课题基金 / 基金详情

RIA: Deformable Kernel Filtering for Early Visual Processing

RIA: Deformable Kernel Filtering for Early Visual Processing
RIA:用于早期视觉处理的可变形内核过滤
批准号:
9211651
负责人:
Pietro Perona
金额:
$9.0万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
1992
资助国家:
美国
项目状态:
已结题
起止时间:
1992-12-15 至 1996-11-30

项目摘要

项目成果

Pietro Perona的其他基金

相似基金

相关文献

中文摘要
翻译
在第一步视觉分析中,早期视觉,简单形象 亮度、颜色、纹理、立体感等特性 视差,运动模式进行分析,边界,线条, 测量图像的其它显著视觉结构, 提取。 一些理论和经验论点指出, 所有的早期视力任务都有可能 通过共享共同计算结构的算法: 卷积与不同方向,尺度和 形状,其次是简单的准局部非线性运算。 等 核可以作为变形(旋转、缩放 延伸)的模板内核,该模板内核是从任务 规范. 在过去的两年中,一种基于奇异值分解的方法 值分解(SVD)已经被提出来使得这样的 连续参数滤波可行-已经证明 用于二维的旋转和缩放。 本研究 努力(1)在新的情况下演示该方法,包括 3D旋转和缩放拉伸和曲率变化,(2) 将该方法应用于生成用于各种早期视觉的滤波器, 任务包括纹理和运动分析,(3)探索新的早期 视觉算法通过连续参数滤波成为可能, (4)了解滤波器设计技术之间的联系, SVD方法//
英文摘要
In the first step of visual analysis, early vision, simple image properties such as brightness, color, texture, stereoscopic disparity, motion patterns are analyzed and boundaries, lines, and other salient visual structures of the image are measured and extracted. A number of theoretical and empirical arguments point to the possibility that all early vision tasks may be accomplished by algorithms sharing a common computational structure: convolution with kernels of different orientations, scales, and shapes followed by simple quasi-local nonlinear operations. Such kernals may be generated as deformations (rotations, scalings stretchings) of a template kernel which is synthesized from task specifications. In the last two years a method based on singular value decomposition (SVD) has been proposed to make such continuous-parameter filtering feasible- it has been demonstrated for rotations and scaling in 2 dimensions. This research endeavours to(1) demonstrate the method in new situations including 3D rotations and scalings stretchings and changes of curvature, (2) apply the method to generating filters for various early vision tasks including texture and motion analysis, (3) explore new early vision algorithms made possible by continuous-parameter filtering, (4) understand the connections between filter-design techniques and the SVD method. //
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
RI: Medium: CompCog: Automated Discovery of Macro-Variables from Raw Spatiotemporal Data
  • 批准号:
    1564330
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $110.0万
  • 财政年份:
    2016
  • 负责人:
    Pietro Perona
  • 依托单位:
I-Corps: Combining Machine Vision and Crowdsourcing for Convenient and Accurate Image Annotation
  • 批准号:
    1216839
  • 项目类别:
    Standard Grant
  • 资助金额:
    $5.0万
  • 财政年份:
    2012
  • 负责人:
    Pietro Perona
  • 依托单位:
RI: Small: Collaborative Research: Infinite Bayesian Networks for Hierarchical Visual Categorization
  • 批准号:
    0914789
  • 项目类别:
    Standard Grant
  • 资助金额:
    $20.0万
  • 财政年份:
    2009
  • 负责人:
    Pietro Perona
  • 依托单位:
Collaborative Research: Learning Taxonomies of the Visual World
  • 批准号:
    0535292
  • 项目类别:
    Standard Grant
  • 资助金额:
    $15.62万
  • 财政年份:
    2005
  • 负责人:
    Pietro Perona
  • 依托单位:
海外基金