您现在的位置: 首页> 研究主题> 影像增强

影像增强

影像增强的相关文献在1987年到2022年内共计184篇,主要集中在肿瘤学、自动化技术、计算机技术、测绘学 等领域,其中期刊论文81篇、会议论文4篇、专利文献150983篇;相关期刊67种,包括城市建设理论研究(电子版)、测绘与空间地理信息、海洋测绘等; 相关会议4种,包括全国测绘科技信息网中南分网第二十二次学术信息交流会、第十五届海洋测绘综合性学术研讨会、第四届全国信息获取与处理学术会议等;影像增强的相关文献由406位作者贡献,包括李劲生、田伟国、余绍德等。

影像增强—发文量

期刊论文>

论文:81 占比:0.05%

会议论文>

论文:4 占比:0.00%

专利文献>

论文:150983 占比:99.94%

总计:151068篇

影像增强—发文趋势图

影像增强

-研究学者

  • 李劲生
  • 田伟国
  • 余绍德
  • 吴琨
  • 谢耀钦
  • 赵养社
  • R.贝伦斯
  • 不公告发明人
  • 仲洪海
  • 伍世宾
  • 期刊论文
  • 会议论文
  • 专利文献

搜索

排序:

年份

    • 韩婷婷
    • 摘要: 高景一号卫星是我国首个自主研制的0.5 m级高分辨率商业遥感卫星,具有高空间分辨率和光谱分辨率,已逐渐应用于自然资源、城市规划、生态环境监测、水文地质、交通运输等重点领域。本文以辽宁省全域范围的高景一号卫星影像为数据源,突破以往测绘产品生产过程中遇到的局限问题,引入地形数据和参考影像结合的几何校正方法,归一化植被指数值域大小进行植被颜色增强,大范围拉花变形平滑处理方法,最终完成了全省范围的高分辨率、高精度的底图制作,并进行精度评价,用于更新和完善我省基础地理信息数据库。
    • 杨显琼; 秦荣波
    • 摘要: 针对云、雾、霾条件导致的遥感影像饱和度低,色彩失真,细节模糊等问题.提出一种融合改进暗通道和Retinex的遥感影像去雾增强算法.首先,采用改进的暗通道先验方法对雾度分布不均的有雾影像进行复原;其次,将复原处理后的影像作为单尺度Retinex算法的原始输入图像,使影像更加清晰,细节更加明显,更加符合人类视觉特性.通过主观评价和平均梯度、均方误差和信息熵等影像质量评价指标验证了文章算法的有效性.
    • 杨梦楚(译)
    • 摘要: 摄影师通过智能软件放大图像早已不是什么新闻了,但最近的智能算法进展将会改变超高分辨率摄影的前景。这些智能算法工具的基本功能可以在保留线条细节的情况下使照片分辨率提高400%,在没有检测到边缘的像素之间进行智能填充。
    • 邵东传; 吴钧; 高云; 刘俊; 马钢; 苏平; 普快荣; 岑键昌
    • 摘要: 随着医学影像学技术快速发展,对比剂应用日渐广泛,相关不良反应随之增加.对比剂脑病(CIE)是应用对比剂后出现的短暂性、可逆性神经功能障碍性疾病,多预后良好,但少数患者可出现严重神经功能障碍甚至死亡.本文对CIE临床特点、发病机制、高危因素及治疗措施等研究进展进行综述.
    • 崔浩; 艾海滨; 张力; 孙钰珊; 赵栋梁
    • 摘要: 针对雾霾天气会导致航空影像的色彩失真、信息损失,对影像的后期处理和判读造成了负面影响,以暗原色先验为理论基础,结合航空影像的成像特点和景物内容特点提出一种针对航空影像的去雾算法.首先,获取航空影像透射率图并对其自动分割;其次,对影像透射率全局估计和局部优化;最后,根据大气物理模型对影像恢复处理.选取了山区、村镇、城市等各种场景近20组航空影像进行试验,从主观和客观两方面对算法效果进行评价,结果表明该算法具有处理效果稳定、鲁棒性强的特点.%The hazy weather causes color distortion of aerial imagery and loss of information, which has a negative effect to the subsequent image processing and interpretation.Based on the theory of dark channel prior as well as the imaging and scene characteristics of aerial images, this paper proposes an aerial image haze removal algorithm.Firstly, get transmission ratio map of the aerial image and perform segmentation automatically.Secondly, obtain global estimation and local optimization of transmission rate of the image.Finally, recover the image based on the atmospheric physical model.In this paper, we selected nearly 20 groups of aerial images as experiment data including mountains, villages, cities and so on to evaluate the results from both subjective and objective aspects.The results show that the algorithm has characteristics of stable effects and strong robustness.
    • 程家胜; 穆春迪; 李扬; 姜艳媛
    • 摘要: "天绘一号"卫星2m全色相机焦平面共8片TDI-CCD器件,分上下两行品字形交错排列组成.目前地面处理系统采用基于 SIFT 特征点匹配的分段线性拼接算法,将8片条带影像进行拼接.然而受地形起伏、云层移动、影像对比度等多种因素影响,易出现局部拼接错位现象,条带拼接精度不高,降低了卫星的使用性能.为解决上述问题,文章重点分析了影响拼接精度的因素,并提出了基于分段线性拼接和拼接区域逻辑自适应影像增强技术的影像拼接方法.经过大量试验验证,该方法有效地解决了长条带影像拼接参数不一致、拼接区域影像对比度不高等问题,提高了器件片间拼接精度,在"天绘一号"卫星条带影像的拼接中取得了良好的应用效果.%Focal plane of the full color camera on TH-1 satellite consists of eight TDI-CCD elements, which are staggered in upper and lower rows. The eight TDI-CCD strip images are currently stitched by SIFT-based feature point matching algorithm to form one wide-area image. However, due to terrain change, cloud movement and the difference of image contrast, the stitching accuracy is usually low by misplacement, thus reducing the performance of TH-1 image data significantly. In the paper, we focus on analyzing influenc-ing factors of stitching accuracy, and then propose a new method to improve the accuracy by introducing piecewisely linear stitching and logically adaptive image enhancement of the stitching area. The method is val-idated by real data processing and is currently applied for TH-1strip image stitching, which is effective to solve the stitching parameters inconsistency and low remote sensing image contrast.
