Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 12 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Moving Object Detection Algorithm Based on Dynamic Vision Sensor | |||
SUN Xue,SUN Xue,LIU Dengfeng,LIU Dengfeng | |||
Computer Science and Technology 11 April 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Target detection and tracking mainly use RGB camera and deep learning algorithm. The information in the image is complex and redundant so the computing consumes a lot of resources. To solve the above problems, this paper proposes an improved spectral clustering algorithm to detect moving object. The algorithm is based on event data generated by dynamic vision sensors. In this paper, the cosine - Manhattan fusion distance is used to obtain a more accurate similarity matrix. The clustering results of some data are used to guide other data to speed up operation. The number of clusters is set adaptively to avoid the subjective influence of human beings. The results show that the accuracy of the improved algorithm on multiple data sets is more than 80%, and the time is significantly shortened. Spectral clustering algorithm based on dynamic vision sensor has great application potential in dealing with multi-target motion problems. | |||
TO cite this article:SUN Xue,SUN Xue,LIU Dengfeng, et al. Moving Object Detection Algorithm Based on Dynamic Vision Sensor[OL].[11 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4760291 |
2. Fast Video Stream Super Resolution Reconstruction based on CUDA | |||
LI Ying,HU Jie,LI Hailiang,SHEN Qiang | |||
Computer Science and Technology 04 December 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents a parallel GPU-based solution for video stream super resolution reconstruction. We propose an approach, using the computer unified device architecture (CUDA) platform developed by NVIDIA, to partition the steps of the non-local iterative back projection (NLIBP) algorithm (which is designed for single image super resolution reconstruction). The approach also exploits the redundant information of the video stream in the time-space domain in an effort to further reduce the unnecessary searching work in the motion estimation process. The use of CUDA enhances the programmability and flexibility for general-purpose computation of GPU. Experimental results show that, with the assistance of CUDA, the processing time is approximately 8 times faster than that of using CPU only in C++ language, while preserving good visual quality of the reconstructed video stream. | |||
TO cite this article:LI Ying,HU Jie,LI Hailiang, et al. Fast Video Stream Super Resolution Reconstruction based on CUDA[OL].[ 4 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4663992 |
3. A new image segmentation algorithm based on Mean-Shift for outdoor image | |||
QIN Zheng,YANG Xiao | |||
Computer Science and Technology 13 August 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, an improved outdoor color image segmentation algorithm based on Mean-Shift was proposed in this article, the real-time requirement of the image processing for visual navigation could be satisfied by the algorithm. It presented the theory of Mean-Shift firstly, and then processed fast color image segmentation algorithm by using a scale transformation method. The experiment results indicates that the efficiency of the segmentation is greatly optimized. | |||
TO cite this article:QIN Zheng,YANG Xiao. A new image segmentation algorithm based on Mean-Shift for outdoor image[OL].[13 August 2015] http://en.paper.edu.cn/en_releasepaper/content/4652205 |
4. A Novel Edge Detection Operator Based On Fractional Gaussian Differential | |||
HAN Qirui,LIU Ke | |||
Computer Science and Technology 08 May 2014 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents an improved algorithm for edge detection. The algorithm combines the Gaussian average operator with 1-2 order fractional differential.Gaussian average operatorhas outstanding performance in image denoising and 1-2 order fractional differential retain more detailed imageinformation during sharping. It has been proved by theoretical analysis and experimental verificationsthat this method could extract image edge information effectively and reserve partial near edgedetails, and shows better noise immunity in edge detection. | |||
TO cite this article:HAN Qirui,LIU Ke. A Novel Edge Detection Operator Based On Fractional Gaussian Differential[OL].[ 8 May 2014] http://en.paper.edu.cn/en_releasepaper/content/4595118 |
5. Fast 2G Bandelet Transform Based On Optimal Direction | |||
Li Qimin,Li Hongjie | |||
Computer Science and Technology 14 October 2012 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Construction of quadtree and selection of the best geometry direction (BGDS) are the most time-consuming parts in 2G Bandelet Transform, and the result of original method is not the best. To solve the problem, in this paper, a BGDS method based on the advance and retreat method was presented firstly; then the genetic algorithm for BGDS was proposed; finally, these two methods were combined to get better results. Experiments show that these three methods all have some advantages compared with original method. Furthermore, the original bottom-up quadtree algorithm was improved to a top-down quadtree algorithm, which has some advantages in processing some special images. In the ending of this paper, the application of improved bandelet based on genetic algorithm was presented, and the time complexity and space complexity of these algorithms were compared. | |||
TO cite this article:Li Qimin,Li Hongjie. Fast 2G Bandelet Transform Based On Optimal Direction[OL].[14 October 2012] http://en.paper.edu.cn/en_releasepaper/content/4491899 |
6. Adaptive Tag Ranking based on Saliency Analysis | |||
ZHAO Ripeng,SONG Zehai,FENG Songhe | |||
