位置：成果数据库 > 期刊 > 期刊详情页
基于灰度直方图的加权模板匹配法在摄像机标定中的应用
  • ISSN号：1673-0291
  • 期刊名称：交大学报,
  • 时间：2013
  • 页码：22-26
  • 分类：TN911.73[电子电信—通信与信息系统;电子电信—信息与通信工程]
  • 作者机构：[1]北京交通大学计算机与信息技术学院,北京100044, [2]北京交通大学现代信息科学与网络技术北京市重点实验室,北京100044
  • 相关基金：国家自然科学基金资助项目（60973060）; 高等学校博士学科点专项科研基金项目资助（200800040008）; 北京交通大学优秀博士研究生创新研究基金资助项目（KKJB12029536）
  • 相关项目：基于多目视觉的形体语言感知与识别研究
作者： 李小利|阮秋琦|阮成雄|
关键词： 摄像机标定, 模板匹配, 加权平均, 灰度直方图, camera calibration, template match, weighted average, histogram
中文摘要：

采用基于灰度直方图的加权模板匹配法实现摄像机的标定.首先以一个游标卡尺作为目标采集图像,此采集图像作为后续分析的同时用于模板的多处提取;提取的每个模板都将用于后续的模板匹配来提取目标区域（Region of Interest,ROI）;匹配所获得的所有目标区域二值化后并旋转90°,以提取其水平方向的灰度直方图;所获得灰度直方图经过优化获得单一峰值后用于获取测量精度;最终标定出的测量精度是由所获得的所有测量精度值进行可信区间的加权平均决定的.本文所采用的加权模板匹配方法不仅降低了单一模板匹配的风险,而且充分利用了具有相似纹理这一有利信息,实验结果表明,提出的方法可以达到工程要求的亚像素级别误差,由此说明该方法在摄像机标定的应用中是行之有效的.

英文摘要：

This paper employs the weighted template matching method based on the histogram for camera calibration.Firstly,a vernier caliper is used as an subject to capture the image.Then the image is used to extract numbers of templates,and each template is used to extract ROI based on template matching method.After the matching results are transferred into binary image and rotated 90 degrees to get the histogram;the histogram is optimized and used to get the measure accuracy.Finally,the weighted average of these measure accuracy is obtained as the final result.Comparing with the true value,the final results show that the weighted template matching method is efficient for camera calibration and it＇s easy to implement.

