中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
机构
采集方式
内容类型
发表日期
学科主题
筛选

浏览/检索结果: 共19条，第1-10条 帮助

条数/页： 排序方式：
STAM: A SpatioTemporal Attention Based Memory for Video Prediction 期刊论文  OAI收割
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 2354-2367
作者:  Chang, Zheng;  Zhang, Xinfeng;  Wang, Shanshe;  Ma, Siwei;  Gao, Wen
  |  收藏  |  浏览/下载：22/0  |  提交时间：2023/12/04
Applying maximally stable extremal regions and local binary patterns for guide-wire detecting in percutaneous coronary intervention 期刊论文  OAI收割
IET IMAGE PROCESSING, 2019, 卷号: 13, 期号: 13, 页码: 2579-2586
作者:  Pusit, Prasong;  Xie, Xiao-Liang;  Hou, Zeng-Guang
  |  收藏  |  浏览/下载：51/0  |  提交时间：2020/03/30
Learning explicit video attributes from mid-level representation for video captioning 期刊论文  OAI收割
COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 卷号: 163, 页码: 126-138
作者:  Nian, Fudong;  Li, Teng;  Wang, Yan;  Wu, Xinyu;  Ni, Bingbing
  |  收藏  |  浏览/下载：38/0  |  提交时间：2018/03/03
Automatic face annotation in TV series by video/script alignment 期刊论文  OAI收割
NEUROCOMPUTING, 2015, 卷号: 152, 页码: 316-321
作者:  Zhang, Yifan;  Tang, Zhiqang;  Zhang, Chunjie;  Liu, Jing;  Lu, Hanqing
收藏  |  浏览/下载：28/0  |  提交时间：2015/09/18
广播视频节目层结构分析及视觉内容检索研究 学位论文  OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2013
作者:  陈见耸
收藏  |  浏览/下载：61/0  |  提交时间：2015/09/02
Image mosaic technique based on the information of edge (EI CONFERENCE) 会议论文  OAI收割
2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012, July 31, 2012 - August 2, 2012, Guilin, Guangxi, China
作者:  Wang Y.-Q.
收藏  |  浏览/下载：35/0  |  提交时间：2013/03/25
Image mosaic is an important branch in the field of image processing. This paper designs and realizes an image mosaic technique based on the information of edge. The technology is suitable for engineering application. First of all  two images of the adjoining frames are processed by convolution operation  get the edge images. And then we cut edge image into pieces and compute their spatial frequency. According to the value of the spatial frequency select reasonable registration model group. We compute correlation strength and the value of movement offset which are the model group and the current frame edge image. We can complete image mosaic by them. We use video sequence which of the resolution is 1024 * 768 do the experiment. The results show that the method has good effect and strong adaptability. Algorithm is high efficiency which running time is 24 ms. It is suitable for real-time processing requirements of the application. This method is an effective mosaic technique which is suitable for engineering application. 2012 IEEE.  
The sequence measurement system of the IR camera (EI CONFERENCE) 会议论文  OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, May 24, 2011 - May 24, 2011, Beijing, China
作者:  Zhang H.-B.;  Han H.-X.;  Geng A.-H.
收藏  |  浏览/下载：36/0  |  提交时间：2013/03/25
Currently  the IR cameras are broadly used in the optic-electronic tracking  optic-electronic measuring  fire control and optic-electronic countermeasure field  but the output sequence of the most presently applied IR cameras in the project is complex and the giving sequence documents from the leave factory are not detailed. Aiming at the requirement that the continuous image transmission and image procession system need the detailed sequence of the IR cameras  the sequence measurement system of the IR camera is designed  and the detailed sequence measurement way of the applied IR camera is carried out. The FPGA programming combined with the SignalTap online observation way has been applied in the sequence measurement system  and the precise sequence of the IR camera's output signal has been achieved  the detailed document of the IR camera has been supplied to the continuous image transmission system  image processing system and etc. The sequence measurement system of the IR camera includes CameraLink input interface part  LVDS input interface part  FPGA part  CameraLink output interface part and etc  thereinto the FPGA part is the key composed part in the sequence measurement system. Both the video signal of the CmaeraLink style and the video signal of LVDS style can be accepted by the sequence measurement system  and because the image processing card and image memory card always use the CameraLink interface as its input interface style  the output signal style of the sequence measurement system has been designed into CameraLink interface. The sequence measurement system does the IR camera's sequence measurement work and meanwhile does the interface transmission work to some cameras. Inside the FPGA of the sequence measurement system  the sequence measurement program  the pixel clock modification  the SignalTap file configuration and the SignalTap online observation has been integrated to realize the precise measurement to the IR camera. Te sequence measurement program written by the verilog language combining the SignalTap tool on line observation can count the line numbers in one frame  pixel numbers in one line and meanwhile account the line offset and row offset of the image. Aiming at the complex sequence of the IR camera's output signal  the sequence measurement system of the IR camera accurately measures the sequence of the project applied camera  supplies the detailed sequence document to the continuous system such as image processing system and image transmission system and gives out the concrete parameters of the fval  lval  pixclk  line offset and row offset. The experiment shows that the sequence measurement system of the IR camera can get the precise sequence measurement result and works stably  laying foundation for the continuous system. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).  