Computer Science and Technology 25 April 2012 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Tag ranking has become a hot research topic due to its importance for image analysis and retrieval. Existing annotation methods about tag ranking can be roughly classified into two categories: tag relevance ranking and tag saliency ranking. Both methods have pros and cons. In this paper, we propose an adaptive tag ranking based on saliency analysis which combines the advantages of tag relevance ranking and tag saliency ranking. The main idea behind the approach is apparently simple. In short, to the given image, we first carry out image salient region detection and image saliency analysis by machine learning techno-logies like Support Vector Machine (SVM). If there exist visually salient regions of the given image, the corresponding annotated tags can be ranked according to the saliency property of the corresponding visual content; else tags can be ranked according to the relevance scores to the content of the image. The performance will be better than existing methods. To demonstrate the effectiveness and efficiency of the proposed algorithm, we do experiments on the COREL and MSRC image datasets. | |||
TO cite this article:ZHAO Ripeng,SONG Zehai,FENG Songhe. Adaptive Tag Ranking based on Saliency Analysis[OL].[25 April 2012] http://en.paper.edu.cn/en_releasepaper/content/4476147 |
7. A Fast Algorithm for Fractional-order Total Variation Based Multiplicative Noise Removal | |||
Zhang Jun,Wei Zhihui | |||
Computer Science and Technology 31 December 2011 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, using the operator splitting technique, we propose a fast alternating iterative algorithm for the fractional-order total variation regularized model with general fidelity term. As an application, we use the new algorithm to solve two models for multiplicative noise removal with different fidelity terms. To improve the performance, we choose the parameters adaptively and propose an adaptive algorithm for multiplicative noise removal. Numerical results show that the new algorithm with fixed parameters has low computational cost. The adaptive algorithms can not only remove the noise and eliminate the staircase effect in the non-textured region, but also preserve the textures well in the textured region, and therefore can improve the result visually efficiently. | |||
TO cite this article:Zhang Jun,Wei Zhihui. A Fast Algorithm for Fractional-order Total Variation Based Multiplicative Noise Removal[OL].[31 December 2011] http://en.paper.edu.cn/en_releasepaper/content/4457900 |
8. Semi-Split Bregman Iteration Algorithm for Image Denoising | |||
Zhang Jun,Wei Zhihui | |||
Computer Science and Technology 26 December 2010 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The split Bregman iteration has been demonstrated to be an efficient tool for solving total variation regularized minimization problems. In denosing case, it can remove noise efficiently, but it can not preserve textures well. In this paper, we analyze the split Bregman method from the perspective of function matching, and reveal the reason why it can not preserve textures well. Based on this analysis, we develop a new method called the semi-split Bregman iteration algorithm for image denoising. The numerical results show that the semi-split Bregman iteration algorithm can preserve the textures and improve the peak signal to noise ratio efficiently in the processing of denoising. | |||
TO cite this article:Zhang Jun,Wei Zhihui. Semi-Split Bregman Iteration Algorithm for Image Denoising[OL].[26 December 2010] http://en.paper.edu.cn/en_releasepaper/content/4401265 |
9. Image Interpolation by combination of two-dimension surface patches | |||
Yue Yizhen ,Zhang Caiming | |||
Computer Science and Technology 22 June 2009 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper develops a new method for image interpolation by constructing fitting surfaces to discrete image data. Usually, the image data is obtained by area sampling which can reduce the accuracy of the interpolation. So the point sampling values must be computed first, then a polynomial surface patch is obtained by the Lagrange method to approximate the local original continuous image surface. The whole image surface is constructed by combining all the local region surfaces with weighted functions. The experiments for testing the efficiency of the new method show that the interpolated images produced by the new method have higher precision and better quality than normal method, such as bi-cubic, and have no loss of image brightness. | |||
TO cite this article:Yue Yizhen ,Zhang Caiming . Image Interpolation by combination of two-dimension surface patches[OL].[22 June 2009] http://en.paper.edu.cn/en_releasepaper/content/33333 |
10. A New Nonrigid Registration Algorithm of Medical Image Based on Random Field Model and B-spline wavelet | |||
Wang Bo ,He Liu ,Li Hua ,Wang Anna ,Wang Haihong | |||
Computer Science and Technology 11 June 2008 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:A new nonrigid registration algorithm is proposed in this paper, which applies Markov-Gibbs random fields model (MGRF) to the nonrigid registration field of medical images. The algorithm is constructed by integrating the nonrigid registration algorithm based on B-spline wavelet and the priori knowledge of the maximum likelihood (ML) and maximum a posteriori (MAP) estimation into a MGRF model. In the MGRF model, the reference and test images are the known conditions and B-spline wavelet is the basis function constructing the nonrigid deformation function. The coefficients of B-spline wavelet in the deformation function are the parameters to be evaluated. The algorithm leads to a better result of registration because the use of the priori knowledge. Various medical images are selected to verify the algorithm, which show that the algorithm proposed in this paper is superior to the nonrigid registration algorithm without the priori knowledge. | |||
TO cite this article:Wang Bo ,He Liu ,Li Hua , et al. A New Nonrigid Registration Algorithm of Medical Image Based on Random Field Model and B-spline wavelet[OL].[11 June 2008] http://en.paper.edu.cn/en_releasepaper/content/22105 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated