检索结果-南通市图书馆

Two Improved Methods of sift algorithm Combined with Harris

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Two Improved Methods of SIFT Algorithm Combined with Harris

第24届中国控制与决策会议

作者： Shao Wei 1 , Li Na 2 ,Sun Lijuan 1 , Sui Shulin 2 , Liu Xiangpeng 2 1. College of Automation Electronic&Engineering, Qingdao University of Science and Technology, Qingdao, 266042 China 2. College of Mathematical Science and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China

Due to the invariance of scale, rotation and illumination, sift algorithm is commonly used in image matching. According to Harris algorithm, two simplified methods of sift algorithm are developed to improve real-time efficiency and robustness of feature detection. In the stage of accurate keypoints localization, two improved methods are proposed to eliminate edge responses. One is the replacement of Hessian matrix by the local autocorrelation function of Harris;the other is using the measure of corner response function of the Hessian matrix. The experimental results show that the improved methods can increase the performance of sift algorithm.

关键词： sift algorithm Harris algorithm The Hessian matrix

An improved sift algorithm for Feature Points matching of dairy cow images

在线全文

cnki会议

学校读者我要写书评

暂无评论

An improved SIFT Algorithm for Feature Points matching of da...

亚洲精细农业与计算机农业应用联合大会

作者： Lizhong Wang Vocational and Technical College Inner Mongolia Agricultural university Hohhot Inner Mongolia China Shuoshi Ma College of Mechanical and Electrical Engineering Inner Mongolia Agricultural university Hohhot Inner Mongolia China Heru Xue Zhenjie Hou College of Computer and Information Engineering Inner Mongolia Agricultural university Hohhot Inner Mongolia China

The conformation is the main parameter in dairy cow appraisal;hence, it is necessary for the measuring and evaluating of dairy conformation to use machine vision technology in 3D reconstruction. The feature points detecting and matching are the pivotal steps in 3D reconstruction. The conventional sift feature points matching algorithm has shortcomings of too large search area and low efficiency, An improved sift feature points matching algorithm is proposed to reduce the search range from both row and column directions based on binocular vision principle. 2.7 times of in speed by the improved algorithm has been shown in the experiments compared with that of the conventional algorithm with the same matching precision.

关键词： diary cow conformation feature points detecting feature points matching sift algorithm

A reliable algorithm for image matching based on sift

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2012年第4期19卷 90-95页

作者：霍炬杨宁曹茂永杨明 Dept.of Electrical Engineering Harbin Institute of Technology Control and Simulation Center Harbin Institute of Technology College of Information and Electrical Engineering Shan Dong University of Science and Technology

A novel algorithm is presented to make the results of image matching more reliable and accurate based on sift (Scale Invariant Feature Transform). sift algorithm has been identified as the most resistant matching algorithm to common image deformations; however, if there are similar regions in images, sift algorithm still generates some analogical descriptors and provides many mismatches. This paper examines the local image descriptor used by sift and presents a new algorithm by integrating sift with two-dimensional moment invariants and disparity gradient to improve the matching results. In the new algorithm, decision tree is used, and the whole matching process is divided into three levels with different primitives. Matching points are considered as correct ones only when they satisfy all the three similarity measurements. Experiment results demonstrate that the new approach is more reliable and accurate.

关键词： image matching sift algorithm two-dimensional moment invariants disparity gradient

Research on the algorithm of Image Matching based on Improved sift

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

International Journal of Technology Management 2014年第8期 36-39页

作者： Xiangchen Qiao Zaozhuang Vocational College of Science & Technology TengzhouShandong277500 China

The paper analyze and improve the sift optimized algorithm, and proposes an image matching method for sift algorithm based on quasi Euclidean distance and KD-tree. Experiments show that this algorithm has matching more points, high matching accuracy, no repealed points and higher advantage of matching efficiency based on keeping the basic characteristics of sift algorithm unchanged, and provides precise matching point to generate precise image stitching and other related fields of the follow-up product. At the same time, this method was applied to the layout optimization and achieved good results.

关键词： Matching pretreatment sift algorithm quasi Euclidean distance image matching

A New Registration Method Base on Improved Sobel and sift algorithms

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A New Registration Method Base on Improved Sobel and SIFT Al...

