QQ客服 官方微博 反馈留言

浏览/检索结果: 共2条，第1-2条 帮助 限定条件 内容类型：会议论文    专题：长春光学精密机械与物理研究所    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Remote sensing image restoration using estimated point spread function (EI CONFERENCE) 会议论文 2010 International Conference on Information, Networking and Automation, ICINA 2010, October 17, 2010 - October 19, 2010, Kunming, China Yang L.; Ren J. 收藏  |  浏览/下载：27/0  |  提交时间：2013/03/25 In order to reduce image blur caused by the degradation phenomenon in the imaging process  the acquired images of the space remote sensing camera are restored. First  the frequency-domain notch filter is adopted to remove strip noises in the images. Then degradation function  which is referred to as the point spread function (PSF) of the imaging system is estimated using the knife-edge method. To improve the accuracy of the estimation  the estimated PSF is adjusted with Gaussian fitting. Finally  the images are restored by Wiener filtering with the fitted PSF. The restoration results of the remote sensing images show that almost all strip noises are eliminated by the notch filter. After denoising and restoration  the variance of the remote sensing image worked with in this paper increases 30.979 and the gray mean gradient increases 3.312. Due to Gaussian fitting  the accuracy of the PSF estimation is heightened. Image restoration with the final PSF is benefit to interpreting and analyzing the remote sensing images. After restoration  the contrasts of the restored images are increased and the visual effects become clearer. 2010 IEEE.   Integrated intensity, orientation code and spatial information for robust tracking (EI CONFERENCE) 会议论文 2007 2nd IEEE Conference on Industrial Electronics and Applications, ICIEA 2007, May 23, 2007 - May 25, 2007, Harbin, China Zhang X.; Sun H.; Wang Y. 收藏  |  浏览/下载：20/0  |  提交时间：2013/03/25 real-time tracking is an important topic in computer vision. Conventional single cue algorithms typically fail outside limited tracking conditions. Integration of multimodal visual cues with complementary failure modes allows tracking to continue despite losing individual cues. In this paper  we combine intensity  orientation codes and special information to form a new intensity-orientation codes-special (IOS) feature to represent the target. The intensity feature is not affected by the shape variance of object and has good stability. Orientation codes matching is robust for searching object in cluttered environments even in the cases of illumination fluctuations resulting from shadowing or highlighting  etc The spatial locations of the pixels are used which allow us to take into account the spatial information which is lost in traditional histogram. Histograms of intensity  orientation codes and spatial information are employed for represent the target Mean shift algorithm is a nonparametric density estimation method. The fast and optimal mode matching can be achieved by this method. In order to reduce the compute time  we use the mean shift procedure to reach the target localization. Experiment results show that the new method can successfully cope with clutter  partial occlusions  illumination change  and target variations such as scale and rotation. The computational complexity is very low. If the size of the target is 3628 pixels  it only needs 12ms to complete the method. 2007 IEEE.