    • 赵芸芸; 高燕军; 董季平; 宁文德; 邬小平
    • 摘要: Objective To explore the application value of contrast-enhanced MRI and curved planar reformation (CPR) in diagnosis of facial neuritis.Methods Contrast-enhanced MRI scans were performed on 30 patients with facial neuritis.The involvement of intracranial facial nerve was observed,and the signal intensity of facial nerve and adjacent temporal lobe was measured with GE AW 4.5 workstation.While the signal intensity ratio (SIR) between facial nerve and adjacent temporal lobe was calculated.CPR of facial nerve was done with Philips EBW workstation,in order to observe the whole course and involvement of facial nerve.Results Among the 30 patients,SIR of affected geniculate ganglion,tympanic segment,labyrinthine segment,internal auditory meatus segment and mastoid segment was 1.59±0.28,1.16±0.16,1.38±0.20,1.30 ±0.19 and 0.96±0.14,respectively.While SIR of the relevant segment in contralateral side was 1.08±±0.19,0.74±0.13,0.81±0.13,0.83±0.08 and 0.69±0.12,respectively.There were significant differences of SIR between the affected and the contralateral segments (all P<0.001).CPR could display the involved location and facilitate visualizing the whole course of facial nerve clearly.Conclusion Contrast-enhanced MRI and CPR are helpful to facilitate visualizing the whole course of facial nerve and clearly reveal the involvement.%目的 探讨MR增强扫描及曲面重建(CPR)在面神经炎诊断中的应用价值.方法 对30例面神经炎患者行MR增强扫描.通过GE AW 4.5工作站观察患者颅内面神经受累情况,测量面神经及邻近颞叶组织的信号强度,计算面神经与同一层面邻近颞叶的信号强度比值(SIR).通过Philips EBW工作站进行面神经的CPR重建,整体观察患者面神经的颅内走行及受累情况.结果 30例面神经炎患者中,患侧面神经膝状神经节、鼓室段、迷路段、内听道段及乳突段的SIR分别为1.59±0.28、1.16±0.16、1.38±0.20、1.30±0.19及0.96±0.14,健侧SIR分别为1.08±0.19、0.74±0.13、0.81±0.13、0.83±0.08及0.69±0.12,各受累部位患侧面神经SIR与健侧差异均有统计学意义(P均<0.001).CPR图像可直观显示面神经受累部位及面神经的颅内走行情况.结论 面神经MR增强扫描及CPR技术有助于清晰显示面神经炎患者颅内面神经走行及受累情况.
    • 王渊; 毛亮军; 唐文澜; 王新生; 陈志杰
    • 摘要: Adopting a method of ISODATA algorithm which combining the enhancement of single band image and takes wheat and rape as examples. When using GF⁃1 satellite image as the data sources,comparing with the ISODATA algorithm,the overall classification accuracy increased by 19%,and reached to 95. 33%. At the same time,using the Landsat 8 image as the data source,the overall classification accuracy increased by 6%,reached to 95. 83%. The Kappa coefficients of classification results are all in 0. 9 1. 0,which almost completely matched with the original image,thus solved the problem of crop⁃confusion. In addition,the method was short time⁃consuming,high⁃accuracy and could be popularized in a large scale.%采用基于单波段影像增强的ISODATA算法,以小麦和油菜为例进行实验.采用高分一号卫星影像作为数据源时,总体分类精度达到95.33%,比单独使用ISODATA算法提高约19%;采用Landsat 8影像作为数据源时,总体分类精度达到95.83%,比单独使用ISODATA算法提高约6%.分类结果的Kappa系数均在0.91.0之间,与原影像几乎完全匹配,有效解决农作物之间的混淆问题.该方法耗时短,精度高,可大范围推广.
  • 查看更多

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号