Precise motion compensation based on weighted sub-pixel image matching (EI CONFERENCE) 会议论文  OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Imaging Detectors and Applications, May 24, 2011 - May 26, 2011, Beijing, China
Liang H. G.
收藏  |  浏览/下载：25/0  |  提交时间：2013/03/25
This paper proposed a sub-pixel image correlation algorithm that can get more Precise result  its principle is apply the distribute of relativity peak to get weighted multi-pixel comprehensive of location. Image correlation be as to calculates the greyscale relativity of image template and matching image  the relativity of correspond location where match best with template will be most high  and in its neighbour range  the relativity will be still keep high too. We used these pixel in this local area of calculated match point to get sub-pixel accuracy  the relativity of every pixel be used as its weight for participate the sub-pixel calculation. The sub-pixel location is more accuracy than the integer one  we applied this method to perform background compensation in processing the target detecting for video image sequence. At the end of this paper  some experiment data be proposed  it proved this sub-pixel image correlation can obtain better result. 2011 SPIE.  
The new approach for infrared target tracking based on the particle filter algorithm (EI CONFERENCE) 会议论文  OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, May 24, 2011 - May 24, 2011, Beijing, China
作者:  Sun H.;  Han H.-X.;  Sun H.
收藏  |  浏览/下载：59/0  |  提交时间：2013/03/25
Target tracking on the complex background in the infrared image sequence is hot research field. It provides the important basis in some fields such as video monitoring  precision  and video compression human-computer interaction. As a typical algorithms in the target tracking framework based on filtering and data connection  the particle filter with non-parameter estimation characteristic have ability to deal with nonlinear and non-Gaussian problems so it were widely used. There are various forms of density in the particle filter algorithm to make it valid when target occlusion occurred or recover tracking back from failure in track procedure  but in order to capture the change of the state space  it need a certain amount of particles to ensure samples is enough  and this number will increase in accompany with dimension and increase exponentially  this led to the increased amount of calculation is presented. In this paper particle filter algorithm and the Mean shift will be combined. Aiming at deficiencies of the classic mean shift Tracking algorithm easily trapped into local minima and Unable to get global optimal under the complex background. From these two perspectives that "adaptive multiple information fusion" and "with particle filter framework combining"  we expand the classic Mean Shift tracking framework.Based on the previous perspective  we proposed an improved Mean Shift infrared target tracking algorithm based on multiple information fusion. In the analysis of the infrared characteristics of target basis  Algorithm firstly extracted target gray and edge character and Proposed to guide the above two characteristics by the moving of the target information thus we can get new sports guide grayscale characteristics and motion guide border feature. Then proposes a new adaptive fusion mechanism  used these two new information adaptive to integrate into the Mean Shift tracking framework. Finally we designed a kind of automatic target model updating strategy to further improve tracking performance. Experimental results show that this algorithm can compensate shortcoming of the particle filter has too much computation  and can effectively overcome the fault that mean shift is easy to fall into local extreme value instead of global maximum value.Last because of the gray and fusion target motion information  this approach also inhibit interference from the background  ultimately improve the stability and the real-time of the target track. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).  
Sequence multi-labeling: a unified video annotation scheme with spatial and temporal context 期刊论文  iSwitch采集
Ieee transactions on multimedia, 2010, 卷号: 12, 期号: 8, 页码: 814-828
作者:  Li, Yuanning;  Tian, Yonghong;  Duan, Ling-Yu;  Yang, Jingjing;  Huang, Tiejun
收藏  |  浏览/下载：42/0  |  提交时间：2019/05/10