键词： Camera ego motion compensation Gabor function ransac algorithm Scale space

来源：评论

学校读者我要写书评

暂无评论

An automatic target image mosaic algorithm

An automatic target image mosaic algorithm

引用

International Conference on Computer as a Tool (EUROCON 2007)

作者： Gu, Lingjia Jilin Univ Coll Elect Sci & Engn Changchun Jilin Province Peoples R China

ISBN: (纸本)9781424408122

In order to resolve the problem of capturing double shadow images in the shooting range test, a novel automatic image mosaic algorithm is proposed in the paper. Each double shadow image will be split into the odd field image and the even field image, then two field images will be complemented to two frame images, finally mosaic the middle image of two frame images by the algorithm. The mosaic algorithm mainly adopts SUSAN algorithm to abstract the feature points in the two images, then a pseudo matching set is obtained by comparing local neighborhoods of features through intensity cross-correlation method, these pseudo matches are divided into inliers and outliers using robust ransac algorithm, then estimate the point transformation matrix between two images accurately, finally seamlessly stitch two overlapping images. The experimental results show that the image mosaic effect is wonderful;the algorithm expands the applicable scope of the traditional mosaic algorithm.

关键词： target image mosaic double shadow image SUSAN algorithm ransac algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust camera motion estimation and classification for video analysis

Robust camera motion estimation and classification for video...

引用

Conference on Visual Communications and Image Processing 2004

作者： Chang, HC Lai, SH Natl Tsing Hua Univ Dept Comp Sci Hsinchu 300 Taiwan

ISBN: (纸本)0819452114

Camera motion estimation is very important for indexing and retrieving video information. In this paper, we propose a robust camera motion estimation and classification algorithm. Our camera motion estimation algorithm consists of optical flow computation, iterative ransac (RANdom Sample Consensus) multiple motion estimation, and lone-term camera motion estimation through a shortest-path search. In this approach, we first estimate multiple global affine motions from the computed optical flow field for every frame in the video sequence. Then, the long-term camera motion is determined from searching, a shortest path in a graph of cascaded nodes of global motions. After the camera motion is determined for the whole video, we apply an artificial neural network to classify the camera motion type. This neural network is trained from a large set of different types of camera motion data. We show accurate camera motion classification results through experiments on real videos.

关键词： camera motion classification video analysis optical flow computation motion estimation affine motion computation ransac algorithm artificial neural network

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：