检索结果-南通市图书馆

Modified SIFT descriptor and key-point matching for fast and robust image mosaic

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2016年第4期25卷 562-570页

作者：何玉青王雪王思远刘明奇诸加丹金伟其 Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of ChinaBeijing Institute of Technology

To improve the performance of the scale invariant feature transform （ SIFT）, a modified SIFT （M-SIFT） descriptor is proposed to realize fast and robust key-point extraction and matching. In descriptor generation, 3 rotation-invariant concentric-ring grids around the key-point location are used instead of 16 square grids used in the original SIFT. Then, 10 orientations are accumulated for each grid, which results in a 30-dimension descriptor. In descriptor matching, rough rejection mismatches is proposed based on the difference of grey information between matching points. The per- formance of the proposed method is tested for image mosaic on simulated and real-worid images. Experimental results show that the M-SIFT descriptor inherits the SIFT＇ s ability of being invariant to image scale and rotation, illumination change and affine distortion. Besides the time cost of feature extraction is reduced by 50% compared with the original SIFT. And the rough rejection mismatches can reject at least 70% of mismatches. The results also demonstrate that the performance of the pro- posed M-SIFT method is superior to other improved SIFT methods in speed and robustness.

关键词： modified scale invariant feature transform (SIFT) image mosaic feature extraction key-point matching

image mosaic Techniques Optimization Using Wavelet

在线全文

学校读者我要写书评

暂无评论

Computer Aided Drafting,Design and Manufacturing 2014年第4期24卷 26-32页

作者： ZHOU An-qi CUI Li School of Mathematical Sciences Beijing Normal University

This essay concentrates on two key procedures of image mosaic--image registration and *** the character of geometric transformation invariance of edge points, wecalculate the angle difference of the direction vector ofedge points in different images anddraw an angle difference histogramto adjust the rotationproblem. Through this way, algorithm based on gray information is expandedandcan be used in images withdisplacementand rotation. Inthe term of image fusion, wavelet multi-scale analysis is used to fuse spliced images. In order to choose the best method of imagefusion,weevaluate the results of different methods of image fusion by cross entropy.

关键词： image mosaic image registration image fusion wavelet angle difference histogram

image mosaic Based View Synthesis for Interactive Stereoscopic Display

在线全文

学校读者我要写书评

暂无评论

Image Mosaic Based View Synthesis for Interactive Stereoscop...

2007亚洲显示国际会议

作者： Giuyan Guo Key Laboratory of Advanced Displays and System Application Ministry of EducationShanghai 200072China School of Communication and Information EngineeringShanghai UniversityShanghai 200072China

In stereoscopic display,view synthesis is a key technology to realize interactivity what is the ability to look around with- in a three dimensional(3D)scene by freely choosing a *** paper presents an intermediate view synthesis al- gorithm,combining view interpolation with view morphing based on image ***,the original stereo image pairs are ***,the disparity of only object area is estimated by a predict recursion method to improve the matching speed and ***,credible areas in left and right views should be determined and chosen to create a transi- tional *** last,a method combining view interpolation and morphing is used to synthesis the intermediate view from the transitional *** results show that the edge of created intermediate view object is clear and smooth,and the processing speed of view synthesis is obviously *** algorithm can be used in interactive stereoscopic dis- play in varius 3D video application which an arbitrary view needs to be rendered in real-time.

关键词： View Synthesis View Morphing image mosaic Transitional View

image mosaic Based on SURF and Results Optimization

在线全文

cnki会议

学校读者我要写书评

暂无评论

Image Mosaic Based on SURF and Results Optimization

2013年中国智能自动化学术会议

作者： Tie Jiang Guibin Zhu Chongqing Key Laboratory of Emergency Communication 13 teamChongqing Communication Institute

In order to improve the insufficiency of SURF algorithm,we present an auto-adjusted algorithm of image size based on *** detect the zoom relationship and translation co-efficiency between the images and modulate the unregistrated image’s scale to the same level as the original *** obtain the Region of Interest(ROI) according to the translation parameter and then pretreat the *** propose an image matching method based on the saliency *** calculate the saliency map in the Region of Interest and mark the interest points in the area by using SURF *** the part of image fusion,the method of gradated in-and-out which we commonly use is improved to eliminate *** the image exposure differences,we propose two methods to adjust the exposure of spliced *** is based on mean value and the other is based on mean-variance *** the experiment,the validity of the proposed methods is demonstrated and the quality of the mosaic image is better.

关键词： image mosaic Saliency map SURF algorithm Mean value Mean-variance specification

Slicing Method for Reverse Engineering Based on image mosaic

在线全文

cnki会议

学校读者我要写书评

暂无评论

Computer Aided Drafting,Design and Manufacturing 2008年第2期18卷 33-38页

作者： ZHAN Yi-bin,LIN Da-jun,AN Qi (School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, China)

Reverse engineering dealing with images is traditionally based on image processing and contour recognition. A new method is presented based on the combination of sectional slicing with image mosaic. Sectional contours of the target object are generated by colorful liquid or laser scanning, these images from different views are fused into a set of complete cross-sectional images, thereby the whole practical model is reconstructed in 3D space.

