机构

• 长春光学精密机械与物... [2]
• 自动化研究所 [1]
• 沈阳自动化研究所 [1]

采集方式

• OAI收割 [4]

内容类型

• 会议论文 [3]
• 学位论文 [1]

发表日期

• 2015 [1]
• 2013 [1]
• 2012 [1]
• 2010 [1]

学科主题

筛选

浏览/检索结果: 共4条，第1-4条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 社交媒体短文本自动摘要 学位论文  OAI收割 工学硕士, 中国科学院自动化研究所: 中国科学院大学, 2015 吴玉芳 收藏  |  浏览/下载：138/0  |  提交时间：2015/09/02 社交短文本自动摘要  句子打分  Key-Bigram 提取  相似度度量  次模函数优化  深度学习  Social Media Short Texts Automatic Summarization  Sentene Scoring  Key-Bigram Extraction  Similarity Measuring  Submodular Functions Optimization  Deep Learning   A line mapping based automatic registration algorithm of infrared and visible images 会议论文  OAI收割 5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013 作者:  Ai R(艾锐);  Shi ZL(史泽林);  Xu DJ(徐德江);  Zhang CS(张程硕) 收藏  |  浏览/下载：36/0  |  提交时间：2013/12/26 There exist complex gray mapping relationships among infrared and visible images because of the different imaging mechanisms. The difficulty of infrared and visible image registration is to find a reasonable similarity definition. In this paper, we develop a novel image similarity called implicit linesegment similarity(ILS) and a registration algorithm of infrared and visible images based on ILS. Essentially, the algorithm achieves image registration by aligning the corresponding line segment features in two images. First, we extract line segment features and record their coordinate positions in one of the images, and map these line segments into the second image based on the geometric transformation model. Then we iteratively maximize the degree of similarity between the line segment features and correspondence regions in the second image to obtain the model parameters. The advantage of doing this is no need directly measuring the gray similarity between the two images. We adopt a multi-resolution analysis method to calculate the model parameters from coarse to fine on Gaussian scale space. The geometric transformation parameters are finally obtained by the improved Powell algorithm. Comparative experiments demonstrate that the proposed algorithm can effectively achieve the automatic registration for infrared and visible images, and under considerable accuracy it makes a more significant improvement on computational efficiency and anti-noise ability than previously proposed algorithms.   Image quality assessment based on gradient complex matrix (EI CONFERENCE) 会议论文  OAI收割 2012 International Conference on Systems and Informatics, ICSAI 2012, May 19, 2012 - May 20, 2012, Yantai, China 作者:  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y. 收藏  |  浏览/下载：22/0  |  提交时间：2013/03/25 An image quality assessment model based on gradient complex matrix is proposed. The vertical and horizontal gradient information of grayscale image is calculated. Complex number is used to construct the measuring matrix. Singular value decomposition is performed in order to obtain the main structure information of the image. The singular value feature vectors of the image gradient complex matrices corresponding to the reference image and the distorted image are used to measure the structural similarity of the two images. PSNR is taken as a tool to evaluate the gradient distribution similarity. Their properties are analyzed by using LIVE database and nonlinearity regression function. 2012 IEEE.   An electro-optical tracking method in target separation based on fuzzy clustering association rules (EI CONFERENCE) 会议论文  OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China Guo T.-J.; Gao H.-B.; Zhang S.-M.; Wu Y.-J. 收藏  |  浏览/下载：31/0  |  提交时间：2013/03/25 An effective tracking method is proposed to solve the problem that the electro-optical tracking system in Missile Range easily loses the real target during the target separation. Before target separation  the error correcting value of the theoretical trajectory is obtained by the theoretical trajectory correcting algorithm. In the phase of target separation  the theoretical trajectory of the target is corrected by the error correcting value firstly  and then the fuzzy clustering association algorithm is applied to calculate the similarity between the measuring data of the target from sensors and the corrected theoretical trajectory. The similarity helps to identify whether the measured data is from the real target or not. Experimental results show that the authenticity of the target can be determined effectively. The identified results can be used as the decision-making basis of the servo sub-system and TV trackers  which can improve the continuous tracking probability of the electro-optical tracking system in the target separation. 2010 IEEE.