同期刊论文项目
基于多目视觉的形体语言感知与识别研究
期刊论文 49 会议论文 22 著作 1
三维人脸不变性特征提取及识别算法研究
期刊论文 30 会议论文 34
同项目期刊论文
Enhancing sparsity via ‘p (0opo1) minimization for robust face recognition
基于轮廓线特征的三维人脸识别改进算法
Semi-supervised dimensionality reduction using estimated class membership probabilities
Fuzzy nearest feature line-based manifold embedding for facial expression recognition
Graph-preserving shortest feature line segment for dimensionality reduction,
Facial Expression Recognition using Spectral Supervised Canonical Correlation Analysis
Graph-preserving shortest feature line segment for dimensionality reduction
Coupled Discriminative Feature Learning for Heterogeneous Face Recognition,
Ruizhen Zhao: Multiplestrategies to enhance automatic 3D facial expression recognition
Context and locality constrained linearcoding for human action recognition
FullyAutomatic 3D Facial Expression Recognition using Polytypic Multi‐block LocalBinary Patterns
A remarkable standard for estimating the performance of 3D facial expression features
Face Recognition Using Double Sparse LocalFisher Discriminant Analysis
Coupled Discriminative Feature Learning for Heterogeneous Face Recognition
Ruizhen Zhao: Fully automatic 3D facial expression recognition using polytypic multi-block local bin
Semi-supervised Sparse Feature Selection based on Multi-view Laplacian Regularization,
Face Recognition Using Double Sparse Local Fisher Discriminant Analysis
Multiple strategies to enhance automatic 3D facial expression recognition.
Sparse Feature Selection Based on L2,1/2-Matrix Norm For Web Image Annotation.
Hesssian Sparse Feature Selection Based on L2,1/2-Matrix Norm.
基于增强稀疏性特征选择的网络图像标注
视频中人体行为的慢特征提取算法
改进的自适应灰度视频序列阴影检测方法
结合尺度不变特征变换和Kalman滤波的Mean Shift视频运动目标跟踪
较大尺度运动下的人体特征点跟踪算法研究
单幅图像融合参考模型的三维人脸重建
Sparse Feature Selection Based onL2,1/2-Matrix Norm For Web Image Annotation.
Ruizhen Zhao. Hesssian Sparse Feature Selection Based on L2,1/2-Matrix Norm.
Fully automatic 3D facial expression recognition using polytypic multi-block local binary patterns
Semi-supervised Sparse FeatureSelection based on Multi-view Laplacian Regularization
Image and Vision Computing
Projection-optimal local Fisher discriminant analysis for feature extraction.
"Context and locality constrained linear coding for human action recognition.
基于Hessian半监督特征选择的网络图像标注
One-shot Learning Gesture Recognition from RGB-D Data Using Bag of Features
行人跟踪的多特征融合算法研究
颜色不变量空间下的行人跟踪算法研究
基于轮廓线特征的三维人脸识别改进算法
3D face recognition using Patched Locality Preserving Projections
An illumination normalization model for face recognition under varied lighting conditions
Statistical gait recognition based on tangent angle features
Enhancing sparsity via ‘p (0opo1) minimization for robust face recognition
基于三维谱回归的有效三维人脸识别算法
Robust sparse bounding sphere for 3D face recognition
Graph-Preserving Sparse Nonnegative Matrix Factorization With Application to Facial Expression Recog
Region covariance matrices as feature descriptors for palmprint recognition using gabor features
Orthogonal Tensor Neighborhood Preserving Embedding for facial expression recognition
Facial expression recognition using fuzzy laplacianfaces
Face recognition using l-fisherfaces
Probabilistic model-based silhouette refinement for gait recognition
Expression-robust 3D face recognition using bending invariant correlative features
MEAN AND STANDARD DEVIATION AS FEATURES FOR PALMPRINT RECOGNITION BASED ON GABOR FILTERS
Modified 3D face recognition algorithm based on contour curve features
Shift and gray scale invariant features for palmprint identification using complex directional wavel
Orthogonal tensor rank one differential graph preserving projections with its application to facial
Tensor rank one differential graph preserving analysis for facial expression recognition
Efficient 3d face recognition with gabor patched spectral regression
A Mandarin edutainment system integrated virtual learning environments
Facial expression recognition via sparse representation
一种新的H.264视频场景切换检测算法
张量正交局部敏感判别式分析及其在人脸识别中的应用
基于块运动轨迹相似性的H.264运动修复-错误隐藏算法
基于LoG梯度加权Haar—like特征的车轮裂纹检测
期刊信息
  • 《北京交通大学学报：自然科学版》
  • 北大核心期刊（2011版）
  • 主管单位:教育部
  • 主办单位:北京交通大学
  • 主编：孙守光
  • 地址：北京市西直门外上园村3号北方交通大学8楼8101室
  • 邮编：100044
  • 邮箱：bfxb@bjtu.edu.cn
  • 电话：010-51688053
  • 国际标准刊号：ISSN：1673-0291
  • 国内统一刊号：ISSN：11-5258/U
  • 邮发代号:
  • 获奖情况:
  • 1995年铁道部科技期刊一等奖、1999年教育部组织的...
  • 国内外数据库收录:
  • 俄罗斯文摘杂志,美国化学文摘（网络版）,波兰哥白尼索引,荷兰文摘与引文数据库,美国剑桥科学文摘,日本日本科学技术振兴机构数据库,中国中国科技核心期刊,中国北大核心期刊（2008版）,中国北大核心期刊（2011版）,中国北大核心期刊（2014版）
  • 被引量:5152