关键词： reverse engineering image mosaic slicing contour 3D reconstruction

Optimal Derivative Filters with Well-Distributed Based image mosaic Algorithm

在线全文

学校读者我要写书评

暂无评论

Optimal Derivative Filters with Well-Distributed Based Image...

第三十届中国控制会议

作者： YI Meng,GUO Bao-Long,ZHANG Xu School of Electromechanical Engineering,Xidian University,Xi''an 710071,P.R.China

＜正＞An automatic image mosaic method based on the optimal derivative filters with well-distributed was proposed. Firstly interest points in an image are detected by Harris operator with optimal derivative filters,delaunay triangulation is used to reject the spurious feature points pair and estimate the parameters of geometric transform *** the geometric transform of input images,the two images were fused and the image stitching was *** experimental results show that the proposed algorithm produces an improvement in mosaic accuracy、efficiency and robustness.

关键词： image mosaic Optimal Derivative Filter Well-Distributed Delaunay Triangulation

Global Automatic Recognition and Localization of Multi Screws Based on image mosaic

在线全文

cnki会议

学校读者我要写书评

暂无评论

Global Automatic Recognition and Localization of Multi Screw...

第三十九届中国控制会议

作者： Hang Yin Yan Yuan Chaolong Yao Xiaoqi Wang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In the tuning system based on vision sensor, the object recognition and localization is very important. In order to meet the practical tuning of the microwave cavity filter by the mechanical arm, a global recognition and localization method of multiple adjustable screws is proposed, which combines image mosaic and template matching. A high-definition global image of microwave cavity filter is composed of multiple local images according to feature point registration, and then all adjustable screws in the global image are recognized by template matching algorithm based on shape feature, which solves the problem of limited field of vision of a single industrial camera. It realizes the recognition, localization and numbering of all tuning objects in the whole tuning range, and transmits the coordinate information corresponding to the number to the mechanical arm. This method can be used to tune various types of microwave cavity filters, and it has certain versatility. The experimental results show that the recognition effect of the screws is favorable when the above method is applied to the actual tuning of 12-step microwave cavity filter with the hand-eye integrated four-axis mechanical arm. And it meets the requirements of tuning accuracy.

关键词： image mosaic microwave cavity filter image localization template matching

Automatic Panoramic UAV image mosaic Using ORB Features and Robust Transformation Estimation

在线全文

cnki会议

学校读者我要写书评

暂无评论

Automatic Panoramic UAV Image Mosaic Using ORB Features and ...

第37届中国控制会议

作者： Jun Chen Linbo Luo Siwei Wang Hui Wu School of Automation China University of Geosciences School of Mechanical Engineering and Electronic Information China University of Geosciences

Panoramic image mosaic, which aims to take many regular photographic or video images in order to cover the entire viewing space, plays an important role in many remote sensing tasks including map updating, change detection, environmental monitoring and surveillance. Typical mosaic methods involve four steps, namely, feature extraction, feature matching, transformation estimation, and blending. In this study, we introduce several novel strategies in these steps for the fast and automatic construction of unmanned aerial vehicle（UAV） panoramic image mosaic. First, we analyze and test several existing feature extraction techniques and propose to use oriented FAST and rotated BRIEF（ORB） because of its efficiency and capability to generate high-quality feature points. Second, we introduce a fast and robust feature matching strategy based on descriptor similarity along with a locality preserving geometric constraint. Third, we model the spatial transformation between a UAV image pair with an affine function and introduce a robust Bayesian framework to estimate this transformation from the ORB feature matches even if these matches are contaminated by false ones. Finally, we propose a gradual fading method to fuse and blend the matched images to create an attractive panorama. The qualitative and quantitative results of an image set demonstrate that our method exhibits superior performance over existing methods in terms of accuracy and efficiency.

关键词： image mosaic UAV images ORB LPM feature matching

Bionic mosaic Method of Panoramic image Based on Compound Eye of Fly

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2011年第4期8卷 440-448页

作者： Haipeng Chen Xuanjing Shen Xiaofei Li Yushan Jin College of Computer Science and Technology Jilin University Changchun 130012 P. R. China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 P. R. China

To satisfy the requirements of real-time and high quality mosaics, a bionic compound eye visual system was designed by simulating the visual mechanism of a fly compound eye. Several CCD cameras were used in this system to imitate the small eyes of a compound eye. Based on the optical analysis of this system, a direct panoramic image mosaic algorithm was proposed. Several sub-images were collected by the bionic compound eye visual system, and then the system obtained the overlapping proportions of these sub-images and cut the overlap sections of the neighboring images. Thus, a panoramic image with a large field of view was directly mosaicked, which expanded the field and guaranteed the high resolution. The experimental results show that the time consumed by the direct mosaic algorithm is only 2.2% of that by the traditional image mosaic algorithm while guaranteeing mosaic quality. Furthermore, the proposed method effectively solved the problem of misalignment of the mosaic image and eliminated mosaic cracks as a result of the illumination factor and other factors. This method has better real-time properties compared to other methods.

关键词： bionic compound eye panoramic image image mosaic direct mosaic algorithm