2010 3rd International Conference on Computer and Electrical Engineering(ICCEE 2010)

作者： Qiu-Ju Yang Xue-Mei Xiao College of Computer Science Sichuan University

In order to remove the unstable edge response points of the image registration using original sift algorithm and get more stable matching results in image registration, a new registration method based on improved Sobel algorithm and sift algorithm is proposed. The new method firstly detects out key points of image by original sift algorithm, then uses the features for image registration and finds out the edge responses of the matching point with the improved Sobel algorithm at last. It would remove some registration points if their coordinates are equal to the edge point. The rest registration points have different coordinates will be kept. The experimental results show that the improved registration algorithm can effectively remove the edge response points, further improve the accuracy of the registration result and display better stability than the traditional registration algorithm.

关键词： sift algorithm key points Sobel algorithm Image registration edge detection

sift-based Camera Tamper Detection For Video Surveillance 25th

在线全文

cnki会议

学校读者我要写书评

暂无评论

Sift-based Camera Tamper Detection For Video Surveillance

第25届中国控制与决策会议

作者： Hongpeng Yin Xuguo Jiao Xianke Luo Chai Yi College of Automation Chongqing University State Key Laboratory of Power Transmission Equipment & System Security and New Technology(College of Autotion Chongqing University)

ISBN: (纸本)9781467355339

Keeping the camera long time proper functioning without tamper is the fundamentally requirement of a video surveillance system. Traditional camera tamper detection is applied by surveillance system operators. It’s large human resource consuming and inefficiency. In this paper, a sift-based automatic camera tamper detection algorithm for video surveillance is proposed. When camera tamper occurred, the real-time frame will be large changed. Therefore, a sift feature based decision function is employed to detect camera tamper. The threshold is carefully chosen to reduce false alarms. Several experiments are conducted to demonstrate the effectiveness and robust of the proposed method.

关键词： video surveillance camera tamper sift algorithm covered camera detection moved camera detection

High-resolution remote sensing image-based extensive deformation-induced landslide displacement field monitoring method

在线全文

cnki会议

学校读者我要写书评

暂无评论

International Journal of Coal Science & Technology 2015年第3期2卷 170-177页

作者： Shanjun Liu Han Wang Jianwei Huang Lixin Wu College of Resources and Civil Engineering NortheasternUniversity Shenyang 110819 China IOT Perception Mine Research Center China University ofMining and Technology Xuzhou 220116 China

Landslide is one of the multitudinous serious geological hazards. The key to its control and reduction lies on dynamic monitoring and early warning. The article points out the insufficiency of traditional measuring means applied for large-scale landslide monitoring and proposes the method for extensive landslide displacement field monitoring using high- resolution remote images. Matching of cognominal points is realized by using the invariant features of sift algorithm in image translation, rotation, zooming, and affine transformation, and through recognition and comparison of characteristics of high-resolution images in different landsliding periods. Following that, landslide displacement vector field can be made known by measuring the distances and directions between cognominal points. As evidenced by field application of the method for landslide monitoring at West Open Mine in Fushun city of China, the method has the attraction of being able to make areal measurement through satellite observation and capable of obtaining at the same time the information of large- area intensive displacement field, for facilitating automatic delimitation of extent of landslide displacement vector field and sliding mass. This can serve as a basis for making analysis of laws governing occurrence of landslide and adoption of countermeasures.

关键词： Landslide monitoring High-resolution remote sensing sift algorithm Deformation field

Improved Frame Difference algorithm Based on CNN for Moving Target Detection

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Improved Frame Difference Algorithm Based on CNN for Moving ...

第三十九届中国控制会议

作者： Xuanxuan Cui Weibin Zhang Dan Liu Nanjing University of Science and Technology School of Electronic and Optical Engineering Nanjing University of Science and Technology School of Computer Engineering Chang'an University School of Economics and Management

In order to improve the shortcomings of frame difference method in moving target detection and improve the accuracy and robustness of moving target detection,an improved frame difference method based on CNN is ***,in order to solve the problem of blind spot in autopilot and improve the safety of autopilot,sift algorithm is used to obtain the panoramic image of moving ***,frame difference method is adopted to obtain the foreground image,and then CNN is used to repair the foreground ***,sift is used to splicing the restored foreground image to obtain the panoramic image of the foreground *** simulation results show that the proposed algorithm is effective,efficient and accurate in the extraction and repair of moving *** the proposed method,a complete panoramic image of moving targets can be obtained.

关键词： Autopilot sift algorithm CNN Panoramic Image Object Contour Extraction